youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

commit 146323a7f8bf434de91298e48a81a8e0ff689244
parent 57e086dcea6a9981c4943b6a281c0c7f806efaf8
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Fri, 12 Dec 2014 17:39:33 +0100

[groupon] Add extractor (Fixes #4386)

Diffstat:
Myoutube_dl/extractor/__init__.py | 1+
Ayoutube_dl/extractor/groupon.py | 50++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 51 insertions(+), 0 deletions(-)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py @@ -159,6 +159,7 @@ from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE from .grooveshark import GroovesharkIE +from .groupon import GrouponIE from .hark import HarkIE from .heise import HeiseIE from .helsinki import HelsinkiIE diff --git a/youtube_dl/extractor/groupon.py b/youtube_dl/extractor/groupon.py @@ -0,0 +1,50 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GrouponIE(InfoExtractor): + _VALID_URL = r'https?://www\.groupon\.com/deals/(?P<id>[^?#]+)' + + _TEST = { + 'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'info_dict': { + 'id': 'bikram-yoga-huntington-beach-2', + 'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)', + 'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors', + }, + 'playlist': [{ + 'info_dict': { + 'id': 'tubGNycTo_9Uxg82uESj4i61EYX8nyuf', + 'ext': 'mp4', + 'title': 'Bikram Yoga Huntington Beach | Orange County', + }, + }], + 'params': { + 'skip_download': 'HLS', + } + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + + payload = self._parse_json(self._search_regex( + r'var\s+payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id) + videos = payload['carousel'].get('dealVideos', []) + entries = [] + for v in videos: + if v.get('provider') != 'OOYALA': + self.report_warning( + '%s: Unsupported video provider %s, skipping video' % + (playlist_id, v.get('provider'))) + continue + entries.append(self.url_result('ooyala:%s' % v['media'])) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'entries': entries, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + }