1
0
mirror of https://github.com/searx/searx synced 2024-11-17 23:47:39 +01:00

[enh] yahoo engine added

This commit is contained in:
asciimoo 2014-01-30 02:33:24 +01:00
parent fe82637eac
commit 642986c2e7

42
searx/engines/yahoo.py Normal file
View File

@ -0,0 +1,42 @@
#!/usr/bin/env python
from urllib import urlencode
from searx.engines.xpath import extract_text, extract_url
from lxml import html
categories = ['general']
search_url = 'http://search.yahoo.com/search?{query}&b={offset}'
results_xpath = '//div[@class="res"]'
url_xpath = './/h3/a/@href'
title_xpath = './/h3/a'
content_xpath = './/div[@class="abstr"]'
suggestion_xpath = '//div[@id="satat"]//a'
paging = True
def request(query, params):
offset = (params['pageno'] - 1) * 10 + 1
params['url'] = search_url.format(offset=offset,
query=urlencode({'p': query}))
print params['url']
return params
def response(resp):
results = []
dom = html.fromstring(resp.text)
for result in dom.xpath(results_xpath):
url = extract_url(result.xpath(url_xpath), search_url)
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
results.append({'url': url, 'title': title, 'content': content})
if not suggestion_xpath:
return results
for suggestion in dom.xpath(suggestion_xpath):
results.append({'suggestion': extract_text(suggestion)})
return results