[youtube] Skip unsupported adaptive stream type (#18804)
[youtube-dl] / youtube_dl / extractor / adultswim.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .turner import TurnerBaseIE
7 from ..utils import (
8     int_or_none,
9     strip_or_none,
10     url_or_none,
11 )
12
13
14 class AdultSwimIE(TurnerBaseIE):
15     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
16
17     _TESTS = [{
18         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
19         'info_dict': {
20             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
21             'ext': 'mp4',
22             'title': 'Rick and Morty - Pilot',
23             'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
24             'timestamp': 1493267400,
25             'upload_date': '20170427',
26         },
27         'params': {
28             # m3u8 download
29             'skip_download': True,
30         },
31         'expected_warnings': ['Unable to download f4m manifest'],
32     }, {
33         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
34         'info_dict': {
35             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
36             'ext': 'mp4',
37             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
38             'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
39             'upload_date': '20080124',
40             'timestamp': 1201150800,
41         },
42         'params': {
43             # m3u8 download
44             'skip_download': True,
45         },
46     }, {
47         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
48         'info_dict': {
49             'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
50             'ext': 'mp4',
51             'title': 'Decker - Inside Decker: A New Hero',
52             'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
53             'timestamp': 1469480460,
54             'upload_date': '20160725',
55         },
56         'params': {
57             # m3u8 download
58             'skip_download': True,
59         },
60         'expected_warnings': ['Unable to download f4m manifest'],
61     }, {
62         'url': 'http://www.adultswim.com/videos/attack-on-titan',
63         'info_dict': {
64             'id': 'b7A69dzfRzuaXIECdxW8XQ',
65             'title': 'Attack on Titan',
66             'description': 'md5:6c8e003ea0777b47013e894767f5e114',
67         },
68         'playlist_mincount': 12,
69     }, {
70         'url': 'http://www.adultswim.com/videos/streams/williams-stream',
71         'info_dict': {
72             'id': 'd8DEBj7QRfetLsRgFnGEyg',
73             'ext': 'mp4',
74             'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
75             'description': 'original programming',
76         },
77         'params': {
78             # m3u8 download
79             'skip_download': True,
80         },
81     }]
82
83     def _real_extract(self, url):
84         show_path, episode_path = re.match(self._VALID_URL, url).groups()
85         display_id = episode_path or show_path
86         webpage = self._download_webpage(url, display_id)
87         initial_data = self._parse_json(self._search_regex(
88             r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
89             webpage, 'initial data'), display_id)
90
91         is_stream = show_path == 'streams'
92         if is_stream:
93             if not episode_path:
94                 episode_path = 'live-stream'
95
96             video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
97             video_id = video_data.get('stream')
98
99             if not video_id:
100                 entries = []
101                 for episode in video_data.get('archiveEpisodes', []):
102                     episode_url = url_or_none(episode.get('url'))
103                     if not episode_url:
104                         continue
105                     entries.append(self.url_result(
106                         episode_url, 'AdultSwim', episode.get('id')))
107                 return self.playlist_result(
108                     entries, video_data.get('id'), video_data.get('title'),
109                     strip_or_none(video_data.get('description')))
110         else:
111             show_data = initial_data['show']
112
113             if not episode_path:
114                 entries = []
115                 for video in show_data.get('videos', []):
116                     slug = video.get('slug')
117                     if not slug:
118                         continue
119                     entries.append(self.url_result(
120                         'http://adultswim.com/videos/%s/%s' % (show_path, slug),
121                         'AdultSwim', video.get('id')))
122                 return self.playlist_result(
123                     entries, show_data.get('id'), show_data.get('title'),
124                     strip_or_none(show_data.get('metadata', {}).get('description')))
125
126             video_data = show_data['sluggedVideo']
127             video_id = video_data['id']
128
129         info = self._extract_cvp_info(
130             'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id,
131             video_id, {
132                 'secure': {
133                     'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
134                     'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
135                 },
136             }, {
137                 'url': url,
138                 'site_name': 'AdultSwim',
139                 'auth_required': video_data.get('auth'),
140             })
141
142         info.update({
143             'id': video_id,
144             'display_id': display_id,
145             'description': info.get('description') or strip_or_none(video_data.get('description')),
146         })
147         if not is_stream:
148             info.update({
149                 'duration': info.get('duration') or int_or_none(video_data.get('duration')),
150                 'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
151                 'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
152                 'episode': info['title'],
153                 'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
154             })
155
156             info['series'] = video_data.get('collection_title') or info.get('series')
157             if info['series'] and info['series'] != info['title']:
158                 info['title'] = '%s - %s' % (info['series'], info['title'])
159
160         return info