kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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): class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search' IE_DESC = 'Google Video search'
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search' IE_NAME = 'video.google:search'
_SEARCH_KEY = 'gvsearch' _SEARCH_KEY = 'gvsearch'
_WORKING = False _TESTS = [{
_TEST = {
'url': 'gvsearch15:python language', 'url': 'gvsearch15:python language',
'info_dict': { 'info_dict': {
'id': 'python language', 'id': 'python language',
'title': 'python language', 'title': 'python language',
}, },
'playlist_count': 15, 'playlist_count': 15,
} }]
_PAGE_SIZE = 100
def _search_results(self, query): def _search_results(self, query):
for pagenum in itertools.count(): for pagenum in itertools.count():
webpage = self._download_webpage( webpage = self._download_webpage(
'http://www.google.com/search', 'http://www.google.com/search', f'gvsearch:{query}',
'gvsearch:' + query, note=f'Downloading result page {pagenum + 1}',
note='Downloading result page %s' % (pagenum + 1),
query={ query={
'tbm': 'vid', 'tbm': 'vid',
'q': query, 'q': query,
'start': pagenum * 10, 'start': pagenum * self._PAGE_SIZE,
'num': self._PAGE_SIZE,
'hl': 'en', 'hl': 'en',
}) })
for hit_idx, mobj in enumerate(re.finditer( for url in re.findall(r'<div[^>]* class="dXiKIc"[^>]*><a href="([^"]+)"', webpage):
r'<h3 class="r"><a href="([^"]+)"', webpage)): yield self.url_result(url)
if re.search(f'id="vidthumb{hit_idx + 1}"', webpage):
yield self.url_result(mobj.group(1))
if not re.search(r'id="pnnext"', webpage): if not re.search(r'id="pnnext"', webpage):
return return