From 478c2c619364f5fb0c1ee9e9489048ab4ae26521 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 21 Apr 2014 07:12:02 +0200 Subject: [PATCH] [clubic] Add extractor (Fixes #2773) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/clubic.py | 58 ++++++++++++++++++++++++++++++++ youtube_dl/utils.py | 11 ++++++ 3 files changed, 70 insertions(+) create mode 100644 youtube_dl/extractor/clubic.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e0ef1cd3e..8235d42b6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -40,6 +40,7 @@ from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE +from .clubic import ClubicIE from .cmt import CMTIE from .cnet import CNETIE from .cnn import ( diff --git a/youtube_dl/extractor/clubic.py b/youtube_dl/extractor/clubic.py new file mode 100644 index 000000000..14f215c5c --- /dev/null +++ b/youtube_dl/extractor/clubic.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + qualities, +) + + +class ClubicIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P[0-9]+)\.html' + + _TEST = { + 'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html', + 'md5': '1592b694ba586036efac1776b0b43cd3', + 'info_dict': { + 'id': '448474', + 'ext': 'mp4', + 'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité', + 'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*', + 'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id + player_page = self._download_webpage(player_url, video_id) + + config_json = self._search_regex( + r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page, + 'configuration') + config = json.loads(config_json) + + video_info = config['videoInfo'] + sources = config['sources'] + quality_order = qualities(['sd', 'hq']) + + formats = [{ + 'format_id': src['streamQuality'], + 'url': src['src'], + 'quality': quality_order(src['streamQuality']), + } for src in sources] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_info['title'], + 'formats': formats, + 'description': clean_html(video_info.get('description')), + 'thumbnail': config.get('poster'), + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 116eb3610..d4df78071 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1406,3 +1406,14 @@ def compat_getpass(prompt, *args, **kwargs): def strip_jsonp(code): return re.sub(r'(?s)^[a-zA-Z_]+\s*\(\s*(.*)\);\s*?\s*$', r'\1', code) + + +def qualities(quality_ids): + """ Get a numeric quality value out of a list of possible values """ + def q(qid): + try: + return quality_ids.index(qid) + except ValueError: + return -1 + return q +