From 217d5ae0137943829db23d13eee425e5fd7c08ae Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 4 Aug 2016 09:37:27 +0100 Subject: [PATCH] [vodplatform] Add new extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 8 ++++ youtube_dl/extractor/vodplatform.py | 58 +++++++++++++++++++++++++++++ 3 files changed, 67 insertions(+) create mode 100644 youtube_dl/extractor/vodplatform.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8b866ed575..909f7d25c8 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1004,6 +1004,7 @@ from .vk import ( ) from .vlive import VLiveIE from .vodlocker import VodlockerIE +from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE from .voxmedia import VoxMediaIE from .vporn import VpornIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5364f0b197..e89a037603 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2207,6 +2207,14 @@ class GenericIE(InfoExtractor): return self.url_result( self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine') + # Look for VODPlatform embeds + mobj = re.search( + r']+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)', + webpage) + if mobj is not None: + return self.url_result( + self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform') + # Look for Instagram embeds instagram_embed_url = InstagramIE._extract_embed_url(webpage) if instagram_embed_url is not None: diff --git a/youtube_dl/extractor/vodplatform.py b/youtube_dl/extractor/vodplatform.py new file mode 100644 index 0000000000..b49542b162 --- /dev/null +++ b/youtube_dl/extractor/vodplatform.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import unescapeHTML + + +class VODPlatformIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vod-platform\.net/embed/(?P[^/?#]+)' + _TEST = { + # from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar + 'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw', + 'md5': '1db2b7249ce383d6be96499006e951fc', + 'info_dict': { + 'id': 'RufMcytHDolTH1MuKHY9Fw', + 'ext': 'mp4', + 'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = unescapeHTML(self._og_search_title(webpage)) + hidden_inputs = self._hidden_inputs(webpage) + + base_url = self._search_regex( + '(.*/)(?:playlist.m3u8|manifest.mpd)', + hidden_inputs.get('HiddenmyhHlsLink') or hidden_inputs['HiddenmyDashLink'], + 'base url') + formats = self._extract_m3u8_formats( + base_url + 'playlist.m3u8', video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + formats.extend(self._extract_mpd_formats( + base_url + 'manifest.mpd', video_id, + mpd_id='dash', fatal=False)) + rtmp_formats = self._extract_smil_formats( + base_url + 'jwplayer.smil', video_id, fatal=False) + for rtmp_format in rtmp_formats: + rtsp_format = rtmp_format.copy() + rtsp_format['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path']) + del rtsp_format['play_path'] + del rtsp_format['ext'] + rtsp_format.update({ + 'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'), + 'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'), + 'protocol': 'rtsp', + }) + formats.extend([rtmp_format, rtsp_format]) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': hidden_inputs.get('HiddenThumbnail') or self._og_search_thumbnail(webpage), + 'formats': formats, + }