From 650bd9471697390a9cdef2a54d35ec6dd5dc49ce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 17 May 2017 23:38:27 +0700 Subject: [PATCH] [vier] Relax regexes and extract more metadata (closes #12539) --- youtube_dl/extractor/vier.py | 39 ++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index 7fb718343..3e67eb8c2 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -27,6 +27,8 @@ class VierIE(InfoExtractor): 'title': 'Het wordt warm in De Moestuin', 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', 'upload_date': '20121025', + 'series': 'Plan B', + 'tags': ['De Moestuin', 'Moestuin', 'meisjes', 'Tomaat', 'Wim', 'Droom'], }, }, { 'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614', @@ -37,6 +39,8 @@ class VierIE(InfoExtractor): 'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7', 'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe', 'upload_date': '20170228', + 'series': 'Temptation Island', + 'tags': list, }, 'params': { 'skip_download': True, @@ -50,7 +54,9 @@ class VierIE(InfoExtractor): 'title': 'Jani gaat naar Tokio - Aflevering 4', 'description': 'md5:aa8d611541db6ae9e863125704511f88', 'upload_date': '20170501', + 'series': 'Jani gaat', 'episode_number': 4, + 'tags': ['Jani Gaat', 'Volledige Aflevering'], }, 'params': { 'skip_download': True, @@ -135,33 +141,36 @@ class VierIE(InfoExtractor): webpage, 'filename') playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename) - formats = self._extract_wowza_formats(playlist_url, display_id, skip_protocols=['dash']) + formats = self._extract_wowza_formats( + playlist_url, display_id, skip_protocols=['dash']) self._sort_formats(formats) title = self._og_search_title(webpage, default=display_id) - thumbnail = self._og_search_thumbnail(webpage, default=None) description = self._html_search_regex( - r'''(?x)\s* - (?:\s*)* -

\s*(?:)?(.+?)]+\bclass=(["\'])[^>]*?\bfield-type-text-with-summary\b[^>]*?\1[^>]*>.*?

(?P.+?)

', + webpage, 'description', default=None, group='value') + thumbnail = self._og_search_thumbnail(webpage, default=None) upload_date = unified_strdate(self._html_search_regex( - r'''(?x)\s* - (?:\s*)* - (\d{2}/\d{2}/\d{4})''', - webpage, 'upload_date', default=None)) + r'(?s)]+\bclass=(["\'])[^>]*?\bfield-name-post-date\b[^>]*?\1[^>]*>.*?(?P\d{2}/\d{2}/\d{4})', + webpage, 'upload date', default=None, group='value')) + + series = self._search_regex( + r'data-program=(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'series', default=None, group='value') + episode_number = int_or_none(self._search_regex( + r'(?i)aflevering (\d+)', title, 'episode number', default=None)) + tags = re.findall(r']+\bhref=["\']/tags/[^>]+>([^<]+)<', webpage) return { 'id': video_id, 'display_id': display_id, 'title': title, 'description': description, - 'episode_number': episode_number, - 'upload_date': upload_date, 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'series': series, + 'episode_number': episode_number, + 'tags': tags, 'formats': formats, }