[format.python] initial formatting of the python code

This patch was generated by black [1]::

    make format.python

[1] https://github.com/psf/black

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2021-12-27 09:26:22 +01:00
parent fcdc2c2cd2
commit 3d96a9839a
184 changed files with 2800 additions and 2836 deletions

View File

@ -29,6 +29,7 @@ if settings is not None:
_unset = object() _unset = object()
def get_setting(name, default=_unset): def get_setting(name, default=_unset):
"""Returns the value to which ``name`` point. If there is no such name in the """Returns the value to which ``name`` point. If there is no such name in the
settings and the ``default`` is unset, a :py:obj:`KeyError` is raised. settings and the ``default`` is unset, a :py:obj:`KeyError` is raised.
@ -80,14 +81,9 @@ def logging_config_debug():
'levelname': {'color': 8}, 'levelname': {'color': 8},
'name': {'color': 8}, 'name': {'color': 8},
'programname': {'color': 'cyan'}, 'programname': {'color': 'cyan'},
'username': {'color': 'yellow'} 'username': {'color': 'yellow'},
} }
coloredlogs.install( coloredlogs.install(level=log_level, level_styles=level_styles, field_styles=field_styles, fmt=LOG_FORMAT_DEBUG)
level=log_level,
level_styles=level_styles,
field_styles=field_styles,
fmt=LOG_FORMAT_DEBUG
)
else: else:
logging.basicConfig(level=logging.getLevelName(log_level), format=LOG_FORMAT_DEBUG) logging.basicConfig(level=logging.getLevelName(log_level), format=LOG_FORMAT_DEBUG)

View File

@ -8,13 +8,12 @@ from flask_babel import gettext
# specifies which search query keywords triggers this answerer # specifies which search query keywords triggers this answerer
keywords = ('random',) keywords = ('random',)
random_int_max = 2**31 random_int_max = 2 ** 31
random_string_letters = string.ascii_lowercase + string.digits + string.ascii_uppercase random_string_letters = string.ascii_lowercase + string.digits + string.ascii_uppercase
def random_characters(): def random_characters():
return [random.choice(random_string_letters) return [random.choice(random_string_letters) for _ in range(random.randint(8, 32))]
for _ in range(random.randint(8, 32))]
def random_string(): def random_string():
@ -39,11 +38,13 @@ def random_uuid():
return str(uuid.uuid4()) return str(uuid.uuid4())
random_types = {'string': random_string, random_types = {
'string': random_string,
'int': random_int, 'int': random_int,
'float': random_float, 'float': random_float,
'sha256': random_sha256, 'sha256': random_sha256,
'uuid': random_uuid} 'uuid': random_uuid,
}
# required answerer function # required answerer function
@ -62,6 +63,8 @@ def answer(query):
# required answerer function # required answerer function
# returns information about the answerer # returns information about the answerer
def self_info(): def self_info():
return {'name': gettext('Random value generator'), return {
'name': gettext('Random value generator'),
'description': gettext('Generate different random values'), 'description': gettext('Generate different random values'),
'examples': ['random {}'.format(x) for x in random_types]} 'examples': ['random {}'.format(x) for x in random_types],
}

View File

@ -4,11 +4,7 @@ from operator import mul
from flask_babel import gettext from flask_babel import gettext
keywords = ('min', keywords = ('min', 'max', 'avg', 'sum', 'prod')
'max',
'avg',
'sum',
'prod')
# required answerer function # required answerer function
@ -47,6 +43,8 @@ def answer(query):
# required answerer function # required answerer function
# returns information about the answerer # returns information about the answerer
def self_info(): def self_info():
return {'name': gettext('Statistics functions'), return {
'name': gettext('Statistics functions'),
'description': gettext('Compute {functions} of the arguments').format(functions='/'.join(keywords)), 'description': gettext('Compute {functions} of the arguments').format(functions='/'.join(keywords)),
'examples': ['avg 123 548 2.04 24.2']} 'examples': ['avg 123 548 2.04 24.2'],
}

View File

@ -120,14 +120,15 @@ def wikipedia(query, lang):
return [] return []
backends = {'dbpedia': dbpedia, backends = {
'dbpedia': dbpedia,
'duckduckgo': duckduckgo, 'duckduckgo': duckduckgo,
'google': google, 'google': google,
'startpage': startpage, 'startpage': startpage,
'swisscows': swisscows, 'swisscows': swisscows,
'qwant': qwant, 'qwant': qwant,
'wikipedia': wikipedia 'wikipedia': wikipedia,
} }
def search_autocomplete(backend_name, query, lang): def search_autocomplete(backend_name, query, lang):

View File

@ -23,10 +23,12 @@ from pathlib import Path
data_dir = Path(__file__).parent data_dir = Path(__file__).parent
def _load(filename): def _load(filename):
with open(data_dir / filename, encoding='utf-8') as f: with open(data_dir / filename, encoding='utf-8') as f:
return json.load(f) return json.load(f)
def ahmia_blacklist_loader(): def ahmia_blacklist_loader():
"""Load data from `ahmia_blacklist.txt` and return a list of MD5 values of onion """Load data from `ahmia_blacklist.txt` and return a list of MD5 values of onion
names. The MD5 values are fetched by:: names. The MD5 values are fetched by::
@ -39,6 +41,7 @@ def ahmia_blacklist_loader():
with open(str(data_dir / 'ahmia_blacklist.txt'), encoding='utf-8') as f: with open(str(data_dir / 'ahmia_blacklist.txt'), encoding='utf-8') as f:
return f.read().split() return f.read().split()
ENGINES_LANGUAGES = _load('engines_languages.json') ENGINES_LANGUAGES = _load('engines_languages.json')
CURRENCIES = _load('currencies.json') CURRENCIES = _load('currencies.json')
USER_AGENTS = _load('useragents.json') USER_AGENTS = _load('useragents.json')

View File

@ -43,11 +43,15 @@ def response(resp):
filesize, filesize_multiplier = filesize_info.split() filesize, filesize_multiplier = filesize_info.split()
filesize = get_torrent_size(filesize, filesize_multiplier) filesize = get_torrent_size(filesize, filesize_multiplier)
results.append({'url': href, results.append(
{
'url': href,
'title': title, 'title': title,
'seed': seed, 'seed': seed,
'leech': leech, 'leech': leech,
'filesize': filesize, 'filesize': filesize,
'template': 'torrent.html'}) 'template': 'torrent.html',
}
)
return results return results

View File

@ -57,6 +57,7 @@ engine_shortcuts = {}
""" """
def load_engine(engine_data): def load_engine(engine_data):
"""Load engine from ``engine_data``. """Load engine from ``engine_data``.
@ -166,20 +167,19 @@ def set_language_attributes(engine):
# settings.yml # settings.yml
if engine.language not in engine.supported_languages: if engine.language not in engine.supported_languages:
raise ValueError( raise ValueError(
"settings.yml - engine: '%s' / language: '%s' not supported" % ( "settings.yml - engine: '%s' / language: '%s' not supported" % (engine.name, engine.language)
engine.name, engine.language )) )
if isinstance(engine.supported_languages, dict): if isinstance(engine.supported_languages, dict):
engine.supported_languages = { engine.supported_languages = {engine.language: engine.supported_languages[engine.language]}
engine.language : engine.supported_languages[engine.language]
}
else: else:
engine.supported_languages = [engine.language] engine.supported_languages = [engine.language]
# find custom aliases for non standard language codes # find custom aliases for non standard language codes
for engine_lang in engine.supported_languages: for engine_lang in engine.supported_languages:
iso_lang = match_language(engine_lang, BABEL_LANGS, fallback=None) iso_lang = match_language(engine_lang, BABEL_LANGS, fallback=None)
if (iso_lang if (
iso_lang
and iso_lang != engine_lang and iso_lang != engine_lang
and not engine_lang.startswith(iso_lang) and not engine_lang.startswith(iso_lang)
and iso_lang not in engine.supported_languages and iso_lang not in engine.supported_languages
@ -197,14 +197,12 @@ def set_language_attributes(engine):
} }
engine.fetch_supported_languages = ( engine.fetch_supported_languages = (
# pylint: disable=protected-access # pylint: disable=protected-access
lambda: engine._fetch_supported_languages( lambda: engine._fetch_supported_languages(get(engine.supported_languages_url, headers=headers))
get(engine.supported_languages_url, headers=headers))
) )
def update_attributes_for_tor(engine): def update_attributes_for_tor(engine):
if (settings['outgoing'].get('using_tor_proxy') if settings['outgoing'].get('using_tor_proxy') and hasattr(engine, 'onion_url'):
and hasattr(engine, 'onion_url') ):
engine.search_url = engine.onion_url + getattr(engine, 'search_path', '') engine.search_url = engine.onion_url + getattr(engine, 'search_path', '')
engine.timeout += settings['outgoing'].get('extra_proxy_timeout', 0) engine.timeout += settings['outgoing'].get('extra_proxy_timeout', 0)
@ -217,9 +215,7 @@ def is_missing_required_attributes(engine):
missing = False missing = False
for engine_attr in dir(engine): for engine_attr in dir(engine):
if not engine_attr.startswith('_') and getattr(engine, engine_attr) is None: if not engine_attr.startswith('_') and getattr(engine, engine_attr) is None:
logger.error( logger.error('Missing engine config attribute: "{0}.{1}"'.format(engine.name, engine_attr))
'Missing engine config attribute: "{0}.{1}"'
.format(engine.name, engine_attr))
missing = True missing = True
return missing return missing
@ -230,8 +226,7 @@ def is_engine_active(engine):
return False return False
# exclude onion engines if not using tor # exclude onion engines if not using tor
if ('onions' in engine.categories if 'onions' in engine.categories and not settings['outgoing'].get('using_tor_proxy'):
and not settings['outgoing'].get('using_tor_proxy') ):
return False return False
return True return True
@ -253,8 +248,7 @@ def register_engine(engine):
def load_engines(engine_list): def load_engines(engine_list):
"""usage: ``engine_list = settings['engines']`` """usage: ``engine_list = settings['engines']``"""
"""
engines.clear() engines.clear()
engine_shortcuts.clear() engine_shortcuts.clear()
categories.clear() categories.clear()

View File

@ -25,9 +25,7 @@ page_size = 10
# search url # search url
search_url = 'http://juhanurmihxlp77nkq76byazcldy2hlmovfu2epvl5ankdibsot4csyd.onion/search/?{query}' search_url = 'http://juhanurmihxlp77nkq76byazcldy2hlmovfu2epvl5ankdibsot4csyd.onion/search/?{query}'
time_range_support = True time_range_support = True
time_range_dict = {'day': 1, time_range_dict = {'day': 1, 'week': 7, 'month': 30}
'week': 7,
'month': 30}
# xpaths # xpaths
results_xpath = '//li[@class="result"]' results_xpath = '//li[@class="result"]'
@ -54,7 +52,7 @@ def response(resp):
# trim results so there's not way too many at once # trim results so there's not way too many at once
first_result_index = page_size * (resp.search_params.get('pageno', 1) - 1) first_result_index = page_size * (resp.search_params.get('pageno', 1) - 1)
all_results = eval_xpath_list(dom, results_xpath) all_results = eval_xpath_list(dom, results_xpath)
trimmed_results = all_results[first_result_index:first_result_index + page_size] trimmed_results = all_results[first_result_index : first_result_index + page_size]
# get results # get results
for result in trimmed_results: for result in trimmed_results:
@ -65,10 +63,7 @@ def response(resp):
title = extract_text(eval_xpath(result, title_xpath)) title = extract_text(eval_xpath(result, title_xpath))
content = extract_text(eval_xpath(result, content_xpath)) content = extract_text(eval_xpath(result, content_xpath))
results.append({'url': cleaned_url, results.append({'url': cleaned_url, 'title': title, 'content': content, 'is_onion': True})
'title': title,
'content': content,
'is_onion': True})
# get spelling corrections # get spelling corrections
for correction in eval_xpath_list(dom, correction_xpath): for correction in eval_xpath_list(dom, correction_xpath):

View File

@ -35,8 +35,8 @@ search_url = base_url + '/?post_type=app_release&searchtype=apk&page={pageno}&{q
def request(query, params): def request(query, params):
params['url'] = search_url.format( params['url'] = search_url.format(
pageno = params['pageno'], pageno=params['pageno'],
query = urlencode({'s': query}), query=urlencode({'s': query}),
) )
logger.debug("query_url --> %s", params['url']) logger.debug("query_url --> %s", params['url'])
return params return params
@ -55,11 +55,7 @@ def response(resp):
url = base_url + link.attrib.get('href') + '#downloads' url = base_url + link.attrib.get('href') + '#downloads'
title = extract_text(link) title = extract_text(link)
img_src = base_url + eval_xpath_getindex(result, './/img/@src', 0) img_src = base_url + eval_xpath_getindex(result, './/img/@src', 0)
res = { res = {'url': url, 'title': title, 'img_src': img_src}
'url': url,
'title': title,
'img_src': img_src
}
results.append(res) results.append(res)

View File

@ -97,7 +97,7 @@ main_langs = {
'sl': 'Slovenský', 'sl': 'Slovenský',
'th': 'ไทย', 'th': 'ไทย',
'uk': 'Українська', 'uk': 'Українська',
'zh': '简体中文' 'zh': '简体中文',
} }
supported_languages = dict(lang_urls, **main_langs) supported_languages = dict(lang_urls, **main_langs)
@ -141,7 +141,6 @@ def response(resp):
href = urljoin(base_url, link.attrib.get('href')) href = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link) title = extract_text(link)
results.append({'url': href, results.append({'url': href, 'title': title})
'title': title})
return results return results

View File

@ -27,19 +27,23 @@ nb_per_page = 20
search_api = 'https://api.artic.edu/api/v1/artworks/search?' search_api = 'https://api.artic.edu/api/v1/artworks/search?'
image_api = 'https://www.artic.edu/iiif/2/' image_api = 'https://www.artic.edu/iiif/2/'
def request(query, params): def request(query, params):
args = urlencode({ args = urlencode(
'q' : query, {
'page' : params['pageno'], 'q': query,
'fields' : 'id,title,artist_display,medium_display,image_id,date_display,dimensions,artist_titles', 'page': params['pageno'],
'limit' : nb_per_page, 'fields': 'id,title,artist_display,medium_display,image_id,date_display,dimensions,artist_titles',
}) 'limit': nb_per_page,
}
)
params['url'] = search_api + args params['url'] = search_api + args
logger.debug("query_url --> %s", params['url']) logger.debug("query_url --> %s", params['url'])
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -50,14 +54,16 @@ def response(resp):
if not result['image_id']: if not result['image_id']:
continue continue
results.append({ results.append(
{
'url': 'https://artic.edu/artworks/%(id)s' % result, 'url': 'https://artic.edu/artworks/%(id)s' % result,
'title': result['title'] + " (%(date_display)s) // %(artist_display)s" % result, 'title': result['title'] + " (%(date_display)s) // %(artist_display)s" % result,
'content': result['medium_display'], 'content': result['medium_display'],
'author': ', '.join(result['artist_titles']), 'author': ', '.join(result['artist_titles']),
'img_src': image_api + '/%(image_id)s/full/843,/0/default.jpg' % result, 'img_src': image_api + '/%(image_id)s/full/843,/0/default.jpg' % result,
'img_format': result['dimensions'], 'img_format': result['dimensions'],
'template': 'images.html' 'template': 'images.html',
}) }
)
return results return results

View File

@ -20,8 +20,9 @@ about = {
categories = ['science'] categories = ['science']
paging = True paging = True
base_url = 'https://export.arxiv.org/api/query?search_query=all:'\ base_url = (
+ '{query}&start={offset}&max_results={number_of_results}' 'https://export.arxiv.org/api/query?search_query=all:' + '{query}&start={offset}&max_results={number_of_results}'
)
# engine dependent config # engine dependent config
number_of_results = 10 number_of_results = 10
@ -31,9 +32,7 @@ def request(query, params):
# basic search # basic search
offset = (params['pageno'] - 1) * number_of_results offset = (params['pageno'] - 1) * number_of_results
string_args = dict(query=query, string_args = dict(query=query, offset=offset, number_of_results=number_of_results)
offset=offset,
number_of_results=number_of_results)
params['url'] = base_url.format(**string_args) params['url'] = base_url.format(**string_args)
@ -65,10 +64,7 @@ def response(resp):
publishedDate = datetime.strptime(eval_xpath_getindex(entry, './/published', 0).text, '%Y-%m-%dT%H:%M:%SZ') publishedDate = datetime.strptime(eval_xpath_getindex(entry, './/published', 0).text, '%Y-%m-%dT%H:%M:%SZ')
res_dict = {'url': url, res_dict = {'url': url, 'title': title, 'publishedDate': publishedDate, 'content': content}
'title': title,
'publishedDate': publishedDate,
'content': content}
results.append(res_dict) results.append(res_dict)

View File

@ -44,9 +44,7 @@ def request(query, params):
pageno : 1 # number of the requested page pageno : 1 # number of the requested page
''' '''
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), page=params['pageno'])
query=urlencode({'q': query}),
page=params['pageno'])
params['url'] = base_url + search_path params['url'] = base_url + search_path

View File

@ -21,8 +21,10 @@ about = {
categories = ['science'] categories = ['science']
base_url = 'https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi'\ base_url = (
'https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi'
+ '?func=PerformSearch&{query}&boost=oa&hits={hits}&offset={offset}' + '?func=PerformSearch&{query}&boost=oa&hits={hits}&offset={offset}'
)
# engine dependent config # engine dependent config
paging = True paging = True
@ -47,7 +49,7 @@ shorcut_dict = {
'source:': 'dcsource:', 'source:': 'dcsource:',
'subject:': 'dcsubject:', 'subject:': 'dcsubject:',
'title:': 'dctitle:', 'title:': 'dctitle:',
'type:': 'dcdctype:' 'type:': 'dcdctype:',
} }
@ -59,9 +61,7 @@ def request(query, params):
# basic search # basic search
offset = (params['pageno'] - 1) * number_of_results offset = (params['pageno'] - 1) * number_of_results
string_args = dict(query=urlencode({'query': query}), string_args = dict(query=urlencode({'query': query}), offset=offset, hits=number_of_results)
offset=offset,
hits=number_of_results)
params['url'] = base_url.format(**string_args) params['url'] = base_url.format(**string_args)
@ -93,7 +93,7 @@ def response(resp):
if len(item.text) > 300: if len(item.text) > 300:
content += "..." content += "..."
# dates returned by the BASE API are not several formats # dates returned by the BASE API are not several formats
publishedDate = None publishedDate = None
for date_format in ['%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d', '%Y-%m', '%Y']: for date_format in ['%Y-%m-%dT%H:%M:%SZ', '%Y-%m-%d', '%Y-%m', '%Y']:
try: try:
@ -103,14 +103,9 @@ def response(resp):
pass pass
if publishedDate is not None: if publishedDate is not None:
res_dict = {'url': url, res_dict = {'url': url, 'title': title, 'publishedDate': publishedDate, 'content': content}
'title': title,
'publishedDate': publishedDate,
'content': content}
else: else:
res_dict = {'url': url, res_dict = {'url': url, 'title': title, 'content': content}
'title': title,
'content': content}
results.append(res_dict) results.append(res_dict)

View File

@ -36,9 +36,11 @@ inital_query = 'search?{query}&search=&form=QBLH'
# following queries: https://www.bing.com/search?q=foo&search=&first=11&FORM=PERE # following queries: https://www.bing.com/search?q=foo&search=&first=11&FORM=PERE
page_query = 'search?{query}&search=&first={offset}&FORM=PERE' page_query = 'search?{query}&search=&first={offset}&FORM=PERE'
def _get_offset_from_pageno(pageno): def _get_offset_from_pageno(pageno):
return (pageno - 1) * 10 + 1 return (pageno - 1) * 10 + 1
def request(query, params): def request(query, params):
offset = _get_offset_from_pageno(params.get('pageno', 1)) offset = _get_offset_from_pageno(params.get('pageno', 1))
@ -53,30 +55,23 @@ def request(query, params):
if params['language'] == 'all': if params['language'] == 'all':
lang = 'EN' lang = 'EN'
else: else:
lang = match_language( lang = match_language(params['language'], supported_languages, language_aliases)
params['language'], supported_languages, language_aliases
)
query = 'language:{} {}'.format( query = 'language:{} {}'.format(lang.split('-')[0].upper(), query)
lang.split('-')[0].upper(), query
)
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), offset=offset)
query = urlencode({'q': query}),
offset = offset)
if offset > 1: if offset > 1:
referer = base_url + inital_query.format(query = urlencode({'q': query})) referer = base_url + inital_query.format(query=urlencode({'q': query}))
params['headers']['Referer'] = referer params['headers']['Referer'] = referer
logger.debug("headers.Referer --> %s", referer ) logger.debug("headers.Referer --> %s", referer)
params['url'] = base_url + search_path params['url'] = base_url + search_path
params['headers']['Accept-Language'] = "en-US,en;q=0.5" params['headers']['Accept-Language'] = "en-US,en;q=0.5"
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -95,11 +90,7 @@ def response(resp):
content = extract_text(eval_xpath(result, './/p')) content = extract_text(eval_xpath(result, './/p'))
# append result # append result
results.append({ results.append({'url': url, 'title': title, 'content': content})
'url': url,
'title': title,
'content': content
})
# parse results again if nothing is found yet # parse results again if nothing is found yet
for result in eval_xpath(dom, '//li[@class="b_algo"]'): for result in eval_xpath(dom, '//li[@class="b_algo"]'):
@ -110,18 +101,14 @@ def response(resp):
content = extract_text(eval_xpath(result, './/p')) content = extract_text(eval_xpath(result, './/p'))
# append result # append result
results.append({ results.append({'url': url, 'title': title, 'content': content})
'url': url,
'title': title,
'content': content
})
try: try:
result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()')) result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
if "-" in result_len_container: if "-" in result_len_container:
# Remove the part "from-to" for paginated request ... # Remove the part "from-to" for paginated request ...
result_len_container = result_len_container[result_len_container.find("-") * 2 + 2:] result_len_container = result_len_container[result_len_container.find("-") * 2 + 2 :]
result_len_container = re.sub('[^0-9]', '', result_len_container) result_len_container = re.sub('[^0-9]', '', result_len_container)

View File

@ -9,7 +9,10 @@ from json import loads
from searx.utils import match_language from searx.utils import match_language
from searx.engines.bing import language_aliases from searx.engines.bing import language_aliases
from searx.engines.bing import _fetch_supported_languages, supported_languages_url # NOQA # pylint: disable=unused-import from searx.engines.bing import (
_fetch_supported_languages,
supported_languages_url,
) # NOQA # pylint: disable=unused-import
# about # about
about = { about = {
@ -31,39 +34,25 @@ number_of_results = 28
# search-url # search-url
base_url = 'https://www.bing.com/' base_url = 'https://www.bing.com/'
search_string = 'images/search'\ search_string = 'images/search' '?{query}' '&count={count}' '&first={first}' '&tsc=ImageHoverTitle'
'?{query}'\
'&count={count}'\
'&first={first}'\
'&tsc=ImageHoverTitle'
time_range_string = '&qft=+filterui:age-lt{interval}' time_range_string = '&qft=+filterui:age-lt{interval}'
time_range_dict = {'day': '1440', time_range_dict = {'day': '1440', 'week': '10080', 'month': '43200', 'year': '525600'}
'week': '10080',
'month': '43200',
'year': '525600'}
# safesearch definitions # safesearch definitions
safesearch_types = {2: 'STRICT', safesearch_types = {2: 'STRICT', 1: 'DEMOTE', 0: 'OFF'}
1: 'DEMOTE',
0: 'OFF'}
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = ((params['pageno'] - 1) * number_of_results) + 1 offset = ((params['pageno'] - 1) * number_of_results) + 1
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), count=number_of_results, first=offset)
query=urlencode({'q': query}),
count=number_of_results,
first=offset)
language = match_language(params['language'], supported_languages, language_aliases).lower() language = match_language(params['language'], supported_languages, language_aliases).lower()
params['cookies']['SRCHHPGUSR'] = \ params['cookies']['SRCHHPGUSR'] = 'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
params['cookies']['_EDGE_S'] = 'mkt=' + language +\ params['cookies']['_EDGE_S'] = 'mkt=' + language + '&ui=' + language + '&F=1'
'&ui=' + language + '&F=1'
params['url'] = base_url + search_path params['url'] = base_url + search_path
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
@ -92,14 +81,18 @@ def response(resp):
# strip 'Unicode private use area' highlighting, they render to Tux # strip 'Unicode private use area' highlighting, they render to Tux
# the Linux penguin and a standing diamond on my machine... # the Linux penguin and a standing diamond on my machine...
title = m.get('t', '').replace('\ue000', '').replace('\ue001', '') title = m.get('t', '').replace('\ue000', '').replace('\ue001', '')
results.append({'template': 'images.html', results.append(
{
'template': 'images.html',
'url': m['purl'], 'url': m['purl'],
'thumbnail_src': m['turl'], 'thumbnail_src': m['turl'],
'img_src': m['murl'], 'img_src': m['murl'],
'content': '', 'content': '',
'title': title, 'title': title,
'source': source, 'source': source,
'img_format': img_format}) 'img_format': img_format,
}
)
except: except:
continue continue

View File

@ -13,10 +13,7 @@ from datetime import datetime
from dateutil import parser from dateutil import parser
from lxml import etree from lxml import etree
from lxml.etree import XPath from lxml.etree import XPath
from searx.utils import ( from searx.utils import match_language, eval_xpath_getindex
match_language,
eval_xpath_getindex
)
from searx.engines.bing import ( # pylint: disable=unused-import from searx.engines.bing import ( # pylint: disable=unused-import
language_aliases, language_aliases,
_fetch_supported_languages, _fetch_supported_languages,
@ -42,11 +39,8 @@ time_range_support = True
base_url = 'https://www.bing.com/' base_url = 'https://www.bing.com/'
search_string = 'news/search?{query}&first={offset}&format=RSS' search_string = 'news/search?{query}&first={offset}&format=RSS'
search_string_with_time = 'news/search?{query}&first={offset}&qft=interval%3d"{interval}"&format=RSS' search_string_with_time = 'news/search?{query}&first={offset}&qft=interval%3d"{interval}"&format=RSS'
time_range_dict = { time_range_dict = {'day': '7', 'week': '8', 'month': '9'}
'day': '7',
'week': '8',
'month': '9'
}
def url_cleanup(url_string): def url_cleanup(url_string):
"""remove click""" """remove click"""
@ -57,6 +51,7 @@ def url_cleanup(url_string):
url_string = query.get('url', None) url_string = query.get('url', None)
return url_string return url_string
def image_url_cleanup(url_string): def image_url_cleanup(url_string):
"""replace the http://*bing.com/th?id=... by https://www.bing.com/th?id=...""" """replace the http://*bing.com/th?id=... by https://www.bing.com/th?id=..."""
@ -66,6 +61,7 @@ def image_url_cleanup(url_string):
url_string = "https://www.bing.com/th?id=" + quote(query.get('id')) url_string = "https://www.bing.com/th?id=" + quote(query.get('id'))
return url_string return url_string
def _get_url(query, language, offset, time_range): def _get_url(query, language, offset, time_range):
if time_range in time_range_dict: if time_range in time_range_dict:
search_path = search_string_with_time.format( search_path = search_string_with_time.format(
@ -91,6 +87,7 @@ def _get_url(query, language, offset, time_range):
) )
return base_url + search_path return base_url + search_path
def request(query, params): def request(query, params):
if params['time_range'] and params['time_range'] not in time_range_dict: if params['time_range'] and params['time_range'] not in time_range_dict:
@ -105,6 +102,7 @@ def request(query, params):
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -127,26 +125,16 @@ def response(resp):
publishedDate = datetime.now() publishedDate = datetime.now()
# thumbnail # thumbnail
thumbnail = eval_xpath_getindex( thumbnail = eval_xpath_getindex(item, XPath('./News:Image/text()', namespaces=namespaces), 0, default=None)
item, XPath('./News:Image/text()', namespaces=namespaces), 0, default=None)
if thumbnail is not None: if thumbnail is not None:
thumbnail = image_url_cleanup(thumbnail) thumbnail = image_url_cleanup(thumbnail)
# append result # append result
if thumbnail is not None: if thumbnail is not None:
results.append({ results.append(
'url': url, {'url': url, 'title': title, 'publishedDate': publishedDate, 'content': content, 'img_src': thumbnail}
'title': title, )
'publishedDate': publishedDate,
'content': content,
'img_src': thumbnail
})
else: else:
results.append({ results.append({'url': url, 'title': title, 'publishedDate': publishedDate, 'content': content})
'url': url,
'title': title,
'publishedDate': publishedDate,
'content': content
})
return results return results

View File

@ -9,7 +9,10 @@ from urllib.parse import urlencode
from searx.utils import match_language from searx.utils import match_language
from searx.engines.bing import language_aliases from searx.engines.bing import language_aliases
from searx.engines.bing import _fetch_supported_languages, supported_languages_url # NOQA # pylint: disable=unused-import from searx.engines.bing import (
_fetch_supported_languages,
supported_languages_url,
) # NOQA # pylint: disable=unused-import
# about # about
about = { about = {
@ -28,36 +31,22 @@ time_range_support = True
number_of_results = 28 number_of_results = 28
base_url = 'https://www.bing.com/' base_url = 'https://www.bing.com/'
search_string = 'videos/search'\ search_string = 'videos/search' '?{query}' '&count={count}' '&first={first}' '&scope=video' '&FORM=QBLH'
'?{query}'\
'&count={count}'\
'&first={first}'\
'&scope=video'\
'&FORM=QBLH'
time_range_string = '&qft=+filterui:videoage-lt{interval}' time_range_string = '&qft=+filterui:videoage-lt{interval}'
time_range_dict = {'day': '1440', time_range_dict = {'day': '1440', 'week': '10080', 'month': '43200', 'year': '525600'}
'week': '10080',
'month': '43200',
'year': '525600'}
# safesearch definitions # safesearch definitions
safesearch_types = {2: 'STRICT', safesearch_types = {2: 'STRICT', 1: 'DEMOTE', 0: 'OFF'}
1: 'DEMOTE',
0: 'OFF'}
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = ((params['pageno'] - 1) * number_of_results) + 1 offset = ((params['pageno'] - 1) * number_of_results) + 1
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), count=number_of_results, first=offset)
query=urlencode({'q': query}),
count=number_of_results,
first=offset)
# safesearch cookie # safesearch cookie
params['cookies']['SRCHHPGUSR'] = \ params['cookies']['SRCHHPGUSR'] = 'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
'ADLT=' + safesearch_types.get(params['safesearch'], 'DEMOTE')
# language cookie # language cookie
language = match_language(params['language'], supported_languages, language_aliases).lower() language = match_language(params['language'], supported_languages, language_aliases).lower()
@ -89,11 +78,15 @@ def response(resp):
info = ' - '.join(result.xpath('.//div[@class="mc_vtvc_meta_block"]//span/text()')).strip() info = ' - '.join(result.xpath('.//div[@class="mc_vtvc_meta_block"]//span/text()')).strip()
content = '{0} - {1}'.format(metadata['du'], info) content = '{0} - {1}'.format(metadata['du'], info)
thumbnail = '{0}th?id={1}'.format(base_url, metadata['thid']) thumbnail = '{0}th?id={1}'.format(base_url, metadata['thid'])
results.append({'url': metadata['murl'], results.append(
{
'url': metadata['murl'],
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'title': metadata.get('vt', ''), 'title': metadata.get('vt', ''),
'content': content, 'content': content,
'template': 'videos.html'}) 'template': 'videos.html',
}
)
except: except:
continue continue

View File

@ -11,10 +11,7 @@ from searx.utils import extract_text, get_torrent_size
about = { about = {
"website": 'https://btdig.com', "website": 'https://btdig.com',
"wikidata_id": 'Q4836698', "wikidata_id": 'Q4836698',
"official_api_documentation": { "official_api_documentation": {'url': 'https://btdig.com/contacts', 'comment': 'on demand'},
'url': 'https://btdig.com/contacts',
'comment': 'on demand'
},
"use_official_api": False, "use_official_api": False,
"require_api_key": False, "require_api_key": False,
"results": 'HTML', "results": 'HTML',
@ -31,8 +28,7 @@ search_url = url + '/search?q={search_term}&p={pageno}'
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = search_url.format(search_term=quote(query), params['url'] = search_url.format(search_term=quote(query), pageno=params['pageno'] - 1)
pageno=params['pageno'] - 1)
return params return params
@ -77,13 +73,17 @@ def response(resp):
magnetlink = result.xpath('.//div[@class="torrent_magnet"]//a')[0].attrib['href'] magnetlink = result.xpath('.//div[@class="torrent_magnet"]//a')[0].attrib['href']
# append result # append result
results.append({'url': href, results.append(
{
'url': href,
'title': title, 'title': title,
'content': content, 'content': content,
'filesize': filesize, 'filesize': filesize,
'files': files, 'files': files,
'magnetlink': magnetlink, 'magnetlink': magnetlink,
'template': 'torrent.html'}) 'template': 'torrent.html',
}
)
# return results sorted by seeder # return results sorted by seeder
return results return results

View File

@ -29,10 +29,7 @@ search_string = '&page={page}&page_size={nb_per_page}&format=json&{query}'
def request(query, params): def request(query, params):
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), nb_per_page=nb_per_page, page=params['pageno'])
query=urlencode({'q': query}),
nb_per_page=nb_per_page,
page=params['pageno'])
params['url'] = base_url + search_path params['url'] = base_url + search_path
@ -45,9 +42,13 @@ def response(resp):
json_data = loads(resp.text) json_data = loads(resp.text)
for result in json_data['results']: for result in json_data['results']:
results.append({'url': result['foreign_landing_url'], results.append(
{
'url': result['foreign_landing_url'],
'title': result['title'], 'title': result['title'],
'img_src': result['url'], 'img_src': result['url'],
'template': 'images.html'}) 'template': 'images.html',
}
)
return results return results

View File

@ -138,7 +138,7 @@ def __check_query_params(params):
def check_parsing_options(engine_settings): def check_parsing_options(engine_settings):
""" Checks if delimiter based parsing or regex parsing is configured correctly """ """Checks if delimiter based parsing or regex parsing is configured correctly"""
if 'delimiter' not in engine_settings and 'parse_regex' not in engine_settings: if 'delimiter' not in engine_settings and 'parse_regex' not in engine_settings:
raise ValueError('failed to init settings for parsing lines: missing delimiter or parse_regex') raise ValueError('failed to init settings for parsing lines: missing delimiter or parse_regex')
@ -151,7 +151,7 @@ def check_parsing_options(engine_settings):
def __parse_single_result(raw_result): def __parse_single_result(raw_result):
""" Parses command line output based on configuration """ """Parses command line output based on configuration"""
result = {} result = {}
@ -167,6 +167,6 @@ def __parse_single_result(raw_result):
found = regex.search(raw_result) found = regex.search(raw_result)
if not found: if not found:
return {} return {}
result[result_key] = raw_result[found.start():found.end()] result[result_key] = raw_result[found.start() : found.end()]
return result return result

View File

@ -28,22 +28,24 @@ api_key = 'unset'
base_url = 'https://core.ac.uk:443/api-v2/search/' base_url = 'https://core.ac.uk:443/api-v2/search/'
search_string = '{query}?page={page}&pageSize={nb_per_page}&apiKey={apikey}' search_string = '{query}?page={page}&pageSize={nb_per_page}&apiKey={apikey}'
def request(query, params): def request(query, params):
if api_key == 'unset': if api_key == 'unset':
raise SearxEngineAPIException('missing CORE API key') raise SearxEngineAPIException('missing CORE API key')
search_path = search_string.format( search_path = search_string.format(
query = urlencode({'q': query}), query=urlencode({'q': query}),
nb_per_page = nb_per_page, nb_per_page=nb_per_page,
page = params['pageno'], page=params['pageno'],
apikey = api_key, apikey=api_key,
) )
params['url'] = base_url + search_path params['url'] = base_url + search_path
logger.debug("query_url --> %s", params['url']) logger.debug("query_url --> %s", params['url'])
return params return params
def response(resp): def response(resp):
results = [] results = []
json_data = loads(resp.text) json_data = loads(resp.text)
@ -52,7 +54,7 @@ def response(resp):
source = result['_source'] source = result['_source']
time = source['publishedDate'] or source['depositedDate'] time = source['publishedDate'] or source['depositedDate']
if time : if time:
date = datetime.fromtimestamp(time / 1000) date = datetime.fromtimestamp(time / 1000)
else: else:
date = None date = None
@ -66,12 +68,14 @@ def response(resp):
metadata.append(source['doi']) metadata.append(source['doi'])
metadata = ' / '.join(metadata) metadata = ' / '.join(metadata)
results.append({ results.append(
{
'url': source['urls'][0].replace('http://', 'https://', 1), 'url': source['urls'][0].replace('http://', 'https://', 1),
'title': source['title'], 'title': source['title'],
'content': source['description'], 'content': source['description'],
'publishedDate': date, 'publishedDate': date,
'metadata' : metadata, 'metadata': metadata,
}) }
)
return results return results

View File

@ -30,7 +30,7 @@ def request(query, params):
def response(resp): def response(resp):
"""remove first and last lines to get only json""" """remove first and last lines to get only json"""
json_resp = resp.text[resp.text.find('\n') + 1:resp.text.rfind('\n') - 2] json_resp = resp.text[resp.text.find('\n') + 1 : resp.text.rfind('\n') - 2]
results = [] results = []
try: try:
conversion_rate = float(json.loads(json_resp)['conversion']['converted-amount']) conversion_rate = float(json.loads(json_resp)['conversion']['converted-amount'])
@ -47,7 +47,8 @@ def response(resp):
) )
url = 'https://duckduckgo.com/js/spice/currency/1/{0}/{1}'.format( url = 'https://duckduckgo.com/js/spice/currency/1/{0}/{1}'.format(
resp.search_params['from'].upper(), resp.search_params['to']) resp.search_params['from'].upper(), resp.search_params['to']
)
results.append({'answer': answer, 'url': url}) results.append({'answer': answer, 'url': url})

View File

@ -25,8 +25,10 @@ paging = True
# search-url # search-url
# see http://www.dailymotion.com/doc/api/obj-video.html # see http://www.dailymotion.com/doc/api/obj-video.html
search_url = 'https://api.dailymotion.com/videos?fields=created_time,title,description,duration,url,thumbnail_360_url,id&sort=relevance&limit=5&page={pageno}&{query}' # noqa search_url = 'https://api.dailymotion.com/videos?fields=created_time,title,description,duration,url,thumbnail_360_url,id&sort=relevance&limit=5&page={pageno}&{query}' # noqa
embedded_url = '<iframe frameborder="0" width="540" height="304" ' +\ embedded_url = (
'data-src="https://www.dailymotion.com/embed/video/{videoid}" allowfullscreen></iframe>' '<iframe frameborder="0" width="540" height="304" '
+ 'data-src="https://www.dailymotion.com/embed/video/{videoid}" allowfullscreen></iframe>'
)
supported_languages_url = 'https://api.dailymotion.com/languages' supported_languages_url = 'https://api.dailymotion.com/languages'
@ -39,8 +41,8 @@ def request(query, params):
locale = match_language(params['language'], supported_languages) locale = match_language(params['language'], supported_languages)
params['url'] = search_url.format( params['url'] = search_url.format(
query=urlencode({'search': query, 'localization': locale}), query=urlencode({'search': query, 'localization': locale}), pageno=params['pageno']
pageno=params['pageno']) )
return params return params
@ -67,13 +69,17 @@ def response(resp):
# http to https # http to https
thumbnail = thumbnail.replace("http://", "https://") thumbnail = thumbnail.replace("http://", "https://")
results.append({'template': 'videos.html', results.append(
{
'template': 'videos.html',
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'embedded': embedded, 'embedded': embedded,
'thumbnail': thumbnail}) 'thumbnail': thumbnail,
}
)
# return results # return results
return results return results

View File

@ -24,9 +24,11 @@ paging = True
url = 'https://api.deezer.com/' url = 'https://api.deezer.com/'
search_url = url + 'search?{query}&index={offset}' search_url = url + 'search?{query}&index={offset}'
embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\ embedded_url = (
'data-src="https://www.deezer.com/plugins/player?type=tracks&id={audioid}" ' +\ '<iframe scrolling="no" frameborder="0" allowTransparency="true" '
'width="540" height="80"></iframe>' + 'data-src="https://www.deezer.com/plugins/player?type=tracks&id={audioid}" '
+ 'width="540" height="80"></iframe>'
)
# do search-request # do search-request
@ -53,18 +55,12 @@ def response(resp):
if url.startswith('http://'): if url.startswith('http://'):
url = 'https' + url[4:] url = 'https' + url[4:]
content = '{} - {} - {}'.format( content = '{} - {} - {}'.format(result['artist']['name'], result['album']['title'], result['title'])
result['artist']['name'],
result['album']['title'],
result['title'])
embedded = embedded_url.format(audioid=result['id']) embedded = embedded_url.format(audioid=result['id'])
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'embedded': embedded, 'content': content})
'title': title,
'embedded': embedded,
'content': content})
# return results # return results
return results return results

View File

@ -31,6 +31,7 @@ about = {
# if there is a need for globals, use a leading underline # if there is a need for globals, use a leading underline
_my_offline_engine = None _my_offline_engine = None
def init(engine_settings=None): def init(engine_settings=None):
"""Initialization of the (offline) engine. The origin of this demo engine is a """Initialization of the (offline) engine. The origin of this demo engine is a
simple json string which is loaded in this example while the engine is simple json string which is loaded in this example while the engine is
@ -44,11 +45,10 @@ def init(engine_settings=None):
', {"value":"first item"}' ', {"value":"first item"}'
', {"value":"second item"}' ', {"value":"second item"}'
', {"value":"third item"}' ', {"value":"third item"}'
']' ']' % engine_settings.get('name')
% engine_settings.get('name')
) )
def search(query, request_params): def search(query, request_params):
"""Query (offline) engine and return results. Assemble the list of results from """Query (offline) engine and return results. Assemble the list of results from
your local engine. In this demo engine we ignore the 'query' term, usual your local engine. In this demo engine we ignore the 'query' term, usual
@ -62,11 +62,11 @@ def search(query, request_params):
for row in result_list: for row in result_list:
entry = { entry = {
'query' : query, 'query': query,
'language' : request_params['language'], 'language': request_params['language'],
'value' : row.get("value"), 'value': row.get("value"),
# choose a result template or comment out to use the *default* # choose a result template or comment out to use the *default*
'template' : 'key-value.html', 'template': 'key-value.html',
} }
ret_val.append(entry) ret_val.append(entry)

View File

@ -43,6 +43,7 @@ about = {
# if there is a need for globals, use a leading underline # if there is a need for globals, use a leading underline
_my_online_engine = None _my_online_engine = None
def init(engine_settings): def init(engine_settings):
"""Initialization of the (online) engine. If no initialization is needed, drop """Initialization of the (online) engine. If no initialization is needed, drop
this init function. this init function.
@ -51,20 +52,24 @@ def init(engine_settings):
global _my_online_engine # pylint: disable=global-statement global _my_online_engine # pylint: disable=global-statement
_my_online_engine = engine_settings.get('name') _my_online_engine = engine_settings.get('name')
def request(query, params): def request(query, params):
"""Build up the ``params`` for the online request. In this example we build a """Build up the ``params`` for the online request. In this example we build a
URL to fetch images from `artic.edu <https://artic.edu>`__ URL to fetch images from `artic.edu <https://artic.edu>`__
""" """
args = urlencode({ args = urlencode(
'q' : query, {
'page' : params['pageno'], 'q': query,
'fields' : 'id,title,artist_display,medium_display,image_id,date_display,dimensions,artist_titles', 'page': params['pageno'],
'limit' : page_size, 'fields': 'id,title,artist_display,medium_display,image_id,date_display,dimensions,artist_titles',
}) 'limit': page_size,
}
)
params['url'] = search_api + args params['url'] = search_api + args
return params return params
def response(resp): def response(resp):
"""Parse out the result items from the response. In this example we parse the """Parse out the result items from the response. In this example we parse the
response from `api.artic.edu <https://artic.edu>`__ and filter out all response from `api.artic.edu <https://artic.edu>`__ and filter out all
@ -79,14 +84,16 @@ def response(resp):
if not result['image_id']: if not result['image_id']:
continue continue
results.append({ results.append(
{
'url': 'https://artic.edu/artworks/%(id)s' % result, 'url': 'https://artic.edu/artworks/%(id)s' % result,
'title': result['title'] + " (%(date_display)s) // %(artist_display)s" % result, 'title': result['title'] + " (%(date_display)s) // %(artist_display)s" % result,
'content': result['medium_display'], 'content': result['medium_display'],
'author': ', '.join(result['artist_titles']), 'author': ', '.join(result['artist_titles']),
'img_src': image_api + '/%(image_id)s/full/843,/0/default.jpg' % result, 'img_src': image_api + '/%(image_id)s/full/843,/0/default.jpg' % result,
'img_format': result['dimensions'], 'img_format': result['dimensions'],
'template': 'images.html' 'template': 'images.html',
}) }
)
return results return results

View File

@ -32,13 +32,14 @@ time_range_dict = {
# search-url # search-url
base_url = 'https://www.deviantart.com' base_url = 'https://www.deviantart.com'
def request(query, params): def request(query, params):
# https://www.deviantart.com/search/deviations?page=5&q=foo # https://www.deviantart.com/search/deviations?page=5&q=foo
query = { query = {
'page' : params['pageno'], 'page': params['pageno'],
'q' : query, 'q': query,
} }
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
query['order'] = time_range_dict[params['time_range']] query['order'] = time_range_dict[params['time_range']]
@ -47,6 +48,7 @@ def request(query, params):
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -67,11 +69,13 @@ def response(resp):
continue continue
img_tag = img_tag[0] img_tag = img_tag[0]
results.append({ results.append(
{
'template': 'images.html', 'template': 'images.html',
'url': a_tag.attrib.get('href'), 'url': a_tag.attrib.get('href'),
'img_src': img_tag.attrib.get('src'), 'img_src': img_tag.attrib.get('src'),
'title': img_tag.attrib.get('alt'), 'title': img_tag.attrib.get('alt'),
}) }
)
return results return results

View File

@ -27,9 +27,7 @@ https_support = True
def request(query, params): def request(query, params):
params['url'] = url.format(from_lang=params['from_lang'][2], params['url'] = url.format(from_lang=params['from_lang'][2], to_lang=params['to_lang'][2], query=params['query'])
to_lang=params['to_lang'][2],
query=params['query'])
return params return params
@ -51,10 +49,12 @@ def response(resp):
if t.strip(): if t.strip():
to_results.append(to_result.text_content()) to_results.append(to_result.text_content())
results.append({ results.append(
{
'url': urljoin(str(resp.url), '?%d' % k), 'url': urljoin(str(resp.url), '?%d' % k),
'title': from_result.text_content(), 'title': from_result.text_content(),
'content': '; '.join(to_results) 'content': '; '.join(to_results),
}) }
)
return results return results

View File

@ -48,13 +48,17 @@ def response(resp):
filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER]) filesize = get_torrent_size(files_data[FILESIZE], files_data[FILESIZE_MULTIPLIER])
magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0] magnetlink = result.xpath('.//div[@class="tail"]//a[@class="title"]/@href')[0]
results.append({'url': url, results.append(
{
'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
'filesize': filesize, 'filesize': filesize,
'magnetlink': magnetlink, 'magnetlink': magnetlink,
'seed': 'N/A', 'seed': 'N/A',
'leech': 'N/A', 'leech': 'N/A',
'template': 'torrent.html'}) 'template': 'torrent.html',
}
)
return results return results

View File

@ -15,7 +15,7 @@ about = {
"use_official_api": True, "use_official_api": True,
"require_api_key": False, "require_api_key": False,
"results": 'JSON', "results": 'JSON',
} }
categories = ['it'] # optional categories = ['it'] # optional
paging = True paging = True
@ -23,6 +23,7 @@ paging = True
base_url = "https://hub.docker.com/" base_url = "https://hub.docker.com/"
search_url = base_url + "api/content/v1/products/search?{query}&type=image&page_size=25" search_url = base_url + "api/content/v1/products/search?{query}&type=image&page_size=25"
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode(dict(q=query, page=params["pageno"]))) params['url'] = search_url.format(query=urlencode(dict(q=query, page=params["pageno"])))
@ -30,6 +31,7 @@ def request(query, params):
return params return params
def response(resp): def response(resp):
'''post-response callback '''post-response callback
resp: requests response object resp: requests response object
@ -53,12 +55,8 @@ def response(resp):
result["url"] = base_url + "r/" + item.get('slug', "") result["url"] = base_url + "r/" + item.get('slug', "")
result["title"] = item.get("name") result["title"] = item.get("name")
result["content"] = item.get("short_description") result["content"] = item.get("short_description")
result["publishedDate"] = parser.parse( result["publishedDate"] = parser.parse(item.get("updated_at") or item.get("created_at"))
item.get("updated_at") or item.get("created_at") result["thumbnail"] = item["logo_url"].get("large") or item["logo_url"].get("small")
)
result["thumbnail"] = (
item["logo_url"].get("large") or item["logo_url"].get("small")
)
results.append(result) results.append(result)
return results return results

View File

@ -25,8 +25,7 @@ number_of_results = 5
# search-url # search-url
# Doku is OpenSearch compatible # Doku is OpenSearch compatible
base_url = 'http://localhost:8090' base_url = 'http://localhost:8090'
search_url = '/?do=search'\ search_url = '/?do=search' '&{query}'
'&{query}'
# TODO '&startRecord={offset}'\ # TODO '&startRecord={offset}'\
# TODO '&maximumRecords={limit}'\ # TODO '&maximumRecords={limit}'\
@ -34,8 +33,7 @@ search_url = '/?do=search'\
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = base_url +\ params['url'] = base_url + search_url.format(query=urlencode({'id': query}))
search_url.format(query=urlencode({'id': query}))
return params return params
@ -60,9 +58,7 @@ def response(resp):
title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title')) title = extract_text(eval_xpath(r, './/a[@class="wikilink1"]/@title'))
# append result # append result
results.append({'title': title, results.append({'title': title, 'content': "", 'url': base_url + res_url})
'content': "",
'url': base_url + res_url})
# Search results # Search results
for r in eval_xpath(doc, '//dl[@class="search_results"]/*'): for r in eval_xpath(doc, '//dl[@class="search_results"]/*'):
@ -74,9 +70,7 @@ def response(resp):
content = extract_text(eval_xpath(r, '.')) content = extract_text(eval_xpath(r, '.'))
# append result # append result
results.append({'title': title, results.append({'title': title, 'content': content, 'url': base_url + res_url})
'content': content,
'url': base_url + res_url})
except: except:
continue continue

View File

@ -39,15 +39,10 @@ language_aliases = {
'ko': 'kr-KR', 'ko': 'kr-KR',
'sl-SI': 'sl-SL', 'sl-SI': 'sl-SL',
'zh-TW': 'tzh-TW', 'zh-TW': 'tzh-TW',
'zh-HK': 'tzh-HK' 'zh-HK': 'tzh-HK',
} }
time_range_dict = { time_range_dict = {'day': 'd', 'week': 'w', 'month': 'm', 'year': 'y'}
'day': 'd',
'week': 'w',
'month': 'm',
'year': 'y'
}
# search-url # search-url
url = 'https://lite.duckduckgo.com/lite' url = 'https://lite.duckduckgo.com/lite'
@ -118,6 +113,7 @@ def request(query, params):
logger.debug("param cookies: %s", params['cookies']) logger.debug("param cookies: %s", params['cookies'])
return params return params
# get response from search-request # get response from search-request
def response(resp): def response(resp):
@ -163,21 +159,24 @@ def response(resp):
if td_content is None: if td_content is None:
continue continue
results.append({ results.append(
{
'title': a_tag.text_content(), 'title': a_tag.text_content(),
'content': extract_text(td_content), 'content': extract_text(td_content),
'url': a_tag.get('href'), 'url': a_tag.get('href'),
}) }
)
return results return results
# get supported languages from their site # get supported languages from their site
def _fetch_supported_languages(resp): def _fetch_supported_languages(resp):
# response is a js file with regions as an embedded object # response is a js file with regions as an embedded object
response_page = resp.text response_page = resp.text
response_page = response_page[response_page.find('regions:{') + 8:] response_page = response_page[response_page.find('regions:{') + 8 :]
response_page = response_page[:response_page.find('}') + 1] response_page = response_page[: response_page.find('}') + 1]
regions_json = loads(response_page) regions_json = loads(response_page)
supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys()) supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys())

View File

@ -10,7 +10,10 @@ from lxml import html
from searx.data import WIKIDATA_UNITS from searx.data import WIKIDATA_UNITS
from searx.engines.duckduckgo import language_aliases from searx.engines.duckduckgo import language_aliases
from searx.engines.duckduckgo import _fetch_supported_languages, supported_languages_url # NOQA # pylint: disable=unused-import from searx.engines.duckduckgo import (
_fetch_supported_languages,
supported_languages_url,
) # NOQA # pylint: disable=unused-import
from searx.utils import extract_text, html_to_text, match_language, get_string_replaces_function from searx.utils import extract_text, html_to_text, match_language, get_string_replaces_function
from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom
@ -24,19 +27,15 @@ about = {
"results": 'JSON', "results": 'JSON',
} }
URL = 'https://api.duckduckgo.com/'\ URL = 'https://api.duckduckgo.com/' + '?{query}&format=json&pretty=0&no_redirect=1&d=1'
+ '?{query}&format=json&pretty=0&no_redirect=1&d=1'
WIKIDATA_PREFIX = [ WIKIDATA_PREFIX = ['http://www.wikidata.org/entity/', 'https://www.wikidata.org/entity/']
'http://www.wikidata.org/entity/',
'https://www.wikidata.org/entity/'
]
replace_http_by_https = get_string_replaces_function({'http:': 'https:'}) replace_http_by_https = get_string_replaces_function({'http:': 'https:'})
def is_broken_text(text): def is_broken_text(text):
""" duckduckgo may return something like "<a href="xxxx">http://somewhere Related website<a/>" """duckduckgo may return something like "<a href="xxxx">http://somewhere Related website<a/>"
The href URL is broken, the "Related website" may contains some HTML. The href URL is broken, the "Related website" may contains some HTML.
@ -61,11 +60,7 @@ def result_to_text(text, htmlResult):
def request(query, params): def request(query, params):
params['url'] = URL.format(query=urlencode({'q': query})) params['url'] = URL.format(query=urlencode({'q': query}))
language = match_language( language = match_language(params['language'], supported_languages, language_aliases)
params['language'],
supported_languages,
language_aliases
)
language = language.split('-')[0] language = language.split('-')[0]
params['headers']['Accept-Language'] = language params['headers']['Accept-Language'] = language
return params return params
@ -127,23 +122,14 @@ def response(resp):
firstURL = ddg_result.get('FirstURL') firstURL = ddg_result.get('FirstURL')
text = ddg_result.get('Text') text = ddg_result.get('Text')
if not is_broken_text(text): if not is_broken_text(text):
suggestion = result_to_text( suggestion = result_to_text(text, ddg_result.get('Result'))
text,
ddg_result.get('Result')
)
if suggestion != heading and suggestion is not None: if suggestion != heading and suggestion is not None:
results.append({'suggestion': suggestion}) results.append({'suggestion': suggestion})
elif 'Topics' in ddg_result: elif 'Topics' in ddg_result:
suggestions = [] suggestions = []
relatedTopics.append({ relatedTopics.append({'name': ddg_result.get('Name', ''), 'suggestions': suggestions})
'name': ddg_result.get('Name', ''),
'suggestions': suggestions
})
for topic_result in ddg_result.get('Topics', []): for topic_result in ddg_result.get('Topics', []):
suggestion = result_to_text( suggestion = result_to_text(topic_result.get('Text'), topic_result.get('Result'))
topic_result.get('Text'),
topic_result.get('Result')
)
if suggestion != heading and suggestion is not None: if suggestion != heading and suggestion is not None:
suggestions.append(suggestion) suggestions.append(suggestion)
@ -152,25 +138,15 @@ def response(resp):
if abstractURL != '': if abstractURL != '':
# add as result ? problem always in english # add as result ? problem always in english
infobox_id = abstractURL infobox_id = abstractURL
urls.append({ urls.append({'title': search_res.get('AbstractSource'), 'url': abstractURL, 'official': True})
'title': search_res.get('AbstractSource'), results.append({'url': abstractURL, 'title': heading})
'url': abstractURL,
'official': True
})
results.append({
'url': abstractURL,
'title': heading
})
# definition # definition
definitionURL = search_res.get('DefinitionURL', '') definitionURL = search_res.get('DefinitionURL', '')
if definitionURL != '': if definitionURL != '':
# add as result ? as answer ? problem always in english # add as result ? as answer ? problem always in english
infobox_id = definitionURL infobox_id = definitionURL
urls.append({ urls.append({'title': search_res.get('DefinitionSource'), 'url': definitionURL})
'title': search_res.get('DefinitionSource'),
'url': definitionURL
})
# to merge with wikidata's infobox # to merge with wikidata's infobox
if infobox_id: if infobox_id:
@ -198,10 +174,7 @@ def response(resp):
# * netflix_id # * netflix_id
external_url = get_external_url(data_type, data_value) external_url = get_external_url(data_type, data_value)
if external_url is not None: if external_url is not None:
urls.append({ urls.append({'title': data_label, 'url': external_url})
'title': data_label,
'url': external_url
})
elif data_type in ['instance', 'wiki_maps_trigger', 'google_play_artist_id']: elif data_type in ['instance', 'wiki_maps_trigger', 'google_play_artist_id']:
# ignore instance: Wikidata value from "Instance Of" (Qxxxx) # ignore instance: Wikidata value from "Instance Of" (Qxxxx)
# ignore wiki_maps_trigger: reference to a javascript # ignore wiki_maps_trigger: reference to a javascript
@ -211,11 +184,7 @@ def response(resp):
# There is already an URL for the website # There is already an URL for the website
pass pass
elif data_type == 'area': elif data_type == 'area':
attributes.append({ attributes.append({'label': data_label, 'value': area_to_str(data_value), 'entity': 'P2046'})
'label': data_label,
'value': area_to_str(data_value),
'entity': 'P2046'
})
osm_zoom = area_to_osm_zoom(data_value.get('amount')) osm_zoom = area_to_osm_zoom(data_value.get('amount'))
elif data_type == 'coordinates': elif data_type == 'coordinates':
if data_value.get('globe') == 'http://www.wikidata.org/entity/Q2': if data_value.get('globe') == 'http://www.wikidata.org/entity/Q2':
@ -224,16 +193,9 @@ def response(resp):
coordinates = info coordinates = info
else: else:
# coordinate NOT on Earth # coordinate NOT on Earth
attributes.append({ attributes.append({'label': data_label, 'value': data_value, 'entity': 'P625'})
'label': data_label,
'value': data_value,
'entity': 'P625'
})
elif data_type == 'string': elif data_type == 'string':
attributes.append({ attributes.append({'label': data_label, 'value': data_value})
'label': data_label,
'value': data_value
})
if coordinates: if coordinates:
data_label = coordinates.get('label') data_label = coordinates.get('label')
@ -241,31 +203,24 @@ def response(resp):
latitude = data_value.get('latitude') latitude = data_value.get('latitude')
longitude = data_value.get('longitude') longitude = data_value.get('longitude')
url = get_earth_coordinates_url(latitude, longitude, osm_zoom) url = get_earth_coordinates_url(latitude, longitude, osm_zoom)
urls.append({ urls.append({'title': 'OpenStreetMap', 'url': url, 'entity': 'P625'})
'title': 'OpenStreetMap',
'url': url,
'entity': 'P625'
})
if len(heading) > 0: if len(heading) > 0:
# TODO get infobox.meta.value where .label='article_title' # pylint: disable=fixme # TODO get infobox.meta.value where .label='article_title' # pylint: disable=fixme
if image is None and len(attributes) == 0 and len(urls) == 1 and\ if image is None and len(attributes) == 0 and len(urls) == 1 and len(relatedTopics) == 0 and len(content) == 0:
len(relatedTopics) == 0 and len(content) == 0: results.append({'url': urls[0]['url'], 'title': heading, 'content': content})
results.append({
'url': urls[0]['url'],
'title': heading,
'content': content
})
else: else:
results.append({ results.append(
{
'infobox': heading, 'infobox': heading,
'id': infobox_id, 'id': infobox_id,
'content': content, 'content': content,
'img_src': image, 'img_src': image,
'attributes': attributes, 'attributes': attributes,
'urls': urls, 'urls': urls,
'relatedTopics': relatedTopics 'relatedTopics': relatedTopics,
}) }
)
return results return results
@ -273,7 +228,7 @@ def response(resp):
def unit_to_str(unit): def unit_to_str(unit):
for prefix in WIKIDATA_PREFIX: for prefix in WIKIDATA_PREFIX:
if unit.startswith(prefix): if unit.startswith(prefix):
wikidata_entity = unit[len(prefix):] wikidata_entity = unit[len(prefix) :]
return WIKIDATA_UNITS.get(wikidata_entity, unit) return WIKIDATA_UNITS.get(wikidata_entity, unit)
return unit return unit

View File

@ -7,7 +7,10 @@ from json import loads
from urllib.parse import urlencode from urllib.parse import urlencode
from searx.exceptions import SearxEngineAPIException from searx.exceptions import SearxEngineAPIException
from searx.engines.duckduckgo import get_region_code from searx.engines.duckduckgo import get_region_code
from searx.engines.duckduckgo import _fetch_supported_languages, supported_languages_url # NOQA # pylint: disable=unused-import from searx.engines.duckduckgo import (
_fetch_supported_languages,
supported_languages_url,
) # NOQA # pylint: disable=unused-import
from searx.network import get from searx.network import get
# about # about
@ -41,8 +44,8 @@ def get_vqd(query, headers):
content = res.text content = res.text
if content.find('vqd=\'') == -1: if content.find('vqd=\'') == -1:
raise SearxEngineAPIException('Request failed') raise SearxEngineAPIException('Request failed')
vqd = content[content.find('vqd=\'') + 5:] vqd = content[content.find('vqd=\'') + 5 :]
vqd = vqd[:vqd.find('\'')] vqd = vqd[: vqd.find('\'')]
return vqd return vqd
@ -61,10 +64,10 @@ def request(query, params):
region_code = get_region_code(params['language'], lang_list=supported_languages) region_code = get_region_code(params['language'], lang_list=supported_languages)
if region_code: if region_code:
params['url'] = images_url.format( params['url'] = images_url.format(
query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd) query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd
)
else: else:
params['url'] = images_url.format( params['url'] = images_url.format(query=urlencode({'q': query}), offset=offset, safesearch=safesearch, vqd=vqd)
query=urlencode({'q': query}), offset=offset, safesearch=safesearch, vqd=vqd)
return params return params
@ -84,11 +87,15 @@ def response(resp):
image = result['image'] image = result['image']
# append result # append result
results.append({'template': 'images.html', results.append(
{
'template': 'images.html',
'title': title, 'title': title,
'content': '', 'content': '',
'thumbnail_src': thumbnail, 'thumbnail_src': thumbnail,
'img_src': image, 'img_src': image,
'url': url}) 'url': url,
}
)
return results return results

View File

@ -38,7 +38,7 @@ def request(query, params):
pageno : 1 # number of the requested page pageno : 1 # number of the requested page
''' '''
offset = (params['pageno'] - 1) offset = params['pageno'] - 1
if offset == 0: if offset == 0:
search_url_fmt = base_url + 'suchen/dudenonline/{query}' search_url_fmt = base_url + 'suchen/dudenonline/{query}'
params['url'] = search_url_fmt.format(query=quote(query)) params['url'] = search_url_fmt.format(query=quote(query))
@ -58,9 +58,9 @@ def response(resp):
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
number_of_results_element =\ number_of_results_element = eval_xpath_getindex(
eval_xpath_getindex(dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()', dom, '//a[@class="active" and contains(@href,"/suchen/dudenonline")]/span/text()', 0, default=None
0, default=None) )
if number_of_results_element is not None: if number_of_results_element is not None:
number_of_results_string = re.sub('[^0-9]', '', number_of_results_element) number_of_results_string = re.sub('[^0-9]', '', number_of_results_element)
results.append({'number_of_results': int(number_of_results_string)}) results.append({'number_of_results': int(number_of_results_string)})
@ -71,8 +71,6 @@ def response(resp):
title = eval_xpath(result, 'string(.//h2/a)').strip() title = eval_xpath(result, 'string(.//h2/a)').strip()
content = extract_text(eval_xpath(result, './/p')) content = extract_text(eval_xpath(result, './/p'))
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'content': content})
'title': title,
'content': content})
return results return results

View File

@ -15,6 +15,8 @@ about = {
def search(query, request_params): def search(query, request_params):
return [{ return [
{
'result': 'this is what you get', 'result': 'this is what you get',
}] }
]

View File

@ -58,7 +58,8 @@ def response(resp):
if title == "": if title == "":
continue continue
results.append({ results.append(
{
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
@ -67,7 +68,7 @@ def response(resp):
'source_country': source_country, 'source_country': source_country,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'template': 'products.html', 'template': 'products.html',
}
}) )
return results return results

View File

@ -119,9 +119,7 @@ def response(resp):
r['template'] = 'key-value.html' r['template'] = 'key-value.html'
if show_metadata: if show_metadata:
r['metadata'] = {'index': result['_index'], r['metadata'] = {'index': result['_index'], 'id': result['_id'], 'score': result['_score']}
'id': result['_id'],
'score': result['_score']}
results.append(r) results.append(r)
@ -133,12 +131,10 @@ _available_query_types = {
# https://www.elastic.co/guide/en/elasticsearch/reference/current/full-text-queries.html # https://www.elastic.co/guide/en/elasticsearch/reference/current/full-text-queries.html
'match': _match_query, 'match': _match_query,
'simple_query_string': _simple_query_string_query, 'simple_query_string': _simple_query_string_query,
# Term-level queries # Term-level queries
# https://www.elastic.co/guide/en/elasticsearch/reference/current/term-level-queries.html # https://www.elastic.co/guide/en/elasticsearch/reference/current/term-level-queries.html
'term': _term_query, 'term': _term_query,
'terms': _terms_query, 'terms': _terms_query,
# Query JSON defined by the instance administrator. # Query JSON defined by the instance administrator.
'custom': _custom_query, 'custom': _custom_query,
} }

View File

@ -22,10 +22,7 @@ paging = False
safesearch = True safesearch = True
base_url = 'https://www.etools.ch' base_url = 'https://www.etools.ch'
search_path = '/searchAdvancedSubmit.do'\ search_path = '/searchAdvancedSubmit.do' '?query={search_term}' '&pageResults=20' '&safeSearch={safesearch}'
'?query={search_term}'\
'&pageResults=20'\
'&safeSearch={safesearch}'
def request(query, params): def request(query, params):
@ -49,8 +46,6 @@ def response(resp):
title = extract_text(eval_xpath(result, './a//text()')) title = extract_text(eval_xpath(result, './a//text()'))
content = extract_text(eval_xpath(result, './/div[@class="text"]//text()')) content = extract_text(eval_xpath(result, './/div[@class="text"]//text()'))
results.append({'url': url, results.append({'url': url, 'title': title, 'content': content})
'title': title,
'content': content})
return results return results

View File

@ -42,13 +42,13 @@ def response(resp):
for app in dom.xpath('//a[@class="package-header"]'): for app in dom.xpath('//a[@class="package-header"]'):
app_url = app.xpath('./@href')[0] app_url = app.xpath('./@href')[0]
app_title = extract_text(app.xpath('./div/h4[@class="package-name"]/text()')) app_title = extract_text(app.xpath('./div/h4[@class="package-name"]/text()'))
app_content = extract_text(app.xpath('./div/div/span[@class="package-summary"]')).strip() \ app_content = (
+ ' - ' + extract_text(app.xpath('./div/div/span[@class="package-license"]')).strip() extract_text(app.xpath('./div/div/span[@class="package-summary"]')).strip()
+ ' - '
+ extract_text(app.xpath('./div/div/span[@class="package-license"]')).strip()
)
app_img_src = app.xpath('./img[@class="package-icon"]/@src')[0] app_img_src = app.xpath('./img[@class="package-icon"]/@src')[0]
results.append({'url': app_url, results.append({'url': app_url, 'title': app_title, 'content': app_content, 'img_src': app_img_src})
'title': app_title,
'content': app_content,
'img_src': app_img_src})
return results return results

View File

@ -25,10 +25,12 @@ paging = True
api_key = None api_key = None
url = 'https://api.flickr.com/services/rest/?method=flickr.photos.search' +\ url = (
'&api_key={api_key}&{text}&sort=relevance' +\ 'https://api.flickr.com/services/rest/?method=flickr.photos.search'
'&extras=description%2C+owner_name%2C+url_o%2C+url_n%2C+url_z' +\ + '&api_key={api_key}&{text}&sort=relevance'
'&per_page={nb_per_page}&format=json&nojsoncallback=1&page={page}' + '&extras=description%2C+owner_name%2C+url_o%2C+url_n%2C+url_z'
+ '&per_page={nb_per_page}&format=json&nojsoncallback=1&page={page}'
)
photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}' photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
paging = True paging = True
@ -39,10 +41,9 @@ def build_flickr_url(user_id, photo_id):
def request(query, params): def request(query, params):
params['url'] = url.format(text=urlencode({'text': query}), params['url'] = url.format(
api_key=api_key, text=urlencode({'text': query}), api_key=api_key, nb_per_page=nb_per_page, page=params['pageno']
nb_per_page=nb_per_page, )
page=params['pageno'])
return params return params
@ -69,7 +70,7 @@ def response(resp):
else: else:
continue continue
# For a bigger thumbnail, keep only the url_z, not the url_n # For a bigger thumbnail, keep only the url_z, not the url_n
if 'url_n' in photo: if 'url_n' in photo:
thumbnail_src = photo['url_n'] thumbnail_src = photo['url_n']
elif 'url_z' in photo: elif 'url_z' in photo:
@ -80,13 +81,17 @@ def response(resp):
url = build_flickr_url(photo['owner'], photo['id']) url = build_flickr_url(photo['owner'], photo['id'])
# append result # append result
results.append({'url': url, results.append(
{
'url': url,
'title': photo['title'], 'title': photo['title'],
'img_src': img_src, 'img_src': img_src,
'thumbnail_src': thumbnail_src, 'thumbnail_src': thumbnail_src,
'content': photo['description']['_content'], 'content': photo['description']['_content'],
'author': photo['ownername'], 'author': photo['ownername'],
'template': 'images.html'}) 'template': 'images.html',
}
)
# return results # return results
return results return results

View File

@ -30,10 +30,12 @@ image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')
paging = True paging = True
time_range_support = True time_range_support = True
time_range_dict = {'day': 60 * 60 * 24, time_range_dict = {
'day': 60 * 60 * 24,
'week': 60 * 60 * 24 * 7, 'week': 60 * 60 * 24 * 7,
'month': 60 * 60 * 24 * 7 * 4, 'month': 60 * 60 * 24 * 7 * 4,
'year': 60 * 60 * 24 * 7 * 52} 'year': 60 * 60 * 24 * 7 * 52,
}
def build_flickr_url(user_id, photo_id): def build_flickr_url(user_id, photo_id):
@ -47,8 +49,9 @@ def _get_time_range_url(time_range):
def request(query, params): def request(query, params):
params['url'] = (search_url.format(query=urlencode({'text': query}), page=params['pageno']) params['url'] = search_url.format(query=urlencode({'text': query}), page=params['pageno']) + _get_time_range_url(
+ _get_time_range_url(params['time_range'])) params['time_range']
)
return params return params
@ -83,10 +86,9 @@ def response(resp):
for image_size in image_sizes: for image_size in image_sizes:
if image_size in photo['sizes']: if image_size in photo['sizes']:
img_src = photo['sizes'][image_size]['url'] img_src = photo['sizes'][image_size]['url']
img_format = 'jpg ' \ img_format = (
+ str(photo['sizes'][image_size]['width']) \ 'jpg ' + str(photo['sizes'][image_size]['width']) + 'x' + str(photo['sizes'][image_size]['height'])
+ 'x' \ )
+ str(photo['sizes'][image_size]['height'])
break break
if not img_src: if not img_src:
@ -113,7 +115,7 @@ def response(resp):
'thumbnail_src': thumbnail_src, 'thumbnail_src': thumbnail_src,
'source': source, 'source': source,
'img_format': img_format, 'img_format': img_format,
'template': 'images.html' 'template': 'images.html',
} }
result['author'] = author.encode(errors='ignore').decode() result['author'] = author.encode(errors='ignore').decode()
result['source'] = source.encode(errors='ignore').decode() result['source'] = source.encode(errors='ignore').decode()

View File

@ -35,9 +35,8 @@ content_xpath = './/div[@class="content"]//p'
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) offset = params['pageno'] - 1
params['url'] = search_url.format(query=urlencode({'keys': query}), params['url'] = search_url.format(query=urlencode({'keys': query}), offset=offset)
offset=offset)
return params return params
@ -63,10 +62,7 @@ def response(resp):
content = escape(extract_text(result.xpath(content_xpath))) content = escape(extract_text(result.xpath(content_xpath)))
# append result # append result
results.append({'url': href, results.append({'url': href, 'title': title, 'img_src': thumbnail, 'content': content})
'title': title,
'img_src': thumbnail,
'content': content})
# return results # return results
return results return results

View File

@ -26,8 +26,7 @@ paging = True
# search url # search url
url = "https://freesound.org/apiv2/" url = "https://freesound.org/apiv2/"
search_url = ( search_url = (
url url + "search/text/?query={query}&page={page}&fields=name,url,download,created,description,type&token={api_key}"
+ "search/text/?query={query}&page={page}&fields=name,url,download,created,description,type&token={api_key}"
) )
embedded_url = '<audio controls><source src="{uri}" type="audio/{ftype}"></audio>' embedded_url = '<audio controls><source src="{uri}" type="audio/{ftype}"></audio>'

View File

@ -10,10 +10,7 @@ from urllib.parse import urlencode
about = { about = {
"website": 'https://frinkiac.com', "website": 'https://frinkiac.com',
"wikidata_id": 'Q24882614', "wikidata_id": 'Q24882614',
"official_api_documentation": { "official_api_documentation": {'url': None, 'comment': 'see https://github.com/MitchellAW/CompuGlobal'},
'url': None,
'comment': 'see https://github.com/MitchellAW/CompuGlobal'
},
"use_official_api": False, "use_official_api": False,
"require_api_key": False, "require_api_key": False,
"results": 'JSON', "results": 'JSON',
@ -40,12 +37,15 @@ def response(resp):
episode = result['Episode'] episode = result['Episode']
timestamp = result['Timestamp'] timestamp = result['Timestamp']
results.append({'template': 'images.html', results.append(
'url': RESULT_URL.format(base=BASE, {
query=urlencode({'p': 'caption', 'e': episode, 't': timestamp})), 'template': 'images.html',
'url': RESULT_URL.format(base=BASE, query=urlencode({'p': 'caption', 'e': episode, 't': timestamp})),
'title': episode, 'title': episode,
'content': '', 'content': '',
'thumbnail_src': THUMB_URL.format(base=BASE, episode=episode, timestamp=timestamp), 'thumbnail_src': THUMB_URL.format(base=BASE, episode=episode, timestamp=timestamp),
'img_src': IMAGE_URL.format(base=BASE, episode=episode, timestamp=timestamp)}) 'img_src': IMAGE_URL.format(base=BASE, episode=episode, timestamp=timestamp),
}
)
return results return results

View File

@ -37,15 +37,12 @@ def locale_to_lang_code(locale):
# wikis for some languages were moved off from the main site, we need to make # wikis for some languages were moved off from the main site, we need to make
# requests to correct URLs to be able to get results in those languages # requests to correct URLs to be able to get results in those languages
lang_urls = { lang_urls = {
'en': { 'en': {'base': 'https://wiki.gentoo.org', 'search': '/index.php?title=Special:Search&offset={offset}&{query}'},
'base': 'https://wiki.gentoo.org',
'search': '/index.php?title=Special:Search&offset={offset}&{query}'
},
'others': { 'others': {
'base': 'https://wiki.gentoo.org', 'base': 'https://wiki.gentoo.org',
'search': '/index.php?title=Special:Search&offset={offset}&{query}\ 'search': '/index.php?title=Special:Search&offset={offset}&{query}\
&profile=translation&languagefilter={language}' &profile=translation&languagefilter={language}',
} },
} }
@ -78,7 +75,7 @@ main_langs = {
'sl': 'Slovenský', 'sl': 'Slovenský',
'th': 'ไทย', 'th': 'ไทย',
'uk': 'Українська', 'uk': 'Українська',
'zh': '简体中文' 'zh': '简体中文',
} }
supported_languages = dict(lang_urls, **main_langs) supported_languages = dict(lang_urls, **main_langs)
@ -101,8 +98,7 @@ def request(query, params):
urls = get_lang_urls(language) urls = get_lang_urls(language)
search_url = urls['base'] + urls['search'] search_url = urls['base'] + urls['search']
params['url'] = search_url.format(query=query, offset=offset, params['url'] = search_url.format(query=query, offset=offset, language=language)
language=language)
return params return params
@ -123,7 +119,6 @@ def response(resp):
href = urljoin(base_url, link.attrib.get('href')) href = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link) title = extract_text(link)
results.append({'url': href, results.append({'url': href, 'title': title})
'title': title})
return results return results

View File

@ -55,12 +55,12 @@ def fetch_extra_param(query_args, headers):
extra_param_path = search_path + urlencode(query_args) extra_param_path = search_path + urlencode(query_args)
text = get(base_url + extra_param_path, headers=headers).text text = get(base_url + extra_param_path, headers=headers).text
re_var= None re_var = None
for line in text.splitlines(): for line in text.splitlines():
if re_var is None and extra_param_path in line: if re_var is None and extra_param_path in line:
var = line.split("=")[0].split()[1] # e.g. var --> 'uxrl' var = line.split("=")[0].split()[1] # e.g. var --> 'uxrl'
re_var = re.compile(var + "\\s*=\\s*" + var + "\\s*\\+\\s*'" + "(.*)" + "'(.*)") re_var = re.compile(var + "\\s*=\\s*" + var + "\\s*\\+\\s*'" + "(.*)" + "'(.*)")
extra_param = line.split("'")[1][len(extra_param_path):] extra_param = line.split("'")[1][len(extra_param_path) :]
continue continue
if re_var is not None and re_var.search(line): if re_var is not None and re_var.search(line):
extra_param += re_var.search(line).group(1) extra_param += re_var.search(line).group(1)
@ -69,12 +69,7 @@ def fetch_extra_param(query_args, headers):
# do search-request # do search-request
def request(query, params): # pylint: disable=unused-argument def request(query, params): # pylint: disable=unused-argument
query_args = dict( query_args = dict(c='main', q=query, dr=1, showgoodimages=0)
c = 'main'
, q = query
, dr = 1
, showgoodimages = 0
)
if params['language'] and params['language'] != 'all': if params['language'] and params['language'] != 'all':
query_args['qlangcountry'] = params['language'] query_args['qlangcountry'] = params['language']
@ -93,6 +88,7 @@ def request(query, params): # pylint: disable=unused-argument
return params return params
# get response from search-request # get response from search-request
def response(resp): def response(resp):
results = [] results = []
@ -125,10 +121,6 @@ def response(resp):
if len(subtitle) > 3 and subtitle != title: if len(subtitle) > 3 and subtitle != title:
title += " - " + subtitle title += " - " + subtitle
results.append(dict( results.append(dict(url=url, title=title, content=content))
url = url
, title = title
, content = content
))
return results return results

View File

@ -55,9 +55,7 @@ def response(resp):
content = '' content = ''
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'content': content})
'title': title,
'content': content})
# return results # return results
return results return results

View File

@ -100,22 +100,13 @@ google_domains = {
'UA': 'google.com.ua', # Ukraine 'UA': 'google.com.ua', # Ukraine
'CN': 'google.com.hk', # There is no google.cn, we use .com.hk for zh-CN 'CN': 'google.com.hk', # There is no google.cn, we use .com.hk for zh-CN
'HK': 'google.com.hk', # Hong Kong 'HK': 'google.com.hk', # Hong Kong
'TW': 'google.com.tw' # Taiwan 'TW': 'google.com.tw', # Taiwan
} }
time_range_dict = { time_range_dict = {'day': 'd', 'week': 'w', 'month': 'm', 'year': 'y'}
'day': 'd',
'week': 'w',
'month': 'm',
'year': 'y'
}
# Filter results. 0: None, 1: Moderate, 2: Strict # Filter results. 0: None, 1: Moderate, 2: Strict
filter_mapping = { filter_mapping = {0: 'off', 1: 'medium', 2: 'high'}
0: 'off',
1: 'medium',
2: 'high'
}
# specific xpath variables # specific xpath variables
# ------------------------ # ------------------------
@ -140,6 +131,7 @@ content_xpath = './/div[@class="IsZvec"]'
# from the links not the links itself. # from the links not the links itself.
suggestion_xpath = '//div[contains(@class, "EIaa9b")]//a' suggestion_xpath = '//div[contains(@class, "EIaa9b")]//a'
def get_lang_info(params, lang_list, custom_aliases, supported_any_language): def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
"""Composing various language properties for the google engines. """Composing various language properties for the google engines.
@ -184,11 +176,11 @@ def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
request's headers) request's headers)
""" """
ret_val = { ret_val = {
'language' : None, 'language': None,
'country' : None, 'country': None,
'subdomain' : None, 'subdomain': None,
'params' : {}, 'params': {},
'headers' : {}, 'headers': {},
} }
# language ... # language ...
@ -250,15 +242,18 @@ def get_lang_info(params, lang_list, custom_aliases, supported_any_language):
ret_val['params']['lr'] = "lang_" + lang_list.get(lang_country, language) ret_val['params']['lr'] = "lang_" + lang_list.get(lang_country, language)
# Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5 # Accept-Language: fr-CH, fr;q=0.8, en;q=0.6, *;q=0.5
ret_val['headers']['Accept-Language'] = ','.join([ ret_val['headers']['Accept-Language'] = ','.join(
[
lang_country, lang_country,
language + ';q=0.8,', language + ';q=0.8,',
'en;q=0.6', 'en;q=0.6',
'*;q=0.5', '*;q=0.5',
]) ]
)
return ret_val return ret_val
def detect_google_sorry(resp): def detect_google_sorry(resp):
if resp.url.host == 'sorry.google.com' or resp.url.path.startswith('/sorry'): if resp.url.host == 'sorry.google.com' or resp.url.path.startswith('/sorry'):
raise SearxEngineCaptchaException() raise SearxEngineCaptchaException()
@ -269,9 +264,7 @@ def request(query, params):
offset = (params['pageno'] - 1) * 10 offset = (params['pageno'] - 1) * 10
lang_info = get_lang_info( lang_info = get_lang_info(params, supported_languages, language_aliases, True)
params, supported_languages, language_aliases, True
)
additional_parameters = {} additional_parameters = {}
if use_mobile_ui: if use_mobile_ui:
@ -281,7 +274,13 @@ def request(query, params):
} }
# https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium # https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = (
'https://'
+ lang_info['subdomain']
+ '/search'
+ "?"
+ urlencode(
{
'q': query, 'q': query,
**lang_info['params'], **lang_info['params'],
'ie': "utf8", 'ie': "utf8",
@ -289,7 +288,9 @@ def request(query, params):
'start': offset, 'start': offset,
'filter': '0', 'filter': '0',
**additional_parameters, **additional_parameters,
}) }
)
)
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]}) query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
@ -301,9 +302,7 @@ def request(query, params):
if use_mobile_ui: if use_mobile_ui:
params['headers']['Accept'] = '*/*' params['headers']['Accept'] = '*/*'
else: else:
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
return params return params
@ -355,11 +354,7 @@ def response(resp):
if url is None: if url is None:
continue continue
content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True) content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True)
results.append({ results.append({'url': url, 'title': title, 'content': content})
'url': url,
'title': title,
'content': content
})
except Exception as e: # pylint: disable=broad-except except Exception as e: # pylint: disable=broad-except
logger.error(e, exc_info=True) logger.error(e, exc_info=True)
# from lxml import etree # from lxml import etree

View File

@ -30,10 +30,8 @@ from searx.engines.google import (
) )
# pylint: disable=unused-import # pylint: disable=unused-import
from searx.engines.google import ( from searx.engines.google import supported_languages_url, _fetch_supported_languages
supported_languages_url
, _fetch_supported_languages
)
# pylint: enable=unused-import # pylint: enable=unused-import
# about # about
@ -53,21 +51,16 @@ use_locale_domain = True
time_range_support = True time_range_support = True
safesearch = True safesearch = True
filter_mapping = { filter_mapping = {0: 'images', 1: 'active', 2: 'active'}
0: 'images',
1: 'active',
2: 'active'
}
def scrap_out_thumbs(dom): def scrap_out_thumbs(dom):
"""Scrap out thumbnail data from <script> tags. """Scrap out thumbnail data from <script> tags."""
"""
ret_val = {} ret_val = {}
for script in eval_xpath(dom, '//script[contains(., "_setImgSrc(")]'): for script in eval_xpath(dom, '//script[contains(., "_setImgSrc(")]'):
_script = script.text _script = script.text
# _setImgSrc('0','data:image\/jpeg;base64,\/9j\/4AAQSkZJR ....'); # _setImgSrc('0','data:image\/jpeg;base64,\/9j\/4AAQSkZJR ....');
_thumb_no, _img_data = _script[len("_setImgSrc("):-2].split(",", 1) _thumb_no, _img_data = _script[len("_setImgSrc(") : -2].split(",", 1)
_thumb_no = _thumb_no.replace("'", "") _thumb_no = _thumb_no.replace("'", "")
_img_data = _img_data.replace("'", "") _img_data = _img_data.replace("'", "")
_img_data = _img_data.replace(r"\/", r"/") _img_data = _img_data.replace(r"\/", r"/")
@ -76,8 +69,7 @@ def scrap_out_thumbs(dom):
def scrap_img_by_id(script, data_id): def scrap_img_by_id(script, data_id):
"""Get full image URL by data-id in parent element """Get full image URL by data-id in parent element"""
"""
img_url = '' img_url = ''
_script = script.split('\n') _script = script.split('\n')
for i, line in enumerate(_script): for i, line in enumerate(_script):
@ -91,20 +83,25 @@ def scrap_img_by_id(script, data_id):
def request(query, params): def request(query, params):
"""Google-Video search request""" """Google-Video search request"""
lang_info = get_lang_info( lang_info = get_lang_info(params, supported_languages, language_aliases, False)
params, supported_languages, language_aliases, False logger.debug("HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = (
'https://'
+ lang_info['subdomain']
+ '/search'
+ "?"
+ urlencode(
{
'q': query, 'q': query,
'tbm': "isch", 'tbm': "isch",
**lang_info['params'], **lang_info['params'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'num': 30, 'num': 30,
}) }
)
)
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]}) query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
@ -113,9 +110,7 @@ def request(query, params):
params['url'] = query_url params['url'] = query_url
params['headers'].update(lang_info['headers']) params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
return params return params
@ -128,8 +123,7 @@ def response(resp):
# convert the text to dom # convert the text to dom
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
img_bas64_map = scrap_out_thumbs(dom) img_bas64_map = scrap_out_thumbs(dom)
img_src_script = eval_xpath_getindex( img_src_script = eval_xpath_getindex(dom, '//script[contains(., "AF_initDataCallback({key: ")]', 1).text
dom, '//script[contains(., "AF_initDataCallback({key: ")]', 1).text
# parse results # parse results
# #
@ -189,7 +183,8 @@ def response(resp):
if not src_url: if not src_url:
src_url = thumbnail_src src_url = thumbnail_src
results.append({ results.append(
{
'url': url, 'url': url,
'title': img_alt, 'title': img_alt,
'content': pub_descr, 'content': pub_descr,
@ -197,7 +192,8 @@ def response(resp):
'img_src': src_url, 'img_src': src_url,
# 'img_format': img_format, # 'img_format': img_format,
'thumbnail_src': thumbnail_src, 'thumbnail_src': thumbnail_src,
'template': 'images.html' 'template': 'images.html',
}) }
)
return results return results

View File

@ -32,6 +32,7 @@ from searx.engines.google import (
supported_languages_url, supported_languages_url,
_fetch_supported_languages, _fetch_supported_languages,
) )
# pylint: enable=unused-import # pylint: enable=unused-import
from searx.engines.google import ( from searx.engines.google import (
@ -71,14 +72,12 @@ time_range_support = True
# safesearch : results are identitical for safesearch=0 and safesearch=2 # safesearch : results are identitical for safesearch=0 and safesearch=2
safesearch = False safesearch = False
def request(query, params): def request(query, params):
"""Google-News search request""" """Google-News search request"""
lang_info = get_lang_info( lang_info = get_lang_info(params, supported_languages, language_aliases, False)
params, supported_languages, language_aliases, False logger.debug("HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
# google news has only one domain # google news has only one domain
lang_info['subdomain'] = 'news.google.com' lang_info['subdomain'] = 'news.google.com'
@ -94,19 +93,26 @@ def request(query, params):
if params['time_range']: if params['time_range']:
query += ' ' + time_range_dict[params['time_range']] query += ' ' + time_range_dict[params['time_range']]
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = (
'https://'
+ lang_info['subdomain']
+ '/search'
+ "?"
+ urlencode(
{
'q': query, 'q': query,
**lang_info['params'], **lang_info['params'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'gl': lang_info['country'], 'gl': lang_info['country'],
}) + ('&ceid=%s' % ceid) # ceid includes a ':' character which must not be urlencoded }
)
+ ('&ceid=%s' % ceid)
) # ceid includes a ':' character which must not be urlencoded
params['url'] = query_url params['url'] = query_url
params['headers'].update(lang_info['headers']) params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
params['headers']['Cookie'] = "CONSENT=YES+cb.%s-14-p0.en+F+941;" % datetime.now().strftime("%Y%m%d") params['headers']['Cookie'] = "CONSENT=YES+cb.%s-14-p0.en+F+941;" % datetime.now().strftime("%Y%m%d")
return params return params
@ -141,7 +147,7 @@ def response(resp):
# jslog="95014; 5:W251bGwsbnVsbCxudW...giXQ==; track:click" # jslog="95014; 5:W251bGwsbnVsbCxudW...giXQ==; track:click"
jslog = jslog.split(";")[1].split(':')[1].strip() jslog = jslog.split(";")[1].split(':')[1].strip()
try: try:
padding = (4 -(len(jslog) % 4)) * "=" padding = (4 - (len(jslog) % 4)) * "="
jslog = b64decode(jslog + padding) jslog = b64decode(jslog + padding)
except binascii.Error: except binascii.Error:
# URL cant be read, skip this result # URL cant be read, skip this result
@ -178,12 +184,14 @@ def response(resp):
img_src = extract_text(result.xpath('preceding-sibling::a/figure/img/@src')) img_src = extract_text(result.xpath('preceding-sibling::a/figure/img/@src'))
results.append({ results.append(
{
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
'img_src': img_src, 'img_src': img_src,
}) }
)
# return results # return results
return results return results

View File

@ -32,6 +32,7 @@ from searx.engines.google import (
supported_languages_url, supported_languages_url,
_fetch_supported_languages, _fetch_supported_languages,
) )
# pylint: enable=unused-import # pylint: enable=unused-import
# about # about
@ -52,6 +53,7 @@ use_locale_domain = True
time_range_support = True time_range_support = True
safesearch = False safesearch = False
def time_range_url(params): def time_range_url(params):
"""Returns a URL query component for a google-Scholar time range based on """Returns a URL query component for a google-Scholar time range based on
``params['time_range']``. Google-Scholar does only support ranges in years. ``params['time_range']``. Google-Scholar does only support ranges in years.
@ -64,7 +66,7 @@ def time_range_url(params):
# as_ylo=2016&as_yhi=2019 # as_ylo=2016&as_yhi=2019
ret_val = '' ret_val = ''
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
ret_val= urlencode({'as_ylo': datetime.now().year -1 }) ret_val = urlencode({'as_ylo': datetime.now().year - 1})
return '&' + ret_val return '&' + ret_val
@ -72,34 +74,38 @@ def request(query, params):
"""Google-Scholar search request""" """Google-Scholar search request"""
offset = (params['pageno'] - 1) * 10 offset = (params['pageno'] - 1) * 10
lang_info = get_lang_info( lang_info = get_lang_info(params, supported_languages, language_aliases, False)
params, supported_languages, language_aliases, False logger.debug("HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
# subdomain is: scholar.google.xy # subdomain is: scholar.google.xy
lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.") lang_info['subdomain'] = lang_info['subdomain'].replace("www.", "scholar.")
query_url = 'https://'+ lang_info['subdomain'] + '/scholar' + "?" + urlencode({ query_url = (
'https://'
+ lang_info['subdomain']
+ '/scholar'
+ "?"
+ urlencode(
{
'q': query, 'q': query,
**lang_info['params'], **lang_info['params'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
'start' : offset, 'start': offset,
}) }
)
)
query_url += time_range_url(params) query_url += time_range_url(params)
params['url'] = query_url params['url'] = query_url
params['headers'].update(lang_info['headers']) params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
#params['google_subdomain'] = subdomain # params['google_subdomain'] = subdomain
return params return params
def response(resp): def response(resp):
"""Get response from google's search request""" """Get response from google's search request"""
results = [] results = []
@ -132,11 +138,13 @@ def response(resp):
if pub_type: if pub_type:
title = title + " " + pub_type title = title + " " + pub_type
results.append({ results.append(
{
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
}) }
)
# parse suggestion # parse suggestion
for suggestion in eval_xpath(dom, '//div[contains(@class, "gs_qsuggest_wrap")]//li//a'): for suggestion in eval_xpath(dom, '//div[contains(@class, "gs_qsuggest_wrap")]//li//a'):

View File

@ -38,10 +38,8 @@ from searx.engines.google import (
) )
# pylint: disable=unused-import # pylint: disable=unused-import
from searx.engines.google import ( from searx.engines.google import supported_languages_url, _fetch_supported_languages
supported_languages_url
, _fetch_supported_languages
)
# pylint: enable=unused-import # pylint: enable=unused-import
# about # about
@ -65,6 +63,7 @@ safesearch = True
RE_CACHE = {} RE_CACHE = {}
def _re(regexpr): def _re(regexpr):
"""returns compiled regular expression""" """returns compiled regular expression"""
RE_CACHE[regexpr] = RE_CACHE.get(regexpr, re.compile(regexpr)) RE_CACHE[regexpr] = RE_CACHE.get(regexpr, re.compile(regexpr))
@ -77,18 +76,17 @@ def scrap_out_thumbs_src(dom):
for script in eval_xpath_list(dom, '//script[contains(., "google.ldi={")]'): for script in eval_xpath_list(dom, '//script[contains(., "google.ldi={")]'):
_script = script.text _script = script.text
# "dimg_35":"https://i.ytimg.c....", # "dimg_35":"https://i.ytimg.c....",
_dimurl = _re("s='([^']*)").findall( _script) _dimurl = _re("s='([^']*)").findall(_script)
for k,v in _re('(' + thumb_name + '[0-9]*)":"(http[^"]*)' ).findall(_script): for k, v in _re('(' + thumb_name + '[0-9]*)":"(http[^"]*)').findall(_script):
v = v.replace(r'\u003d','=') v = v.replace(r'\u003d', '=')
v = v.replace(r'\u0026','&') v = v.replace(r'\u0026', '&')
ret_val[k] = v ret_val[k] = v
logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys()) logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
return ret_val return ret_val
def scrap_out_thumbs(dom): def scrap_out_thumbs(dom):
"""Scrap out thumbnail data from <script> tags. """Scrap out thumbnail data from <script> tags."""
"""
ret_val = {} ret_val = {}
thumb_name = 'dimg_' thumb_name = 'dimg_'
@ -96,7 +94,7 @@ def scrap_out_thumbs(dom):
_script = script.text _script = script.text
# var s='data:image/jpeg;base64, ...' # var s='data:image/jpeg;base64, ...'
_imgdata = _re("s='([^']*)").findall( _script) _imgdata = _re("s='([^']*)").findall(_script)
if not _imgdata: if not _imgdata:
continue continue
@ -112,19 +110,24 @@ def scrap_out_thumbs(dom):
def request(query, params): def request(query, params):
"""Google-Video search request""" """Google-Video search request"""
lang_info = get_lang_info( lang_info = get_lang_info(params, supported_languages, language_aliases, False)
params, supported_languages, language_aliases, False logger.debug("HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
)
logger.debug(
"HTTP header Accept-Language --> %s", lang_info['headers']['Accept-Language'])
query_url = 'https://' + lang_info['subdomain'] + '/search' + "?" + urlencode({ query_url = (
'https://'
+ lang_info['subdomain']
+ '/search'
+ "?"
+ urlencode(
{
'q': query, 'q': query,
'tbm': "vid", 'tbm': "vid",
**lang_info['params'], **lang_info['params'],
'ie': "utf8", 'ie': "utf8",
'oe': "utf8", 'oe': "utf8",
}) }
)
)
if params['time_range'] in time_range_dict: if params['time_range'] in time_range_dict:
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]}) query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
@ -133,9 +136,7 @@ def request(query, params):
params['url'] = query_url params['url'] = query_url
params['headers'].update(lang_info['headers']) params['headers'].update(lang_info['headers'])
params['headers']['Accept'] = ( params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
)
return params return params
@ -171,13 +172,13 @@ def response(resp):
title = extract_text(eval_xpath_getindex(result, title_xpath, 0)) title = extract_text(eval_xpath_getindex(result, title_xpath, 0))
url = eval_xpath_getindex(result, './/div[@class="dXiKIc"]//a/@href', 0) url = eval_xpath_getindex(result, './/div[@class="dXiKIc"]//a/@href', 0)
length = extract_text(eval_xpath( length = extract_text(eval_xpath(result, './/div[contains(@class, "P7xzyf")]/span/span'))
result, './/div[contains(@class, "P7xzyf")]/span/span'))
c_node = eval_xpath_getindex(result, './/div[@class="Uroaid"]', 0) c_node = eval_xpath_getindex(result, './/div[@class="Uroaid"]', 0)
content = extract_text(c_node) content = extract_text(c_node)
pub_info = extract_text(eval_xpath(result, './/div[@class="Zg1NU"]')) pub_info = extract_text(eval_xpath(result, './/div[@class="Zg1NU"]'))
results.append({ results.append(
{
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
@ -185,7 +186,8 @@ def response(resp):
'author': pub_info, 'author': pub_info,
'thumbnail': img_src, 'thumbnail': img_src,
'template': 'videos.html', 'template': 'videos.html',
}) }
)
# parse suggestion # parse suggestion
for suggestion in eval_xpath_list(dom, suggestion_xpath): for suggestion in eval_xpath_list(dom, suggestion_xpath):

View File

@ -27,7 +27,9 @@ about = {
"results": 'HTML', "results": 'HTML',
} }
categories = ['general', ] categories = [
'general',
]
paging = False paging = False
# suggestion_url = "https://sg.media-imdb.com/suggestion/{letter}/{query}.json" # suggestion_url = "https://sg.media-imdb.com/suggestion/{letter}/{query}.json"
@ -35,13 +37,7 @@ suggestion_url = "https://v2.sg.media-imdb.com/suggestion/{letter}/{query}.json"
href_base = 'https://imdb.com/{category}/{entry_id}' href_base = 'https://imdb.com/{category}/{entry_id}'
search_categories = { search_categories = {"nm": "name", "tt": "title", "kw": "keyword", "co": "company", "ep": "episode"}
"nm": "name",
"tt": "title",
"kw": "keyword",
"co": "company",
"ep": "episode"
}
def request(query, params): def request(query, params):
@ -63,9 +59,7 @@ def response(resp):
entry_id = entry['id'] entry_id = entry['id']
categ = search_categories.get(entry_id[:2]) categ = search_categories.get(entry_id[:2])
if categ is None: if categ is None:
logger.error( logger.error('skip unknown category tag %s in %s', entry_id[:2], entry_id)
'skip unknown category tag %s in %s', entry_id[:2], entry_id
)
continue continue
title = entry['l'] title = entry['l']
@ -95,11 +89,13 @@ def response(resp):
if not image_url_name.endswith('_V1_'): if not image_url_name.endswith('_V1_'):
magic = '_V1_' + magic magic = '_V1_' + magic
image_url = image_url_name + magic + '.' + image_url_prefix image_url = image_url_name + magic + '.' + image_url_prefix
results.append({ results.append(
{
"title": title, "title": title,
"url": href_base.format(category=categ, entry_id=entry_id), "url": href_base.format(category=categ, entry_id=entry_id),
"content": content, "content": content,
"img_src" : image_url, "img_src": image_url,
}) }
)
return results return results

View File

@ -41,9 +41,7 @@ content_xpath = './/p[@class="media-body__summary"]'
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = search_url.format(ps=page_size, params['url'] = search_url.format(ps=page_size, start=params['pageno'] * page_size, query=urlencode({'q': query}))
start=params['pageno'] * page_size,
query=urlencode({'q': query}))
return params return params
@ -75,12 +73,16 @@ def response(resp):
content = extract_text(result.xpath(content_xpath)) content = extract_text(result.xpath(content_xpath))
# append result # append result
results.append({'url': url, results.append(
{
'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
'template': 'videos.html', 'template': 'videos.html',
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'thumbnail': thumbnail}) 'thumbnail': thumbnail,
}
)
# return results # return results
return results return results

View File

@ -46,14 +46,10 @@ def request(query, params):
base_url_rand = base_url base_url_rand = base_url
search_url = base_url_rand + "api/v1/search?q={query}" search_url = base_url_rand + "api/v1/search?q={query}"
params["url"] = search_url.format( params["url"] = search_url.format(query=quote_plus(query)) + "&page={pageno}".format(pageno=params["pageno"])
query=quote_plus(query)
) + "&page={pageno}".format(pageno=params["pageno"])
if params["time_range"] in time_range_dict: if params["time_range"] in time_range_dict:
params["url"] += "&date={timerange}".format( params["url"] += "&date={timerange}".format(timerange=time_range_dict[params["time_range"]])
timerange=time_range_dict[params["time_range"]]
)
if params["language"] != "all": if params["language"] != "all":
lang = params["language"].split("-") lang = params["language"].split("-")
@ -88,17 +84,13 @@ def response(resp):
url = base_invidious_url + videoid url = base_invidious_url + videoid
embedded = embedded_url.format(videoid=videoid) embedded = embedded_url.format(videoid=videoid)
thumbs = result.get("videoThumbnails", []) thumbs = result.get("videoThumbnails", [])
thumb = next( thumb = next((th for th in thumbs if th["quality"] == "sddefault"), None)
(th for th in thumbs if th["quality"] == "sddefault"), None
)
if thumb: if thumb:
thumbnail = thumb.get("url", "") thumbnail = thumb.get("url", "")
else: else:
thumbnail = "" thumbnail = ""
publishedDate = parser.parse( publishedDate = parser.parse(time.ctime(result.get("published", 0)))
time.ctime(result.get("published", 0))
)
length = time.gmtime(result.get("lengthSeconds")) length = time.gmtime(result.get("lengthSeconds"))
if length.tm_hour: if length.tm_hour:
length = time.strftime("%H:%M:%S", length) length = time.strftime("%H:%M:%S", length)

View File

@ -119,22 +119,22 @@ def response(resp):
content = query(result, content_query)[0] content = query(result, content_query)[0]
except: except:
content = "" content = ""
results.append({ results.append(
{
'url': to_string(url), 'url': to_string(url),
'title': title_filter(to_string(title)), 'title': title_filter(to_string(title)),
'content': content_filter(to_string(content)), 'content': content_filter(to_string(content)),
}) }
)
else: else:
for url, title, content in zip( for url, title, content in zip(query(json, url_query), query(json, title_query), query(json, content_query)):
query(json, url_query), results.append(
query(json, title_query), {
query(json, content_query)
):
results.append({
'url': to_string(url), 'url': to_string(url),
'title': title_filter(to_string(title)), 'title': title_filter(to_string(title)),
'content': content_filter(to_string(content)), 'content': content_filter(to_string(content)),
}) }
)
if not suggestion_query: if not suggestion_query:
return results return results

View File

@ -34,8 +34,7 @@ content_xpath = './/span[@class="font11px lightgrey block"]'
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = search_url.format(search_term=quote(query), params['url'] = search_url.format(search_term=quote(query), pageno=params['pageno'])
pageno=params['pageno'])
return params return params
@ -79,7 +78,9 @@ def response(resp):
torrentfileurl = quote(torrentfile, safe="%/:=&?~#+!$,;'@()*") torrentfileurl = quote(torrentfile, safe="%/:=&?~#+!$,;'@()*")
# append result # append result
results.append({'url': href, results.append(
{
'url': href,
'title': title, 'title': title,
'content': content, 'content': content,
'seed': seed, 'seed': seed,
@ -88,7 +89,9 @@ def response(resp):
'files': files, 'files': files,
'magnetlink': magnetlink, 'magnetlink': magnetlink,
'torrentfile': torrentfileurl, 'torrentfile': torrentfileurl,
'template': 'torrent.html'}) 'template': 'torrent.html',
}
)
# return results sorted by seeder # return results sorted by seeder
return sorted(results, key=itemgetter('seed'), reverse=True) return sorted(results, key=itemgetter('seed'), reverse=True)

View File

@ -34,9 +34,7 @@ IMG_SRC_FIXES = {
def request(query, params): def request(query, params):
search_path = search_string.format( search_path = search_string.format(query=urlencode({'q': query}), page=params['pageno'])
query=urlencode({'q': query}),
page=params['pageno'])
params['url'] = base_url + search_path params['url'] = base_url + search_path
@ -56,13 +54,15 @@ def response(resp):
break break
else: else:
img_src = result['image']['thumb'] img_src = result['image']['thumb']
results.append({ results.append(
{
'url': result['links']['item'], 'url': result['links']['item'],
'title': result['title'], 'title': result['title'],
'img_src': img_src, 'img_src': img_src,
'thumbnail_src': result['image']['thumb'], 'thumbnail_src': result['image']['thumb'],
'author': result['creator'], 'author': result['creator'],
'template': 'images.html' 'template': 'images.html',
}) }
)
return results return results

View File

@ -22,29 +22,33 @@ paging = True
time_range_support = False time_range_support = False
safesearch = False safesearch = False
def request(query, params): def request(query, params):
params['url'] = 'https://mediathekviewweb.de/api/query' params['url'] = 'https://mediathekviewweb.de/api/query'
params['method'] = 'POST' params['method'] = 'POST'
params['headers']['Content-type'] = 'text/plain' params['headers']['Content-type'] = 'text/plain'
params['data'] = dumps({ params['data'] = dumps(
'queries' : [
{ {
'fields' : [ 'queries': [
{
'fields': [
'title', 'title',
'topic', 'topic',
], ],
'query' : query 'query': query,
}, },
], ],
'sortBy' : 'timestamp', 'sortBy': 'timestamp',
'sortOrder' : 'desc', 'sortOrder': 'desc',
'future' : True, 'future': True,
'offset' : (params['pageno'] - 1 )* 10, 'offset': (params['pageno'] - 1) * 10,
'size' : 10 'size': 10,
}) }
)
return params return params
def response(resp): def response(resp):
resp = loads(resp.text) resp = loads(resp.text)
@ -58,11 +62,13 @@ def response(resp):
item['hms'] = str(datetime.timedelta(seconds=item['duration'])) item['hms'] = str(datetime.timedelta(seconds=item['duration']))
results.append({ results.append(
'url' : item['url_video_hd'], {
'title' : "%(channel)s: %(title)s (%(hms)s)" % item, 'url': item['url_video_hd'],
'length' : item['hms'], 'title': "%(channel)s: %(title)s (%(hms)s)" % item,
'content' : "%(description)s" % item, 'length': item['hms'],
}) 'content': "%(description)s" % item,
}
)
return results return results

View File

@ -25,23 +25,24 @@ search_type = 'nearmatch' # possible values: title, text, nearmatch
# search-url # search-url
base_url = 'https://{language}.wikipedia.org/' base_url = 'https://{language}.wikipedia.org/'
search_postfix = 'w/api.php?action=query'\ search_postfix = (
'&list=search'\ 'w/api.php?action=query'
'&{query}'\ '&list=search'
'&format=json'\ '&{query}'
'&sroffset={offset}'\ '&format=json'
'&srlimit={limit}'\ '&sroffset={offset}'
'&srlimit={limit}'
'&srwhat={searchtype}' '&srwhat={searchtype}'
)
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * number_of_results offset = (params['pageno'] - 1) * number_of_results
string_args = dict(query=urlencode({'srsearch': query}), string_args = dict(
offset=offset, query=urlencode({'srsearch': query}), offset=offset, limit=number_of_results, searchtype=search_type
limit=number_of_results, )
searchtype=search_type)
format_strings = list(Formatter().parse(base_url)) format_strings = list(Formatter().parse(base_url))
@ -78,13 +79,14 @@ def response(resp):
for result in search_results['query']['search']: for result in search_results['query']['search']:
if result.get('snippet', '').startswith('#REDIRECT'): if result.get('snippet', '').startswith('#REDIRECT'):
continue continue
url = base_url.format(language=resp.search_params['language']) +\ url = (
'wiki/' + quote(result['title'].replace(' ', '_').encode()) base_url.format(language=resp.search_params['language'])
+ 'wiki/'
+ quote(result['title'].replace(' ', '_').encode())
)
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': result['title'], 'content': ''})
'title': result['title'],
'content': ''})
# return results # return results
return results return results

View File

@ -26,7 +26,8 @@ def request(query, params):
params['url'] = search_url params['url'] = search_url
params['method'] = 'POST' params['method'] = 'POST'
params['headers']['content-type'] = 'application/json; charset=utf-8' params['headers']['content-type'] = 'application/json; charset=utf-8'
params['data'] = dumps({ params['data'] = dumps(
{
'query': query, 'query': query,
'queryExpression': '', 'queryExpression': '',
'filters': [], 'filters': [],
@ -36,7 +37,8 @@ def request(query, params):
'take': 10, 'take': 10,
'includeCitationContexts': False, 'includeCitationContexts': False,
'profileId': '', 'profileId': '',
}) }
)
return params return params
@ -54,11 +56,13 @@ def response(resp):
title = result['paper']['dn'] title = result['paper']['dn']
content = _get_content(result['paper']) content = _get_content(result['paper'])
url = _paper_url.format(id=result['paper']['id']) url = _paper_url.format(id=result['paper']['id'])
results.append({ results.append(
{
'url': url, 'url': url,
'title': html_to_text(title), 'title': html_to_text(title),
'content': html_to_text(content), 'content': html_to_text(content),
}) }
)
return results return results

View File

@ -25,16 +25,17 @@ paging = True
url = 'https://api.mixcloud.com/' url = 'https://api.mixcloud.com/'
search_url = url + 'search/?{query}&type=cloudcast&limit=10&offset={offset}' search_url = url + 'search/?{query}&type=cloudcast&limit=10&offset={offset}'
embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\ embedded_url = (
'data-src="https://www.mixcloud.com/widget/iframe/?feed={url}" width="300" height="300"></iframe>' '<iframe scrolling="no" frameborder="0" allowTransparency="true" '
+ 'data-src="https://www.mixcloud.com/widget/iframe/?feed={url}" width="300" height="300"></iframe>'
)
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 10 offset = (params['pageno'] - 1) * 10
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}), offset=offset)
offset=offset)
return params return params
@ -54,11 +55,9 @@ def response(resp):
publishedDate = parser.parse(result['created_time']) publishedDate = parser.parse(result['created_time'])
# append result # append result
results.append({'url': url, results.append(
'title': title, {'url': url, 'title': title, 'embedded': embedded, 'publishedDate': publishedDate, 'content': content}
'embedded': embedded, )
'publishedDate': publishedDate,
'content': content})
# return results # return results
return results return results

View File

@ -26,38 +26,35 @@ result_template = 'key-value.html'
_client = None _client = None
def init(_): def init(_):
connect() connect()
def connect(): def connect():
global _client # pylint: disable=global-statement global _client # pylint: disable=global-statement
kwargs = { 'port': port } kwargs = {'port': port}
if username: if username:
kwargs['username'] = username kwargs['username'] = username
if password: if password:
kwargs['password'] = password kwargs['password'] = password
_client = MongoClient(host, **kwargs)[database][collection] _client = MongoClient(host, **kwargs)[database][collection]
def search(query, params): def search(query, params):
results = [] results = []
if exact_match_only: if exact_match_only:
q = { '$eq': query } q = {'$eq': query}
else: else:
_re = re.compile('.*{0}.*'.format(re.escape(query)), re.I | re.M ) _re = re.compile('.*{0}.*'.format(re.escape(query)), re.I | re.M)
q = { '$regex': _re } q = {'$regex': _re}
query = _client.find( query = _client.find({key: q}).skip((params['pageno'] - 1) * results_per_page).limit(results_per_page)
{key: q}
).skip(
( params['pageno'] -1 ) * results_per_page
).limit(
results_per_page
)
results.append({ 'number_of_results': query.count() }) results.append({'number_of_results': query.count()})
for r in query: for r in query:
del r['_id'] del r['_id']
r = { str(k):str(v) for k,v in r.items() } r = {str(k): str(v) for k, v in r.items()}
r['template'] = result_template r['template'] = result_template
results.append(r) results.append(r)

View File

@ -20,6 +20,7 @@ paging = True
result_template = 'key-value.html' result_template = 'key-value.html'
_connection = None _connection = None
def init(engine_settings): def init(engine_settings):
global _connection # pylint: disable=global-statement global _connection # pylint: disable=global-statement
@ -30,13 +31,14 @@ def init(engine_settings):
raise ValueError('only SELECT query is supported') raise ValueError('only SELECT query is supported')
_connection = mysql.connector.connect( _connection = mysql.connector.connect(
database = database, database=database,
user = username, user=username,
password = password, password=password,
host = host, host=host,
auth_plugin=auth_plugin, auth_plugin=auth_plugin,
) )
def search(query, params): def search(query, params):
query_params = {'query': query} query_params = {'query': query}
query_to_run = query_str + ' LIMIT {0} OFFSET {1}'.format(limit, (params['pageno'] - 1) * limit) query_to_run = query_str + ' LIMIT {0} OFFSET {1}'.format(limit, (params['pageno'] - 1) * limit)
@ -46,6 +48,7 @@ def search(query, params):
return _fetch_results(cur) return _fetch_results(cur)
def _fetch_results(cur): def _fetch_results(cur):
results = [] results = []
for res in cur: for res in cur:

View File

@ -98,7 +98,9 @@ def response(resp):
content = 'Category: "{category}". Downloaded {downloads} times.' content = 'Category: "{category}". Downloaded {downloads} times.'
content = content.format(category=category, downloads=downloads) content = content.format(category=category, downloads=downloads)
results.append({'url': href, results.append(
{
'url': href,
'title': title, 'title': title,
'content': content, 'content': content,
'seed': seed, 'seed': seed,
@ -106,6 +108,8 @@ def response(resp):
'filesize': filesize, 'filesize': filesize,
'torrentfile': torrent_link, 'torrentfile': torrent_link,
'magnetlink': magnet_link, 'magnetlink': magnet_link,
'template': 'torrent.html'}) 'template': 'torrent.html',
}
)
return results return results

View File

@ -151,10 +151,12 @@ def response(resp):
user_language = resp.search_params['language'] user_language = resp.search_params['language']
if resp.search_params['route']: if resp.search_params['route']:
results.append({ results.append(
{
'answer': gettext('Get directions'), 'answer': gettext('Get directions'),
'url': route_url.format(*resp.search_params['route'].groups()), 'url': route_url.format(*resp.search_params['route'].groups()),
}) }
)
fetch_wikidata(nominatim_json, user_language) fetch_wikidata(nominatim_json, user_language)
@ -170,7 +172,8 @@ def response(resp):
links, link_keys = get_links(result, user_language) links, link_keys = get_links(result, user_language)
data = get_data(result, user_language, link_keys) data = get_data(result, user_language, link_keys)
results.append({ results.append(
{
'template': 'map.html', 'template': 'map.html',
'title': title, 'title': title,
'address': address, 'address': address,
@ -181,15 +184,14 @@ def response(resp):
'img_src': img_src, 'img_src': img_src,
'links': links, 'links': links,
'data': data, 'data': data,
'type': get_tag_label( 'type': get_tag_label(result.get('category'), result.get('type', ''), user_language),
result.get('category'), result.get('type', ''), user_language
),
'type_icon': result.get('icon'), 'type_icon': result.get('icon'),
'content': '', 'content': '',
'longitude': result['lon'], 'longitude': result['lon'],
'latitude': result['lat'], 'latitude': result['lat'],
'boundingbox': result['boundingbox'], 'boundingbox': result['boundingbox'],
}) }
)
return results return results
@ -297,8 +299,7 @@ def get_title_address(result):
def get_url_osm_geojson(result): def get_url_osm_geojson(result):
"""Get url, osm and geojson """Get url, osm and geojson"""
"""
osm_type = result.get('osm_type', result.get('type')) osm_type = result.get('osm_type', result.get('type'))
if 'osm_id' not in result: if 'osm_id' not in result:
# see https://github.com/osm-search/Nominatim/issues/1521 # see https://github.com/osm-search/Nominatim/issues/1521
@ -349,11 +350,13 @@ def get_links(result, user_language):
url, url_label = mapping_function(raw_value) url, url_label = mapping_function(raw_value)
if url.startswith('https://wikidata.org'): if url.startswith('https://wikidata.org'):
url_label = result.get('wikidata', {}).get('itemLabel') or url_label url_label = result.get('wikidata', {}).get('itemLabel') or url_label
links.append({ links.append(
{
'label': get_key_label(k, user_language), 'label': get_key_label(k, user_language),
'url': url, 'url': url,
'url_label': url_label, 'url_label': url_label,
}) }
)
link_keys.add(k) link_keys.add(k)
return links, link_keys return links, link_keys
@ -373,11 +376,13 @@ def get_data(result, user_language, ignore_keys):
continue continue
k_label = get_key_label(k, user_language) k_label = get_key_label(k, user_language)
if k_label: if k_label:
data.append({ data.append(
{
'label': k_label, 'label': k_label,
'key': k, 'key': k,
'value': v, 'value': v,
}) }
)
data.sort(key=lambda entry: (get_key_rank(entry['key']), entry['label'])) data.sort(key=lambda entry: (get_key_rank(entry['key']), entry['label']))
return data return data

View File

@ -34,10 +34,7 @@ def request(query, params):
params['url'] = pdbe_solr_url params['url'] = pdbe_solr_url
params['method'] = 'POST' params['method'] = 'POST'
params['data'] = { params['data'] = {'q': query, 'wt': "json"} # request response in parsable format
'q': query,
'wt': "json" # request response in parsable format
}
return params return params
@ -53,12 +50,21 @@ def construct_body(result):
if result['journal']: if result['journal']:
content = content.format( content = content.format(
title=result['citation_title'], title=result['citation_title'],
authors=result['entry_author_list'][0], journal=result['journal'], volume=result['journal_volume'], authors=result['entry_author_list'][0],
page=result['journal_page'], year=result['citation_year']) journal=result['journal'],
volume=result['journal_volume'],
page=result['journal_page'],
year=result['citation_year'],
)
else: else:
content = content.format( content = content.format(
title=result['citation_title'], title=result['citation_title'],
authors=result['entry_author_list'][0], journal='', volume='', page='', year=result['release_year']) authors=result['entry_author_list'][0],
journal='',
volume='',
page='',
year=result['release_year'],
)
img_src = pdbe_preview_url.format(pdb_id=result['pdb_id']) img_src = pdbe_preview_url.format(pdb_id=result['pdb_id'])
except (KeyError): except (KeyError):
content = None content = None
@ -96,20 +102,21 @@ def response(resp):
# since we can't construct a proper body from the response, we'll make up our own # since we can't construct a proper body from the response, we'll make up our own
msg_superseded = gettext("This entry has been superseded by") msg_superseded = gettext("This entry has been superseded by")
content = '{msg_superseded}: {url} ({pdb_id})'.format( content = '{msg_superseded}: {url} ({pdb_id})'.format(
msg_superseded=msg_superseded, msg_superseded=msg_superseded, url=superseded_url, pdb_id=result['superseded_by']
url=superseded_url, )
pdb_id=result['superseded_by'])
# obsoleted entries don't have preview images # obsoleted entries don't have preview images
img_src = None img_src = None
else: else:
title, content, img_src = construct_body(result) title, content, img_src = construct_body(result)
results.append({ results.append(
{
'url': pdbe_entry_url.format(pdb_id=result['pdb_id']), 'url': pdbe_entry_url.format(pdb_id=result['pdb_id']),
'title': title, 'title': title,
'content': content, 'content': content,
'img_src': img_src 'img_src': img_src,
}) }
)
return results return results

View File

@ -36,9 +36,7 @@ def request(query, params):
language = params["language"].split("-")[0] language = params["language"].split("-")[0]
if "all" != language and language in supported_languages: if "all" != language and language in supported_languages:
query_dict["languageOneOf"] = language query_dict["languageOneOf"] = language
params["url"] = search_url.format( params["url"] = search_url.format(query=urlencode(query_dict), pageno=pageno)
query=urlencode(query_dict), pageno=pageno
)
return params return params

View File

@ -33,9 +33,7 @@ supported_languages = ['de', 'en', 'fr', 'it']
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = base_url +\ params['url'] = base_url + search_string.format(query=urlencode({'q': query}), limit=number_of_results)
search_string.format(query=urlencode({'q': query}),
limit=number_of_results)
if params['language'] != 'all': if params['language'] != 'all':
language = params['language'].split('_')[0] language = params['language'].split('_')[0]
@ -75,50 +73,60 @@ def response(resp):
# continue if invalide osm-type # continue if invalide osm-type
continue continue
url = result_base_url.format(osm_type=osm_type, url = result_base_url.format(osm_type=osm_type, osm_id=properties.get('osm_id'))
osm_id=properties.get('osm_id'))
osm = {'type': osm_type, osm = {'type': osm_type, 'id': properties.get('osm_id')}
'id': properties.get('osm_id')}
geojson = r.get('geometry') geojson = r.get('geometry')
if properties.get('extent'): if properties.get('extent'):
boundingbox = [properties.get('extent')[3], boundingbox = [
properties.get('extent')[3],
properties.get('extent')[1], properties.get('extent')[1],
properties.get('extent')[0], properties.get('extent')[0],
properties.get('extent')[2]] properties.get('extent')[2],
]
else: else:
# TODO: better boundingbox calculation # TODO: better boundingbox calculation
boundingbox = [geojson['coordinates'][1], boundingbox = [
geojson['coordinates'][1],
geojson['coordinates'][1], geojson['coordinates'][1],
geojson['coordinates'][0], geojson['coordinates'][0],
geojson['coordinates'][0]] geojson['coordinates'][0],
]
# address calculation # address calculation
address = {} address = {}
# get name # get name
if properties.get('osm_key') == 'amenity' or\ if (
properties.get('osm_key') == 'shop' or\ properties.get('osm_key') == 'amenity'
properties.get('osm_key') == 'tourism' or\ or properties.get('osm_key') == 'shop'
properties.get('osm_key') == 'leisure': or properties.get('osm_key') == 'tourism'
or properties.get('osm_key') == 'leisure'
):
address = {'name': properties.get('name')} address = {'name': properties.get('name')}
# add rest of adressdata, if something is already found # add rest of adressdata, if something is already found
if address.get('name'): if address.get('name'):
address.update({'house_number': properties.get('housenumber'), address.update(
{
'house_number': properties.get('housenumber'),
'road': properties.get('street'), 'road': properties.get('street'),
'locality': properties.get('city', 'locality': properties.get(
properties.get('town', # noqa 'city', properties.get('town', properties.get('village')) # noqa
properties.get('village'))), # noqa ), # noqa
'postcode': properties.get('postcode'), 'postcode': properties.get('postcode'),
'country': properties.get('country')}) 'country': properties.get('country'),
}
)
else: else:
address = None address = None
# append result # append result
results.append({'template': 'map.html', results.append(
{
'template': 'map.html',
'title': title, 'title': title,
'content': '', 'content': '',
'longitude': geojson['coordinates'][0], 'longitude': geojson['coordinates'][0],
@ -127,7 +135,9 @@ def response(resp):
'geojson': geojson, 'geojson': geojson,
'address': address, 'address': address,
'osm': osm, 'osm': osm,
'url': url}) 'url': url,
}
)
# return results # return results
return results return results

View File

@ -40,17 +40,14 @@ trackers = [
] ]
# piratebay specific type-definitions # piratebay specific type-definitions
search_types = {"files": "0", search_types = {"files": "0", "music": "100", "videos": "200"}
"music": "100",
"videos": "200"}
# do search-request # do search-request
def request(query, params): def request(query, params):
search_type = search_types.get(params["category"], "0") search_type = search_types.get(params["category"], "0")
params["url"] = search_url.format(search_term=quote(query), params["url"] = search_url.format(search_term=quote(query), search_type=search_type)
search_type=search_type)
return params return params
@ -68,8 +65,9 @@ def response(resp):
# parse results # parse results
for result in search_res: for result in search_res:
link = url + "description.php?id=" + result["id"] link = url + "description.php?id=" + result["id"]
magnetlink = "magnet:?xt=urn:btih:" + result["info_hash"] + "&dn=" + result["name"]\ magnetlink = (
+ "&tr=" + "&tr=".join(trackers) "magnet:?xt=urn:btih:" + result["info_hash"] + "&dn=" + result["name"] + "&tr=" + "&tr=".join(trackers)
)
params = { params = {
"url": link, "url": link,
@ -77,7 +75,7 @@ def response(resp):
"seed": result["seeders"], "seed": result["seeders"],
"leech": result["leechers"], "leech": result["leechers"],
"magnetlink": magnetlink, "magnetlink": magnetlink,
"template": "torrent.html" "template": "torrent.html",
} }
# extract and convert creation date # extract and convert creation date

View File

@ -20,6 +20,7 @@ paging = True
result_template = 'key-value.html' result_template = 'key-value.html'
_connection = None _connection = None
def init(engine_settings): def init(engine_settings):
global _connection # pylint: disable=global-statement global _connection # pylint: disable=global-statement
@ -30,25 +31,24 @@ def init(engine_settings):
raise ValueError('only SELECT query is supported') raise ValueError('only SELECT query is supported')
_connection = psycopg2.connect( _connection = psycopg2.connect(
database = database, database=database,
user = username, user=username,
password = password, password=password,
host = host, host=host,
port = port, port=port,
) )
def search(query, params): def search(query, params):
query_params = {'query': query} query_params = {'query': query}
query_to_run = ( query_to_run = query_str + ' LIMIT {0} OFFSET {1}'.format(limit, (params['pageno'] - 1) * limit)
query_str
+ ' LIMIT {0} OFFSET {1}'.format(limit, (params['pageno'] - 1) * limit)
)
with _connection: with _connection:
with _connection.cursor() as cur: with _connection.cursor() as cur:
cur.execute(query_to_run, query_params) cur.execute(query_to_run, query_params)
return _fetch_results(cur) return _fetch_results(cur)
def _fetch_results(cur): def _fetch_results(cur):
results = [] results = []
titles = [] titles = []

View File

@ -15,7 +15,7 @@ about = {
"wikidata_id": 'Q1540899', "wikidata_id": 'Q1540899',
"official_api_documentation": { "official_api_documentation": {
'url': 'https://www.ncbi.nlm.nih.gov/home/develop/api/', 'url': 'https://www.ncbi.nlm.nih.gov/home/develop/api/',
'comment': 'More info on api: https://www.ncbi.nlm.nih.gov/books/NBK25501/' 'comment': 'More info on api: https://www.ncbi.nlm.nih.gov/books/NBK25501/',
}, },
"use_official_api": True, "use_official_api": True,
"require_api_key": False, "require_api_key": False,
@ -24,8 +24,9 @@ about = {
categories = ['science'] categories = ['science']
base_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi'\ base_url = (
+ '?db=pubmed&{query}&retstart={offset}&retmax={hits}' 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi' + '?db=pubmed&{query}&retstart={offset}&retmax={hits}'
)
# engine dependent config # engine dependent config
number_of_results = 10 number_of_results = 10
@ -36,9 +37,7 @@ def request(query, params):
# basic search # basic search
offset = (params['pageno'] - 1) * number_of_results offset = (params['pageno'] - 1) * number_of_results
string_args = dict(query=urlencode({'term': query}), string_args = dict(query=urlencode({'term': query}), offset=offset, hits=number_of_results)
offset=offset,
hits=number_of_results)
params['url'] = base_url.format(**string_args) params['url'] = base_url.format(**string_args)
@ -49,8 +48,9 @@ def response(resp):
results = [] results = []
# First retrieve notice of each result # First retrieve notice of each result
pubmed_retrieve_api_url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?'\ pubmed_retrieve_api_url = (
+ 'db=pubmed&retmode=xml&id={pmids_string}' 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?' + 'db=pubmed&retmode=xml&id={pmids_string}'
)
pmids_results = etree.XML(resp.content) pmids_results = etree.XML(resp.content)
pmids = pmids_results.xpath('//eSearchResult/IdList/Id') pmids = pmids_results.xpath('//eSearchResult/IdList/Id')
@ -88,14 +88,17 @@ def response(resp):
content = content[0:300] + "..." content = content[0:300] + "..."
# TODO: center snippet on query term # TODO: center snippet on query term
res_dict = {'url': url, res_dict = {'url': url, 'title': title, 'content': content}
'title': title,
'content': content}
try: try:
publishedDate = datetime.strptime(entry.xpath('.//DateCreated/Year')[0].text publishedDate = datetime.strptime(
+ '-' + entry.xpath('.//DateCreated/Month')[0].text entry.xpath('.//DateCreated/Year')[0].text
+ '-' + entry.xpath('.//DateCreated/Day')[0].text, '%Y-%m-%d') + '-'
+ entry.xpath('.//DateCreated/Month')[0].text
+ '-'
+ entry.xpath('.//DateCreated/Day')[0].text,
'%Y-%m-%d',
)
res_dict['publishedDate'] = publishedDate res_dict['publishedDate'] = publishedDate
except: except:
pass pass

View File

@ -61,6 +61,7 @@ category_to_keyword = {
# search-url # search-url
url = 'https://api.qwant.com/v3/search/{keyword}?{query}&count={count}&offset={offset}' url = 'https://api.qwant.com/v3/search/{keyword}?{query}&count={count}&offset={offset}'
def request(query, params): def request(query, params):
"""Qwant search request""" """Qwant search request"""
keyword = category_to_keyword[categories[0]] keyword = category_to_keyword[categories[0]]
@ -77,10 +78,10 @@ def request(query, params):
offset = min(offset, 40) offset = min(offset, 40)
params['url'] = url.format( params['url'] = url.format(
keyword = keyword, keyword=keyword,
query = urlencode({'q': query}), query=urlencode({'q': query}),
offset = offset, offset=offset,
count = count, count=count,
) )
# add language tag # add language tag
@ -111,7 +112,14 @@ def response(resp):
# check for an API error # check for an API error
if search_results.get('status') != 'success': if search_results.get('status') != 'success':
msg = ",".join(data.get('message', ['unknown', ])) msg = ",".join(
data.get(
'message',
[
'unknown',
],
)
)
raise SearxEngineAPIException('API error::' + msg) raise SearxEngineAPIException('API error::' + msg)
# raise for other errors # raise for other errors
@ -128,7 +136,7 @@ def response(resp):
# result['items']. # result['items'].
mainline = data.get('result', {}).get('items', []) mainline = data.get('result', {}).get('items', [])
mainline = [ mainline = [
{'type' : keyword, 'items' : mainline }, {'type': keyword, 'items': mainline},
] ]
# return empty array if there are no results # return empty array if there are no results
@ -153,11 +161,13 @@ def response(resp):
if mainline_type == 'web': if mainline_type == 'web':
content = item['desc'] content = item['desc']
results.append({ results.append(
{
'title': title, 'title': title,
'url': res_url, 'url': res_url,
'content': content, 'content': content,
}) }
)
elif mainline_type == 'news': elif mainline_type == 'news':
@ -168,23 +178,27 @@ def response(resp):
img_src = None img_src = None
if news_media: if news_media:
img_src = news_media[0].get('pict', {}).get('url', None) img_src = news_media[0].get('pict', {}).get('url', None)
results.append({ results.append(
{
'title': title, 'title': title,
'url': res_url, 'url': res_url,
'publishedDate': pub_date, 'publishedDate': pub_date,
'img_src': img_src, 'img_src': img_src,
}) }
)
elif mainline_type == 'images': elif mainline_type == 'images':
thumbnail = item['thumbnail'] thumbnail = item['thumbnail']
img_src = item['media'] img_src = item['media']
results.append({ results.append(
{
'title': title, 'title': title,
'url': res_url, 'url': res_url,
'template': 'images.html', 'template': 'images.html',
'thumbnail_src': thumbnail, 'thumbnail_src': thumbnail,
'img_src': img_src, 'img_src': img_src,
}) }
)
elif mainline_type == 'videos': elif mainline_type == 'videos':
# some videos do not have a description: while qwant-video # some videos do not have a description: while qwant-video
@ -208,11 +222,9 @@ def response(resp):
thumbnail = item['thumbnail'] thumbnail = item['thumbnail']
# from some locations (DE and others?) the s2 link do # from some locations (DE and others?) the s2 link do
# response a 'Please wait ..' but does not deliver the thumbnail # response a 'Please wait ..' but does not deliver the thumbnail
thumbnail = thumbnail.replace( thumbnail = thumbnail.replace('https://s2.qwant.com', 'https://s1.qwant.com', 1)
'https://s2.qwant.com', results.append(
'https://s1.qwant.com', 1 {
)
results.append({
'title': title, 'title': title,
'url': res_url, 'url': res_url,
'content': content, 'content': content,
@ -220,7 +232,8 @@ def response(resp):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'template': 'videos.html', 'template': 'videos.html',
'length': length, 'length': length,
}) }
)
return results return results
@ -229,8 +242,8 @@ def response(resp):
def _fetch_supported_languages(resp): def _fetch_supported_languages(resp):
# list of regions is embedded in page as a js object # list of regions is embedded in page as a js object
response_text = resp.text response_text = resp.text
response_text = response_text[response_text.find('INITIAL_PROPS'):] response_text = response_text[response_text.find('INITIAL_PROPS') :]
response_text = response_text[response_text.find('{'):response_text.find('</script>')] response_text = response_text[response_text.find('{') : response_text.find('</script>')]
regions_json = loads(response_text) regions_json = loads(response_text)

View File

@ -28,18 +28,12 @@ mount_prefix = None
dl_prefix = None dl_prefix = None
# embedded # embedded
embedded_url = '<{ttype} controls height="166px" ' +\ embedded_url = '<{ttype} controls height="166px" ' + 'src="{url}" type="{mtype}"></{ttype}>'
'src="{url}" type="{mtype}"></{ttype}>'
# helper functions # helper functions
def get_time_range(time_range): def get_time_range(time_range):
sw = { sw = {'day': 1, 'week': 7, 'month': 30, 'year': 365}
'day': 1,
'week': 7,
'month': 30,
'year': 365
}
offset = sw.get(time_range, 0) offset = sw.get(time_range, 0)
if not offset: if not offset:
@ -52,11 +46,9 @@ def get_time_range(time_range):
def request(query, params): def request(query, params):
search_after = get_time_range(params['time_range']) search_after = get_time_range(params['time_range'])
search_url = base_url + 'json?{query}&highlight=0' search_url = base_url + 'json?{query}&highlight=0'
params['url'] = search_url.format(query=urlencode({ params['url'] = search_url.format(
'query': query, query=urlencode({'query': query, 'page': params['pageno'], 'after': search_after, 'dir': search_dir})
'page': params['pageno'], )
'after': search_after,
'dir': search_dir}))
return params return params
@ -76,10 +68,7 @@ def response(resp):
content = '{}'.format(result['snippet']) content = '{}'.format(result['snippet'])
# append result # append result
item = {'url': url, item = {'url': url, 'title': title, 'content': content, 'template': 'files.html'}
'title': title,
'content': content,
'template': 'files.html'}
if result['size']: if result['size']:
item['size'] = int(result['size']) item['size'] = int(result['size'])
@ -96,9 +85,8 @@ def response(resp):
if mtype in ['audio', 'video']: if mtype in ['audio', 'video']:
item['embedded'] = embedded_url.format( item['embedded'] = embedded_url.format(
ttype=mtype, ttype=mtype, url=quote(url.encode('utf8'), '/:'), mtype=result['mtype']
url=quote(url.encode('utf8'), '/:'), )
mtype=result['mtype'])
if mtype in ['image'] and subtype in ['bmp', 'gif', 'jpeg', 'png']: if mtype in ['image'] and subtype in ['bmp', 'gif', 'jpeg', 'png']:
item['img_src'] = url item['img_src'] = url

View File

@ -52,10 +52,7 @@ def response(resp):
data = post['data'] data = post['data']
# extract post information # extract post information
params = { params = {'url': urljoin(base_url, data['permalink']), 'title': data['title']}
'url': urljoin(base_url, data['permalink']),
'title': data['title']
}
# if thumbnail field contains a valid URL, we need to change template # if thumbnail field contains a valid URL, we need to change template
thumbnail = data['thumbnail'] thumbnail = data['thumbnail']

View File

@ -20,16 +20,19 @@ result_template = 'key-value.html'
exact_match_only = True exact_match_only = True
_redis_client = None _redis_client = None
def init(_engine_settings): def init(_engine_settings):
global _redis_client # pylint: disable=global-statement global _redis_client # pylint: disable=global-statement
_redis_client = redis.StrictRedis( _redis_client = redis.StrictRedis(
host = host, host=host,
port = port, port=port,
db = db, db=db,
password = password or None, password=password or None,
decode_responses = True, decode_responses=True,
) )
def search(query, _params): def search(query, _params):
if not exact_match_only: if not exact_match_only:
return search_keys(query) return search_keys(query)
@ -42,21 +45,20 @@ def search(query, _params):
if ' ' in query: if ' ' in query:
qset, rest = query.split(' ', 1) qset, rest = query.split(' ', 1)
ret = [] ret = []
for res in _redis_client.hscan_iter( for res in _redis_client.hscan_iter(qset, match='*{}*'.format(rest)):
qset, match='*{}*'.format(rest) ret.append(
): {
ret.append({
res[0]: res[1], res[0]: res[1],
'template': result_template, 'template': result_template,
}) }
)
return ret return ret
return [] return []
def search_keys(query): def search_keys(query):
ret = [] ret = []
for key in _redis_client.scan_iter( for key in _redis_client.scan_iter(match='*{}*'.format(query)):
match='*{}*'.format(query)
):
key_type = _redis_client.type(key) key_type = _redis_client.type(key)
res = None res = None

View File

@ -68,7 +68,8 @@ def response(resp):
else: else:
content = f"{views} views - {rumbles} rumbles" content = f"{views} views - {rumbles} rumbles"
results.append({ results.append(
{
'url': url, 'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
@ -77,5 +78,6 @@ def response(resp):
'template': 'videos.html', 'template': 'videos.html',
'publishedDate': fixed_date, 'publishedDate': fixed_date,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
}) }
)
return results return results

View File

@ -32,12 +32,16 @@ def request(query, params):
params['url'] = search_url params['url'] = search_url
params['method'] = 'POST' params['method'] = 'POST'
params['headers']['Content-type'] = "application/json" params['headers']['Content-type'] = "application/json"
params['data'] = dumps({"query": query, params['data'] = dumps(
{
"query": query,
"searchField": "ALL", "searchField": "ALL",
"sortDirection": "ASC", "sortDirection": "ASC",
"sortOrder": "RELEVANCY", "sortOrder": "RELEVANCY",
"page": params['pageno'], "page": params['pageno'],
"pageSize": page_size}) "pageSize": page_size,
}
)
return params return params
@ -69,11 +73,15 @@ def response(resp):
content = result['highlights'][0]['value'] content = result['highlights'][0]['value']
# append result # append result
results.append({'url': url + 'structure/' + result['id'], results.append(
{
'url': url + 'structure/' + result['id'],
'title': result['label'], 'title': result['label'],
# 'thumbnail': thumbnail, # 'thumbnail': thumbnail,
'img_src': thumbnail, 'img_src': thumbnail,
'content': html_to_text(content)}) 'content': html_to_text(content),
}
)
# return results # return results
return results return results

View File

@ -25,10 +25,7 @@ url = 'https://searchcode.com/'
search_url = url + 'api/codesearch_I/?{query}&p={pageno}' search_url = url + 'api/codesearch_I/?{query}&p={pageno}'
# special code-endings which are not recognised by the file ending # special code-endings which are not recognised by the file ending
code_endings = {'cs': 'c#', code_endings = {'cs': 'c#', 'h': 'c', 'hpp': 'cpp', 'cxx': 'cpp'}
'h': 'c',
'hpp': 'cpp',
'cxx': 'cpp'}
# do search-request # do search-request
@ -55,17 +52,21 @@ def response(resp):
lines[int(line)] = code lines[int(line)] = code
code_language = code_endings.get( code_language = code_endings.get(
result['filename'].split('.')[-1].lower(), result['filename'].split('.')[-1].lower(), result['filename'].split('.')[-1].lower()
result['filename'].split('.')[-1].lower()) )
# append result # append result
results.append({'url': href, results.append(
{
'url': href,
'title': title, 'title': title,
'content': '', 'content': '',
'repository': repo, 'repository': repo,
'codelines': sorted(lines.items()), 'codelines': sorted(lines.items()),
'code_language': code_language, 'code_language': code_language,
'template': 'code.html'}) 'template': 'code.html',
}
)
# return results # return results
return results return results

View File

@ -37,7 +37,7 @@ def request(query, params):
'language': params['language'], 'language': params['language'],
'time_range': params['time_range'], 'time_range': params['time_range'],
'category': params['category'], 'category': params['category'],
'format': 'json' 'format': 'json',
} }
return params return params

View File

@ -13,7 +13,8 @@ def request(query, params):
params['url'] = search_url params['url'] = search_url
params['method'] = 'POST' params['method'] = 'POST'
params['headers']['content-type'] = 'application/json' params['headers']['content-type'] = 'application/json'
params['data'] = dumps({ params['data'] = dumps(
{
"queryString": query, "queryString": query,
"page": params['pageno'], "page": params['pageno'],
"pageSize": 10, "pageSize": 10,
@ -25,7 +26,8 @@ def request(query, params):
"coAuthors": [], "coAuthors": [],
"venues": [], "venues": [],
"performTitleMatch": True, "performTitleMatch": True,
}) }
)
return params return params
@ -33,10 +35,12 @@ def response(resp):
res = loads(resp.text) res = loads(resp.text)
results = [] results = []
for result in res['results']: for result in res['results']:
results.append({ results.append(
{
'url': result['primaryPaperLink']['url'], 'url': result['primaryPaperLink']['url'],
'title': result['title']['text'], 'title': result['title']['text'],
'content': result['paperAbstractTruncated'] 'content': result['paperAbstractTruncated'],
}) }
)
return results return results

View File

@ -31,17 +31,13 @@ supported_languages = [
] ]
base_url = 'https://sepiasearch.org/api/v1/search/videos' base_url = 'https://sepiasearch.org/api/v1/search/videos'
safesearch_table = { safesearch_table = {0: 'both', 1: 'false', 2: 'false'}
0: 'both',
1: 'false',
2: 'false'
}
time_range_table = { time_range_table = {
'day': relativedelta.relativedelta(), 'day': relativedelta.relativedelta(),
'week': relativedelta.relativedelta(weeks=-1), 'week': relativedelta.relativedelta(weeks=-1),
'month': relativedelta.relativedelta(months=-1), 'month': relativedelta.relativedelta(months=-1),
'year': relativedelta.relativedelta(years=-1) 'year': relativedelta.relativedelta(years=-1),
} }
@ -55,13 +51,19 @@ def minute_to_hm(minute):
def request(query, params): def request(query, params):
params['url'] = base_url + '?' + urlencode({ params['url'] = (
base_url
+ '?'
+ urlencode(
{
'search': query, 'search': query,
'start': (params['pageno'] - 1) * 10, 'start': (params['pageno'] - 1) * 10,
'count': 10, 'count': 10,
'sort': '-match', 'sort': '-match',
'nsfw': safesearch_table[params['safesearch']] 'nsfw': safesearch_table[params['safesearch']],
}) }
)
)
language = params['language'].split('-')[0] language = params['language'].split('-')[0]
if language in supported_languages: if language in supported_languages:
@ -91,7 +93,9 @@ def response(resp):
length = minute_to_hm(result.get('duration')) length = minute_to_hm(result.get('duration'))
url = result['url'] url = result['url']
results.append({'url': url, results.append(
{
'url': url,
'title': title, 'title': title,
'content': content, 'content': content,
'author': author, 'author': author,
@ -99,6 +103,8 @@ def response(resp):
'template': 'videos.html', 'template': 'videos.html',
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'embedded': embedded, 'embedded': embedded,
'thumbnail': thumbnail}) 'thumbnail': thumbnail,
}
)
return results return results

View File

@ -58,10 +58,12 @@ def response(resp):
if result_data is None: if result_data is None:
continue continue
title_element = eval_xpath_getindex(result_element, './/h3/a', 0) title_element = eval_xpath_getindex(result_element, './/h3/a', 0)
results.append({ results.append(
{
'url': title_element.get('href'), 'url': title_element.get('href'),
'title': extract_text(title_element), 'title': extract_text(title_element),
'content': extract_text(eval_xpath(result_data, './/div[@class="_3eded7"]')), 'content': extract_text(eval_xpath(result_data, './/div[@class="_3eded7"]')),
}) }
)
return results return results

View File

@ -28,9 +28,11 @@ URL = 'https://sjp.pwn.pl'
SEARCH_URL = URL + '/szukaj/{query}.html' SEARCH_URL = URL + '/szukaj/{query}.html'
word_xpath = '//div[@class="query"]' word_xpath = '//div[@class="query"]'
dict_xpath = ['//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]', dict_xpath = [
'//div[@class="wyniki sjp-so-wyniki sjp-so-anchor"]',
'//div[@class="wyniki sjp-wyniki sjp-anchor"]', '//div[@class="wyniki sjp-wyniki sjp-anchor"]',
'//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]'] '//div[@class="wyniki sjp-doroszewski-wyniki sjp-doroszewski-anchor"]',
]
def request(query, params): def request(query, params):
@ -85,9 +87,11 @@ def response(resp):
infobox += "</ol>" infobox += "</ol>"
infobox += "</ul></div>" infobox += "</ul></div>"
results.append({ results.append(
{
'infobox': word, 'infobox': word,
'content': infobox, 'content': infobox,
}) }
)
return results return results

View File

@ -36,7 +36,8 @@ def response(resp):
search_results = loads(resp.text) search_results = loads(resp.text)
for result in search_results["results"]: for result in search_results["results"]:
results.append({ results.append(
{
'infohash': result["infohash"], 'infohash': result["infohash"],
'seed': result["swarm"]["seeders"], 'seed': result["swarm"]["seeders"],
'leech': result["swarm"]["leechers"], 'leech': result["swarm"]["leechers"],
@ -45,5 +46,6 @@ def response(resp):
'filesize': result["size"], 'filesize': result["size"],
'magnetlink': result["magnet"], 'magnetlink': result["magnet"],
'template': "torrent.html", 'template': "torrent.html",
}) }
)
return results return results

View File

@ -27,17 +27,21 @@ paging = True
# search-url # search-url
# missing attribute: user_id, app_version, app_locale # missing attribute: user_id, app_version, app_locale
url = 'https://api-v2.soundcloud.com/' url = 'https://api-v2.soundcloud.com/'
search_url = url + 'search?{query}'\ search_url = (
'&variant_ids='\ url + 'search?{query}'
'&facet=model'\ '&variant_ids='
'&limit=20'\ '&facet=model'
'&offset={offset}'\ '&limit=20'
'&linked_partitioning=1'\ '&offset={offset}'
'&client_id={client_id}' # noqa '&linked_partitioning=1'
'&client_id={client_id}'
) # noqa
embedded_url = '<iframe width="100%" height="166" ' +\ embedded_url = (
'scrolling="no" frameborder="no" ' +\ '<iframe width="100%" height="166" '
'data-src="https://w.soundcloud.com/player/?url={uri}"></iframe>' + 'scrolling="no" frameborder="no" '
+ 'data-src="https://w.soundcloud.com/player/?url={uri}"></iframe>'
)
cid_re = re.compile(r'client_id:"([^"]*)"', re.I | re.U) cid_re = re.compile(r'client_id:"([^"]*)"', re.I | re.U)
guest_client_id = '' guest_client_id = ''
@ -75,9 +79,7 @@ def init(engine_settings=None):
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 20 offset = (params['pageno'] - 1) * 20
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}), offset=offset, client_id=guest_client_id)
offset=offset,
client_id=guest_client_id)
return params return params
@ -98,11 +100,15 @@ def response(resp):
embedded = embedded_url.format(uri=uri) embedded = embedded_url.format(uri=uri)
# append result # append result
results.append({'url': result['permalink_url'], results.append(
{
'url': result['permalink_url'],
'title': title, 'title': title,
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'embedded': embedded, 'embedded': embedded,
'content': content}) 'content': content,
}
)
# return results # return results
return results return results

View File

@ -42,9 +42,10 @@ def request(query, params):
r = http_post( r = http_post(
'https://accounts.spotify.com/api/token', 'https://accounts.spotify.com/api/token',
data={'grant_type': 'client_credentials'}, data={'grant_type': 'client_credentials'},
headers={'Authorization': 'Basic ' + base64.b64encode( headers={
"{}:{}".format(api_client_id, api_client_secret).encode() 'Authorization': 'Basic '
).decode()} + base64.b64encode("{}:{}".format(api_client_id, api_client_secret).encode()).decode()
},
) )
j = loads(r.text) j = loads(r.text)
params['headers'] = {'Authorization': 'Bearer {}'.format(j.get('access_token'))} params['headers'] = {'Authorization': 'Bearer {}'.format(j.get('access_token'))}
@ -63,18 +64,12 @@ def response(resp):
if result['type'] == 'track': if result['type'] == 'track':
title = result['name'] title = result['name']
url = result['external_urls']['spotify'] url = result['external_urls']['spotify']
content = '{} - {} - {}'.format( content = '{} - {} - {}'.format(result['artists'][0]['name'], result['album']['name'], result['name'])
result['artists'][0]['name'],
result['album']['name'],
result['name'])
embedded = embedded_url.format(audioid=result['id']) embedded = embedded_url.format(audioid=result['id'])
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'embedded': embedded, 'content': content})
'title': title,
'embedded': embedded,
'content': content})
# return results # return results
return results return results

View File

@ -26,15 +26,11 @@ api_key = 'unset'
base_url = 'https://api.springernature.com/metadata/json?' base_url = 'https://api.springernature.com/metadata/json?'
def request(query, params): def request(query, params):
if api_key == 'unset': if api_key == 'unset':
raise SearxEngineAPIException('missing Springer-Nature API key') raise SearxEngineAPIException('missing Springer-Nature API key')
args = urlencode({ args = urlencode({'q': query, 's': nb_per_page * (params['pageno'] - 1), 'p': nb_per_page, 'api_key': api_key})
'q' : query,
's' : nb_per_page * (params['pageno'] - 1),
'p' : nb_per_page,
'api_key' : api_key
})
params['url'] = base_url + args params['url'] = base_url + args
logger.debug("query_url --> %s", params['url']) logger.debug("query_url --> %s", params['url'])
return params return params
@ -50,21 +46,27 @@ def response(resp):
content += "..." content += "..."
published = datetime.strptime(record['publicationDate'], '%Y-%m-%d') published = datetime.strptime(record['publicationDate'], '%Y-%m-%d')
metadata = [record[x] for x in [ metadata = [
record[x]
for x in [
'publicationName', 'publicationName',
'identifier', 'identifier',
'contentType', 'contentType',
] if record.get(x) is not None] ]
if record.get(x) is not None
]
metadata = ' / '.join(metadata) metadata = ' / '.join(metadata)
if record.get('startingPage') and record.get('endingPage') is not None: if record.get('startingPage') and record.get('endingPage') is not None:
metadata += " (%(startingPage)s-%(endingPage)s)" % record metadata += " (%(startingPage)s-%(endingPage)s)" % record
results.append({ results.append(
{
'title': record['title'], 'title': record['title'],
'url': record['url'][0]['value'].replace('http://', 'https://', 1), 'url': record['url'][0]['value'].replace('http://', 'https://', 1),
'content' : content, 'content': content,
'publishedDate' : published, 'publishedDate': published,
'metadata' : metadata 'metadata': metadata,
}) }
)
return results return results

View File

@ -49,7 +49,7 @@ def search(query, params):
'query': query, 'query': query,
'wildcard': r'%' + query.replace(' ', r'%') + r'%', 'wildcard': r'%' + query.replace(' ', r'%') + r'%',
'limit': limit, 'limit': limit,
'offset': (params['pageno'] - 1) * limit 'offset': (params['pageno'] - 1) * limit,
} }
query_to_run = query_str + ' LIMIT :limit OFFSET :offset' query_to_run = query_str + ' LIMIT :limit OFFSET :offset'
@ -59,7 +59,7 @@ def search(query, params):
col_names = [cn[0] for cn in cur.description] col_names = [cn[0] for cn in cur.description]
for row in cur.fetchall(): for row in cur.fetchall():
item = dict( zip(col_names, map(str, row)) ) item = dict(zip(col_names, map(str, row)))
item['template'] = result_template item['template'] = result_template
logger.debug("append result --> %s", item) logger.debug("append result --> %s", item)
results.append(item) results.append(item)

View File

@ -23,26 +23,30 @@ paging = True
pagesize = 10 pagesize = 10
api_site = 'stackoverflow' api_site = 'stackoverflow'
api_sort= 'activity' api_sort = 'activity'
api_order = 'desc' api_order = 'desc'
# https://api.stackexchange.com/docs/advanced-search # https://api.stackexchange.com/docs/advanced-search
search_api = 'https://api.stackexchange.com/2.3/search/advanced?' search_api = 'https://api.stackexchange.com/2.3/search/advanced?'
def request(query, params): def request(query, params):
args = urlencode({ args = urlencode(
'q' : query, {
'page' : params['pageno'], 'q': query,
'pagesize' : pagesize, 'page': params['pageno'],
'site' : api_site, 'pagesize': pagesize,
'sort' : api_sort, 'site': api_site,
'sort': api_sort,
'order': 'desc', 'order': 'desc',
}) }
)
params['url'] = search_api + args params['url'] = search_api + args
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -56,10 +60,12 @@ def response(resp):
content += ' // is answered' content += ' // is answered'
content += " // score: %s" % result['score'] content += " // score: %s" % result['score']
results.append({ results.append(
{
'url': "https://%s.com/q/%s" % (api_site, result['question_id']), 'url': "https://%s.com/q/%s" % (api_site, result['question_id']),
'title': html.unescape(result['title']), 'title': html.unescape(result['title']),
'content': html.unescape(content), 'content': html.unescape(content),
}) }
)
return results return results

View File

@ -101,7 +101,7 @@ def response(resp):
# check if search result starts with something like: "2 Sep 2014 ... " # check if search result starts with something like: "2 Sep 2014 ... "
if re.match(r"^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content): if re.match(r"^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content):
date_pos = content.find('...') + 4 date_pos = content.find('...') + 4
date_string = content[0:date_pos - 5] date_string = content[0 : date_pos - 5]
# fix content string # fix content string
content = content[date_pos:] content = content[date_pos:]
@ -113,7 +113,7 @@ def response(resp):
# check if search result starts with something like: "5 days ago ... " # check if search result starts with something like: "5 days ago ... "
elif re.match(r"^[0-9]+ days? ago \.\.\. ", content): elif re.match(r"^[0-9]+ days? ago \.\.\. ", content):
date_pos = content.find('...') + 4 date_pos = content.find('...') + 4
date_string = content[0:date_pos - 5] date_string = content[0 : date_pos - 5]
# calculate datetime # calculate datetime
published_date = datetime.now() - timedelta(days=int(re.match(r'\d+', date_string).group())) published_date = datetime.now() - timedelta(days=int(re.match(r'\d+', date_string).group()))
@ -123,15 +123,10 @@ def response(resp):
if published_date: if published_date:
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'content': content, 'publishedDate': published_date})
'title': title,
'content': content,
'publishedDate': published_date})
else: else:
# append result # append result
results.append({'url': url, results.append({'url': url, 'title': title, 'content': content})
'title': title,
'content': content})
# return results # return results
return results return results
@ -152,7 +147,7 @@ def _fetch_supported_languages(resp):
'malayam': 'ml', 'malayam': 'ml',
'norsk': 'nb', 'norsk': 'nb',
'sinhalese': 'si', 'sinhalese': 'si',
'sudanese': 'su' 'sudanese': 'su',
} }
# get the English name of every language known by babel # get the English name of every language known by babel

View File

@ -56,11 +56,7 @@ def response(resp):
name_row = rows[i] name_row = rows[i]
links = name_row.xpath('./td[@class="desc-top"]/a') links = name_row.xpath('./td[@class="desc-top"]/a')
params = { params = {'template': 'torrent.html', 'url': links[-1].attrib.get('href'), 'title': extract_text(links[-1])}
'template': 'torrent.html',
'url': links[-1].attrib.get('href'),
'title': extract_text(links[-1])
}
# I have not yet seen any torrents without magnet links, but # I have not yet seen any torrents without magnet links, but
# it's better to be prepared to stumble upon one some day # it's better to be prepared to stumble upon one some day
if len(links) == 2: if len(links) == 2:

View File

@ -35,10 +35,12 @@ api_key = ''
# https://newznab.readthedocs.io/en/latest/misc/api/#predefined-categories # https://newznab.readthedocs.io/en/latest/misc/api/#predefined-categories
torznab_categories = [] torznab_categories = []
def init(engine_settings=None): # pylint: disable=unused-argument def init(engine_settings=None): # pylint: disable=unused-argument
if len(base_url) < 1: if len(base_url) < 1:
raise ValueError('missing torznab base_url') raise ValueError('missing torznab base_url')
def request(query, params): def request(query, params):
search_url = base_url + '?t=search&q={search_query}' search_url = base_url + '?t=search&q={search_query}'
@ -48,13 +50,12 @@ def request(query, params):
search_url += '&cat={torznab_categories}' search_url += '&cat={torznab_categories}'
params['url'] = search_url.format( params['url'] = search_url.format(
search_query = quote(query), search_query=quote(query), api_key=api_key, torznab_categories=",".join([str(x) for x in torznab_categories])
api_key = api_key,
torznab_categories = ",".join([str(x) for x in torznab_categories])
) )
return params return params
def response(resp): def response(resp):
results = [] results = []
@ -103,8 +104,7 @@ def response(resp):
result["publishedDate"] = None result["publishedDate"] = None
try: try:
result["publishedDate"] = datetime.strptime( result["publishedDate"] = datetime.strptime(get_property(item, 'pubDate'), '%a, %d %b %Y %H:%M:%S %z')
get_property(item, 'pubDate'), '%a, %d %b %Y %H:%M:%S %z')
except (ValueError, TypeError) as e: except (ValueError, TypeError) as e:
logger.debug("ignore exception (publishedDate): %s", e) logger.debug("ignore exception (publishedDate): %s", e)
@ -134,9 +134,7 @@ def get_property(item, property_name):
def get_torznab_attr(item, attr_name): def get_torznab_attr(item, attr_name):
element = item.find( element = item.find(
'.//torznab:attr[@name="{attr_name}"]'.format(attr_name=attr_name), './/torznab:attr[@name="{attr_name}"]'.format(attr_name=attr_name),
{ {'torznab': 'http://torznab.com/schemas/2015/feed'},
'torznab': 'http://torznab.com/schemas/2015/feed'
}
) )
if element is not None: if element is not None:

View File

@ -28,24 +28,25 @@ def request(query, params):
key_form = '&key=' + api_key key_form = '&key=' + api_key
else: else:
key_form = '' key_form = ''
params['url'] = url.format(from_lang=params['from_lang'][1], params['url'] = url.format(
to_lang=params['to_lang'][1], from_lang=params['from_lang'][1], to_lang=params['to_lang'][1], query=params['query'], key=key_form
query=params['query'], )
key=key_form)
return params return params
def response(resp): def response(resp):
results = [] results = []
results.append({ results.append(
{
'url': web_url.format( 'url': web_url.format(
from_lang=resp.search_params['from_lang'][2], from_lang=resp.search_params['from_lang'][2],
to_lang=resp.search_params['to_lang'][2], to_lang=resp.search_params['to_lang'][2],
query=resp.search_params['query']), query=resp.search_params['query'],
),
'title': '[{0}-{1}] {2}'.format( 'title': '[{0}-{1}] {2}'.format(
resp.search_params['from_lang'][1], resp.search_params['from_lang'][1], resp.search_params['to_lang'][1], resp.search_params['query']
resp.search_params['to_lang'][1], ),
resp.search_params['query']), 'content': resp.json()['responseData']['translatedText'],
'content': resp.json()['responseData']['translatedText'] }
}) )
return results return results

View File

@ -26,23 +26,13 @@ paging = True
def clean_url(url): def clean_url(url):
parsed = urlparse(url) parsed = urlparse(url)
query = [(k, v) for (k, v) query = [(k, v) for (k, v) in parse_qsl(parsed.query) if k not in ['ixid', 's']]
in parse_qsl(parsed.query) if k not in ['ixid', 's']]
return urlunparse(( return urlunparse((parsed.scheme, parsed.netloc, parsed.path, parsed.params, urlencode(query), parsed.fragment))
parsed.scheme,
parsed.netloc,
parsed.path,
parsed.params,
urlencode(query),
parsed.fragment
))
def request(query, params): def request(query, params):
params['url'] = search_url + urlencode({ params['url'] = search_url + urlencode({'query': query, 'page': params['pageno'], 'per_page': page_size})
'query': query, 'page': params['pageno'], 'per_page': page_size
})
logger.debug("query_url --> %s", params['url']) logger.debug("query_url --> %s", params['url'])
return params return params
@ -53,13 +43,15 @@ def response(resp):
if 'results' in json_data: if 'results' in json_data:
for result in json_data['results']: for result in json_data['results']:
results.append({ results.append(
{
'template': 'images.html', 'template': 'images.html',
'url': clean_url(result['links']['html']), 'url': clean_url(result['links']['html']),
'thumbnail_src': clean_url(result['urls']['thumb']), 'thumbnail_src': clean_url(result['urls']['thumb']),
'img_src': clean_url(result['urls']['raw']), 'img_src': clean_url(result['urls']['raw']),
'title': result.get('alt_description') or 'unknown', 'title': result.get('alt_description') or 'unknown',
'content': result.get('description') or '' 'content': result.get('description') or '',
}) }
)
return results return results

View File

@ -25,15 +25,16 @@ paging = True
base_url = 'https://vimeo.com/' base_url = 'https://vimeo.com/'
search_url = base_url + '/search/page:{pageno}?{query}' search_url = base_url + '/search/page:{pageno}?{query}'
embedded_url = '<iframe data-src="https://player.vimeo.com/video/{videoid}" ' +\ embedded_url = (
'width="540" height="304" frameborder="0" ' +\ '<iframe data-src="https://player.vimeo.com/video/{videoid}" '
'webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>' + 'width="540" height="304" frameborder="0" '
+ 'webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>'
)
# do search-request # do search-request
def request(query, params): def request(query, params):
params['url'] = search_url.format(pageno=params['pageno'], params['url'] = search_url.format(pageno=params['pageno'], query=urlencode({'q': query}))
query=urlencode({'q': query}))
return params return params
@ -56,13 +57,17 @@ def response(resp):
embedded = embedded_url.format(videoid=videoid) embedded = embedded_url.format(videoid=videoid)
# append result # append result
results.append({'url': url, results.append(
{
'url': url,
'title': title, 'title': title,
'content': '', 'content': '',
'template': 'videos.html', 'template': 'videos.html',
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'embedded': embedded, 'embedded': embedded,
'thumbnail': thumbnail}) 'thumbnail': thumbnail,
}
)
# return results # return results
return results return results

View File

@ -14,7 +14,10 @@ from searx.data import WIKIDATA_UNITS
from searx.network import post, get from searx.network import post, get
from searx.utils import match_language, searx_useragent, get_string_replaces_function from searx.utils import match_language, searx_useragent, get_string_replaces_function
from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom
from searx.engines.wikipedia import _fetch_supported_languages, supported_languages_url # NOQA # pylint: disable=unused-import from searx.engines.wikipedia import (
_fetch_supported_languages,
supported_languages_url,
) # NOQA # pylint: disable=unused-import
# about # about
about = { about = {
@ -112,10 +115,7 @@ replace_http_by_https = get_string_replaces_function({'http:': 'https:'})
def get_headers(): def get_headers():
# user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits # user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits
return { return {'Accept': 'application/sparql-results+json', 'User-Agent': searx_useragent()}
'Accept': 'application/sparql-results+json',
'User-Agent': searx_useragent()
}
def get_label_for_entity(entity_id, language): def get_label_for_entity(entity_id, language):
@ -211,9 +211,9 @@ def get_results(attribute_result, attributes, language):
results.append({'title': infobox_title, 'url': url}) results.append({'title': infobox_title, 'url': url})
# update the infobox_id with the wikipedia URL # update the infobox_id with the wikipedia URL
# first the local wikipedia URL, and as fallback the english wikipedia URL # first the local wikipedia URL, and as fallback the english wikipedia URL
if attribute_type == WDArticle\ if attribute_type == WDArticle and (
and ((attribute.language == 'en' and infobox_id_lang is None) (attribute.language == 'en' and infobox_id_lang is None) or attribute.language != 'en'
or attribute.language != 'en'): ):
infobox_id_lang = attribute.language infobox_id_lang = attribute.language
infobox_id = url infobox_id = url
elif attribute_type == WDImageAttribute: elif attribute_type == WDImageAttribute:
@ -232,13 +232,11 @@ def get_results(attribute_result, attributes, language):
osm_zoom = area_to_osm_zoom(area) if area else 19 osm_zoom = area_to_osm_zoom(area) if area else 19
url = attribute.get_geo_url(attribute_result, osm_zoom=osm_zoom) url = attribute.get_geo_url(attribute_result, osm_zoom=osm_zoom)
if url: if url:
infobox_urls.append({'title': attribute.get_label(language), infobox_urls.append({'title': attribute.get_label(language), 'url': url, 'entity': attribute.name})
'url': url,
'entity': attribute.name})
else: else:
infobox_attributes.append({'label': attribute.get_label(language), infobox_attributes.append(
'value': value, {'label': attribute.get_label(language), 'value': value, 'entity': attribute.name}
'entity': attribute.name}) )
if infobox_id: if infobox_id:
infobox_id = replace_http_by_https(infobox_id) infobox_id = replace_http_by_https(infobox_id)
@ -246,22 +244,19 @@ def get_results(attribute_result, attributes, language):
# add the wikidata URL at the end # add the wikidata URL at the end
infobox_urls.append({'title': 'Wikidata', 'url': attribute_result['item']}) infobox_urls.append({'title': 'Wikidata', 'url': attribute_result['item']})
if img_src is None and len(infobox_attributes) == 0 and len(infobox_urls) == 1 and\ if img_src is None and len(infobox_attributes) == 0 and len(infobox_urls) == 1 and len(infobox_content) == 0:
len(infobox_content) == 0: results.append({'url': infobox_urls[0]['url'], 'title': infobox_title, 'content': infobox_content})
results.append({
'url': infobox_urls[0]['url'],
'title': infobox_title,
'content': infobox_content
})
else: else:
results.append({ results.append(
{
'infobox': infobox_title, 'infobox': infobox_title,
'id': infobox_id, 'id': infobox_id,
'content': infobox_content, 'content': infobox_content,
'img_src': img_src, 'img_src': img_src,
'urls': infobox_urls, 'urls': infobox_urls,
'attributes': infobox_attributes 'attributes': infobox_attributes,
}) }
)
return results return results
@ -271,13 +266,14 @@ def get_query(query, language):
where = list(filter(lambda s: len(s) > 0, [a.get_where() for a in attributes])) where = list(filter(lambda s: len(s) > 0, [a.get_where() for a in attributes]))
wikibase_label = list(filter(lambda s: len(s) > 0, [a.get_wikibase_label() for a in attributes])) wikibase_label = list(filter(lambda s: len(s) > 0, [a.get_wikibase_label() for a in attributes]))
group_by = list(filter(lambda s: len(s) > 0, [a.get_group_by() for a in attributes])) group_by = list(filter(lambda s: len(s) > 0, [a.get_group_by() for a in attributes]))
query = QUERY_TEMPLATE\ query = (
.replace('%QUERY%', sparql_string_escape(query))\ QUERY_TEMPLATE.replace('%QUERY%', sparql_string_escape(query))
.replace('%SELECT%', ' '.join(select))\ .replace('%SELECT%', ' '.join(select))
.replace('%WHERE%', '\n '.join(where))\ .replace('%WHERE%', '\n '.join(where))
.replace('%WIKIBASE_LABELS%', '\n '.join(wikibase_label))\ .replace('%WIKIBASE_LABELS%', '\n '.join(wikibase_label))
.replace('%GROUP_BY%', ' '.join(group_by))\ .replace('%GROUP_BY%', ' '.join(group_by))
.replace('%LANGUAGE%', language) .replace('%LANGUAGE%', language)
)
return query, attributes return query, attributes
@ -303,28 +299,34 @@ def get_attributes(language):
attributes.append(WDDateAttribute(name)) attributes.append(WDDateAttribute(name))
# Dates # Dates
for p in ['P571', # inception date for p in [
'P571', # inception date
'P576', # dissolution date 'P576', # dissolution date
'P580', # start date 'P580', # start date
'P582', # end date 'P582', # end date
'P569', # date of birth 'P569', # date of birth
'P570', # date of death 'P570', # date of death
'P619', # date of spacecraft launch 'P619', # date of spacecraft launch
'P620']: # date of spacecraft landing 'P620',
]: # date of spacecraft landing
add_date(p) add_date(p)
for p in ['P27', # country of citizenship for p in [
'P27', # country of citizenship
'P495', # country of origin 'P495', # country of origin
'P17', # country 'P17', # country
'P159']: # headquarters location 'P159',
]: # headquarters location
add_label(p) add_label(p)
# Places # Places
for p in ['P36', # capital for p in [
'P36', # capital
'P35', # head of state 'P35', # head of state
'P6', # head of government 'P6', # head of government
'P122', # basic form of government 'P122', # basic form of government
'P37']: # official language 'P37',
]: # official language
add_label(p) add_label(p)
add_value('P1082') # population add_value('P1082') # population
@ -334,7 +336,8 @@ def get_attributes(language):
add_amount('P2048') # heigth (building) add_amount('P2048') # heigth (building)
# Media # Media
for p in ['P400', # platform (videogames, computing) for p in [
'P400', # platform (videogames, computing)
'P50', # author 'P50', # author
'P170', # creator 'P170', # creator
'P57', # director 'P57', # director
@ -348,7 +351,8 @@ def get_attributes(language):
'P123', # publisher 'P123', # publisher
'P449', # original network 'P449', # original network
'P750', # distributed by 'P750', # distributed by
'P86']: # composer 'P86',
]: # composer
add_label(p) add_label(p)
add_date('P577') # publication date add_date('P577') # publication date
@ -415,7 +419,7 @@ def get_attributes(language):
class WDAttribute: class WDAttribute:
__slots__ = 'name', __slots__ = ('name',)
def __init__(self, name): def __init__(self, name):
self.name = name self.name = name
@ -443,14 +447,15 @@ class WDAttribute:
class WDAmountAttribute(WDAttribute): class WDAmountAttribute(WDAttribute):
def get_select(self): def get_select(self):
return '?{name} ?{name}Unit'.replace('{name}', self.name) return '?{name} ?{name}Unit'.replace('{name}', self.name)
def get_where(self): def get_where(self):
return """ OPTIONAL { ?item p:{name} ?{name}Node . return """ OPTIONAL { ?item p:{name} ?{name}Node .
?{name}Node rdf:type wikibase:BestRank ; ps:{name} ?{name} . ?{name}Node rdf:type wikibase:BestRank ; ps:{name} ?{name} .
OPTIONAL { ?{name}Node psv:{name}/wikibase:quantityUnit ?{name}Unit. } }""".replace('{name}', self.name) OPTIONAL { ?{name}Node psv:{name}/wikibase:quantityUnit ?{name}Unit. } }""".replace(
'{name}', self.name
)
def get_group_by(self): def get_group_by(self):
return self.get_select() return self.get_select()
@ -484,7 +489,9 @@ class WDArticle(WDAttribute):
return """OPTIONAL { ?article{language} schema:about ?item ; return """OPTIONAL { ?article{language} schema:about ?item ;
schema:inLanguage "{language}" ; schema:inLanguage "{language}" ;
schema:isPartOf <https://{language}.wikipedia.org/> ; schema:isPartOf <https://{language}.wikipedia.org/> ;
schema:name ?articleName{language} . }""".replace('{language}', self.language) schema:name ?articleName{language} . }""".replace(
'{language}', self.language
)
def get_group_by(self): def get_group_by(self):
return self.get_select() return self.get_select()
@ -495,7 +502,6 @@ class WDArticle(WDAttribute):
class WDLabelAttribute(WDAttribute): class WDLabelAttribute(WDAttribute):
def get_select(self): def get_select(self):
return '(group_concat(distinct ?{name}Label;separator=", ") as ?{name}Labels)'.replace('{name}', self.name) return '(group_concat(distinct ?{name}Label;separator=", ") as ?{name}Labels)'.replace('{name}', self.name)
@ -526,14 +532,13 @@ class WDURLAttribute(WDAttribute):
value = value.split(',')[0] value = value.split(',')[0]
url_id = self.url_id url_id = self.url_id
if value.startswith(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE): if value.startswith(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE):
value = value[len(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE):] value = value[len(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE) :]
url_id = 'wikimedia_image' url_id = 'wikimedia_image'
return get_external_url(url_id, value) return get_external_url(url_id, value)
return value return value
class WDGeoAttribute(WDAttribute): class WDGeoAttribute(WDAttribute):
def get_label(self, language): def get_label(self, language):
return "OpenStreetMap" return "OpenStreetMap"
@ -543,7 +548,9 @@ class WDGeoAttribute(WDAttribute):
def get_where(self): def get_where(self):
return """OPTIONAL { ?item p:{name}/psv:{name} [ return """OPTIONAL { ?item p:{name}/psv:{name} [
wikibase:geoLatitude ?{name}Lat ; wikibase:geoLatitude ?{name}Lat ;
wikibase:geoLongitude ?{name}Long ] }""".replace('{name}', self.name) wikibase:geoLongitude ?{name}Long ] }""".replace(
'{name}', self.name
)
def get_group_by(self): def get_group_by(self):
return self.get_select() return self.get_select()
@ -565,7 +572,7 @@ class WDGeoAttribute(WDAttribute):
class WDImageAttribute(WDURLAttribute): class WDImageAttribute(WDURLAttribute):
__slots__ = 'priority', __slots__ = ('priority',)
def __init__(self, name, url_id=None, priority=100): def __init__(self, name, url_id=None, priority=100):
super().__init__(name, url_id) super().__init__(name, url_id)
@ -573,7 +580,6 @@ class WDImageAttribute(WDURLAttribute):
class WDDateAttribute(WDAttribute): class WDDateAttribute(WDAttribute):
def get_select(self): def get_select(self):
return '?{name} ?{name}timePrecision ?{name}timeZone ?{name}timeCalendar'.replace('{name}', self.name) return '?{name} ?{name}timePrecision ?{name}timeZone ?{name}timeCalendar'.replace('{name}', self.name)
@ -587,7 +593,9 @@ class WDDateAttribute(WDAttribute):
wikibase:timePrecision ?{name}timePrecision ; wikibase:timePrecision ?{name}timePrecision ;
wikibase:timeTimezone ?{name}timeZone ; wikibase:timeTimezone ?{name}timeZone ;
wikibase:timeCalendarModel ?{name}timeCalendar ] . } wikibase:timeCalendarModel ?{name}timeCalendar ] . }
hint:Prior hint:rangeSafe true;""".replace('{name}', self.name) hint:Prior hint:rangeSafe true;""".replace(
'{name}', self.name
)
def get_group_by(self): def get_group_by(self):
return self.get_select() return self.get_select()
@ -619,11 +627,12 @@ class WDDateAttribute(WDAttribute):
def format_13(self, value, locale): def format_13(self, value, locale):
timestamp = isoparse(value) timestamp = isoparse(value)
# precision: minute # precision: minute
return get_datetime_format(format, locale=locale) \ return (
.replace("'", "") \ get_datetime_format(format, locale=locale)
.replace('{0}', format_time(timestamp, 'full', tzinfo=None, .replace("'", "")
locale=locale)) \ .replace('{0}', format_time(timestamp, 'full', tzinfo=None, locale=locale))
.replace('{1}', format_date(timestamp, 'short', locale=locale)) .replace('{1}', format_date(timestamp, 'short', locale=locale))
)
def format_14(self, value, locale): def format_14(self, value, locale):
# precision: second. # precision: second.
@ -644,7 +653,7 @@ class WDDateAttribute(WDAttribute):
'11': ('format_11', 0), # day '11': ('format_11', 0), # day
'12': ('format_13', 0), # hour (not supported by babel, display minute) '12': ('format_13', 0), # hour (not supported by babel, display minute)
'13': ('format_13', 0), # minute '13': ('format_13', 0), # minute
'14': ('format_14', 0) # second '14': ('format_14', 0), # second
} }
def get_str(self, result, language): def get_str(self, result, language):

View File

@ -39,8 +39,7 @@ def request(query, params):
query = query.title() query = query.title()
language = url_lang(params['language']) language = url_lang(params['language'])
params['url'] = search_url.format(title=quote(query), params['url'] = search_url.format(title=quote(query), language=language)
language=language)
if params['language'].lower() in language_variants.get(language, []): if params['language'].lower() in language_variants.get(language, []):
params['headers']['Accept-Language'] = params['language'].lower() params['headers']['Accept-Language'] = params['language'].lower()
@ -63,8 +62,10 @@ def response(resp):
except: except:
pass pass
else: else:
if api_result['type'] == 'https://mediawiki.org/wiki/HyperSwitch/errors/bad_request' \ if (
and api_result['detail'] == 'title-invalid-characters': api_result['type'] == 'https://mediawiki.org/wiki/HyperSwitch/errors/bad_request'
and api_result['detail'] == 'title-invalid-characters'
):
return [] return []
raise_for_httperror(resp) raise_for_httperror(resp)
@ -81,11 +82,15 @@ def response(resp):
results.append({'url': wikipedia_link, 'title': title}) results.append({'url': wikipedia_link, 'title': title})
results.append({'infobox': title, results.append(
{
'infobox': title,
'id': wikipedia_link, 'id': wikipedia_link,
'content': api_result.get('extract', ''), 'content': api_result.get('extract', ''),
'img_src': api_result.get('thumbnail', {}).get('source'), 'img_src': api_result.get('thumbnail', {}).get('source'),
'urls': [{'title': 'Wikipedia', 'url': wikipedia_link}]}) 'urls': [{'title': 'Wikipedia', 'url': wikipedia_link}],
}
)
return results return results

Some files were not shown because too many files have changed in this diff Show More