forked from zaclys/searxng
[fix] pep8
This commit is contained in:
parent
91f9973227
commit
a508d540ac
|
@ -57,12 +57,16 @@ def response(resp):
|
||||||
link = result.xpath('.//div[@class="newstitle"]/a')[0]
|
link = result.xpath('.//div[@class="newstitle"]/a')[0]
|
||||||
url = link.attrib.get('href')
|
url = link.attrib.get('href')
|
||||||
title = ' '.join(link.xpath('.//text()'))
|
title = ' '.join(link.xpath('.//text()'))
|
||||||
contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]//text()')
|
contentXPath = result.xpath('.//div[@class="sn_txt"]/div'
|
||||||
|
'//span[@class="sn_snip"]//text()')
|
||||||
if contentXPath is not None:
|
if contentXPath is not None:
|
||||||
content = escape(' '.join(contentXPath))
|
content = escape(' '.join(contentXPath))
|
||||||
|
|
||||||
# parse publishedDate
|
# parse publishedDate
|
||||||
publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div//span[contains(@class,"sn_ST")]//span[contains(@class,"sn_tm")]//text()')
|
publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div'
|
||||||
|
'//span[contains(@class,"sn_ST")]'
|
||||||
|
'//span[contains(@class,"sn_tm")]'
|
||||||
|
'//text()')
|
||||||
if publishedDateXPath is not None:
|
if publishedDateXPath is not None:
|
||||||
publishedDate = escape(' '.join(publishedDateXPath))
|
publishedDate = escape(' '.join(publishedDateXPath))
|
||||||
|
|
||||||
|
@ -74,7 +78,8 @@ def response(resp):
|
||||||
timeNumbers = re.findall(r'\d+', publishedDate)
|
timeNumbers = re.findall(r'\d+', publishedDate)
|
||||||
publishedDate = datetime.now()\
|
publishedDate = datetime.now()\
|
||||||
- timedelta(hours=int(timeNumbers[0]))
|
- timedelta(hours=int(timeNumbers[0]))
|
||||||
elif re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$", publishedDate):
|
elif re.match("^[0-9]+ hour(s|),"
|
||||||
|
" [0-9]+ minute(s|) ago$", publishedDate):
|
||||||
timeNumbers = re.findall(r'\d+', publishedDate)
|
timeNumbers = re.findall(r'\d+', publishedDate)
|
||||||
publishedDate = datetime.now()\
|
publishedDate = datetime.now()\
|
||||||
- timedelta(hours=int(timeNumbers[0]))\
|
- timedelta(hours=int(timeNumbers[0]))\
|
||||||
|
|
|
@ -22,7 +22,14 @@ api_key = None
|
||||||
|
|
||||||
# search-url
|
# search-url
|
||||||
url = 'http://www.faroo.com/'
|
url = 'http://www.faroo.com/'
|
||||||
search_url = url + 'api?{query}&start={offset}&length={number_of_results}&l={language}&src={categorie}&i=false&f=json&key={api_key}'
|
search_url = url + 'api?{query}'\
|
||||||
|
'&start={offset}'\
|
||||||
|
'&length={number_of_results}'\
|
||||||
|
'&l={language}'\
|
||||||
|
'&src={categorie}'\
|
||||||
|
'&i=false'\
|
||||||
|
'&f=json'\
|
||||||
|
'&key={api_key}' # noqa
|
||||||
|
|
||||||
search_category = {'general': 'web',
|
search_category = {'general': 'web',
|
||||||
'news': 'news'}
|
'news': 'news'}
|
||||||
|
@ -80,8 +87,8 @@ def response(resp):
|
||||||
# parse results
|
# parse results
|
||||||
for result in search_res['results']:
|
for result in search_res['results']:
|
||||||
if result['news']:
|
if result['news']:
|
||||||
# timestamp (how many milliseconds have passed between now and the beginning of 1970)
|
# timestamp (milliseconds since 1970)
|
||||||
publishedDate = datetime.datetime.fromtimestamp(result['date']/1000.0)
|
publishedDate = datetime.datetime.fromtimestamp(result['date']/1000.0) # noqa
|
||||||
|
|
||||||
# append news result
|
# append news result
|
||||||
results.append({'url': result['url'],
|
results.append({'url': result['url'],
|
||||||
|
|
|
@ -9,7 +9,7 @@
|
||||||
# @stable yes (but deprecated)
|
# @stable yes (but deprecated)
|
||||||
# @parse url, title, img_src
|
# @parse url, title, img_src
|
||||||
|
|
||||||
from urllib import urlencode,unquote
|
from urllib import urlencode, unquote
|
||||||
from json import loads
|
from json import loads
|
||||||
|
|
||||||
# engine dependent config
|
# engine dependent config
|
||||||
|
|
|
@ -13,7 +13,6 @@ from cgi import escape
|
||||||
from urllib import quote
|
from urllib import quote
|
||||||
from lxml import html
|
from lxml import html
|
||||||
from operator import itemgetter
|
from operator import itemgetter
|
||||||
from dateutil import parser
|
|
||||||
|
|
||||||
# engine dependent config
|
# engine dependent config
|
||||||
categories = ['videos', 'music', 'files']
|
categories = ['videos', 'music', 'files']
|
||||||
|
@ -33,7 +32,8 @@ 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'])
|
||||||
|
|
||||||
# FIX: SSLError: hostname 'kickass.so' doesn't match either of '*.kickass.to', 'kickass.to'
|
# FIX: SSLError: hostname 'kickass.so'
|
||||||
|
# doesn't match either of '*.kickass.to', 'kickass.to'
|
||||||
params['verify'] = False
|
params['verify'] = False
|
||||||
|
|
||||||
return params
|
return params
|
||||||
|
|
|
@ -20,7 +20,12 @@ guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28'
|
||||||
|
|
||||||
# search-url
|
# search-url
|
||||||
url = 'https://api.soundcloud.com/'
|
url = 'https://api.soundcloud.com/'
|
||||||
search_url = url + 'search?{query}&facet=model&limit=20&offset={offset}&linked_partitioning=1&client_id={client_id}'
|
search_url = url + 'search?{query}'\
|
||||||
|
'&facet=model'\
|
||||||
|
'&limit=20'\
|
||||||
|
'&offset={offset}'\
|
||||||
|
'&linked_partitioning=1'\
|
||||||
|
'&client_id={client_id}' # noqa
|
||||||
|
|
||||||
|
|
||||||
# do search-request
|
# do search-request
|
||||||
|
|
|
@ -20,7 +20,8 @@ paging = True
|
||||||
language_support = True
|
language_support = True
|
||||||
|
|
||||||
# search-url
|
# search-url
|
||||||
search_url = 'https://search.yahoo.com/search?{query}&b={offset}&fl=1&vl=lang_{lang}'
|
base_url = 'https://search.yahoo.com/'
|
||||||
|
search_url = 'search?{query}&b={offset}&fl=1&vl=lang_{lang}'
|
||||||
|
|
||||||
# specific xpath variables
|
# specific xpath variables
|
||||||
results_xpath = '//div[@class="res"]'
|
results_xpath = '//div[@class="res"]'
|
||||||
|
@ -57,7 +58,7 @@ def request(query, params):
|
||||||
else:
|
else:
|
||||||
language = params['language'].split('_')[0]
|
language = params['language'].split('_')[0]
|
||||||
|
|
||||||
params['url'] = search_url.format(offset=offset,
|
params['url'] = base_url + search_url.format(offset=offset,
|
||||||
query=urlencode({'p': query}),
|
query=urlencode({'p': query}),
|
||||||
lang=language)
|
lang=language)
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue