2014-09-01 12:38:59 +00:00
|
|
|
## Bing (Web)
|
|
|
|
#
|
|
|
|
# @website https://www.bing.com
|
|
|
|
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
|
|
|
|
#
|
|
|
|
# @using-api no (because of query limit)
|
|
|
|
# @results HTML (using search portal)
|
|
|
|
# @stable no (HTML can change)
|
|
|
|
# @parse url, title, content
|
|
|
|
#
|
|
|
|
# @todo publishedDate
|
|
|
|
|
2013-10-24 21:52:57 +00:00
|
|
|
from urllib import urlencode
|
|
|
|
from cgi import escape
|
2014-02-05 19:24:31 +00:00
|
|
|
from lxml import html
|
2013-10-24 21:52:57 +00:00
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# engine dependent config
|
|
|
|
categories = ['general']
|
2014-01-29 20:14:38 +00:00
|
|
|
paging = True
|
2014-01-31 03:35:23 +00:00
|
|
|
language_support = True
|
2014-01-29 20:14:38 +00:00
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# search-url
|
|
|
|
base_url = 'https://www.bing.com/'
|
|
|
|
search_string = 'search?{query}&first={offset}'
|
2013-10-24 21:52:57 +00:00
|
|
|
|
2014-09-02 15:13:44 +00:00
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# do search-request
|
2013-10-24 21:52:57 +00:00
|
|
|
def request(query, params):
|
2014-01-29 20:14:38 +00:00
|
|
|
offset = (params['pageno'] - 1) * 10 + 1
|
2014-09-01 12:38:59 +00:00
|
|
|
|
2014-01-31 03:35:23 +00:00
|
|
|
if params['language'] == 'all':
|
|
|
|
language = 'en-US'
|
|
|
|
else:
|
|
|
|
language = params['language'].replace('_', '-')
|
2014-09-01 12:38:59 +00:00
|
|
|
|
2014-01-19 21:59:01 +00:00
|
|
|
search_path = search_string.format(
|
2014-01-31 03:35:23 +00:00
|
|
|
query=urlencode({'q': query, 'setmkt': language}),
|
2014-01-29 20:14:38 +00:00
|
|
|
offset=offset)
|
2014-01-31 03:35:23 +00:00
|
|
|
|
|
|
|
params['cookies']['SRCHHPGUSR'] = \
|
|
|
|
'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0]
|
2014-09-01 12:38:59 +00:00
|
|
|
|
2013-10-24 21:52:57 +00:00
|
|
|
params['url'] = base_url + search_path
|
|
|
|
return params
|
|
|
|
|
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# get response from search-request
|
2013-10-24 21:52:57 +00:00
|
|
|
def response(resp):
|
|
|
|
results = []
|
2014-09-01 12:38:59 +00:00
|
|
|
|
2013-10-24 21:52:57 +00:00
|
|
|
dom = html.fromstring(resp.content)
|
2014-09-01 12:38:59 +00:00
|
|
|
|
|
|
|
# parse results
|
2013-10-24 21:52:57 +00:00
|
|
|
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()')))
|
2013-10-24 23:37:48 +00:00
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# append result
|
|
|
|
results.append({'url': url,
|
|
|
|
'title': title,
|
|
|
|
'content': content})
|
|
|
|
|
|
|
|
# return results if something is found
|
2013-10-24 23:37:48 +00:00
|
|
|
if results:
|
|
|
|
return results
|
|
|
|
|
2014-09-01 12:38:59 +00:00
|
|
|
# parse results again if nothing is found yet
|
2013-10-24 23:37:48 +00:00
|
|
|
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()')))
|
2014-09-01 12:38:59 +00:00
|
|
|
|
|
|
|
# append result
|
|
|
|
results.append({'url': url,
|
|
|
|
'title': title,
|
|
|
|
'content': content})
|
|
|
|
|
|
|
|
# return results
|
2013-10-24 21:52:57 +00:00
|
|
|
return results
|