commit: 1d5741954eb6786bbbc31e9bc4d540f73bccdb46
parent 46277888340ceaa76233c57be23fb21591188e26
Author: Thomas Pointhuber <thomas.pointhuber@gmx.at>
Date: Tue, 4 Mar 2014 13:10:04 +0100
Create bing_news.py
Diffstat:
1 file changed, 51 insertions(+), 0 deletions(-)
diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py
@@ -0,0 +1,51 @@
+from urllib import urlencode
+from cgi import escape
+from lxml import html
+
+categories = ['news']
+
+base_url = 'http://www.bing.com/'
+search_string = 'news/search?{query}&first={offset}'
+paging = True
+language_support = True
+
+
+def request(query, params):
+ offset = (params['pageno'] - 1) * 10 + 1
+ if params['language'] == 'all':
+ language = 'en-US'
+ else:
+ language = params['language'].replace('_', '-')
+ search_path = search_string.format(
+ query=urlencode({'q': query, 'setmkt': language}),
+ offset=offset)
+
+ params['cookies']['SRCHHPGUSR'] = \
+ 'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0]
+ #if params['category'] == 'images':
+ # params['url'] = base_url + 'images/' + search_path
+ params['url'] = base_url + search_path
+ return params
+
+
+def response(resp):
+ global base_url
+ results = []
+ dom = html.fromstring(resp.content)
+ for result in dom.xpath('//div[@class="sa_cc"]'):
+ link = result.xpath('.//h3/a')[0]
+ url = link.attrib.get('href')
+ title = ' '.join(link.xpath('.//text()'))
+ content = escape(' '.join(result.xpath('.//p//text()')))
+ results.append({'url': url, 'title': title, 'content': content})
+
+ if results:
+ return results
+
+ for result in dom.xpath('//li[@class="b_algo"]'):
+ link = result.xpath('.//h2/a')[0]
+ url = link.attrib.get('href')
+ title = ' '.join(link.xpath('.//text()'))
+ content = escape(' '.join(result.xpath('.//p//text()')))
+ results.append({'url': url, 'title': title, 'content': content})
+ return results