mirrors
/
youtube-dl
0
0
Fork 0
Code Releases 1 Activity

[prosiebensat1] extract all formats

main
Remita Amine 2016-07-05 17:11:45 +01:00
parent e3f88be7a9
commit 84f214d840
1 changed files with 88 additions and 77 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

165
youtube_dl/extractor/prosiebensat1.py
View File

@ -5,7 +5,7 @@ import re
from hashlib import sha1 from hashlib import sha1
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode from ..compat import compat_str
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
determine_ext, determine_ext,
@ -71,6 +71,7 @@ class ProSiebenSat1IE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video is unavailable',
}, },
{ {
'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip', 'url': 'http://www.sixx.de/stars-style/video/sexy-laufen-in-ugg-boots-clip',
@ -86,6 +87,7 @@ class ProSiebenSat1IE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video is unavailable',
}, },
{ {
'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip', 'url': 'http://www.sat1.de/film/der-ruecktritt/video/im-interview-kai-wiesinger-clip',
@ -101,6 +103,7 @@ class ProSiebenSat1IE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video is unavailable',
}, },
{ {
'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge', 'url': 'http://www.kabeleins.de/tv/rosins-restaurants/videos/jagd-auf-fertigkost-im-elsthal-teil-2-ganze-folge',
@ -116,6 +119,7 @@ class ProSiebenSat1IE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video is unavailable',
}, },
{ {
'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge', 'url': 'http://www.ran.de/fussball/bundesliga/video/schalke-toennies-moechte-raul-zurueck-ganze-folge',
@ -131,6 +135,7 @@ class ProSiebenSat1IE(InfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This video is unavailable',
}, },
{ {
'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip', 'url': 'http://www.the-voice-of-germany.de/video/31-andreas-kuemmert-rocket-man-clip',
@ -227,70 +232,42 @@ class ProSiebenSat1IE(InfoExtractor):
] ]
def _extract_clip(self, url, webpage): def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id') clip_id = self._html_search_regex(
self._CLIPID_REGEXES, webpage, 'clip id')
access_token = 'prosieben' access_token = 'prosieben'
client_name = 'kolibri-2.0.19-splec4' client_name = 'kolibri-2.0.19-splec4'
client_location = url client_location = url
videos_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos?%s' % compat_urllib_parse_urlencode({ video = self._download_json(
'access_token': access_token, 'http://vas.sim-technik.de/vas/live/v2/videos',
'client_location': client_location, clip_id, 'Downloading videos JSON', query={
'client_name': client_name, 'access_token': access_token,
'ids': clip_id, 'client_location': client_location,
}) 'client_name': client_name,
'ids': clip_id,
video = self._download_json(videos_api_url, clip_id, 'Downloading videos JSON')[0] })[0]
if video.get('is_protected') is True: if video.get('is_protected') is True:
raise ExtractorError('This video is DRM protected.', expected=True) raise ExtractorError('This video is DRM protected.', expected=True)
duration = float_or_none(video.get('duration')) duration = float_or_none(video.get('duration'))
source_ids = [source['id'] for source in video['sources']] source_ids = [compat_str(source['id']) for source in video['sources']]
source_ids_str = ','.join(map(str, source_ids))
g = '01!8d8F_)r9]4s[qeuXfP%' g = '01!8d8F_)r9]4s[qeuXfP%'
client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]).encode('utf-8')).hexdigest()
client_id = g[:2] + sha1(''.join([clip_id, g, access_token, client_location, g, client_name]) sources = self._download_json(
.encode('utf-8')).hexdigest() 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources' % clip_id,
clip_id, 'Downloading sources JSON', query={
sources_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources?%s' % (clip_id, compat_urllib_parse_urlencode({ 'access_token': access_token,
'access_token': access_token, 'client_id': client_id,
'client_id': client_id, 'client_location': client_location,
'client_location': client_location, 'client_name': client_name,
'client_name': client_name, })
}))
sources = self._download_json(sources_api_url, clip_id, 'Downloading sources JSON')
server_id = sources['server_id'] server_id = sources['server_id']
client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id,
client_location, source_ids_str, g, client_name])
.encode('utf-8')).hexdigest()
url_api_url = 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url?%s' % (clip_id, compat_urllib_parse_urlencode({
'access_token': access_token,
'client_id': client_id,
'client_location': client_location,
'client_name': client_name,
'server_id': server_id,
'source_ids': source_ids_str,
}))
urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title') title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
description = self._html_search_regex(self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_regex(
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
formats = []
urls_sources = urls['sources']
if isinstance(urls_sources, dict):
urls_sources = urls_sources.values()
def fix_bitrate(bitrate): def fix_bitrate(bitrate):
bitrate = int_or_none(bitrate) bitrate = int_or_none(bitrate)
@ -298,37 +275,71 @@ class ProSiebenSat1IE(InfoExtractor):
return None return None
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
for source in urls_sources: formats = []
protocol = source['protocol'] for source_id in source_ids:
source_url = source['url'] client_id = g[:2] + sha1(''.join([g, clip_id, access_token, server_id, client_location, source_id, g, client_name]).encode('utf-8')).hexdigest()
if protocol == 'rtmp' or protocol == 'rtmpe': urls = self._download_json(
mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url) 'http://vas.sim-technik.de/vas/live/v2/videos/%s/sources/url' % clip_id,
if not mobj: clip_id, 'Downloading urls JSON', query={
'access_token': access_token,
'client_id': client_id,
'client_location': client_location,
'client_name': client_name,
'server_id': server_id,
'source_ids': source_id,
})
if urls.get('status_code') != 0:
raise ExtractorError('This video is unavailable', expected=True)
urls_sources = urls['sources']
if isinstance(urls_sources, dict):
urls_sources = urls_sources.values()
for source in urls_sources:
source_url = source.get('url')
if not source_url:
continue continue
path = mobj.group('path') protocol = source.get('protocol')
mp4colon_index = path.rfind('mp4:') mimetype = source.get('mimetype')
app = path[:mp4colon_index] if mimetype == 'application/f4m+xml' or 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m':
play_path = path[mp4colon_index:] formats.extend(self._extract_f4m_formats(
formats.append({ source_url, clip_id, f4m_id='hds', fatal=False))
'url': '%s/%s' % (mobj.group('url'), app), elif mimetype == 'application/x-mpegURL':
'app': app, formats.extend(self._extract_m3u8_formats(
'play_path': play_path, source_url, clip_id, 'mp4', 'm3u8_native',
'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf', m3u8_id='hls', fatal=False))
'page_url': 'http://www.prosieben.de', else:
'vbr': fix_bitrate(source['bitrate']), tbr = fix_bitrate(source['bitrate'])
'ext': 'mp4', if protocol in ('rtmp', 'rtmpe'):
'format_id': '%s_%s' % (source['cdn'], source['bitrate']), mobj = re.search(r'^(?P<url>rtmpe?://[^/]+)/(?P<path>.+)$', source_url)
}) if not mobj:
elif 'f4mgenerator' in source_url or determine_ext(source_url) == 'f4m': continue
formats.extend(self._extract_f4m_formats(source_url, clip_id)) path = mobj.group('path')
else: mp4colon_index = path.rfind('mp4:')
formats.append({ app = path[:mp4colon_index]
'url': source_url, play_path = path[mp4colon_index:]
'vbr': fix_bitrate(source['bitrate']), formats.append({
}) 'url': '%s/%s' % (mobj.group('url'), app),
'app': app,
'play_path': play_path,
'player_url': 'http://livepassdl.conviva.com/hf/ver/2.79.0.17083/LivePassModuleMain.swf',
'page_url': 'http://www.prosieben.de',
'tbr': tbr,
'ext': 'flv',
'format_id': 'rtmp%s' % ('-%d' % tbr if tbr else ''),
})
else:
formats.append({
'url': source_url,
'tbr': tbr,
'format_id': 'http%s' % ('-%d' % tbr if tbr else ''),
})
self._sort_formats(formats) self._sort_formats(formats)
description = self._html_search_regex(
self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_regex(
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None))
return { return {
'id': clip_id, 'id': clip_id,
'title': title, 'title': title,