[fix] append http if no scheme is provided in xpath's extact_url

This solves a bug with Yahoo where some results don't specify
a protocol.
This commit is contained in:
Marc Abonce Seguin 2018-04-08 20:35:34 -05:00
parent 283f6c9053
commit 343e555ee9
1 changed files with 1 additions and 1 deletions

View File

@ -53,7 +53,7 @@ def extract_url(xpath_results, search_url):
if url.startswith('//'): if url.startswith('//'):
# add http or https to this kind of url //example.com/ # add http or https to this kind of url //example.com/
parsed_search_url = urlparse(search_url) parsed_search_url = urlparse(search_url)
url = u'{0}:{1}'.format(parsed_search_url.scheme, url) url = u'{0}:{1}'.format(parsed_search_url.scheme or 'http', url)
elif url.startswith('/'): elif url.startswith('/'):
# fix relative url to the search engine # fix relative url to the search engine
url = urljoin(search_url, url) url = urljoin(search_url, url)