]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/go.py
c7776b1868e617cf78e37dd4c4b3bc742e89e8b7
[youtubedl] / youtube_dl / extractor / go.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 int_or_none,
9 determine_ext,
10 parse_age_limit,
11 urlencode_postdata,
12 ExtractorError,
13 )
14
15
16 class GoIE(InfoExtractor):
17 _BRANDS = {
18 'abc': '001',
19 'freeform': '002',
20 'watchdisneychannel': '004',
21 'watchdisneyjunior': '008',
22 'watchdisneyxd': '009',
23 }
24 _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_BRANDS.keys())
25 _TESTS = [{
26 'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
27 'info_dict': {
28 'id': '0_g86w5onx',
29 'ext': 'mp4',
30 'title': 'Sneak Peek: Language Arts',
31 'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
32 },
33 'params': {
34 # m3u8 download
35 'skip_download': True,
36 },
37 }, {
38 'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
39 'only_matching': True,
40 }]
41
42 def _real_extract(self, url):
43 sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
44 if not video_id:
45 webpage = self._download_webpage(url, display_id)
46 video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id')
47 brand = self._BRANDS[sub_domain]
48 video_data = self._download_json(
49 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
50 video_id)['video'][0]
51 title = video_data['title']
52
53 formats = []
54 for asset in video_data.get('assets', {}).get('asset', []):
55 asset_url = asset.get('value')
56 if not asset_url:
57 continue
58 format_id = asset.get('format')
59 ext = determine_ext(asset_url)
60 if ext == 'm3u8':
61 video_type = video_data.get('type')
62 if video_type == 'lf':
63 entitlement = self._download_json(
64 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
65 video_id, data=urlencode_postdata({
66 'video_id': video_data['id'],
67 'video_type': video_type,
68 'brand': brand,
69 'device': '001',
70 }))
71 errors = entitlement.get('errors', {}).get('errors', [])
72 if errors:
73 error_message = ', '.join([error['message'] for error in errors])
74 raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
75 asset_url += '?' + entitlement['uplynkData']['sessionKey']
76 formats.extend(self._extract_m3u8_formats(
77 asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
78 else:
79 formats.append({
80 'format_id': format_id,
81 'url': asset_url,
82 'ext': ext,
83 })
84 self._sort_formats(formats)
85
86 subtitles = {}
87 for cc in video_data.get('closedcaption', {}).get('src', []):
88 cc_url = cc.get('value')
89 if not cc_url:
90 continue
91 ext = determine_ext(cc_url)
92 if ext == 'xml':
93 ext = 'ttml'
94 subtitles.setdefault(cc.get('lang'), []).append({
95 'url': cc_url,
96 'ext': ext,
97 })
98
99 thumbnails = []
100 for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
101 thumbnail_url = thumbnail.get('value')
102 if not thumbnail_url:
103 continue
104 thumbnails.append({
105 'url': thumbnail_url,
106 'width': int_or_none(thumbnail.get('width')),
107 'height': int_or_none(thumbnail.get('height')),
108 })
109
110 return {
111 'id': video_id,
112 'title': title,
113 'description': video_data.get('longdescription') or video_data.get('description'),
114 'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
115 'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
116 'episode_number': int_or_none(video_data.get('episodenumber')),
117 'series': video_data.get('show', {}).get('title'),
118 'season_number': int_or_none(video_data.get('season', {}).get('num')),
119 'thumbnails': thumbnails,
120 'formats': formats,
121 'subtitles': subtitles,
122 }