aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/googledrive.py
blob: 3bf462d631d7ca20f8eb1b146b496a7c3a57415f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    ExtractorError,
    int_or_none,
    lowercase_escape,
    update_url_query,
)


class GoogleDriveIE(InfoExtractor):
    _VALID_URL = r'''(?x)
                        https?://
                            (?:
                                (?:docs|drive)\.google\.com/
                                (?:
                                    (?:uc|open)\?.*?id=|
                                    file/d/
                                )|
                                video\.google\.com/get_player\?.*?docid=
                            )
                            (?P<id>[a-zA-Z0-9_-]{28,})
                    '''
    _TESTS = [{
        'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1',
        'md5': '5c602afbbf2c1db91831f5d82f678554',
        'info_dict': {
            'id': '0ByeS4oOUV-49Zzh4R1J6R09zazQ',
            'ext': 'mp4',
            'title': 'Big Buck Bunny.mp4',
            'duration': 45,
        }
    }, {
        # video can't be watched anonymously due to view count limit reached,
        # but can be downloaded (see https://github.com/rg3/youtube-dl/issues/14046)
        'url': 'https://drive.google.com/file/d/0B-vUyvmDLdWDcEt4WjBqcmI2XzQ/view',
        'md5': 'bfbd670d03a470bb1e6d4a257adec12e',
        'info_dict': {
            'id': '0B-vUyvmDLdWDcEt4WjBqcmI2XzQ',
            'ext': 'mp4',
            'title': 'Annabelle Creation (2017)- Z.V1 [TH].MP4',
        }
    }, {
        # video id is longer than 28 characters
        'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit',
        'info_dict': {
            'id': '1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ',
            'ext': 'mp4',
            'title': 'Andreea Banica feat Smiley - Hooky Song (Official Video).mp4',
            'duration': 189,
        },
        'only_matching': True,
    }, {
        'url': 'https://drive.google.com/open?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
        'only_matching': True,
    }, {
        'url': 'https://drive.google.com/uc?id=0B2fjwgkl1A_CX083Tkowdmt6d28',
        'only_matching': True,
    }]
    _FORMATS_EXT = {
        '5': 'flv',
        '6': 'flv',
        '13': '3gp',
        '17': '3gp',
        '18': 'mp4',
        '22': 'mp4',
        '34': 'flv',
        '35': 'flv',
        '36': '3gp',
        '37': 'mp4',
        '38': 'mp4',
        '43': 'webm',
        '44': 'webm',
        '45': 'webm',
        '46': 'webm',
        '59': 'mp4',
    }
    _BASE_URL_CAPTIONS = 'https://drive.google.com/timedtext'
    _CAPTIONS_ENTRY_TAG = {
        'subtitles': 'track',
        'automatic_captions': 'target',
    }
    _caption_formats_ext = []
    _captions_xml = None

    @staticmethod
    def _extract_url(webpage):
        mobj = re.search(
            r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})',
            webpage)
        if mobj:
            return 'https://drive.google.com/file/d/%s' % mobj.group('id')

    def _download_subtitles_xml(self, video_id, subtitles_id, hl):
        if self._captions_xml:
            return
        self._captions_xml = self._download_xml(
            self._BASE_URL_CAPTIONS, video_id, query={
                'id': video_id,
                'vid': subtitles_id,
                'hl': hl,
                'v': video_id,
                'type': 'list',
                'tlangs': '1',
                'fmts': '1',
                'vssids': '1',
            }, note='Downloading subtitles XML',
            errnote='Unable to download subtitles XML', fatal=False)
        if self._captions_xml:
            for f in self._captions_xml.findall('format'):
                if f.attrib.get('fmt_code') and not f.attrib.get('default'):
                    self._caption_formats_ext.append(f.attrib['fmt_code'])

    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)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(
            'http://docs.google.com/file/d/%s' % video_id, video_id)

        title = self._search_regex(
            r'"title"\s*,\s*"([^"]+)', webpage, 'title',
            default=None) or self._og_search_title(webpage)
        duration = int_or_none(self._search_regex(
            r'"length_seconds"\s*,\s*"([^"]+)', webpage, 'length seconds',
            default=None))

        formats = []
        fmt_stream_map = self._search_regex(
            r'"fmt_stream_map"\s*,\s*"([^"]+)', webpage,
            'fmt stream map', default='').split(',')
        fmt_list = self._search_regex(
            r'"fmt_list"\s*,\s*"([^"]+)', webpage,
            'fmt_list', default='').split(',')
        if fmt_stream_map and fmt_list:
            resolutions = {}
            for fmt in fmt_list:
                mobj = re.search(
                    r'^(?P<format_id>\d+)/(?P<width>\d+)[xX](?P<height>\d+)', fmt)
                if mobj:
                    resolutions[mobj.group('format_id')] = (
                        int(mobj.group('width')), int(mobj.group('height')))

            for fmt_stream in fmt_stream_map:
                fmt_stream_split = fmt_stream.split('|')
                if len(fmt_stream_split) < 2:
                    continue
                format_id, format_url = fmt_stream_split[:2]
                f = {
                    'url': lowercase_escape(format_url),
                    'format_id': format_id,
                    'ext': self._FORMATS_EXT[format_id],
                }
                resolution = resolutions.get(format_id)
                if resolution:
                    f.update({
                        'width': resolution[0],
                        'height': resolution[1],
                    })
                formats.append(f)

        source_url = update_url_query(
            'https://drive.google.com/uc', {
                'id': video_id,
                'export': 'download',
            })
        urlh = self._request_webpage(
            source_url, video_id, note='Requesting source file',
            errnote='Unable to request source file', fatal=False)
        if urlh:
            def add_source_format(src_url):
                formats.append({
                    'url': src_url,
                    'ext': determine_ext(title, 'mp4').lower(),
                    'format_id': 'source',
                    'quality': 1,
                })
            if urlh.headers.get('Content-Disposition'):
                add_source_format(source_url)
            else:
                confirmation_webpage = self._webpage_read_content(
                    urlh, url, video_id, note='Downloading confirmation page',
                    errnote='Unable to confirm download', fatal=False)
                if confirmation_webpage:
                    confirm = self._search_regex(
                        r'confirm=([^&"\']+)', confirmation_webpage,
                        'confirmation code', fatal=False)
                    if confirm:
                        add_source_format(update_url_query(source_url, {
                            'confirm': confirm,
                        }))

        if not formats:
            reason = self._search_regex(
                r'"reason"\s*,\s*"([^"]+)', webpage, 'reason', default=None)
            if reason:
                raise ExtractorError(reason, expected=True)

        self._sort_formats(formats)

        hl = self._search_regex(
            r'"hl"\s*,\s*"([^"]+)', webpage, 'hl', default=None)
        subtitles_id = None
        ttsurl = self._search_regex(
            r'"ttsurl"\s*,\s*"([^"]+)', webpage, 'ttsurl', default=None)
        if ttsurl:
            # the video Id for subtitles will be the last value in the ttsurl
            # query string
            subtitles_id = ttsurl.encode('utf-8').decode(
                'unicode_escape').split('=')[-1]

        return {
            'id': video_id,
            'title': title,
            'thumbnail': self._og_search_thumbnail(webpage, default=None),
            'duration': duration,
            'formats': formats,
            'subtitles': self.extract_subtitles(video_id, subtitles_id, hl),
            'automatic_captions': self.extract_automatic_captions(
                video_id, subtitles_id, hl),
        }