mirror/yt-dlc
1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-22 07:43:08 +00:00
Code Issues Releases Wiki Activity

[gvsearch] Modernize and fix page result request (closes #11051)

Browse source
This commit is contained in:
Sergey M․ 2016-10-28 23:19:59 +07:00
parent c725333d41
commit f3517569f6
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 9 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/googlesearch.py
View file

@ -4,9 +4,6 @@ import itertools
import re import re
from .common import SearchInfoExtractor from .common import SearchInfoExtractor
from ..compat import (
compat_urllib_parse,
)
class GoogleSearchIE(SearchInfoExtractor): class GoogleSearchIE(SearchInfoExtractor):
@ -34,13 +31,16 @@ class GoogleSearchIE(SearchInfoExtractor):
} }
for pagenum in itertools.count(): for pagenum in itertools.count():
result_url = (
'http://www.google.com/search?tbm=vid&q=%s&start=%s&hl=en'
% (compat_urllib_parse.quote_plus(query), pagenum * 10))
webpage = self._download_webpage( webpage = self._download_webpage(
result_url, 'gvsearch:' + query, 'http://www.google.com/search',
note='Downloading result page ' + str(pagenum + 1)) 'gvsearch:' + query,
note='Downloading result page %s' % (pagenum + 1),
query={
'tbm': 'vid',
'q': query,
'start': pagenum * 10,
'hl': 'en',
})
for hit_idx, mobj in enumerate(re.finditer( for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)): r'<h3 class="r"><a href="([^"]+)"', webpage)):