-class GoogleDriveIE(InfoExtractor):
- _VALID_URL = r'https?://(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)(?P<id>[a-zA-Z0-9_-]{28})'
- _TEST = {
- 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
- 'info_dict': {
- 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
- 'ext': 'mp4',
- 'title': 'Big Buck Bunny.mp4',
- }
- }
- _formats = {
- '5': {'ext': 'flv'},
- '6': {'ext': 'flv'},
- '13': {'ext': '3gp'},
- '17': {'ext': '3gp'},
- '18': {'ext': 'mp4'},
- '22': {'ext': 'mp4'},
- '34': {'ext': 'flv'},
- '35': {'ext': 'flv'},
- '36': {'ext': '3gp'},
- '37': {'ext': 'mp4'},
- '38': {'ext': 'mp4'},
- '43': {'ext': 'webm'},
- '44': {'ext': 'webm'},
- '45': {'ext': 'webm'},
- '46': {'ext': 'webm'},
- '59': {'ext': 'mp4'}
- }
+ def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
+ origin_lang_code=None):
+ if not subtitles_id or not caption_type:
+ return
+ captions = {}
+ for caption_entry in self._captions_xml.findall(
+ self._CAPTIONS_ENTRY_TAG[caption_type]):
+ caption_lang_code = caption_entry.attrib.get('lang_code')
+ if not caption_lang_code:
+ continue
+ caption_format_data = []
+ for caption_format in self._caption_formats_ext:
+ query = {
+ 'vid': subtitles_id,
+ 'v': video_id,
+ 'fmt': caption_format,
+ 'lang': (caption_lang_code if origin_lang_code is None
+ else origin_lang_code),
+ 'type': 'track',
+ 'name': '',
+ 'kind': '',
+ }
+ if origin_lang_code is not None:
+ query.update({'tlang': caption_lang_code})
+ caption_format_data.append({
+ 'url': update_url_query(self._BASE_URL_CAPTIONS, query),
+ 'ext': caption_format,
+ })
+ captions[caption_lang_code] = caption_format_data
+ return captions
+
+ def _get_subtitles(self, video_id, subtitles_id, hl):
+ if not subtitles_id or not hl:
+ return
+ self._download_subtitles_xml(video_id, subtitles_id, hl)
+ if not self._captions_xml:
+ return
+ return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
+
+ def _get_automatic_captions(self, video_id, subtitles_id, hl):
+ if not subtitles_id or not hl:
+ return
+ self._download_subtitles_xml(video_id, subtitles_id, hl)
+ if not self._captions_xml:
+ return
+ track = self._captions_xml.find('track')
+ if track is None:
+ return
+ origin_lang_code = track.attrib.get('lang_code')
+ if not origin_lang_code:
+ return
+ return self._get_captions_by_type(
+ video_id, subtitles_id, 'automatic_captions', origin_lang_code)