[youtube] fix hd720 format position
[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 )
11
12
13 class AdultSwimIE(TurnerBaseIE):
14     _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
15
16     _TESTS = [{
17         'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
18         'info_dict': {
19             'id': 'rQxZvXQ4ROaSOqq-or2Mow',
20             'ext': 'mp4',
21             'title': 'Rick and Morty - Pilot',
22             'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
23             'timestamp': 1493267400,
24             'upload_date': '20170427',
25         },
26         'params': {
27             # m3u8 download
28             'skip_download': True,
29         },
30         'expected_warnings': ['Unable to download f4m manifest'],
31     }, {
32         'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
33         'info_dict': {
34             'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
35             'ext': 'mp4',
36             'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
37             '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.',
38             'upload_date': '20080124',
39             'timestamp': 1201150800,
40         },
41         'params': {
42             # m3u8 download
43             'skip_download': True,
44         },
45     }, {
46         'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
47         'info_dict': {
48             'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
49             'ext': 'mp4',
50             'title': 'Decker - Inside Decker: A New Hero',
51             '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.',
52             'timestamp': 1469480460,
53             'upload_date': '20160725',
54         },
55         'params': {
56             # m3u8 download
57             'skip_download': True,
58         },
59         'expected_warnings': ['Unable to download f4m manifest'],
60     }, {
61         'url': 'http://www.adultswim.com/videos/attack-on-titan',
62         'info_dict': {
63             'id': 'b7A69dzfRzuaXIECdxW8XQ',
64             'title': 'Attack on Titan',
65             'description': 'md5:6c8e003ea0777b47013e894767f5e114',
66         },
67         'playlist_mincount': 12,
68     }, {
69         'url': 'http://www.adultswim.com/videos/streams/williams-stream',
70         'info_dict': {
71             'id': 'd8DEBj7QRfetLsRgFnGEyg',
72             'ext': 'mp4',
73             'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
74             'description': 'original programming',
75         },
76         'params': {
77             # m3u8 download
78             'skip_download': True,
79         },
80     }]
81
82     def _real_extract(self, url):
83         show_path, episode_path = re.match(self._VALID_URL, url).groups()
84         display_id = episode_path or show_path
85         webpage = self._download_webpage(url, display_id)
86         initial_data = self._parse_json(self._search_regex(
87             r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
88             webpage, 'initial data'), display_id)
89
90         is_stream = show_path == 'streams'
91         if is_stream:
92             if not episode_path:
93                 episode_path = 'live-stream'
94
95             video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
96             video_id = video_data.get('stream')
97
98             if not video_id:
99                 entries = []
100                 for episode in video_data.get('archiveEpisodes', []):
101                     episode_url = episode.get('url')
102                     if not episode_url:
103                         continue
104                     entries.append(self.url_result(
105                         episode_url, 'AdultSwim', episode.get('id')))
106                 return self.playlist_result(
107                     entries, video_data.get('id'), video_data.get('title'),
108                     strip_or_none(video_data.get('description')))
109         else:
110             show_data = initial_data['show']
111
112             if not episode_path:
113                 entries = []
114                 for video in show_data.get('videos', []):
115                     slug = video.get('slug')
116                     if not slug:
117                         continue
118                     entries.append(self.url_result(
119                         'http://adultswim.com/videos/%s/%s' % (show_path, slug),
120                         'AdultSwim', video.get('id')))
121                 return self.playlist_result(
122                     entries, show_data.get('id'), show_data.get('title'),
123                     strip_or_none(show_data.get('metadata', {}).get('description')))
124
125             video_data = show_data['sluggedVideo']
126             video_id = video_data['id']
127
128         info = self._extract_cvp_info(
129             'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id,
130             video_id, {
131                 'secure': {
132                     'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
133                     'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
134                 },
135             }, {
136                 'url': url,
137                 'site_name': 'AdultSwim',
138                 'auth_required': video_data.get('auth'),
139             })
140
141         info.update({
142             'id': video_id,
143             'display_id': display_id,
144             'description': info.get('description') or strip_or_none(video_data.get('description')),
145         })
146         if not is_stream:
147             info.update({
148                 'duration': info.get('duration') or int_or_none(video_data.get('duration')),
149                 'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
150                 'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
151                 'episode': info['title'],
152                 'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
153             })
154
155             info['series'] = video_data.get('collection_title') or info.get('series')
156             if info['series'] and info['series'] != info['title']:
157                 info['title'] = '%s - %s' % (info['series'], info['title'])
158
159         return info