From 25b51c7816b5e8f3a20e7582f04d8dff7e0c788f Mon Sep 17 00:00:00 2001 From: Pierre Rudloff Date: Sun, 18 Aug 2013 16:11:47 +0200 Subject: [PATCH] Download videos from jeuxvideo.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/jeuxvideo.py | 33 +++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100644 youtube_dl/extractor/jeuxvideo.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 84c02c2ed9..b9bd3a4291 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -36,6 +36,7 @@ from .ina import InaIE from .infoq import InfoQIE from .instagram import InstagramIE +from .jeuxvideo import JeuxVideoIE from .jukebox import JukeboxIE from .justintv import JustinTVIE from .kankan import KankanIE diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py new file mode 100644 index 0000000000..d74a1c9b4e --- /dev/null +++ b/youtube_dl/extractor/jeuxvideo.py @@ -0,0 +1,33 @@ +import json +import re + +from .common import InfoExtractor + +class JeuxVideoIE(InfoExtractor): + _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + title = re.match(self._VALID_URL, url).group(1) + webpage = self._download_webpage(url, title) + m_download = re.search(r'', webpage) + + xml_link = m_download.group(1) + + id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1) + + xml_config = self._download_webpage(xml_link, title, + 'Downloading XML config') + info = re.search(r'(.*?)', + xml_config, re.MULTILINE|re.DOTALL).group(1) + info = json.loads(info)['versions'][0] + + video_url = 'http://video720.jeuxvideo.com/' + info['file'] + + track_info = {'id':id, + 'title' : title, + 'ext' : 'mp4', + 'url' : video_url + } + + return [track_info]