[viewlift] Improve extraction (closes #22545)

This commit is contained in:
Sergey M․ 2019-09-29 23:03:39 +07:00
parent 72fd4d0c6a
commit 326ae4ff96
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 39 additions and 7 deletions

View File

@ -13,11 +13,12 @@ from ..utils import (
js_to_json, js_to_json,
parse_age_limit, parse_age_limit,
parse_duration, parse_duration,
try_get,
) )
class ViewLiftBaseIE(InfoExtractor): class ViewLiftBaseIE(InfoExtractor):
_DOMAINS_REGEX = r'(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv'
class ViewLiftEmbedIE(ViewLiftBaseIE): class ViewLiftEmbedIE(ViewLiftBaseIE):
@ -113,7 +114,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
class ViewLiftIE(ViewLiftBaseIE): class ViewLiftIE(ViewLiftBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)/(?:films/title|show|(?:news/)?videos?)/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
_TESTS = [{ _TESTS = [{
'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'url': 'http://www.snagfilms.com/films/title/lost_for_life',
'md5': '19844f897b35af219773fd63bdec2942', 'md5': '19844f897b35af219773fd63bdec2942',
@ -128,7 +129,7 @@ class ViewLiftIE(ViewLiftBaseIE):
'categories': 'mincount:3', 'categories': 'mincount:3',
'age_limit': 14, 'age_limit': 14,
'upload_date': '20150421', 'upload_date': '20150421',
'timestamp': 1429656819, 'timestamp': 1429656820,
} }
}, { }, {
'url': 'http://www.snagfilms.com/show/the_world_cut_project/india', 'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
@ -141,10 +142,26 @@ class ViewLiftIE(ViewLiftBaseIE):
'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f', 'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
'thumbnail': r're:^https?://.*\.jpg', 'thumbnail': r're:^https?://.*\.jpg',
'duration': 979, 'duration': 979,
'categories': 'mincount:2',
'timestamp': 1399478279, 'timestamp': 1399478279,
'upload_date': '20140507', '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': 'Augie, Alone:S. 2 Ep. 12 - Love',
'description': 'md5:db2a5c72d994f16a780c1eb353a8f403',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 107,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://main.snagfilms.com/films/title/the_freebie',
'only_matching': True,
}, { }, {
# Film is not playable in your area. # Film is not playable in your area.
'url': 'http://www.snagfilms.com/films/title/inside_mecca', 'url': 'http://www.snagfilms.com/films/title/inside_mecca',
@ -181,7 +198,21 @@ class ViewLiftIE(ViewLiftBaseIE):
gist = content_data['gist'] gist = content_data['gist']
film_id = gist['id'] film_id = gist['id']
title = gist['title'] title = gist['title']
video_assets = content_data['streamingInfo']['videoAssets'] video_assets = try_get(
content_data, lambda x: x['streamingInfo']['videoAssets'], dict)
if not video_assets:
token = self._download_json(
'https://prod-api.viewlift.com/identity/anonymous-token',
film_id, 'Downloading authorization token',
query={'site': 'snagfilms'})['authorizationToken']
video_assets = self._download_json(
'https://prod-api.viewlift.com/entitlement/video/status',
film_id, headers={
'Authorization': token,
'Referer': url,
}, query={
'id': film_id
})['video']['streamingInfo']['videoAssets']
formats = [] formats = []
mpeg_video_assets = video_assets.get('mpeg') or [] mpeg_video_assets = video_assets.get('mpeg') or []
@ -241,8 +272,9 @@ class ViewLiftIE(ViewLiftBaseIE):
if category.get('title')] if category.get('title')]
break break
else: else:
title = self._search_regex( title = self._html_search_regex(
r'itemprop="title">([^<]+)<', webpage, 'title') (r'itemprop="title">([^<]+)<',
r'(?s)itemprop="title">(.+?)<div'), webpage, 'title')
description = self._html_search_regex( description = self._html_search_regex(
r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>', r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
webpage, 'description', default=None) or self._og_search_description(webpage) webpage, 'description', default=None) or self._og_search_description(webpage)