X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcuriositystream.py;h=e4a7fca6ce1e7352a8ac2785c1fa3e73445c9cca;hb=HEAD;hp=e3c99468c1ce26d34063e140c59f5479bfafb363;hpb=95843da5297965bb535262002c92a4d0afcb7e12;p=youtube-dl diff --git a/youtube_dl/extractor/curiositystream.py b/youtube_dl/extractor/curiositystream.py index e3c99468c..e4a7fca6c 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, @@ -33,7 +35,7 @@ class CuriosityStreamBaseIE(InfoExtractor): return result['data'] def _real_initialize(self): - (email, password) = self._get_login_info() + email, password = self._get_login_info() if email is None: return result = self._download_json( @@ -44,11 +46,68 @@ class CuriosityStreamBaseIE(InfoExtractor): self._handle_errors(result) self._auth_token = result['message']['auth_token'] - def _extract_media_info(self, media): - video_id = compat_str(media['id']) - limelight_media_id = media['limelight_media_id'] + +class CuriosityStreamIE(CuriosityStreamBaseIE): + IE_NAME = 'curiositystream' + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P\d+)' + _TEST = { + 'url': 'https://app.curiositystream.com/video/2', + '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.', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + media = self._call_api('media/' + video_id, video_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') @@ -60,45 +119,21 @@ 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', } -class CuriosityStreamIE(CuriosityStreamBaseIE): - IE_NAME = 'curiositystream' - _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P\d+)' - _TEST = { - 'url': 'https://app.curiositystream.com/video/2', - 'md5': 'a0074c190e6cddaf86900b28d3e9ee7a', - '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', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - media = self._call_api('media/' + video_id, video_id) - return self._extract_media_info(media) - - class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): IE_NAME = 'curiositystream:collection' - _VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P\d+)' - _TEST = { + _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:collection|series)/(?P\d+)' + _TESTS = [{ 'url': 'https://app.curiositystream.com/collection/2', 'info_dict': { 'id': '2', @@ -106,7 +141,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'description': 'How is the internet shaping our lives in the 21st Century?', }, 'playlist_mincount': 17, - } + }, { + 'url': 'https://curiositystream.com/series/2', + 'only_matching': True, + }] def _real_extract(self, url): collection_id = self._match_id(url) @@ -114,7 +152,10 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE): 'collections/' + collection_id, collection_id) entries = [] for media in collection.get('media', []): - entries.append(self._extract_media_info(media)) + media_id = compat_str(media.get('id')) + entries.append(self.url_result( + 'https://curiositystream.com/video/' + media_id, + CuriosityStreamIE.ie_key(), media_id)) return self.playlist_result( entries, collection_id, collection.get('title'), collection.get('description'))