From 0e2a436dcebc7dc17c5848bada4adcad4248491d Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 16 Dec 2013 21:34:41 +0100 Subject: [PATCH] [radiofrance] Add support (Fixes #1942) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/radiofrance.py | 60 +++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) create mode 100644 youtube_dl/extractor/radiofrance.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b8ff750d05..2761b5439f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -119,6 +119,7 @@ from .pornhub import PornHubIE from .pornotube import PornotubeIE from .pyvideo import PyvideoIE +from .radiofrance import RadioFranceIE from .rbmaradio import RBMARadioIE from .redtube import RedTubeIE from .ringtv import RingTVIE diff --git a/youtube_dl/extractor/radiofrance.py b/youtube_dl/extractor/radiofrance.py new file mode 100644 index 0000000000..bb33b50bc7 --- /dev/null +++ b/youtube_dl/extractor/radiofrance.py @@ -0,0 +1,60 @@ +# coding: utf-8 +import datetime +import json +import re + +from .common import InfoExtractor +from ..utils import ( + remove_start, +) + + +class RadioFranceIE(InfoExtractor): + _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P[^?#]+)' + IE_NAME = u'radiofrance' + + _TEST = { + u'url': u'http://maison.radiofrance.fr/radiovisions/one-one', + u'file': u'one-one.mp4', + u'md5': u'todo', + u'info_dict': { + u"title": u"One to one", + u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.", + u"uploader": u"ferdi", + }, + } + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'

(.*?)

', webpage, u'title') + description = self._html_search_regex( + r'
(.*?)
', + webpage, u'description', fatal=False) + uploader = self._html_search_regex( + r'
  © (.*?)
', + webpage, u'uploader', fatal=False) + + formats_str = self._html_search_regex( + r'class="jp-jplayer[^"]*" data-source="([^"]+)">', + webpage, u'audio URLs') + formats = [ + { + 'format_id': m[0], + 'url': m[1], + 'vcodec': 'none', + } + for m in + re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str) + ] + # No sorting, we don't know any more about these formats + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'uploader': uploader, + }