]> asedeno.scripts.mit.edu Git - youtube-dl.git/blob - youtube_dl/extractor/sevenplus.py
[eroprofile] Skip test
[youtube-dl.git] / youtube_dl / extractor / sevenplus.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .brightcove import BrightcoveNewIE
7 from ..compat import (
8     compat_HTTPError,
9     compat_str,
10 )
11 from ..utils import (
12     ExtractorError,
13     try_get,
14     update_url_query,
15 )
16
17
18 class SevenPlusIE(BrightcoveNewIE):
19     IE_NAME = '7plus'
20     _VALID_URL = r'https?://(?:www\.)?7plus\.com\.au/(?P<path>[^?]+\?.*?\bepisode-id=(?P<id>[^&#]+))'
21     _TESTS = [{
22         'url': 'https://7plus.com.au/MTYS?episode-id=MTYS7-003',
23         'info_dict': {
24             'id': 'MTYS7-003',
25             'ext': 'mp4',
26             'title': 'S7 E3 - Wind Surf',
27             'description': 'md5:29c6a69f21accda7601278f81b46483d',
28             'uploader_id': '5303576322001',
29             'upload_date': '20171201',
30             'timestamp': 1512106377,
31             'series': 'Mighty Ships',
32             'season_number': 7,
33             'episode_number': 3,
34             'episode': 'Wind Surf',
35         },
36         'params': {
37             'format': 'bestvideo',
38             'skip_download': True,
39         }
40     }, {
41         'url': 'https://7plus.com.au/UUUU?episode-id=AUMS43-001',
42         'only_matching': True,
43     }]
44
45     def _real_extract(self, url):
46         path, episode_id = re.match(self._VALID_URL, url).groups()
47
48         try:
49             media = self._download_json(
50                 'https://videoservice.swm.digital/playback', episode_id, query={
51                     'appId': '7plus',
52                     'deviceType': 'web',
53                     'platformType': 'web',
54                     'accountId': 5303576322001,
55                     'referenceId': 'ref:' + episode_id,
56                     'deliveryId': 'csai',
57                     'videoType': 'vod',
58                 })['media']
59         except ExtractorError as e:
60             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
61                 raise ExtractorError(self._parse_json(
62                     e.cause.read().decode(), episode_id)[0]['error_code'], expected=True)
63             raise
64
65         for source in media.get('sources', {}):
66             src = source.get('src')
67             if not src:
68                 continue
69             source['src'] = update_url_query(src, {'rule': ''})
70
71         info = self._parse_brightcove_metadata(media, episode_id)
72
73         content = self._download_json(
74             'https://component-cdn.swm.digital/content/' + path,
75             episode_id, headers={
76                 'market-id': 4,
77             }, fatal=False) or {}
78         for item in content.get('items', {}):
79             if item.get('componentData', {}).get('componentType') == 'infoPanel':
80                 for src_key, dst_key in [('title', 'title'), ('shortSynopsis', 'description')]:
81                     value = item.get(src_key)
82                     if value:
83                         info[dst_key] = value
84                 info['series'] = try_get(
85                     item, lambda x: x['seriesLogo']['name'], compat_str)
86                 mobj = re.search(r'^S(\d+)\s+E(\d+)\s+-\s+(.+)$', info['title'])
87                 if mobj:
88                     info.update({
89                         'season_number': int(mobj.group(1)),
90                         'episode_number': int(mobj.group(2)),
91                         'episode': mobj.group(3),
92                     })
93
94         return info