mirror of https://github.com/searxng/searxng.git
[fix] revise of the google-Video engine
This revise is based on the methods developed in the revise of the google engine
(see commit 410c2f9).
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser
parent
f4a17acb7a
commit
89b3050b5c
3
Makefile
3
Makefile
|
|
@ -179,7 +179,8 @@ PYLINT_FILES=\
|
||||||
searx/engines/deviantart.py \
|
searx/engines/deviantart.py \
|
||||||
searx/engines/digg.py \
|
searx/engines/digg.py \
|
||||||
searx/engines/google.py \
|
searx/engines/google.py \
|
||||||
searx/engines/google_news.py
|
searx/engines/google_news.py \
|
||||||
|
searx/engines/google_videos.py
|
||||||
|
|
||||||
test.pylint: pyenvinstall
|
test.pylint: pyenvinstall
|
||||||
$(call cmd,pylint,$(PYLINT_FILES))
|
$(call cmd,pylint,$(PYLINT_FILES))
|
||||||
|
|
|
||||||
|
|
@ -1,13 +1,58 @@
|
||||||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||||
"""
|
"""
|
||||||
Google (Videos)
|
Google (Viedo)
|
||||||
|
|
||||||
|
For detailed description of the *REST-full* API see: `Query Parameter
|
||||||
|
Definitions`_. Not all parameters can be appied.
|
||||||
|
|
||||||
|
.. _admonition:: Content-Security-Policy (CSP)
|
||||||
|
|
||||||
|
This engine needs to allow images from the `data URLs`_ (prefixed with the
|
||||||
|
``data:` scheme).::
|
||||||
|
|
||||||
|
Header set Content-Security-Policy "img-src 'self' data: ;"
|
||||||
|
|
||||||
|
.. _Query Parameter Definitions:
|
||||||
|
https://developers.google.com/custom-search/docs/xml_results#WebSearch_Query_Parameter_Definitions
|
||||||
|
.. _data URLs:
|
||||||
|
https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URIs
|
||||||
|
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from datetime import date, timedelta
|
# pylint: disable=invalid-name, missing-function-docstring
|
||||||
from urllib.parse import urlencode
|
|
||||||
from lxml import html
|
|
||||||
from searx.utils import extract_text, eval_xpath, eval_xpath_list, eval_xpath_getindex
|
|
||||||
import re
|
import re
|
||||||
|
from urllib.parse import urlencode, urlparse
|
||||||
|
from lxml import html
|
||||||
|
|
||||||
|
from searx import logger
|
||||||
|
from searx.exceptions import SearxEngineCaptchaException
|
||||||
|
from searx.utils import (
|
||||||
|
eval_xpath,
|
||||||
|
eval_xpath_list,
|
||||||
|
extract_text,
|
||||||
|
)
|
||||||
|
|
||||||
|
from searx.engines.google import (
|
||||||
|
get_lang_country,
|
||||||
|
google_domains,
|
||||||
|
time_range_dict,
|
||||||
|
filter_mapping,
|
||||||
|
results_xpath,
|
||||||
|
g_section_with_header,
|
||||||
|
title_xpath,
|
||||||
|
href_xpath,
|
||||||
|
content_xpath,
|
||||||
|
suggestion_xpath,
|
||||||
|
spelling_suggestion_xpath
|
||||||
|
)
|
||||||
|
|
||||||
|
# pylint: disable=unused-import
|
||||||
|
from searx.engines.google import (
|
||||||
|
supported_languages_url
|
||||||
|
, _fetch_supported_languages
|
||||||
|
)
|
||||||
|
# pylint: enable=unused-import
|
||||||
|
|
||||||
# about
|
# about
|
||||||
about = {
|
about = {
|
||||||
|
|
@ -17,83 +62,162 @@ about = {
|
||||||
"use_official_api": False,
|
"use_official_api": False,
|
||||||
"require_api_key": False,
|
"require_api_key": False,
|
||||||
"results": 'HTML',
|
"results": 'HTML',
|
||||||
|
"template": 'video.html',
|
||||||
|
"parse": ('url', 'title', 'content', 'thumbnail')
|
||||||
}
|
}
|
||||||
|
|
||||||
|
logger = logger.getChild('google video')
|
||||||
|
|
||||||
# engine dependent config
|
# engine dependent config
|
||||||
|
|
||||||
categories = ['videos']
|
categories = ['videos']
|
||||||
paging = True
|
paging = False
|
||||||
safesearch = True
|
language_support = True
|
||||||
|
use_locale_domain = True
|
||||||
time_range_support = True
|
time_range_support = True
|
||||||
number_of_results = 10
|
safesearch = True
|
||||||
|
|
||||||
search_url = 'https://www.google.com/search'\
|
RE_CACHE = {}
|
||||||
'?q={query}'\
|
|
||||||
'&tbm=vid'\
|
def _re(regexpr):
|
||||||
'&{search_options}'
|
"""returns compiled regular expression"""
|
||||||
time_range_attr = "qdr:{range}"
|
RE_CACHE[regexpr] = RE_CACHE.get(regexpr, re.compile(regexpr))
|
||||||
time_range_custom_attr = "cdr:1,cd_min:{start},cd_max{end}"
|
return RE_CACHE[regexpr]
|
||||||
time_range_dict = {'day': 'd',
|
|
||||||
'week': 'w',
|
def scrap_out_thumbs(dom):
|
||||||
'month': 'm'}
|
"""Scrap out thumbnail data from <script> tags.
|
||||||
|
"""
|
||||||
|
ret_val = dict()
|
||||||
|
thumb_name = 'vidthumb'
|
||||||
|
|
||||||
|
for script in eval_xpath(dom, '//script[contains(., "_setImagesSrc")]'):
|
||||||
|
_script = script.text
|
||||||
|
|
||||||
|
# var s='data:image/jpeg;base64, ...'
|
||||||
|
_imgdata = _re("s='([^']*)").findall( _script)
|
||||||
|
if not _imgdata:
|
||||||
|
continue
|
||||||
|
|
||||||
|
# var ii=['vidthumb4','vidthumb7']
|
||||||
|
for _vidthumb in _re(r"(%s\d+)" % thumb_name).findall(_script):
|
||||||
|
# At least the equal sign in the URL needs to be decoded
|
||||||
|
ret_val[_vidthumb] = _imgdata[0].replace(r"\x3d", "=")
|
||||||
|
|
||||||
|
# {google.ldidly=-1;google.ldi={"vidthumb8":"https://...
|
||||||
|
for script in eval_xpath(dom, '//script[contains(., "google.ldi={")]'):
|
||||||
|
_script = script.text
|
||||||
|
for key_val in _re(r'"%s\d+\":\"[^\"]*"' % thumb_name).findall( _script) :
|
||||||
|
match = _re(r'"(%s\d+)":"(.*)"' % thumb_name).search(key_val)
|
||||||
|
if match:
|
||||||
|
# At least the equal sign in the URL needs to be decoded
|
||||||
|
ret_val[match.group(1)] = match.group(2).replace(r"\u003d", "=")
|
||||||
|
|
||||||
|
logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
|
||||||
|
return ret_val
|
||||||
|
|
||||||
|
|
||||||
# do search-request
|
|
||||||
def request(query, params):
|
def request(query, params):
|
||||||
search_options = {
|
"""Google-Video search request"""
|
||||||
'ijn': params['pageno'] - 1,
|
|
||||||
'start': (params['pageno'] - 1) * number_of_results
|
language, country, lang_country = get_lang_country(
|
||||||
}
|
# pylint: disable=undefined-variable
|
||||||
|
params, supported_languages, language_aliases
|
||||||
|
)
|
||||||
|
subdomain = 'www.' + google_domains.get(country.upper(), 'google.com')
|
||||||
|
|
||||||
|
query_url = 'https://'+ subdomain + '/search' + "?" + urlencode({
|
||||||
|
'q': query,
|
||||||
|
'tbm': "vid",
|
||||||
|
'hl': lang_country,
|
||||||
|
'lr': "lang_" + language,
|
||||||
|
'ie': "utf8",
|
||||||
|
'oe': "utf8",
|
||||||
|
})
|
||||||
|
|
||||||
if params['time_range'] in time_range_dict:
|
if params['time_range'] in time_range_dict:
|
||||||
search_options['tbs'] = time_range_attr.format(range=time_range_dict[params['time_range']])
|
query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
|
||||||
elif params['time_range'] == 'year':
|
if params['safesearch']:
|
||||||
now = date.today()
|
query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
|
||||||
then = now - timedelta(days=365)
|
|
||||||
start = then.strftime('%m/%d/%Y')
|
|
||||||
end = now.strftime('%m/%d/%Y')
|
|
||||||
search_options['tbs'] = time_range_custom_attr.format(start=start, end=end)
|
|
||||||
|
|
||||||
if safesearch and params['safesearch']:
|
params['url'] = query_url
|
||||||
search_options['safe'] = 'on'
|
logger.debug("query_url --> %s", query_url)
|
||||||
|
|
||||||
params['url'] = search_url.format(query=urlencode({'q': query}),
|
|
||||||
search_options=urlencode(search_options))
|
|
||||||
|
|
||||||
|
# en-US,en;q=0.8,en;q=0.5
|
||||||
|
params['headers']['Accept-Language'] = (
|
||||||
|
"%s,%s;q=0.8,%s;q=0.5" % (lang_country, language, language))
|
||||||
|
logger.debug(
|
||||||
|
"HTTP Accept-Language --> %s", params['headers']['Accept-Language'])
|
||||||
|
params['headers']['Accept'] = (
|
||||||
|
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
|
||||||
|
)
|
||||||
|
#params['google_subdomain'] = subdomain
|
||||||
return params
|
return params
|
||||||
|
|
||||||
|
|
||||||
# get response from search-request
|
|
||||||
def response(resp):
|
def response(resp):
|
||||||
|
"""Get response from google's search request"""
|
||||||
results = []
|
results = []
|
||||||
|
|
||||||
|
# detect google sorry
|
||||||
|
resp_url = urlparse(resp.url)
|
||||||
|
if resp_url.netloc == 'sorry.google.com' or resp_url.path == '/sorry/IndexRedirect':
|
||||||
|
raise SearxEngineCaptchaException()
|
||||||
|
|
||||||
|
if resp_url.path.startswith('/sorry'):
|
||||||
|
raise SearxEngineCaptchaException()
|
||||||
|
|
||||||
|
# which subdomain ?
|
||||||
|
# subdomain = resp.search_params.get('google_subdomain')
|
||||||
|
|
||||||
|
# convert the text to dom
|
||||||
dom = html.fromstring(resp.text)
|
dom = html.fromstring(resp.text)
|
||||||
|
vidthumb_imgdata = scrap_out_thumbs(dom)
|
||||||
|
|
||||||
# parse results
|
# parse results
|
||||||
for result in eval_xpath_list(dom, '//div[@class="g"]'):
|
for result in eval_xpath_list(dom, results_xpath):
|
||||||
|
|
||||||
title = extract_text(eval_xpath(result, './/h3'))
|
# google *sections*
|
||||||
url = eval_xpath_getindex(result, './/div[@class="r"]/a/@href', 0)
|
if extract_text(eval_xpath(result, g_section_with_header)):
|
||||||
content = extract_text(eval_xpath(result, './/span[@class="st"]'))
|
logger.debug("ingoring <g-section-with-header>")
|
||||||
|
continue
|
||||||
|
|
||||||
# get thumbnails
|
title = extract_text(eval_xpath(result, title_xpath)[0])
|
||||||
script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
|
url = eval_xpath(result, href_xpath)[0]
|
||||||
ids = result.xpath('.//div[@class="s"]//img/@id')
|
c_node = eval_xpath(result, content_xpath)[0]
|
||||||
if len(ids) > 0:
|
|
||||||
thumbnails_data = \
|
|
||||||
re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + ids[0],
|
|
||||||
script)
|
|
||||||
tmp = []
|
|
||||||
if len(thumbnails_data) != 0:
|
|
||||||
tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
|
|
||||||
thumbnail = ''
|
|
||||||
if len(tmp) != 0:
|
|
||||||
thumbnail = tmp[-1]
|
|
||||||
|
|
||||||
# append result
|
# <img id="vidthumb1" ...>
|
||||||
results.append({'url': url,
|
img_id = eval_xpath(c_node, './div[1]//a/g-img/img/@id')
|
||||||
'title': title,
|
if not img_id:
|
||||||
'content': content,
|
continue
|
||||||
'thumbnail': thumbnail,
|
img_id = img_id[0]
|
||||||
'template': 'videos.html'})
|
img_src = vidthumb_imgdata.get(img_id, None)
|
||||||
|
if not img_src:
|
||||||
|
logger.error("no vidthumb imgdata for: %s" % img_id)
|
||||||
|
img_src = eval_xpath(c_node, './div[1]//a/g-img/img/@src')[0]
|
||||||
|
|
||||||
|
duration = extract_text(eval_xpath(c_node, './div[1]//a/span'))
|
||||||
|
content = extract_text(eval_xpath(c_node, './div[2]/span'))
|
||||||
|
pub_info = extract_text(eval_xpath(c_node, './div[2]/div'))
|
||||||
|
|
||||||
|
if len(duration) > 3:
|
||||||
|
content = duration + " - " + content
|
||||||
|
if pub_info:
|
||||||
|
content = content + " (%s)" % pub_info
|
||||||
|
|
||||||
|
results.append({
|
||||||
|
'url': url,
|
||||||
|
'title': title,
|
||||||
|
'content': content,
|
||||||
|
'thumbnail': img_src,
|
||||||
|
'template': 'videos.html',
|
||||||
|
})
|
||||||
|
|
||||||
|
# parse suggestion
|
||||||
|
for suggestion in eval_xpath(dom, suggestion_xpath):
|
||||||
|
# append suggestion
|
||||||
|
results.append({'suggestion': extract_text(suggestion)})
|
||||||
|
|
||||||
|
for correction in eval_xpath(dom, spelling_suggestion_xpath):
|
||||||
|
results.append({'correction': extract_text(correction)})
|
||||||
|
|
||||||
return results
|
return results
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue