about summary refs log tree commit diff
path: root/youtube_dl/extractor/adultswim.py
blob: 989505c8232abf53f99d0af594c84e45f8778eb0 (plain) (blame)
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
# coding: utf-8
from __future__ import unicode_literals

import re

from .turner import TurnerBaseIE
from ..utils import (
    ExtractorError,
    int_or_none,
)


class AdultSwimIE(TurnerBaseIE):
    _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'

    _TESTS = [{
        'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
        'playlist': [
            {
                'md5': '247572debc75c7652f253c8daa51a14d',
                'info_dict': {
                    'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
                    'ext': 'flv',
                    'title': 'Rick and Morty - Pilot Part 1',
                    'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
                },
            },
            {
                'md5': '77b0e037a4b20ec6b98671c4c379f48d',
                'info_dict': {
                    'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
                    'ext': 'flv',
                    'title': 'Rick and Morty - Pilot Part 4',
                    'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
                },
            },
        ],
        'info_dict': {
            'id': 'rQxZvXQ4ROaSOqq-or2Mow',
            'title': 'Rick and Morty - Pilot',
            'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
        },
        'skip': 'This video is only available for registered users',
    }, {
        'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
        'playlist': [
            {
                'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
                'info_dict': {
                    'id': '-t8CamQlQ2aYZ49ItZCFog-0',
                    'ext': 'flv',
                    'title': 'American Dad - Putting Francine Out of Business',
                    'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
                },
            }
        ],
        'info_dict': {
            'id': '-t8CamQlQ2aYZ49ItZCFog',
            'title': 'American Dad - Putting Francine Out of Business',
            'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
        },
    }, {
        'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
        'playlist': [
            {
                'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
                'info_dict': {
                    'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
                    'ext': 'mp4',
                    'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
                    'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
                },
            }
        ],
        'info_dict': {
            'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
            'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
            'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        }
    }, {
        # heroMetadata.trailer
        'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
        'info_dict': {
            'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
            'ext': 'mp4',
            'title': 'Decker - Inside Decker: A New Hero',
            'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
            'duration': 249.008,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
        'expected_warnings': ['Unable to download f4m manifest'],
    }, {
        'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/',
        'info_dict': {
            'id': 'eYiLsKVgQ6qTC6agD67Sig',
            'title': 'Toonami - Friday, October 14th, 2016',
            'description': 'md5:99892c96ffc85e159a428de85c30acde',
        },
        'playlist': [{
            'md5': '',
            'info_dict': {
                'id': 'eYiLsKVgQ6qTC6agD67Sig',
                'ext': 'mp4',
                'title': 'Toonami - Friday, October 14th, 2016',
                'description': 'md5:99892c96ffc85e159a428de85c30acde',
            },
        }],
        'params': {
            # m3u8 download
            'skip_download': True,
        },
        'expected_warnings': ['Unable to download f4m manifest'],
    }]

    @staticmethod
    def find_video_info(collection, slug):
        for video in collection.get('videos'):
            if video.get('slug') == slug:
                return video

    @staticmethod
    def find_collection_by_linkURL(collections, linkURL):
        for collection in collections:
            if collection.get('linkURL') == linkURL:
                return collection

    @staticmethod
    def find_collection_containing_video(collections, slug):
        for collection in collections:
            for video in collection.get('videos'):
                if video.get('slug') == slug:
                    return collection, video
        return None, None

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        show_path = mobj.group('show_path')
        episode_path = mobj.group('episode_path')
        is_playlist = True if mobj.group('is_playlist') else False

        webpage = self._download_webpage(url, episode_path)

        # Extract the value of `bootstrappedData` from the Javascript in the page.
        bootstrapped_data = self._parse_json(self._search_regex(
            r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)

        # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
        # NOTE: We are only downloading one video (the current one) not the playlist
        if is_playlist:
            collections = bootstrapped_data['playlists']['collections']
            collection = self.find_collection_by_linkURL(collections, show_path)
            video_info = self.find_video_info(collection, episode_path)

            show_title = video_info['showTitle']
            segment_ids = [video_info['videoPlaybackID']]
        else:
            collections = bootstrapped_data['show']['collections']
            collection, video_info = self.find_collection_containing_video(collections, episode_path)
            # Video wasn't found in the collections, let's try `slugged_video`.
            if video_info is None:
                if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
                    video_info = bootstrapped_data['slugged_video']
            if not video_info:
                video_info = bootstrapped_data.get(
                    'heroMetadata', {}).get('trailer', {}).get('video')
            if not video_info:
                video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
            if not video_info:
                raise ExtractorError('Unable to find video info')

            show = bootstrapped_data['show']
            show_title = show['title']
            stream = video_info.get('stream')
            if stream and stream.get('videoPlaybackID'):
                segment_ids = [stream['videoPlaybackID']]
            elif video_info.get('clips'):
                segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
            elif video_info.get('videoPlaybackID'):
                segment_ids = [video_info['videoPlaybackID']]
            elif video_info.get('id'):
                segment_ids = [video_info['id']]
            else:
                if video_info.get('auth') is True:
                    raise ExtractorError(
                        'This video is only available via cable service provider subscription that'
                        ' is not currently supported. You may want to use --cookies.', expected=True)
                else:
                    raise ExtractorError('Unable to find stream or clips')

        episode_id = video_info['id']
        episode_title = video_info['title']
        episode_description = video_info.get('description')
        episode_duration = int_or_none(video_info.get('duration'))
        view_count = int_or_none(video_info.get('views'))

        entries = []
        for part_num, segment_id in enumerate(segment_ids):
            segement_info = self._extract_cvp_info(
                'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
                segment_id, {
                    'secure': {
                        'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
                        'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
                    },
                })
            segment_title = '%s - %s' % (show_title, episode_title)
            if len(segment_ids) > 1:
                segment_title += ' Part %d' % (part_num + 1)
            segement_info.update({
                'id': segment_id,
                'title': segment_title,
                'description': episode_description,
            })
            entries.append(segement_info)

        return {
            '_type': 'playlist',
            'id': episode_id,
            'display_id': episode_path,
            'entries': entries,
            'title': '%s - %s' % (show_title, episode_title),
            'description': episode_description,
            'duration': episode_duration,
            'view_count': view_count,
        }