yt-dlp/yt_dlp/extractor/googlesearch.py

41 lines
1.2 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 18:32:49 +00:00
import itertools
import re
from .common import SearchInfoExtractor
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
IE_NAME = 'video.google:search'
2013-06-23 18:32:49 +00:00
_SEARCH_KEY = 'gvsearch'
2022-01-31 07:02:44 +00:00
_TESTS = [{
2014-08-25 15:02:52 +00:00
'url': 'gvsearch15:python language',
'info_dict': {
'id': 'python language',
'title': 'python language',
},
'playlist_count': 15,
2022-01-31 07:02:44 +00:00
}]
_PAGE_SIZE = 100
2013-06-23 18:32:49 +00:00
2021-10-08 20:39:55 +00:00
def _search_results(self, query):
for pagenum in itertools.count():
webpage = self._download_webpage(
2022-01-31 07:02:44 +00:00
'http://www.google.com/search', f'gvsearch:{query}',
note=f'Downloading result page {pagenum + 1}',
query={
'tbm': 'vid',
'q': query,
2022-01-31 07:02:44 +00:00
'start': pagenum * self._PAGE_SIZE,
'num': self._PAGE_SIZE,
'hl': 'en',
})
2022-01-31 07:02:44 +00:00
for url in re.findall(r'<div[^>]* class="dXiKIc"[^>]*><a href="([^"]+)"', webpage):
yield self.url_result(url)
2021-10-08 20:39:55 +00:00
if not re.search(r'id="pnnext"', webpage):
return