git.iko.soy/searx
on master help sign in
[fix] yahoo url extraction
0fc481fAdam Tauber
searx/engines/yahoo.py+5−4
compare with master
unifiedsplit
@@ -15,6 +15,10 @@ suggestion_xpath = '//div[@id="satat"]//a'
15
15
16paging = True
16paging = True
17
17
18+def parse_url(url_string):
19+ start = url_string.find('http', url_string.find('/RU=')+1)
20+ end = min(url_string.rfind('/RS'), url_string.rfind('/RK'))
21+ return unquote(url_string[start:end])
18
22
19def request(query, params):
23def request(query, params):
20 offset = (params['pageno'] - 1) * 10 + 1
24 offset = (params['pageno'] - 1) * 10 + 1
@@ -34,10 +38,7 @@ def response(resp):
34 dom = html.fromstring(resp.text)
38 dom = html.fromstring(resp.text)
35
39
36 for result in dom.xpath(results_xpath):
40 for result in dom.xpath(results_xpath):
37− url_string = extract_url(result.xpath(url_xpath), search_url)
41+ url = parse_url(extract_url(result.xpath(url_xpath), search_url))
38− start = url_string.find('http', url_string.find('/RU=')+1)
39− end = url_string.rfind('/RS')
40− url = unquote(url_string[start:end])
41 title = extract_text(result.xpath(title_xpath)[0])
42 title = extract_text(result.xpath(title_xpath)[0])
42 content = extract_text(result.xpath(content_xpath)[0])
43 content = extract_text(result.xpath(content_xpath)[0])
43 results.append({'url': url, 'title': title, 'content': content})
44 results.append({'url': url, 'title': title, 'content': content})
searx/engines/yahoo_news.py+2−5
@@ -1,9 +1,9 @@
1#!/usr/bin/env python
1#!/usr/bin/env python
2
2
3from urllib import urlencode
3from urllib import urlencode
4−from urlparse import unquote
5from lxml import html
4from lxml import html
6from searx.engines.xpath import extract_text, extract_url
5from searx.engines.xpath import extract_text, extract_url
6+from searx.engines.yahoo import parse_url
7
7
8categories = ['news']
8categories = ['news']
9search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
9search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
@@ -34,10 +34,7 @@ def response(resp):
34 dom = html.fromstring(resp.text)
34 dom = html.fromstring(resp.text)
35
35
36 for result in dom.xpath(results_xpath):
36 for result in dom.xpath(results_xpath):
37− url_string = extract_url(result.xpath(url_xpath), search_url)
37+ url = parse_url(extract_url(result.xpath(url_xpath), search_url))
38− start = url_string.find('http', url_string.find('/RU=')+1)
39− end = url_string.rfind('/RS')
40− url = unquote(url_string[start:end])
41 title = extract_text(result.xpath(title_xpath)[0])
38 title = extract_text(result.xpath(title_xpath)[0])
42 content = extract_text(result.xpath(content_xpath)[0])
39 content = extract_text(result.xpath(content_xpath)[0])
43 results.append({'url': url, 'title': title, 'content': content})
40 results.append({'url': url, 'title': title, 'content': content})