]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/go.py
4c9be47b4faa0e67baa305d22aadbf43387650bc
[youtubedl] / youtube_dl / extractor / go.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .adobepass import AdobePassIE
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(AdobePassIE):
17 _SITE_INFO = {
18 'abc': {
19 'brand': '001',
20 'requestor_id': 'ABC',
21 },
22 'freeform': {
23 'brand': '002',
24 'requestor_id': 'ABCFamily',
25 },
26 'watchdisneychannel': {
27 'brand': '004',
28 'requestor_id': 'Disney',
29 },
30 'watchdisneyjunior': {
31 'brand': '008',
32 'requestor_id': 'DisneyJunior',
33 },
34 'watchdisneyxd': {
35 'brand': '009',
36 'requestor_id': 'DisneyXD',
37 }
38 }
39 _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
40 _TESTS = [{
41 'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
42 'info_dict': {
43 'id': '0_g86w5onx',
44 'ext': 'mp4',
45 'title': 'Sneak Peek: Language Arts',
46 'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
47 },
48 'params': {
49 # m3u8 download
50 'skip_download': True,
51 },
52 }, {
53 'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
54 'only_matching': True,
55 }, {
56 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
57 'only_matching': True,
58 }, {
59 'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
60 'only_matching': True,
61 }]
62
63 def _real_extract(self, url):
64 sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
65 if not video_id:
66 webpage = self._download_webpage(url, display_id)
67 video_id = self._search_regex(
68 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
69 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
70 r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id')
71 site_info = self._SITE_INFO[sub_domain]
72 brand = site_info['brand']
73 video_data = self._download_json(
74 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
75 video_id)['video'][0]
76 title = video_data['title']
77
78 formats = []
79 for asset in video_data.get('assets', {}).get('asset', []):
80 asset_url = asset.get('value')
81 if not asset_url:
82 continue
83 format_id = asset.get('format')
84 ext = determine_ext(asset_url)
85 if ext == 'm3u8':
86 video_type = video_data.get('type')
87 data = {
88 'video_id': video_data['id'],
89 'video_type': video_type,
90 'brand': brand,
91 'device': '001',
92 }
93 if video_data.get('accesslevel') == '1':
94 requestor_id = site_info['requestor_id']
95 resource = self._get_mvpd_resource(
96 requestor_id, title, video_id, None)
97 auth = self._extract_mvpd_auth(
98 url, video_id, requestor_id, resource)
99 data.update({
100 'token': auth,
101 'token_type': 'ap',
102 'adobe_requestor_id': requestor_id,
103 })
104 else:
105 self._initialize_geo_bypass(['US'])
106 entitlement = self._download_json(
107 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
108 video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
109 errors = entitlement.get('errors', {}).get('errors', [])
110 if errors:
111 for error in errors:
112 if error.get('code') == 1002:
113 self.raise_geo_restricted(
114 error['message'], countries=['US'])
115 error_message = ', '.join([error['message'] for error in errors])
116 raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
117 asset_url += '?' + entitlement['uplynkData']['sessionKey']
118 formats.extend(self._extract_m3u8_formats(
119 asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
120 else:
121 f = {
122 'format_id': format_id,
123 'url': asset_url,
124 'ext': ext,
125 }
126 if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
127 f.update({
128 'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
129 'preference': 1,
130 })
131 else:
132 mobj = re.search(r'/(\d+)x(\d+)/', asset_url)
133 if mobj:
134 height = int(mobj.group(2))
135 f.update({
136 'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height,
137 'width': int(mobj.group(1)),
138 'height': height,
139 })
140 formats.append(f)
141 self._sort_formats(formats)
142
143 subtitles = {}
144 for cc in video_data.get('closedcaption', {}).get('src', []):
145 cc_url = cc.get('value')
146 if not cc_url:
147 continue
148 ext = determine_ext(cc_url)
149 if ext == 'xml':
150 ext = 'ttml'
151 subtitles.setdefault(cc.get('lang'), []).append({
152 'url': cc_url,
153 'ext': ext,
154 })
155
156 thumbnails = []
157 for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
158 thumbnail_url = thumbnail.get('value')
159 if not thumbnail_url:
160 continue
161 thumbnails.append({
162 'url': thumbnail_url,
163 'width': int_or_none(thumbnail.get('width')),
164 'height': int_or_none(thumbnail.get('height')),
165 })
166
167 return {
168 'id': video_id,
169 'title': title,
170 'description': video_data.get('longdescription') or video_data.get('description'),
171 'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
172 'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
173 'episode_number': int_or_none(video_data.get('episodenumber')),
174 'series': video_data.get('show', {}).get('title'),
175 'season_number': int_or_none(video_data.get('season', {}).get('num')),
176 'thumbnails': thumbnails,
177 'formats': formats,
178 'subtitles': subtitles,
179 }