administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 07:01:45 +00:00
Code Issues Projects Releases Wiki Activity

[GoogleSearch] Fix extractor

Browse Source
This commit is contained in:
pukkandan 2022-01-31 12:32:44 +05:30
parent b8b3f4562a
commit c533c89ce1
No known key found for this signature in database
GPG Key ID: 0F00D95A001F4698
1 changed files with 9 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
yt_dlp/extractor/googlesearch.py
View File

@ -8,36 +8,33 @@ from .common import SearchInfoExtractor
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search'
_SEARCH_KEY = 'gvsearch'
_WORKING = False
_TEST = {
_TESTS = [{
'url': 'gvsearch15:python language',
'info_dict': {
'id': 'python language',
'title': 'python language',
},
'playlist_count': 15,
}
}]
_PAGE_SIZE = 100
def _search_results(self, query):
for pagenum in itertools.count():
webpage = self._download_webpage(
'http://www.google.com/search',
'gvsearch:' + query,
note='Downloading result page %s' % (pagenum + 1),
'http://www.google.com/search', f'gvsearch:{query}',
note=f'Downloading result page {pagenum + 1}',
query={
'tbm': 'vid',
'q': query,
'start': pagenum * 10,
'start': pagenum * self._PAGE_SIZE,
'num': self._PAGE_SIZE,
'hl': 'en',
})
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):
if re.search(f'id="vidthumb{hit_idx + 1}"', webpage):
yield self.url_result(mobj.group(1))
for url in re.findall(r'<div[^>]* class="dXiKIc"[^>]*><a href="([^"]+)"', webpage):
yield self.url_result(url)
if not re.search(r'id="pnnext"', webpage):
return