From 326ae4ff96ca5663cca273126f95bd7eecf5a012 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 29 Sep 2019 23:03:39 +0700 Subject: [PATCH] [viewlift] Improve extraction (closes #22545) --- youtube_dl/extractor/viewlift.py | 46 +++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py index c43d1a1e83..391419d9ef 100644 --- a/youtube_dl/extractor/viewlift.py +++ b/youtube_dl/extractor/viewlift.py @@ -13,11 +13,12 @@ js_to_json, parse_age_limit, parse_duration, + try_get, ) 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): @@ -113,7 +114,7 @@ def _real_extract(self, url): class ViewLiftIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P%s)/(?:films/title|show|(?:news/)?videos?)/(?P[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX + _VALID_URL = r'https?://(?:www\.)?(?P%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'md5': '19844f897b35af219773fd63bdec2942', @@ -128,7 +129,7 @@ class ViewLiftIE(ViewLiftBaseIE): 'categories': 'mincount:3', 'age_limit': 14, 'upload_date': '20150421', - 'timestamp': 1429656819, + 'timestamp': 1429656820, } }, { 'url': 'http://www.snagfilms.com/show/the_world_cut_project/india', @@ -141,10 +142,26 @@ class ViewLiftIE(ViewLiftBaseIE): 'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 979, - 'categories': 'mincount:2', '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': '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. 'url': 'http://www.snagfilms.com/films/title/inside_mecca', @@ -181,7 +198,21 @@ def _real_extract(self, url): gist = content_data['gist'] film_id = gist['id'] 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 = [] mpeg_video_assets = video_assets.get('mpeg') or [] @@ -241,8 +272,9 @@ def _real_extract(self, url): if category.get('title')] break else: - title = self._search_regex( - r'itemprop="title">([^<]+)<', webpage, 'title') + title = self._html_search_regex( + (r'itemprop="title">([^<]+)<', + r'(?s)itemprop="title">(.+?)(.+?)', webpage, 'description', default=None) or self._og_search_description(webpage)