From df5ae3eb16effec4dc2609ed3520ddc068305efe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 28 Feb 2015 21:25:04 +0600 Subject: [PATCH] [oppetarkiv] Merge with svtplay --- youtube_dl/extractor/__init__.py | 1 - youtube_dl/extractor/oppetarkiv.py | 66 ------------------------------ youtube_dl/extractor/svtplay.py | 42 +++++++++++++++---- 3 files changed, 34 insertions(+), 75 deletions(-) delete mode 100644 youtube_dl/extractor/oppetarkiv.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1544f1059..aecb67bf4 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -350,7 +350,6 @@ from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE from .openfilm import OpenFilmIE -from .oppetarkiv import OppetArkivIE from .orf import ( ORFTVthekIE, ORFOE1IE, diff --git a/youtube_dl/extractor/oppetarkiv.py b/youtube_dl/extractor/oppetarkiv.py deleted file mode 100644 index ae6a28308..000000000 --- a/youtube_dl/extractor/oppetarkiv.py +++ /dev/null @@ -1,66 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - determine_ext, -) - - -class OppetArkivIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?oppetarkiv\.se/video/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318', - 'md5': '5c1eb616e59f733d4af77edc5177d2fe', - '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): - video_id = self._match_id(url) - info = self._download_json( - 'http://www.oppetarkiv.se/video/%s?output=json' % video_id, video_id) - - title = info['context']['title'] - thumbnail = info['context'].get('thumbnailImage') - - video_info = info['video'] - formats = [] - for vr in video_info['videoReferences']: - vurl = vr['url'] - ext = determine_ext(vurl) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - vurl, video_id, - ext='mp4', entry_protocol='m3u8_native', - m3u8_id=vr.get('playerType'))) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - vurl + '?hdcore=3.3.0', video_id, - f4m_id=vr.get('playerType'))) - else: - formats.append({ - 'format_id': vr.get('playerType'), - 'url': vurl, - }) - self._sort_formats(formats) - - duration = video_info.get('materialLength') - - age_limit = 18 if video_info.get('inappropriateForChildren') else 0 - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnail': thumbnail, - 'duration': duration, - 'age_limit': age_limit, - } diff --git a/youtube_dl/extractor/svtplay.py b/youtube_dl/extractor/svtplay.py index eadb9ccb4..433dfd1cb 100644 --- a/youtube_dl/extractor/svtplay.py +++ b/youtube_dl/extractor/svtplay.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, @@ -8,23 +10,40 @@ class SVTPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P[0-9]+)' - _TEST = { + 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': 'f4a184968bc9c802a9b41316657aaa80', + 'md5': 'ade3def0643fa1c40587a422f98edfd9', 'info_dict': { 'id': '2609989', - 'ext': 'mp4', + '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): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') + info = self._download_json( - 'http://www.svtplay.se/video/%s?output=json' % video_id, video_id) + 'http://www.%s.se/video/%s?output=json' % (host, video_id), video_id) title = info['context']['title'] thumbnail = info['context'].get('thumbnailImage') @@ -33,11 +52,16 @@ def _real_extract(self, url): formats = [] for vr in video_info['videoReferences']: vurl = vr['url'] - if determine_ext(vurl) == 'm3u8': + ext = determine_ext(vurl) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( vurl, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=vr.get('playerType'))) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + vurl + '?hdcore=3.3.0', video_id, + f4m_id=vr.get('playerType'))) else: formats.append({ 'format_id': vr.get('playerType'), @@ -46,6 +70,7 @@ def _real_extract(self, url): self._sort_formats(formats) duration = video_info.get('materialLength') + age_limit = 18 if video_info.get('inappropriateForChildren') else 0 return { 'id': video_id, @@ -53,4 +78,5 @@ def _real_extract(self, url): 'formats': formats, 'thumbnail': thumbnail, 'duration': duration, + 'age_limit': age_limit, }