]>
Commit | Line | Data |
---|---|---|
2c3e0af9 RA |
1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
4 | import re | |
5 | ||
ae8d5a5c | 6 | from .adobepass import AdobePassIE |
2c3e0af9 RA |
7 | from ..utils import ( |
8 | int_or_none, | |
9 | determine_ext, | |
10 | parse_age_limit, | |
014b7e6b RA |
11 | urlencode_postdata, |
12 | ExtractorError, | |
2c3e0af9 RA |
13 | ) |
14 | ||
15 | ||
ae8d5a5c RA |
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 | } | |
2c3e0af9 | 38 | } |
ae8d5a5c | 39 | _VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys()) |
2c3e0af9 RA |
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 | ||
57 | def _real_extract(self, url): | |
014b7e6b RA |
58 | sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups() |
59 | if not video_id: | |
60 | webpage = self._download_webpage(url, display_id) | |
c54c01f8 S |
61 | video_id = self._search_regex( |
62 | # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" | |
63 | # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood | |
64 | r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id') | |
ae8d5a5c RA |
65 | site_info = self._SITE_INFO[sub_domain] |
66 | brand = site_info['brand'] | |
2c3e0af9 | 67 | video_data = self._download_json( |
014b7e6b | 68 | 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id), |
2c3e0af9 RA |
69 | video_id)['video'][0] |
70 | title = video_data['title'] | |
71 | ||
72 | formats = [] | |
73 | for asset in video_data.get('assets', {}).get('asset', []): | |
74 | asset_url = asset.get('value') | |
75 | if not asset_url: | |
76 | continue | |
77 | format_id = asset.get('format') | |
78 | ext = determine_ext(asset_url) | |
79 | if ext == 'm3u8': | |
014b7e6b RA |
80 | video_type = video_data.get('type') |
81 | if video_type == 'lf': | |
ae8d5a5c RA |
82 | data = { |
83 | 'video_id': video_data['id'], | |
84 | 'video_type': video_type, | |
85 | 'brand': brand, | |
86 | 'device': '001', | |
87 | } | |
88 | if video_data.get('accesslevel') == '1': | |
89 | requestor_id = site_info['requestor_id'] | |
90 | resource = self._get_mvpd_resource( | |
91 | requestor_id, title, video_id, None) | |
92 | auth = self._extract_mvpd_auth( | |
93 | url, video_id, requestor_id, resource) | |
94 | data.update({ | |
95 | 'token': auth, | |
96 | 'token_type': 'ap', | |
97 | 'adobe_requestor_id': requestor_id, | |
98 | }) | |
014b7e6b RA |
99 | entitlement = self._download_json( |
100 | 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json', | |
ae8d5a5c | 101 | video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers()) |
014b7e6b RA |
102 | errors = entitlement.get('errors', {}).get('errors', []) |
103 | if errors: | |
353f340e RA |
104 | error_message = ', '.join([error['message'] for error in errors]) |
105 | raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) | |
014b7e6b | 106 | asset_url += '?' + entitlement['uplynkData']['sessionKey'] |
2c3e0af9 RA |
107 | formats.extend(self._extract_m3u8_formats( |
108 | asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)) | |
109 | else: | |
110 | formats.append({ | |
111 | 'format_id': format_id, | |
112 | 'url': asset_url, | |
113 | 'ext': ext, | |
114 | }) | |
115 | self._sort_formats(formats) | |
116 | ||
117 | subtitles = {} | |
118 | for cc in video_data.get('closedcaption', {}).get('src', []): | |
119 | cc_url = cc.get('value') | |
120 | if not cc_url: | |
121 | continue | |
122 | ext = determine_ext(cc_url) | |
123 | if ext == 'xml': | |
124 | ext = 'ttml' | |
125 | subtitles.setdefault(cc.get('lang'), []).append({ | |
126 | 'url': cc_url, | |
127 | 'ext': ext, | |
128 | }) | |
129 | ||
130 | thumbnails = [] | |
131 | for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []): | |
132 | thumbnail_url = thumbnail.get('value') | |
133 | if not thumbnail_url: | |
134 | continue | |
135 | thumbnails.append({ | |
136 | 'url': thumbnail_url, | |
137 | 'width': int_or_none(thumbnail.get('width')), | |
138 | 'height': int_or_none(thumbnail.get('height')), | |
139 | }) | |
140 | ||
141 | return { | |
142 | 'id': video_id, | |
143 | 'title': title, | |
144 | 'description': video_data.get('longdescription') or video_data.get('description'), | |
145 | 'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000), | |
146 | 'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')), | |
147 | 'episode_number': int_or_none(video_data.get('episodenumber')), | |
148 | 'series': video_data.get('show', {}).get('title'), | |
149 | 'season_number': int_or_none(video_data.get('season', {}).get('num')), | |
150 | 'thumbnails': thumbnails, | |
151 | 'formats': formats, | |
152 | 'subtitles': subtitles, | |
153 | } |