Philipp Hagemeister
9 years ago
15 changed files with 450 additions and 38 deletions
Split View
Diff Options
-
9youtube_dl/YoutubeDL.py
-
8youtube_dl/__init__.py
-
3youtube_dl/extractor/__init__.py
-
18youtube_dl/extractor/generic.py
-
138youtube_dl/extractor/kaltura.py
-
11youtube_dl/extractor/lynda.py
-
27youtube_dl/extractor/musicvault.py
-
85youtube_dl/extractor/odnoklassniki.py
-
88youtube_dl/extractor/puls4.py
-
5youtube_dl/extractor/rtve.py
-
42youtube_dl/extractor/svtplay.py
-
10youtube_dl/extractor/twitch.py
-
4youtube_dl/options.py
-
2youtube_dl/postprocessor/__init__.py
-
38youtube_dl/postprocessor/ffmpeg.py
@ -0,0 +1,138 @@ |
|||
# coding: utf-8 |
|||
from __future__ import unicode_literals |
|||
|
|||
import re |
|||
|
|||
from .common import InfoExtractor |
|||
from ..compat import compat_urllib_parse |
|||
from ..utils import ( |
|||
ExtractorError, |
|||
int_or_none, |
|||
) |
|||
|
|||
|
|||
class KalturaIE(InfoExtractor): |
|||
_VALID_URL = r'''(?x) |
|||
(?:kaltura:| |
|||
https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ |
|||
)(?P<partner_id>\d+) |
|||
(?::| |
|||
/(?:[^/]+/)*?entry_id/ |
|||
)(?P<id>[0-9a-z_]+)''' |
|||
_API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?' |
|||
_TESTS = [ |
|||
{ |
|||
'url': 'kaltura:269692:1_1jc2y3e4', |
|||
'md5': '3adcbdb3dcc02d647539e53f284ba171', |
|||
'info_dict': { |
|||
'id': '1_1jc2y3e4', |
|||
'ext': 'mp4', |
|||
'title': 'Track 4', |
|||
'upload_date': '20131219', |
|||
'uploader_id': 'mlundberg@wolfgangsvault.com', |
|||
'description': 'The Allman Brothers Band, 12/16/1981', |
|||
'thumbnail': 're:^https?://.*/thumbnail/.*', |
|||
'timestamp': int, |
|||
}, |
|||
}, |
|||
{ |
|||
'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4', |
|||
'only_matching': True, |
|||
}, |
|||
{ |
|||
'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3', |
|||
'only_matching': True, |
|||
}, |
|||
] |
|||
|
|||
def _kaltura_api_call(self, video_id, actions, *args, **kwargs): |
|||
params = actions[0] |
|||
if len(actions) > 1: |
|||
for i, a in enumerate(actions[1:], start=1): |
|||
for k, v in a.items(): |
|||
params['%d:%s' % (i, k)] = v |
|||
|
|||
query = compat_urllib_parse.urlencode(params) |
|||
url = self._API_BASE + query |
|||
data = self._download_json(url, video_id, *args, **kwargs) |
|||
|
|||
status = data if len(actions) == 1 else data[0] |
|||
if status.get('objectType') == 'KalturaAPIException': |
|||
raise ExtractorError( |
|||
'%s said: %s' % (self.IE_NAME, status['message'])) |
|||
|
|||
return data |
|||
|
|||
def _get_kaltura_signature(self, video_id, partner_id): |
|||
actions = [{ |
|||
'apiVersion': '3.1', |
|||
'expiry': 86400, |
|||
'format': 1, |
|||
'service': 'session', |
|||
'action': 'startWidgetSession', |
|||
'widgetId': '_%s' % partner_id, |
|||
}] |
|||
return self._kaltura_api_call( |
|||
video_id, actions, note='Downloading Kaltura signature')['ks'] |
|||
|
|||
def _get_video_info(self, video_id, partner_id): |
|||
signature = self._get_kaltura_signature(video_id, partner_id) |
|||
actions = [ |
|||
{ |
|||
'action': 'null', |
|||
'apiVersion': '3.1.5', |
|||
'clientTag': 'kdp:v3.8.5', |
|||
'format': 1, # JSON, 2 = XML, 3 = PHP |
|||
'service': 'multirequest', |
|||
'ks': signature, |
|||
}, |
|||
{ |
|||
'action': 'get', |
|||
'entryId': video_id, |
|||
'service': 'baseentry', |
|||
'version': '-1', |
|||
}, |
|||
{ |
|||
'action': 'getContextData', |
|||
'contextDataParams:objectType': 'KalturaEntryContextDataParams', |
|||
'contextDataParams:referrer': 'http://www.kaltura.com/', |
|||
'contextDataParams:streamerType': 'http', |
|||
'entryId': video_id, |
|||
'service': 'baseentry', |
|||
}, |
|||
] |
|||
return self._kaltura_api_call( |
|||
video_id, actions, note='Downloading video info JSON') |
|||
|
|||
def _real_extract(self, url): |
|||
video_id = self._match_id(url) |
|||
mobj = re.match(self._VALID_URL, url) |
|||
partner_id, entry_id = mobj.group('partner_id'), mobj.group('id') |
|||
|
|||
info, source_data = self._get_video_info(entry_id, partner_id) |
|||
|
|||
formats = [{ |
|||
'format_id': '%(fileExt)s-%(bitrate)s' % f, |
|||
'ext': f['fileExt'], |
|||
'tbr': f['bitrate'], |
|||
'fps': f.get('frameRate'), |
|||
'filesize_approx': int_or_none(f.get('size'), invscale=1024), |
|||
'container': f.get('containerFormat'), |
|||
'vcodec': f.get('videoCodecId'), |
|||
'height': f.get('height'), |
|||
'width': f.get('width'), |
|||
'url': '%s/flavorId/%s' % (info['dataUrl'], f['id']), |
|||
} for f in source_data['flavorAssets']] |
|||
self._sort_formats(formats) |
|||
|
|||
return { |
|||
'id': video_id, |
|||
'title': info['name'], |
|||
'formats': formats, |
|||
'description': info.get('description'), |
|||
'thumbnail': info.get('thumbnailUrl'), |
|||
'duration': info.get('duration'), |
|||
'timestamp': info.get('createdAt'), |
|||
'uploader_id': info.get('userId'), |
|||
'view_count': info.get('plays'), |
|||
} |
@ -0,0 +1,85 @@ |
|||
# coding: utf-8 |
|||
from __future__ import unicode_literals |
|||
|
|||
from .common import InfoExtractor |
|||
from ..utils import ( |
|||
unified_strdate, |
|||
int_or_none, |
|||
qualities, |
|||
) |
|||
|
|||
|
|||
class OdnoklassnikiIE(InfoExtractor): |
|||
_VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)' |
|||
_TESTS = [{ |
|||
'url': 'http://ok.ru/video/20079905452', |
|||
'md5': '8e24ad2da6f387948e7a7d44eb8668fe', |
|||
'info_dict': { |
|||
'id': '20079905452', |
|||
'ext': 'mp4', |
|||
'title': 'Культура меняет нас (прекрасный ролик!))', |
|||
'duration': 100, |
|||
'upload_date': '20141207', |
|||
'uploader_id': '330537914540', |
|||
'uploader': 'Виталий Добровольский', |
|||
'like_count': int, |
|||
'age_limit': 0, |
|||
}, |
|||
}, { |
|||
'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', |
|||
'only_matching': True, |
|||
}] |
|||
|
|||
def _real_extract(self, url): |
|||
video_id = self._match_id(url) |
|||
|
|||
webpage = self._download_webpage(url, video_id) |
|||
|
|||
player = self._parse_json( |
|||
self._search_regex( |
|||
r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'), |
|||
video_id) |
|||
|
|||
metadata = self._parse_json(player['flashvars']['metadata'], video_id) |
|||
|
|||
movie = metadata['movie'] |
|||
title = movie['title'] |
|||
thumbnail = movie.get('poster') |
|||
duration = int_or_none(movie.get('duration')) |
|||
|
|||
author = metadata.get('author', {}) |
|||
uploader_id = author.get('id') |
|||
uploader = author.get('name') |
|||
|
|||
upload_date = unified_strdate(self._html_search_meta( |
|||
'ya:ovs:upload_date', webpage, 'upload date')) |
|||
|
|||
age_limit = None |
|||
adult = self._html_search_meta( |
|||
'ya:ovs:adult', webpage, 'age limit') |
|||
if adult: |
|||
age_limit = 18 if adult == 'true' else 0 |
|||
|
|||
like_count = int_or_none(metadata.get('likeCount')) |
|||
|
|||
quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd')) |
|||
|
|||
formats = [{ |
|||
'url': f['url'], |
|||
'ext': 'mp4', |
|||
'format_id': f['name'], |
|||
'quality': quality(f['name']), |
|||
} for f in metadata['videos']] |
|||
|
|||
return { |
|||
'id': video_id, |
|||
'title': title, |
|||
'thumbnail': thumbnail, |
|||
'duration': duration, |
|||
'upload_date': upload_date, |
|||
'uploader': uploader, |
|||
'uploader_id': uploader_id, |
|||
'like_count': like_count, |
|||
'age_limit': age_limit, |
|||
'formats': formats, |
|||
} |
@ -0,0 +1,88 @@ |
|||
# -*- coding: utf-8 -*- |
|||
from __future__ import unicode_literals |
|||
|
|||
from .common import InfoExtractor |
|||
from ..utils import ( |
|||
ExtractorError, |
|||
unified_strdate, |
|||
int_or_none, |
|||
) |
|||
|
|||
|
|||
class Puls4IE(InfoExtractor): |
|||
_VALID_URL = r'https?://(?:www\.)?puls4\.com/video/[^/]+/play/(?P<id>[0-9]+)' |
|||
_TESTS = [{ |
|||
'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816', |
|||
'md5': '49f6a6629747eeec43cef6a46b5df81d', |
|||
'info_dict': { |
|||
'id': '2716816', |
|||
'ext': 'mp4', |
|||
'title': 'Pro und Contra vom 23.02.2015', |
|||
'description': 'md5:293e44634d9477a67122489994675db6', |
|||
'duration': 2989, |
|||
'upload_date': '20150224', |
|||
'uploader': 'PULS_4', |
|||
}, |
|||
'skip': 'Only works from Germany', |
|||
}, { |
|||
'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106', |
|||
'md5': '6a48316c8903ece8dab9b9a7bf7a59ec', |
|||
'info_dict': { |
|||
'id': '1298106', |
|||
'ext': 'mp4', |
|||
'title': 'Lucky Fritz', |
|||
}, |
|||
'skip': 'Only works from Germany', |
|||
}] |
|||
|
|||
def _real_extract(self, url): |
|||
video_id = self._match_id(url) |
|||
webpage = self._download_webpage(url, video_id) |
|||
|
|||
error_message = self._html_search_regex( |
|||
r'<div class="message-error">(.+?)</div>', |
|||
webpage, 'error message', default=None) |
|||
if error_message: |
|||
raise ExtractorError( |
|||
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True) |
|||
|
|||
real_url = self._html_search_regex( |
|||
r'\"fsk-button\".+?href=\"([^"]+)', |
|||
webpage, 'fsk_button', default=None) |
|||
if real_url: |
|||
webpage = self._download_webpage(real_url, video_id) |
|||
|
|||
player = self._search_regex( |
|||
r'p4_video_player(?:_iframe)?\("video_\d+_container"\s*,(.+?)\);\s*\}', |
|||
webpage, 'player') |
|||
|
|||
player_json = self._parse_json( |
|||
'[%s]' % player, video_id, |
|||
transform_source=lambda s: s.replace('undefined,', '')) |
|||
|
|||
formats = None |
|||
result = None |
|||
|
|||
for v in player_json: |
|||
if isinstance(v, list) and not formats: |
|||
formats = [{ |
|||
'url': f['url'], |
|||
'format': 'hd' if f.get('hd') else 'sd', |
|||
'width': int_or_none(f.get('size_x')), |
|||
'height': int_or_none(f.get('size_y')), |
|||
'tbr': int_or_none(f.get('bitrate')), |
|||
} for f in v] |
|||
self._sort_formats(formats) |
|||
elif isinstance(v, dict) and not result: |
|||
result = { |
|||
'id': video_id, |
|||
'title': v['videopartname'].strip(), |
|||
'description': v.get('videotitle'), |
|||
'duration': int_or_none(v.get('videoduration') or v.get('episodeduration')), |
|||
'upload_date': unified_strdate(v.get('clipreleasetime')), |
|||
'uploader': v.get('channel'), |
|||
} |
|||
|
|||
result['formats'] = formats |
|||
|
|||
return result |
Write
Preview
Loading…
Cancel
Save