1 from __future__ import unicode_literals
5 from .common import InfoExtractor
15 class GoogleDriveIE(InfoExtractor):
19 (?:docs|drive)\.google\.com/
24 video\.google\.com/get_player\?.*?docid=
26 (?P<id>[a-zA-Z0-9_-]{28,})
29 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
30 'md5': '5c602afbbf2c1db91831f5d82f678554',
32 'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
34 'title': 'Big Buck Bunny.mp4',
38 # video can't be watched anonymously due to view count limit reached,
39 # but can be downloaded (see https://github.com/ytdl-org/youtube-dl/issues/14046)
40 'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
41 'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
43 'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
45 'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
48 # video id is longer than 28 characters
49 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
51 'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
53 'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
56 'only_matching': True,
58 'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
59 'only_matching': True,
61 'url': 'https://drive.google.com/uc?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
62 'only_matching': True,
82 _BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
83 _CAPTIONS_ENTRY_TAG = {
85 'automatic_captions': 'target',
87 _caption_formats_ext = []
91 def _extract_url(webpage):
93 r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
96 return 'https://drive.google.com/file/d/%s' % mobj.group('id')
98 def _download_subtitles_xml(self, video_id, subtitles_id, hl):
99 if self._captions_xml:
101 self._captions_xml = self._download_xml(
102 self._BASE_URL_CAPTIONS, video_id, query={
111 }, note='Downloading subtitles XML',
112 errnote='Unable to download subtitles XML', fatal=False)
113 if self._captions_xml:
114 for f in self._captions_xml.findall('format'):
115 if f.attrib.get('fmt_code') and not f.attrib.get('default'):
116 self._caption_formats_ext.append(f.attrib['fmt_code'])
118 def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
119 origin_lang_code=None):
120 if not subtitles_id or not caption_type:
123 for caption_entry in self._captions_xml.findall(
124 self._CAPTIONS_ENTRY_TAG[caption_type]):
125 caption_lang_code = caption_entry.attrib.get('lang_code')
126 if not caption_lang_code:
128 caption_format_data = []
129 for caption_format in self._caption_formats_ext:
133 'fmt': caption_format,
134 'lang': (caption_lang_code if origin_lang_code is None
135 else origin_lang_code),
140 if origin_lang_code is not None:
141 query.update({'tlang': caption_lang_code})
142 caption_format_data.append({
143 'url': update_url_query(self._BASE_URL_CAPTIONS, query),
144 'ext': caption_format,
146 captions[caption_lang_code] = caption_format_data
149 def _get_subtitles(self, video_id, subtitles_id, hl):
150 if not subtitles_id or not hl:
152 self._download_subtitles_xml(video_id, subtitles_id, hl)
153 if not self._captions_xml:
155 return self._get_captions_by_type(video_id, subtitles_id, 'subtitles')
157 def _get_automatic_captions(self, video_id, subtitles_id, hl):
158 if not subtitles_id or not hl:
160 self._download_subtitles_xml(video_id, subtitles_id, hl)
161 if not self._captions_xml:
163 track = self._captions_xml.find('track')
166 origin_lang_code = track.attrib.get('lang_code')
167 if not origin_lang_code:
169 return self._get_captions_by_type(
170 video_id, subtitles_id, 'automatic_captions', origin_lang_code)
172 def _real_extract(self, url):
173 video_id = self._match_id(url)
174 webpage = self._download_webpage(
175 'http://docs.google.com/file/d/%s' % video_id, video_id)
177 title = self._search_regex(
178 r'"title"\s*,\s*"([^"]+)', webpage, 'title',
179 default=None) or self._og_search_title(webpage)
180 duration = int_or_none(self._search_regex(
181 r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
185 fmt_stream_map = self._search_regex(
186 r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
187 'fmt stream map', default='').split(',')
188 fmt_list = self._search_regex(
189 r'"fmt_list"\s*,\s*"([^"]+)', webpage,
190 'fmt_list', default='').split(',')
191 if fmt_stream_map and fmt_list:
195 r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
197 resolutions[mobj.group('format_id')] = (
198 int(mobj.group('width')), int(mobj.group('height')))
200 for fmt_stream in fmt_stream_map:
201 fmt_stream_split = fmt_stream.split('|')
202 if len(fmt_stream_split) < 2:
204 format_id, format_url = fmt_stream_split[:2]
206 'url': lowercase_escape(format_url),
207 'format_id': format_id,
208 'ext': self._FORMATS_EXT[format_id],
210 resolution = resolutions.get(format_id)
213 'width': resolution[0],
214 'height': resolution[1],
218 source_url = update_url_query(
219 'https://drive.google.com/uc', {
221 'export': 'download',
223 urlh = self._request_webpage(
224 source_url, video_id, note='Requesting source file',
225 errnote='Unable to request source file', fatal=False)
227 def add_source_format(src_url):
230 'ext': determine_ext(title, 'mp4').lower(),
231 'format_id': 'source',
234 if urlh.headers.get('Content-Disposition'):
235 add_source_format(source_url)
237 confirmation_webpage = self._webpage_read_content(
238 urlh, url, video_id, note='Downloading confirmation page',
239 errnote='Unable to confirm download', fatal=False)
240 if confirmation_webpage:
241 confirm = self._search_regex(
242 r'confirm=([^&"\']+)', confirmation_webpage,
243 'confirmation code', fatal=False)
245 add_source_format(update_url_query(source_url, {
250 reason = self._search_regex(
251 r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
253 raise ExtractorError(reason, expected=True)
255 self._sort_formats(formats)
257 hl = self._search_regex(
258 r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
260 ttsurl = self._search_regex(
261 r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
263 # the video Id for subtitles will be the last value in the ttsurl
265 subtitles_id = ttsurl.encode('utf-8').decode(
266 'unicode_escape').split('=')[-1]
271 'thumbnail': self._og_search_thumbnail(webpage, default=None),
272 'duration': duration,
274 'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
275 'automatic_captions': self.extract_automatic_captions(
276 video_id, subtitles_id, hl),