From a206ef62df7e45992ebb26bf41f86c01d904fe75 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 10 Apr 2017 13:50:08 +0100 Subject: [PATCH] [curiositystream] fix extraction(closes #12638) --- youtube_dl/extractor/curiositystream.py | 54 +++++++++++++++++++++---- 1 file changed, 47 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index e3c99468c1..145d9397cb 100644 --- a/youtube_dl/extractor/curiositystream.py +++ b/youtube_dl/extractor/curiositystream.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( int_or_none, @@ -49,6 +51,48 @@ class CuriosityStreamBaseIE(InfoExtractor): limelight_media_id = media['limelight_media_id'] title = media['title'] + formats = [] + for encoding in media.get('encodings', []): + m3u8_url = encoding.get('master_playlist_url') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + encoding_url = encoding.get('url') + file_url = encoding.get('file_url') + if not encoding_url and not file_url: + continue + f = { + 'width': int_or_none(encoding.get('width')), + 'height': int_or_none(encoding.get('height')), + 'vbr': int_or_none(encoding.get('video_bitrate')), + 'abr': int_or_none(encoding.get('audio_bitrate')), + 'filesize': int_or_none(encoding.get('size_in_bytes')), + 'vcodec': encoding.get('video_codec'), + 'acodec': encoding.get('audio_codec'), + 'container': encoding.get('container_type'), + } + for f_url in (encoding_url, file_url): + if not f_url: + continue + fmt = f.copy() + rtmp = re.search(r'^(?Prtmpe?://(?P[^/]+)/(?P.+))/(?Pmp[34]:.+)$', f_url) + if rtmp: + fmt.update({ + 'url': rtmp.group('url'), + 'play_path': rtmp.group('playpath'), + 'app': rtmp.group('app'), + 'ext': 'flv', + 'format_id': 'rtmp', + }) + else: + fmt.update({ + 'url': f_url, + 'format_id': 'http', + }) + formats.append(fmt) + self._sort_formats(formats) + subtitles = {} for closed_caption in media.get('closed_captions', []): sub_url = closed_caption.get('file') @@ -60,16 +104,14 @@ class CuriosityStreamBaseIE(InfoExtractor): }) return { - '_type': 'url_transparent', 'id': video_id, - 'url': 'limelight:media:' + limelight_media_id, + 'formats': formats, 'title': title, 'description': media.get('description'), 'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'), 'duration': int_or_none(media.get('duration')), 'tags': media.get('tags'), 'subtitles': subtitles, - 'ie_key': 'LimelightMedia', } @@ -78,14 +120,12 @@ class CuriosityStreamIE(CuriosityStreamBaseIE): _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P\d+)' _TEST = { 'url': 'https://app.curiositystream.com/video/2', - 'md5': 'a0074c190e6cddaf86900b28d3e9ee7a', + 'md5': '262bb2f257ff301115f1973540de8983', 'info_dict': { 'id': '2', 'ext': 'mp4', 'title': 'How Did You Develop The Internet?', 'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.', - 'timestamp': 1448388615, - 'upload_date': '20151124', } } @@ -105,7 +145,7 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'title': 'Curious Minds: The Internet', 'description': 'How is the internet shaping our lives in the 21st Century?', }, - 'playlist_mincount': 17, + 'playlist_mincount': 12, } def _real_extract(self, url):