mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-10 00:58:17 +02:00
[gvsearch] Modernize and fix page result request (closes #11051)
This commit is contained in:
parent
c725333d41
commit
f3517569f6
@ -4,9 +4,6 @@
|
|||||||
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 @@ def _get_n_results(self, query, n):
|
|||||||
}
|
}
|
||||||
|
|
||||||
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)):
|
||||||
|
Loading…
Reference in New Issue
Block a user