From 79998cd5afb2e16fe14cebdbec81b21c45c24c32 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 May 2015 00:12:42 +0600 Subject: [PATCH] [svtplay] Generalize svt extractors and add svt.se extractor --- youtube_dl/extractor/__init__.py | 5 +- youtube_dl/extractor/svtplay.py | 98 ++++++++++++++++++++------------ 2 files changed, 67 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 7f0070784..79236c6c1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -505,7 +505,10 @@ from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE from .sunporno import SunPornoIE -from .svtplay import SVTPlayIE +from .svtplay import ( + SVTIE, + SVTPlayIE, +) from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE diff --git a/youtube_dl/extractor/svtplay.py b/youtube_dl/extractor/svtplay.py index 433dfd1cb..732f02048 100644 --- a/youtube_dl/extractor/svtplay.py +++ b/youtube_dl/extractor/svtplay.py @@ -9,41 +9,9 @@ from ..utils import ( ) -class SVTPlayIE(InfoExtractor): - IE_DESC = 'SVT Play and Öppet arkiv' - _VALID_URL = r'https?://(?:www\.)?(?Psvtplay|oppetarkiv)\.se/video/(?P[0-9]+)' - _TESTS = [{ - 'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final', - 'md5': 'ade3def0643fa1c40587a422f98edfd9', - 'info_dict': { - 'id': '2609989', - 'ext': 'flv', - 'title': 'SM veckan vinter, Örebro - Rally, final', - 'duration': 4500, - 'thumbnail': 're:^https?://.*[\.-]jpg$', - 'age_limit': 0, - }, - }, { - 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318', - 'md5': 'c3101a17ce9634f4c1f9800f0746c187', - 'info_dict': { - 'id': '1058509', - 'ext': 'flv', - 'title': 'Farlig kryssning', - 'duration': 2566, - 'thumbnail': 're:^https?://.*[\.-]jpg$', - 'age_limit': 0, - }, - 'skip': 'Only works from Sweden', - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - host = mobj.group('host') - - info = self._download_json( - 'http://www.%s.se/video/%s?output=json' % (host, video_id), video_id) +class SVTBaseIE(InfoExtractor): + def _extract_video(self, url, video_id): + info = self._download_json(url, video_id) title = info['context']['title'] thumbnail = info['context'].get('thumbnailImage') @@ -80,3 +48,63 @@ class SVTPlayIE(InfoExtractor): 'duration': duration, 'age_limit': age_limit, } + + +class SVTIE(SVTBaseIE): + _VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P\d+)&.*?\barticleId=(?P\d+)' + _TEST = { + 'url': 'http://www.svt.se/wd?widgetId=23991§ionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false', + 'md5': '9648197555fc1b49e3dc22db4af51d46', + 'info_dict': { + 'id': '2900353', + 'ext': 'flv', + 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', + 'duration': 27, + 'age_limit': 0, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + widget_id = mobj.group('widget_id') + article_id = mobj.group('id') + return self._extract_video( + 'http://www.svt.se/wd?widgetId=%s&articleId=%s&format=json&type=embed&output=json' % (widget_id, article_id), + article_id) + + +class SVTPlayIE(SVTBaseIE): + IE_DESC = 'SVT Play and Öppet arkiv' + _VALID_URL = r'https?://(?:www\.)?(?Psvtplay|oppetarkiv)\.se/video/(?P[0-9]+)' + _TESTS = [{ + 'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final', + 'md5': 'ade3def0643fa1c40587a422f98edfd9', + 'info_dict': { + 'id': '2609989', + 'ext': 'flv', + 'title': 'SM veckan vinter, Örebro - Rally, final', + 'duration': 4500, + 'thumbnail': 're:^https?://.*[\.-]jpg$', + 'age_limit': 0, + }, + }, { + 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318', + 'md5': 'c3101a17ce9634f4c1f9800f0746c187', + 'info_dict': { + 'id': '1058509', + 'ext': 'flv', + 'title': 'Farlig kryssning', + 'duration': 2566, + 'thumbnail': 're:^https?://.*[\.-]jpg$', + 'age_limit': 0, + }, + 'skip': 'Only works from Sweden', + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') + return self._extract_video( + 'http://www.%s.se/video/%s?output=json' % (host, video_id), + video_id)