]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/viewlift.py
[nrktv:episode] Improve video id extraction (closes #25594, closes #26369, closes...
[youtube-dl] / youtube_dl / extractor / viewlift.py
1 from __future__ import unicode_literals
2
3 import json
4 import re
5
6 from .common import InfoExtractor
7 from ..compat import compat_HTTPError
8 from ..utils import (
9     ExtractorError,
10     int_or_none,
11     parse_age_limit,
12 )
13
14
15 class ViewLiftBaseIE(InfoExtractor):
16     _API_BASE = 'https://prod-api.viewlift.com/'
17     _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
18     _SITE_MAP = {
19         'ftfnext': 'lax',
20         'funnyforfree': 'snagfilms',
21         'hoichoi': 'hoichoitv',
22         'kiddovid': 'snagfilms',
23         'laxsportsnetwork': 'lax',
24         'legapallacanestro': 'lnp',
25         'marquee': 'marquee-tv',
26         'monumentalsportsnetwork': 'monumental-network',
27         'moviespree': 'bingeflix',
28         'pflmma': 'pfl',
29         'snagxtreme': 'snagfilms',
30         'theidentitytb': 'tampabay',
31         'vayafilm': 'snagfilms',
32     }
33     _TOKENS = {}
34
35     def _call_api(self, site, path, video_id, query):
36         token = self._TOKENS.get(site)
37         if not token:
38             token_query = {'site': site}
39             email, password = self._get_login_info(netrc_machine=site)
40             if email:
41                 resp = self._download_json(
42                     self._API_BASE + 'identity/signin', video_id,
43                     'Logging in', query=token_query, data=json.dumps({
44                         'email': email,
45                         'password': password,
46                     }).encode())
47             else:
48                 resp = self._download_json(
49                     self._API_BASE + 'identity/anonymous-token', video_id,
50                     'Downloading authorization token', query=token_query)
51             self._TOKENS[site] = token = resp['authorizationToken']
52         return self._download_json(
53             self._API_BASE + path, video_id,
54             headers={'Authorization': token}, query=query)
55
56
57 class ViewLiftEmbedIE(ViewLiftBaseIE):
58     IE_NAME = 'viewlift:embed'
59     _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
60     _TESTS = [{
61         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
62         'md5': '2924e9215c6eff7a55ed35b72276bd93',
63         'info_dict': {
64             'id': '74849a00-85a9-11e1-9660-123139220831',
65             'ext': 'mp4',
66             'title': '#whilewewatch',
67             'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
68             'timestamp': 1334350096,
69             'upload_date': '20120413',
70         }
71     }, {
72         # invalid labels, 360p is better that 480p
73         'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
74         'md5': '882fca19b9eb27ef865efeeaed376a48',
75         'info_dict': {
76             'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
77             'ext': 'mp4',
78             'title': 'Life in Limbo',
79         },
80         'skip': 'The video does not exist',
81     }, {
82         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
83         'only_matching': True,
84     }]
85
86     @staticmethod
87     def _extract_url(webpage):
88         mobj = re.search(
89             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
90             webpage)
91         if mobj:
92             return mobj.group('url')
93
94     def _real_extract(self, url):
95         domain, film_id = re.match(self._VALID_URL, url).groups()
96         site = domain.split('.')[-2]
97         if site in self._SITE_MAP:
98             site = self._SITE_MAP[site]
99         try:
100             content_data = self._call_api(
101                 site, 'entitlement/video/status', film_id, {
102                     'id': film_id
103                 })['video']
104         except ExtractorError as e:
105             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
106                 error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage')
107                 if error_message == 'User does not have a valid subscription or has not purchased this content.':
108                     self.raise_login_required()
109                 raise ExtractorError(error_message, expected=True)
110             raise
111         gist = content_data['gist']
112         title = gist['title']
113         video_assets = content_data['streamingInfo']['videoAssets']
114
115         formats = []
116         mpeg_video_assets = video_assets.get('mpeg') or []
117         for video_asset in mpeg_video_assets:
118             video_asset_url = video_asset.get('url')
119             if not video_asset:
120                 continue
121             bitrate = int_or_none(video_asset.get('bitrate'))
122             height = int_or_none(self._search_regex(
123                 r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
124                 'height', default=None))
125             formats.append({
126                 'url': video_asset_url,
127                 'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
128                 'tbr': bitrate,
129                 'height': height,
130                 'vcodec': video_asset.get('codec'),
131             })
132
133         hls_url = video_assets.get('hls')
134         if hls_url:
135             formats.extend(self._extract_m3u8_formats(
136                 hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
137         self._sort_formats(formats, ('height', 'tbr', 'format_id'))
138
139         info = {
140             'id': film_id,
141             'title': title,
142             'description': gist.get('description'),
143             'thumbnail': gist.get('videoImageUrl'),
144             'duration': int_or_none(gist.get('runtime')),
145             'age_limit': parse_age_limit(content_data.get('parentalRating')),
146             'timestamp': int_or_none(gist.get('publishDate'), 1000),
147             'formats': formats,
148         }
149         for k in ('categories', 'tags'):
150             info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
151         return info
152
153
154 class ViewLiftIE(ViewLiftBaseIE):
155     IE_NAME = 'viewlift'
156     _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
157     _TESTS = [{
158         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
159         'md5': '19844f897b35af219773fd63bdec2942',
160         'info_dict': {
161             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
162             'display_id': 'lost_for_life',
163             'ext': 'mp4',
164             'title': 'Lost for Life',
165             'description': 'md5:ea10b5a50405ae1f7b5269a6ec594102',
166             'thumbnail': r're:^https?://.*\.jpg',
167             'duration': 4489,
168             'categories': 'mincount:3',
169             'age_limit': 14,
170             'upload_date': '20150421',
171             'timestamp': 1429656820,
172         }
173     }, {
174         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
175         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
176         'info_dict': {
177             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
178             'display_id': 'the_world_cut_project/india',
179             'ext': 'mp4',
180             'title': 'India',
181             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
182             'thumbnail': r're:^https?://.*\.jpg',
183             'duration': 979,
184             'timestamp': 1399478279,
185             'upload_date': '20140507',
186         }
187     }, {
188         'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
189         'info_dict': {
190             'id': '00000148-7b53-de26-a9fb-fbf306f70020',
191             'display_id': 'augie_alone/s_2_ep_12_love',
192             'ext': 'mp4',
193             'title': 'S. 2 Ep. 12 - Love',
194             'description': 'Augie finds love.',
195             'thumbnail': r're:^https?://.*\.jpg',
196             'duration': 107,
197             'upload_date': '20141012',
198             'timestamp': 1413129540,
199             'age_limit': 17,
200         },
201         'params': {
202             'skip_download': True,
203         },
204     }, {
205         'url': 'http://main.snagfilms.com/films/title/the_freebie',
206         'only_matching': True,
207     }, {
208         # Film is not playable in your area.
209         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
210         'only_matching': True,
211     }, {
212         # Film is not available.
213         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
214         'only_matching': True,
215     }, {
216         'url': 'http://www.winnersview.com/videos/the-good-son',
217         'only_matching': True,
218     }, {
219         # Was once Kaltura embed
220         'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
221         'only_matching': True,
222     }, {
223         'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
224         'only_matching': True,
225     }]
226
227     @classmethod
228     def suitable(cls, url):
229         return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
230
231     def _real_extract(self, url):
232         domain, path, display_id = re.match(self._VALID_URL, url).groups()
233         site = domain.split('.')[-2]
234         if site in self._SITE_MAP:
235             site = self._SITE_MAP[site]
236         modules = self._call_api(
237             site, 'content/pages', display_id, {
238                 'includeContent': 'true',
239                 'moduleOffset': 1,
240                 'path': path,
241                 'site': site,
242             })['modules']
243         film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
244         return {
245             '_type': 'url_transparent',
246             'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
247             'id': film_id,
248             'display_id': display_id,
249             'ie_key': 'ViewLiftEmbed',
250         }