1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
|
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_age_limit,
traverse_obj,
)
class ViewLiftBaseIE(InfoExtractor):
_API_BASE = 'https://prod-api.viewlift.com/'
_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'
_SITE_MAP = {
'ftfnext': 'lax',
'funnyforfree': 'snagfilms',
'hoichoi': 'hoichoitv',
'kiddovid': 'snagfilms',
'laxsportsnetwork': 'lax',
'legapallacanestro': 'lnp',
'marquee': 'marquee-tv',
'monumentalsportsnetwork': 'monumental-network',
'moviespree': 'bingeflix',
'pflmma': 'pfl',
'snagxtreme': 'snagfilms',
'theidentitytb': 'tampabay',
'vayafilm': 'snagfilms',
}
_TOKENS = {}
def _fetch_token(self, site, url):
if self._TOKENS.get(site):
return
cookies = self._get_cookies(url)
if cookies and cookies.get('token'):
self._TOKENS[site] = self._search_regex(r'22authorizationToken\%22:\%22([^\%]+)\%22', cookies['token'].value, 'token')
if not self._TOKENS.get(site):
self.raise_login_required('Cookies (not necessarily logged in) are needed to download from this website', method='cookies')
def _call_api(self, site, path, video_id, url, query):
self._fetch_token(site, url)
try:
return self._download_json(
self._API_BASE + path, video_id, headers={'Authorization': self._TOKENS.get(site)}, query=query)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
webpage = e.cause.read().decode()
try:
error_message = traverse_obj(json.loads(webpage), 'errorMessage', 'message')
except json.JSONDecodeError:
raise ExtractorError(f'{site} said: {webpage}', cause=e.cause)
if error_message:
if 'has not purchased' in error_message:
self.raise_login_required(method='cookies')
raise ExtractorError(error_message, expected=True)
raise
class ViewLiftEmbedIE(ViewLiftBaseIE):
IE_NAME = 'viewlift:embed'
_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
_TESTS = [{
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
'md5': '2924e9215c6eff7a55ed35b72276bd93',
'info_dict': {
'id': '74849a00-85a9-11e1-9660-123139220831',
'ext': 'mp4',
'title': '#whilewewatch',
'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
'timestamp': 1334350096,
'upload_date': '20120413',
}
}, {
# invalid labels, 360p is better that 480p
'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
'md5': '882fca19b9eb27ef865efeeaed376a48',
'info_dict': {
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
'ext': 'mp4',
'title': 'Life in Limbo',
},
'skip': 'The video does not exist',
}, {
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
domain, film_id = self._match_valid_url(url).groups()
site = domain.split('.')[-2]
if site in self._SITE_MAP:
site = self._SITE_MAP[site]
content_data = self._call_api(
site, 'entitlement/video/status', film_id, url, {
'id': film_id
})['video']
gist = content_data['gist']
title = gist['title']
video_assets = content_data['streamingInfo']['videoAssets']
hls_url = video_assets.get('hls')
formats, subtitles = [], {}
if hls_url:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
for video_asset in video_assets.get('mpeg') or []:
video_asset_url = video_asset.get('url')
if not video_asset_url:
continue
bitrate = int_or_none(video_asset.get('bitrate'))
height = int_or_none(self._search_regex(
r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
'height', default=None))
formats.append({
'url': video_asset_url,
'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
'tbr': bitrate,
'height': height,
'vcodec': video_asset.get('codec'),
})
subs = {}
for sub in traverse_obj(content_data, ('contentDetails', 'closedCaptions')) or []:
sub_url = sub.get('url')
if not sub_url:
continue
subs.setdefault(sub.get('language', 'English'), []).append({
'url': sub_url,
})
self._sort_formats(formats)
return {
'id': film_id,
'title': title,
'description': gist.get('description'),
'thumbnail': gist.get('videoImageUrl'),
'duration': int_or_none(gist.get('runtime')),
'age_limit': parse_age_limit(content_data.get('parentalRating')),
'timestamp': int_or_none(gist.get('publishDate'), 1000),
'formats': formats,
'subtitles': self._merge_subtitles(subs, subtitles),
'categories': traverse_obj(content_data, ('categories', ..., 'title')),
'tags': traverse_obj(content_data, ('tags', ..., 'title')),
}
class ViewLiftIE(ViewLiftBaseIE):
IE_NAME = 'viewlift'
_API_BASE = 'https://prod-api-cached-2.viewlift.com/'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
'md5': '19844f897b35af219773fd63bdec2942',
'info_dict': {
'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
'display_id': 'lost_for_life',
'ext': 'mp4',
'title': 'Lost for Life',
'description': 'md5:ea10b5a50405ae1f7b5269a6ec594102',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 4489,
'categories': 'mincount:3',
'age_limit': 14,
'upload_date': '20150421',
'timestamp': 1429656820,
}
}, {
'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
'info_dict': {
'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
'display_id': 'the_world_cut_project/india',
'ext': 'mp4',
'title': 'India',
'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 979,
'timestamp': 1399478279,
'upload_date': '20140507',
}
}, {
'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love',
'info_dict': {
'id': '00000148-7b53-de26-a9fb-fbf306f70020',
'display_id': 'augie_alone/s_2_ep_12_love',
'ext': 'mp4',
'title': 'S. 2 Ep. 12 - Love',
'description': 'Augie finds love.',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 107,
'upload_date': '20141012',
'timestamp': 1413129540,
'age_limit': 17,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://main.snagfilms.com/films/title/the_freebie',
'only_matching': True,
}, {
# Film is not playable in your area.
'url': 'http://www.snagfilms.com/films/title/inside_mecca',
'only_matching': True,
}, {
# Film is not available.
'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
'only_matching': True,
}, {
'url': 'http://www.winnersview.com/videos/the-good-son',
'only_matching': True,
}, {
# Was once Kaltura embed
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
'only_matching': True,
}, {
'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
'only_matching': True,
}, { # Free film with langauge code
'url': 'https://www.hoichoi.tv/bn/films/title/shuyopoka',
'info_dict': {
'id': '7a7a9d33-1f4c-4771-9173-ee4fb6dbf196',
'ext': 'mp4',
'title': 'Shuyopoka',
'description': 'md5:e28f2fb8680096a69c944d37c1fa5ffc',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20211006',
'series': None
},
'params': {'skip_download': True},
}, { # Free film
'url': 'https://www.hoichoi.tv/films/title/dadu-no1',
'info_dict': {
'id': '0000015b-b009-d126-a1db-b81ff3780000',
'ext': 'mp4',
'title': 'Dadu No.1',
'description': 'md5:605cba408e51a79dafcb824bdeded51e',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20210827',
'series': None
},
'params': {'skip_download': True},
}, { # Free episode
'url': 'https://www.hoichoi.tv/webseries/case-jaundice-s01-e01',
'info_dict': {
'id': 'f779e07c-30c8-459c-8612-5a834ab5e5ba',
'ext': 'mp4',
'title': 'Humans Vs. Corona',
'description': 'md5:ca30a682b4528d02a3eb6d0427dd0f87',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20210830',
'series': 'Case Jaundice'
},
'params': {'skip_download': True},
}, { # Free video
'url': 'https://www.hoichoi.tv/videos/1549072415320-six-episode-02-hindi',
'info_dict': {
'id': 'b41fa1ce-aca6-47b6-b208-283ff0a2de30',
'ext': 'mp4',
'title': 'Woman in red - Hindi',
'description': 'md5:9d21edc1827d32f8633eb67c2054fc31',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20211006',
'series': 'Six (Hindi)'
},
'params': {'skip_download': True},
}, { # Free episode
'url': 'https://www.hoichoi.tv/shows/watch-asian-paints-moner-thikana-online-season-1-episode-1',
'info_dict': {
'id': '1f45d185-8500-455c-b88d-13252307c3eb',
'ext': 'mp4',
'title': 'Jisshu Sengupta',
'description': 'md5:ef6ffae01a3d83438597367400f824ed',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20211004',
'series': 'Asian Paints Moner Thikana'
},
'params': {'skip_download': True},
}, { # Free series
'url': 'https://www.hoichoi.tv/shows/watch-moner-thikana-bengali-web-series-online',
'playlist_mincount': 5,
'info_dict': {
'id': 'watch-moner-thikana-bengali-web-series-online',
},
}, { # Premium series
'url': 'https://www.hoichoi.tv/shows/watch-byomkesh-bengali-web-series-online',
'playlist_mincount': 14,
'info_dict': {
'id': 'watch-byomkesh-bengali-web-series-online',
},
}, { # Premium movie
'url': 'https://www.hoichoi.tv/movies/detective-2020',
'only_matching': True
}]
@classmethod
def suitable(cls, url):
return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
def _show_entries(self, domain, seasons):
for season in seasons:
for episode in season.get('episodes') or []:
path = traverse_obj(episode, ('gist', 'permalink'))
if path:
yield self.url_result(f'https://www.{domain}{path}', ie=self.ie_key())
def _real_extract(self, url):
domain, path, display_id = self._match_valid_url(url).groups()
site = domain.split('.')[-2]
if site in self._SITE_MAP:
site = self._SITE_MAP[site]
modules = self._call_api(
site, 'content/pages', display_id, url, {
'includeContent': 'true',
'moduleOffset': 1,
'path': path,
'site': site,
})['modules']
seasons = next((m['contentData'][0]['seasons'] for m in modules if m.get('moduleType') == 'ShowDetailModule'), None)
if seasons:
return self.playlist_result(self._show_entries(domain, seasons), display_id)
film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
return {
'_type': 'url_transparent',
'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
'id': film_id,
'display_id': display_id,
'ie_key': 'ViewLiftEmbed',
}
|
