From a17d16d59cc39e786d572000df34bcf3f1e3804a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 27 Jan 2014 07:05:28 +0100 Subject: [PATCH] [la7] Add support --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/la7.py | 56 ++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) create mode 100644 youtube_dl/extractor/la7.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5de90d6d9..be3cada98 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -107,6 +107,7 @@ from .keezmovies import KeezMoviesIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE +from .la7 import LA7IE from .liveleak import LiveLeakIE from .livestream import LivestreamIE, LivestreamOriginalIE from .lynda import ( diff --git a/youtube_dl/extractor/la7.py b/youtube_dl/extractor/la7.py new file mode 100644 index 000000000..a91b94ee9 --- /dev/null +++ b/youtube_dl/extractor/la7.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, +) + + +class LA7IE(InfoExtractor): + IE_NAME = 'la7.tv' + _VALID_URL = r'https?://(?:www\.)?la7\.tv/richplayer/\?assetid=(?P[0-9]+)' + + _TEST = { + 'url': 'http://www.la7.tv/richplayer/?assetid=50355319', + 'file': '50355319.mp4', + 'md5': 'ec7d1f0224d20ba293ab56cf2259651f', + 'info_dict': { + 'title': 'IL DIVO', + 'description': 'Un film di Paolo Sorrentino con Toni Servillo, Anna Bonaiuto, Giulio Bosetti e Flavio Bucci', + 'duration': 6254, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + xml_url = 'http://www.la7.tv/repliche/content/index.php?contentId=%s' % video_id + doc = self._download_xml(xml_url, video_id) + + video_title = doc.find('title').text + description = doc.find('description').text + duration = parse_duration(doc.find('duration').text) + thumbnail = doc.find('img').text + view_count = int(doc.find('views').text) + + prefix = doc.find('.//fqdn').text.strip().replace('auto:', 'http:') + + formats = [{ + 'format': vnode.find('quality').text, + 'tbr': int(vnode.find('quality').text), + 'url': vnode.find('fms').text.strip().replace('mp4:', prefix), + } for vnode in doc.findall('.//videos/video')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'view_count': view_count, + }