yt-dlp/yt_dlp/extractor/googlesearch.py

44 lines
1.3 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 14:32:49 -04:00
import itertools
import re
from .common import SearchInfoExtractor
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
2013-06-23 14:32:49 -04:00
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search'
2013-06-23 14:32:49 -04:00
_SEARCH_KEY = 'gvsearch'
2021-10-08 16:39:55 -04:00
_WORKING = False
2014-08-25 11:02:52 -04:00
_TEST = {
'url': 'gvsearch15:python language',
'info_dict': {
'id': 'python language',
'title': 'python language',
},
'playlist_count': 15,
}
2013-06-23 14:32:49 -04:00
2021-10-08 16:39:55 -04:00
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),
query={
'tbm': 'vid',
'q': query,
'start': pagenum * 10,
'hl': 'en',
})
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):
2021-10-08 16:39:55 -04:00
if re.search(f'id="vidthumb{hit_idx + 1}"', webpage):
yield self.url_result(mobj.group(1))
2021-10-08 16:39:55 -04:00
if not re.search(r'id="pnnext"', webpage):
return