[curiositystream] fix extraction(closes #12638)

This commit is contained in:
Remita Amine 2017-04-10 13:50:08 +01:00
parent 3f2ce6896a
commit a206ef62df
1 changed files with 47 additions and 7 deletions

View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
@ -49,6 +51,48 @@ class CuriosityStreamBaseIE(InfoExtractor):
limelight_media_id = media['limelight_media_id'] limelight_media_id = media['limelight_media_id']
title = media['title'] 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'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[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 = {} subtitles = {}
for closed_caption in media.get('closed_captions', []): for closed_caption in media.get('closed_captions', []):
sub_url = closed_caption.get('file') sub_url = closed_caption.get('file')
@ -60,16 +104,14 @@ class CuriosityStreamBaseIE(InfoExtractor):
}) })
return { return {
'_type': 'url_transparent',
'id': video_id, 'id': video_id,
'url': 'limelight:media:' + limelight_media_id, 'formats': formats,
'title': title, 'title': title,
'description': media.get('description'), 'description': media.get('description'),
'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'), 'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
'duration': int_or_none(media.get('duration')), 'duration': int_or_none(media.get('duration')),
'tags': media.get('tags'), 'tags': media.get('tags'),
'subtitles': subtitles, 'subtitles': subtitles,
'ie_key': 'LimelightMedia',
} }
@ -78,14 +120,12 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
_VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)' _VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'https://app.curiositystream.com/video/2', 'url': 'https://app.curiositystream.com/video/2',
'md5': 'a0074c190e6cddaf86900b28d3e9ee7a', 'md5': '262bb2f257ff301115f1973540de8983',
'info_dict': { 'info_dict': {
'id': '2', 'id': '2',
'ext': 'mp4', 'ext': 'mp4',
'title': 'How Did You Develop The Internet?', 'title': 'How Did You Develop The Internet?',
'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created 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', 'title': 'Curious Minds: The Internet',
'description': 'How is the internet shaping our lives in the 21st Century?', 'description': 'How is the internet shaping our lives in the 21st Century?',
}, },
'playlist_mincount': 17, 'playlist_mincount': 12,
} }
def _real_extract(self, url): def _real_extract(self, url):