_ Git - youtube-dl/blob - youtube_dl/extractor/googledrive.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     int_or_none,
  10     lowercase_escape,
  11     update_url_query,
  12 )
  13
  14
  15 class GoogleDriveIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})'
  17     _TESTS = [{
  18         'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
  19         'md5': '5c602afbbf2c1db91831f5d82f678554',
  20         'info_dict': {
  21             'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
  22             'ext': 'mp4',
  23             'title': 'Big Buck Bunny.mp4',
  24             'duration': 45,
  25         }
  26     }, {
  27         # video can't be watched anonymously due to view count limit reached,
  28         # but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
  29         'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
  30         'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
  31         'info_dict': {
  32             'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
  33             'ext': 'mp4',
  34             'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
  35         }
  36     }, {
  37         # video id is longer than 28 characters
  38         'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
  39         'info_dict': {
  40             'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
  41             'ext': 'mp4',
  42             'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
  43             'duration': 189,
  44         },
  45         'only_matching': True
  46     }]
  47     _FORMATS_EXT = {
  48         '5': 'flv',
  49         '6': 'flv',
  50         '13': '3gp',
  51         '17': '3gp',
  52         '18': 'mp4',
  53         '22': 'mp4',
  54         '34': 'flv',
  55         '35': 'flv',
  56         '36': '3gp',
  57         '37': 'mp4',
  58         '38': 'mp4',
  59         '43': 'webm',
  60         '44': 'webm',
  61         '45': 'webm',
  62         '46': 'webm',
  63         '59': 'mp4',
  64     }
  65     _BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
  66     _CAPTIONS_ENTRY_TAG = {
  67         'subtitles': 'track',
  68         'automatic_captions': 'target',
  69     }
  70     _caption_formats_ext = []
  71     _captions_xml = None
  72
  73     @staticmethod
  74     def _extract_url(webpage):
  75         mobj = re.search(
  76             r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
  77             webpage)
  78         if mobj:
  79             return 'https://drive.google.com/file/d/%s' % mobj.group('id')
  80
  81     def _download_subtitles_xml(self, video_id, subtitles_id, hl):
  82         if self._captions_xml:
  83             return
  84         self._captions_xml = self._download_xml(
  85             self._BASE_URL_CAPTIONS, video_id, query={
  86                 'id': video_id,
  87                 'vid': subtitles_id,
  88                 'hl': hl,
  89                 'v': video_id,
  90                 'type': 'list',
  91                 'tlangs': '1',
  92                 'fmts': '1',
  93                 'vssids': '1',
  94             }, note='Downloading subtitles XML',
  95             errnote='Unable to download subtitles XML', fatal=False)
  96         if self._captions_xml:
  97             for f in self._captions_xml.findall('format'):
  98                 if f.attrib.get('fmt_code') and not f.attrib.get('default'):
  99                     self._caption_formats_ext.append(f.attrib['fmt_code'])
 100
 101     def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
 102                               origin_lang_code=None):
 103         if not subtitles_id or not caption_type:
 104             return
 105         captions = {}
 106         for caption_entry in self._captions_xml.findall(
 107                 self._CAPTIONS_ENTRY_TAG[caption_type]):
 108             caption_lang_code = caption_entry.attrib.get('lang_code')
 109             if not caption_lang_code:
 110                 continue
 111             caption_format_data = []
 112             for caption_format in self._caption_formats_ext:
 113                 query = {
 114                     'vid': subtitles_id,
 115                     'v': video_id,
 116                     'fmt': caption_format,
 117                     'lang': (caption_lang_code if origin_lang_code is None
 118                              else origin_lang_code),
 119                     'type': 'track',
 120                     'name': '',
 121                     'kind': '',
 122                 }
 123                 if origin_lang_code is not None:
 124                     query.update({'tlang': caption_lang_code})
 125                 caption_format_data.append({
 126                     'url': update_url_query(self._BASE_URL_CAPTIONS, query),
 127                     'ext': caption_format,
 128                 })
 129             captions[caption_lang_code] = caption_format_data
 130         return captions
 131
 132     def _get_subtitles(self, video_id, subtitles_id, hl):
 133         if not subtitles_id or not hl:
 134             return
 135         self._download_subtitles_xml(video_id, subtitles_id, hl)
 136         if not self._captions_xml:
 137             return
 138         return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
 139
 140     def _get_automatic_captions(self, video_id, subtitles_id, hl):
 141         if not subtitles_id or not hl:
 142             return
 143         self._download_subtitles_xml(video_id, subtitles_id, hl)
 144         if not self._captions_xml:
 145             return
 146         track = self._captions_xml.find('track')
 147         if track is None:
 148             return
 149         origin_lang_code = track.attrib.get('lang_code')
 150         if not origin_lang_code:
 151             return
 152         return self._get_captions_by_type(
 153             video_id, subtitles_id, 'automatic_captions', origin_lang_code)
 154
 155     def _real_extract(self, url):
 156         video_id = self._match_id(url)
 157         webpage = self._download_webpage(
 158             'http://docs.google.com/file/d/%s' % video_id, video_id)
 159
 160         title = self._search_regex(
 161             r'"title"\s*,\s*"([^"]+)', webpage, 'title',
 162             default=None) or self._og_search_title(webpage)
 163         duration = int_or_none(self._search_regex(
 164             r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
 165             default=None))
 166
 167         formats = []
 168         fmt_stream_map = self._search_regex(
 169             r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
 170             'fmt stream map', default='').split(',')
 171         fmt_list = self._search_regex(
 172             r'"fmt_list"\s*,\s*"([^"]+)', webpage,
 173             'fmt_list', default='').split(',')
 174         if fmt_stream_map and fmt_list:
 175             resolutions = {}
 176             for fmt in fmt_list:
 177                 mobj = re.search(
 178                     r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
 179                 if mobj:
 180                     resolutions[mobj.group('format_id')] = (
 181                         int(mobj.group('width')), int(mobj.group('height')))
 182
 183             for fmt_stream in fmt_stream_map:
 184                 fmt_stream_split = fmt_stream.split('|')
 185                 if len(fmt_stream_split) < 2:
 186                     continue
 187                 format_id, format_url = fmt_stream_split[:2]
 188                 f = {
 189                     'url': lowercase_escape(format_url),
 190                     'format_id': format_id,
 191                     'ext': self._FORMATS_EXT[format_id],
 192                 }
 193                 resolution = resolutions.get(format_id)
 194                 if resolution:
 195                     f.update({
 196                         'width': resolution[0],
 197                         'height': resolution[1],
 198                     })
 199                 formats.append(f)
 200
 201         source_url = update_url_query(
 202             'https://drive.google.com/uc', {
 203                 'id': video_id,
 204                 'export': 'download',
 205             })
 206         urlh = self._request_webpage(
 207             source_url, video_id, note='Requesting source file',
 208             errnote='Unable to request source file', fatal=False)
 209         if urlh:
 210             def add_source_format(src_url):
 211                 formats.append({
 212                     'url': src_url,
 213                     'ext': determine_ext(title, 'mp4').lower(),
 214                     'format_id': 'source',
 215                     'quality': 1,
 216                 })
 217             if urlh.headers.get('Content-Disposition'):
 218                 add_source_format(source_url)
 219             else:
 220                 confirmation_webpage = self._webpage_read_content(
 221                     urlh, url, video_id, note='Downloading confirmation page',
 222                     errnote='Unable to confirm download', fatal=False)
 223                 if confirmation_webpage:
 224                     confirm = self._search_regex(
 225                         r'confirm=([^&"\']+)', confirmation_webpage,
 226                         'confirmation code', fatal=False)
 227                     if confirm:
 228                         add_source_format(update_url_query(source_url, {
 229                             'confirm': confirm,
 230                         }))
 231
 232         if not formats:
 233             reason = self._search_regex(
 234                 r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
 235             if reason:
 236                 raise ExtractorError(reason, expected=True)
 237
 238         self._sort_formats(formats)
 239
 240         hl = self._search_regex(
 241             r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
 242         subtitles_id = None
 243         ttsurl = self._search_regex(
 244             r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
 245         if ttsurl:
 246             # the video Id for subtitles will be the last value in the ttsurl
 247             # query string
 248             subtitles_id = ttsurl.encode('utf-8').decode(
 249                 'unicode_escape').split('=')[-1]
 250
 251         return {
 252             'id': video_id,
 253             'title': title,
 254             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 255             'duration': duration,
 256             'formats': formats,
 257             'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
 258             'automatic_captions': self.extract_automatic_captions(
 259                 video_id, subtitles_id, hl),
 260         }