From 65e4ad5bfefa83e4f57f0844ff7cd8f94f8ffd84 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Apr 2014 19:41:58 +0700 Subject: [PATCH] [rtbf] Minor changes and YouTube videos support --- youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/rtbf.py | 39 ++++++++++++++++---------------- 2 files changed, 21 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a8fef27030..4b53bef5c9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -210,7 +210,7 @@ from .ringtv import RingTVIE from .ro220 import Ro220IE from .rottentomatoes import RottenTomatoesIE from .roxwel import RoxwelIE -from .rtbf import RTBFVideoIE +from .rtbf import RTBFIE from .rtlnow import RTLnowIE from .rts import RTSIE from .rtve import RTVEALaCartaIE diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index 5445396655..205f8a1676 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -5,10 +5,10 @@ import re import json from .common import InfoExtractor -from ..utils import clean_html -class RTBFVideoIE(InfoExtractor): - _VALID_URL = r'https?://www.rtbf.be/video/(?P[^?]+)\?.*id=(?P<id>[0-9]+)' + +class RTBFIE(InfoExtractor): + _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)' _TEST = { 'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274', 'md5': '799f334ddf2c0a582ba80c44655be570', @@ -16,7 +16,10 @@ class RTBFVideoIE(InfoExtractor): 'id': '1921274', 'ext': 'mp4', 'title': 'Les Diables au coeur (épisode 2)', + 'description': 'Football - Diables Rouges', 'duration': 3099, + 'timestamp': 1398456336, + 'upload_date': '20140425', } } @@ -24,25 +27,23 @@ class RTBFVideoIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - # TODO more code goes here, for example ... - webpage = self._download_webpage(url, video_id) - title = self._html_search_regex( - r'<meta property="og:description" content="([^"]*)"', - webpage, 'title', mobj.group('title')) + page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) + + data = json.loads(self._html_search_regex( + r'<div class="js-player-embed" data-video="([^"]+)"', page, 'data video'))['data'] - iframe_url = self._html_search_regex(r'<iframe [^>]*src="([^"]+)"', - webpage, 'iframe') - iframe = self._download_webpage(iframe_url, video_id) + video_url = data.get('downloadUrl') or data.get('url') - data_video_idx = iframe.find('data-video') - next_data_idx = iframe.find('data-', data_video_idx + 1) - json_data_start = data_video_idx + len('data-video=') + 1 - json_data_end = next_data_idx - 2 - video_data = json.loads(clean_html(iframe[json_data_start:json_data_end])) + if data['provider'].lower() == 'youtube': + return self.url_result(video_url, 'Youtube') return { 'id': video_id, - 'title': title, - 'url': video_data['data']['downloadUrl'], - 'duration': video_data['data']['duration'], + 'url': video_url, + 'title': data['title'], + 'description': data.get('description') or data.get('subtitle'), + 'thumbnail': data['thumbnail']['large'], + 'duration': data.get('duration') or data.get('realDuration'), + 'timestamp': data['created'], + 'view_count': data['viewCount'], }