[fix] yahoo engine url extraction
commitee1ffbc87f0b2471e33b14561002c400cd8db861
authorAdam Tauber <asciimoo@gmail.com>
dateTue 4 Mar 2014, 14:19 (13 years ago)
parent2d42208
searx/engines/yahoo.py+1−1
@@ -35,7 +35,7 @@ def response(resp):
3535
3636 for result in dom.xpath(results_xpath):
3737 url_string = extract_url(result.xpath(url_xpath), search_url)
38− start = url_string.find('/RU=')+4
38+ start = url_string.find('http', url_string.find('/RU=')+1)
3939 end = url_string.rfind('/RS')
4040 url = unquote(url_string[start:end])
4141 title = extract_text(result.xpath(title_xpath)[0])
searx/engines/yahoo_news.py+1−1
@@ -35,7 +35,7 @@ def response(resp):
3535
3636 for result in dom.xpath(results_xpath):
3737 url_string = extract_url(result.xpath(url_xpath), search_url)
38− start = url_string.find('/RU=')+4
38+ start = url_string.find('http', url_string.find('/RU=')+1)
3939 end = url_string.rfind('/RS')
4040 url = unquote(url_string[start:end])
4141 title = extract_text(result.xpath(title_xpath)[0])