diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py index 5dce4a2b..3dda04cb 100644 --- a/searx/engines/bing_news.py +++ b/searx/engines/bing_news.py @@ -57,12 +57,16 @@ def response(resp): link = result.xpath('.//div[@class="newstitle"]/a')[0] url = link.attrib.get('href') 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: content = escape(' '.join(contentXPath)) # 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: publishedDate = escape(' '.join(publishedDateXPath)) @@ -74,7 +78,8 @@ def response(resp): timeNumbers = re.findall(r'\d+', publishedDate) publishedDate = datetime.now()\ - 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) publishedDate = datetime.now()\ - timedelta(hours=int(timeNumbers[0]))\ diff --git a/searx/engines/faroo.py b/searx/engines/faroo.py index dada4758..5360ea15 100644 --- a/searx/engines/faroo.py +++ b/searx/engines/faroo.py @@ -22,10 +22,17 @@ api_key = None # search-url 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', - 'news': 'news'} + 'news': 'news'} # do search-request @@ -80,8 +87,8 @@ def response(resp): # parse results for result in search_res['results']: if result['news']: - # timestamp (how many milliseconds have passed between now and the beginning of 1970) - publishedDate = datetime.datetime.fromtimestamp(result['date']/1000.0) + # timestamp (milliseconds since 1970) + publishedDate = datetime.datetime.fromtimestamp(result['date']/1000.0) # noqa # append news result results.append({'url': result['url'], diff --git a/searx/engines/google_images.py b/searx/engines/google_images.py index 491f5c2c..79fac3fb 100644 --- a/searx/engines/google_images.py +++ b/searx/engines/google_images.py @@ -9,7 +9,7 @@ # @stable yes (but deprecated) # @parse url, title, img_src -from urllib import urlencode,unquote +from urllib import urlencode, unquote from json import loads # engine dependent config diff --git a/searx/engines/kickass.py b/searx/engines/kickass.py index de732414..f1fcd9e1 100644 --- a/searx/engines/kickass.py +++ b/searx/engines/kickass.py @@ -1,8 +1,8 @@ ## Kickass Torrent (Videos, Music, Files) -# +# # @website https://kickass.so # @provide-api no (nothing found) -# +# # @using-api no # @results HTML (using search portal) # @stable yes (HTML can change) @@ -13,7 +13,6 @@ from cgi import escape from urllib import quote from lxml import html from operator import itemgetter -from dateutil import parser # engine dependent config categories = ['videos', 'music', 'files'] @@ -33,7 +32,8 @@ def request(query, params): params['url'] = search_url.format(search_term=quote(query), 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 return params diff --git a/searx/engines/soundcloud.py b/searx/engines/soundcloud.py index 390e7ca1..164a569a 100644 --- a/searx/engines/soundcloud.py +++ b/searx/engines/soundcloud.py @@ -20,7 +20,12 @@ guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28' # search-url 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 diff --git a/searx/engines/yahoo.py b/searx/engines/yahoo.py index 938540ec..c6c5b0d0 100644 --- a/searx/engines/yahoo.py +++ b/searx/engines/yahoo.py @@ -20,7 +20,8 @@ paging = True language_support = True # 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 results_xpath = '//div[@class="res"]' @@ -57,9 +58,9 @@ def request(query, params): else: language = params['language'].split('_')[0] - params['url'] = search_url.format(offset=offset, - query=urlencode({'p': query}), - lang=language) + params['url'] = base_url + search_url.format(offset=offset, + query=urlencode({'p': query}), + lang=language) # TODO required? params['cookies']['sB'] = 'fl=1&vl=lang_{lang}&sh=1&rw=new&v=1'\