yt_dlp/extractor/googlesearch.py

   1 import itertools
   2 import re
   3
   4 from .common import SearchInfoExtractor
   5
   6
   7 class GoogleSearchIE(SearchInfoExtractor):
   8     IE_DESC = 'Google Video search'
   9     IE_NAME = 'video.google:search'
  10     _SEARCH_KEY = 'gvsearch'
  11     _TESTS = [{
  12         'url': 'gvsearch15:python language',
  13         'info_dict': {
  14             'id': 'python language',
  15             'title': 'python language',
  16         },
  17         'playlist_count': 15,
  18     }]
  19     _PAGE_SIZE = 100
  20
  21     def _search_results(self, query):
  22         for pagenum in itertools.count():
  23             webpage = self._download_webpage(
  24                 'http://www.google.com/search', f'gvsearch:{query}',
  25                 note=f'Downloading result page {pagenum + 1}',
  26                 query={
  27                     'tbm': 'vid',
  28                     'q': query,
  29                     'start': pagenum * self._PAGE_SIZE,
  30                     'num': self._PAGE_SIZE,
  31                     'hl': 'en',
  32                 })
  33
  34             for url in re.findall(r'<div[^>]* class="dXiKIc"[^>]*><a href="([^"]+)"', webpage):
  35                 yield self.url_result(url)
  36
  37             if not re.search(r'id="pnnext"', webpage):
  38                 return