From 648d25d43d86afe853f10dff25029626c7863502 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Tue, 10 Sep 2013 15:50:34 +0200 Subject: [PATCH] [francetv] Add an extractor for francetvinfo.fr (closes #1317) It uses the same system as Pluzz, create a base class for both extractors. --- youtube_dl/extractor/__init__.py | 5 ++- youtube_dl/extractor/francetv.py | 61 +++++++++++++++++++++++--------- 2 files changed, 48 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 0d80acd22..26cf24935 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -29,7 +29,10 @@ from .escapist import EscapistIE from .exfm import ExfmIE from .facebook import FacebookIE from .flickr import FlickrIE -from .francetv import PluzzIE +from .francetv import ( + PluzzIE, + FranceTvInfoIE, +) from .freesound import FreesoundIE from .funnyordie import FunnyOrDieIE from .gamespot import GameSpotIE diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 6e1176470..f2b12c884 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -8,7 +8,29 @@ from ..utils import ( ) -class PluzzIE(InfoExtractor): +class FranceTVBaseInfoExtractor(InfoExtractor): + def _extract_video(self, video_id): + xml_desc = self._download_webpage( + 'http://www.francetvinfo.fr/appftv/webservices/video/' + 'getInfosOeuvre.php?id-diffusion=' + + video_id, video_id, 'Downloading XML config') + info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8')) + + manifest_url = info.find('videos/video/url').text + video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') + video_url = video_url.replace('/z/', '/i/') + thumbnail_path = info.find('image').text + + return {'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': info.find('titre').text, + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), + 'description': info.find('synopsis').text, + } + + +class PluzzIE(FranceTVBaseInfoExtractor): IE_NAME = u'pluzz.francetv.fr' _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html' @@ -29,22 +51,27 @@ class PluzzIE(InfoExtractor): webpage = self._download_webpage(url, title) video_id = self._search_regex( r'data-diffusion="(\d+)"', webpage, 'ID') + return self._extract_video(video_id) - xml_desc = self._download_webpage( - 'http://www.pluzz.fr/appftv/webservices/video/' - 'getInfosOeuvre.php?id-diffusion=' - + video_id, title, 'Downloading XML config') - info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8')) - manifest_url = info.find('videos/video/url').text - video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8') - video_url = video_url.replace('/z/', '/i/') - thumbnail_path = info.find('image').text +class FranceTvInfoIE(FranceTVBaseInfoExtractor): + IE_NAME = u'francetvinfo.fr' + _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P.+).html' - return {'id': video_id, - 'ext': 'mp4', - 'url': video_url, - 'title': info.find('titre').text, - 'thumbnail': compat_urlparse.urljoin(url, thumbnail_path), - 'description': info.find('synopsis').text, - } + _TEST = { + u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', + u'file': u'84981923.mp4', + u'info_dict': { + u'title': u'Soir 3', + }, + u'params': { + u'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + page_title = mobj.group('title') + webpage = self._download_webpage(url, page_title) + video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id') + return self._extract_video(video_id)