2013-10-24 21:52:57 +00:00
|
|
|
from lxml import html
|
|
|
|
from urllib import urlencode
|
|
|
|
from cgi import escape
|
|
|
|
|
|
|
|
base_url = 'http://www.bing.com/'
|
2014-01-29 20:14:38 +00:00
|
|
|
search_string = 'search?{query}&first={offset}'
|
2014-01-19 21:59:01 +00:00
|
|
|
locale = 'en-US' # see http://msdn.microsoft.com/en-us/library/dd251064.aspx
|
2013-10-24 23:37:48 +00:00
|
|
|
|
2014-01-29 20:14:38 +00:00
|
|
|
paging = True
|
|
|
|
|
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
|
2014-01-19 21:59:01 +00:00
|
|
|
search_path = search_string.format(
|
2014-01-29 20:14:38 +00:00
|
|
|
query=urlencode({'q': query, 'setmkt': locale}),
|
|
|
|
offset=offset)
|
2013-10-24 21:52:57 +00:00
|
|
|
#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})
|
2013-10-24 23:37:48 +00:00
|
|
|
|
|
|
|
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})
|
2013-10-24 21:52:57 +00:00
|
|
|
return results
|