From 93ad6c6bfaae8f1ce87a832ece92fa099f0e2095 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 30 Jun 2016 13:50:49 +0100 Subject: [PATCH] [sixplay] Add new extractor(closes #2183) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/m6.py | 35 +---------------- youtube_dl/extractor/sixplay.py | 60 ++++++++++++++++++++++++++++++ 3 files changed, 63 insertions(+), 33 deletions(-) create mode 100644 youtube_dl/extractor/sixplay.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 80d1bbe20..a7b110450 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -710,6 +710,7 @@ from .shahid import ShahidIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE +from .sixplay import SixPlayIE from .skynewsarabia import ( SkyNewsArabiaIE, SkyNewsArabiaArticleIE, diff --git a/youtube_dl/extractor/m6.py b/youtube_dl/extractor/m6.py index d5945ad66..39d2742c8 100644 --- a/youtube_dl/extractor/m6.py +++ b/youtube_dl/extractor/m6.py @@ -1,8 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -23,34 +21,5 @@ class M6IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - rss = self._download_xml('http://ws.m6.fr/v1/video/info/m6/bonus/%s' % video_id, video_id, - 'Downloading video RSS') - - title = rss.find('./channel/item/title').text - description = rss.find('./channel/item/description').text - thumbnail = rss.find('./channel/item/visuel_clip_big').text - duration = int(rss.find('./channel/item/duration').text) - view_count = int(rss.find('./channel/item/nombre_vues').text) - - formats = [] - for format_id in ['lq', 'sd', 'hq', 'hd']: - video_url = rss.find('./channel/item/url_video_%s' % format_id) - if video_url is None: - continue - formats.append({ - 'url': video_url.text, - 'format_id': format_id, - }) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'view_count': view_count, - 'formats': formats, - } + video_id = self._match_id(url) + return self.url_result('6play:%s' % video_id, 'SixPlay', video_id) diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py new file mode 100644 index 000000000..f855a1a00 --- /dev/null +++ b/youtube_dl/extractor/sixplay.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + qualities, + int_or_none, +) + + +class SixPlayIE(InfoExtractor): + _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P[0-9]+)' + _TEST = { + 'url': 'http://www.6play.fr/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320', + 'md5': '42310bffe4ba3982db112b9cd3467328', + 'info_dict': { + 'id': '11495320', + 'ext': 'mp4', + 'title': 'Jamel et ses amis au Marrakech du rire 2015', + 'description': 'md5:ba2149d5c321d5201b78070ee839d872', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + clip_data = self._download_json( + 'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id, + video_id) + video_data = clip_data['videoInfo'] + + preference = qualities(['lq', 'sd', 'hq', 'hd']) + formats = [] + for source in clip_data['sources']: + source_type, source_url = source.get('type'), source.get('src') + if not source_url or source_type == 'hls/primetime': + continue + if source_type == 'application/vnd.apple.mpegURL': + formats.extend(self._extract_m3u8_formats( + source_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + formats.extend(self._extract_f4m_formats( + source_url.replace('.m3u8', '.f4m'), + video_id, f4m_id='hds', fatal=False)) + elif source_type == 'video/mp4': + quality = source.get('quality') + formats.append({ + 'url': source_url, + 'format_id': quality, + 'preference': preference(quality), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_data['title'].strip(), + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'series': video_data.get('titlePgm'), + 'formats': formats, + }