midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[limelight] remove disabled API requests(closes #24255)

Browse source
This commit is contained in:
Remita Amine 2020-03-23 12:57:10 +01:00
parent a6c5859d6b
commit 2e20cb3636
4 changed files with 59 additions and 86 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

125
youtube_dl/extractor/limelight.py
View file

@ -18,7 +18,6 @@ from ..utils import (
class LimelightBaseIE(InfoExtractor): class LimelightBaseIE(InfoExtractor):
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
_API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
@classmethod @classmethod
def _extract_urls(cls, webpage, source_url): def _extract_urls(cls, webpage, source_url):
@ -70,7 +69,8 @@ class LimelightBaseIE(InfoExtractor):
try: try:
return self._download_json( return self._download_json(
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) item_id, 'Downloading PlaylistService %s JSON' % method,
fatal=fatal, headers=headers)
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
@ -79,22 +79,22 @@ class LimelightBaseIE(InfoExtractor):
raise ExtractorError(error, expected=True) raise ExtractorError(error, expected=True)
raise raise
def _call_api(self, organization_id, item_id, method): def _extract(self, item_id, pc_method, mobile_method, referer=None):
return self._download_json(
self._API_URL % (organization_id, self._API_PATH, item_id, method),
item_id, 'Downloading API %s JSON' % method)
def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
pc = self._call_playlist_service(item_id, pc_method, referer=referer) pc = self._call_playlist_service(item_id, pc_method, referer=referer)
metadata = self._call_api(pc['orgId'], item_id, meta_method) mobile = self._call_playlist_service(
mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) item_id, mobile_method, fatal=False, referer=referer)
return pc, mobile, metadata return pc, mobile
def _extract_info(self, pc, mobile, i, referer):
get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
pc_item = get_item(pc, 'playlistItems')
mobile_item = get_item(mobile, 'mediaList')
video_id = pc_item.get('mediaId') or mobile_item['mediaId']
title = pc_item.get('title') or mobile_item['title']
def _extract_info(self, streams, mobile_urls, properties):
video_id = properties['media_id']
formats = [] formats = []
urls = [] urls = []
for stream in streams: for stream in pc_item.get('streams', []):
stream_url = stream.get('url') stream_url = stream.get('url')
if not stream_url or stream.get('drmProtected') or stream_url in urls: if not stream_url or stream.get('drmProtected') or stream_url in urls:
continue continue
@ -155,7 +155,7 @@ class LimelightBaseIE(InfoExtractor):
}) })
formats.append(fmt) formats.append(fmt)
for mobile_url in mobile_urls: for mobile_url in mobile_item.get('mobileUrls', []):
media_url = mobile_url.get('mobileUrl') media_url = mobile_url.get('mobileUrl')
format_id = mobile_url.get('targetMediaPlatform') format_id = mobile_url.get('targetMediaPlatform')
if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls: if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
@ -179,54 +179,34 @@ class LimelightBaseIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
title = properties['title']
description = properties.get('description')
timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date'))
duration = float_or_none(properties.get('duration_in_milliseconds'), 1000)
filesize = int_or_none(properties.get('total_storage_in_bytes'))
categories = [properties.get('category')]
tags = properties.get('tags', [])
thumbnails = [{
'url': thumbnail['url'],
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
} for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
subtitles = {} subtitles = {}
for caption in properties.get('captions', []): for flag in mobile_item.get('flags'):
lang = caption.get('language_code') if flag == 'ClosedCaptions':
subtitles_url = caption.get('url') closed_captions = self._call_playlist_service(
if lang and subtitles_url: video_id, 'getClosedCaptionsDetailsByMediaId',
subtitles.setdefault(lang, []).append({ False, referer) or []
'url': subtitles_url, for cc in closed_captions:
}) cc_url = cc.get('webvttFileUrl')
closed_captions_url = properties.get('closed_captions_url') if not cc_url:
if closed_captions_url: continue
subtitles.setdefault('en', []).append({ lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en')
'url': closed_captions_url, subtitles.setdefault(lang, []).append({
'ext': 'ttml', 'url': cc_url,
}) })
break
get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': get_meta('description'),
'formats': formats, 'formats': formats,
'timestamp': timestamp, 'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
'duration': duration, 'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
'filesize': filesize,
'categories': categories,
'tags': tags,
'thumbnails': thumbnails,
'subtitles': subtitles, 'subtitles': subtitles,
} }
def _extract_info_helper(self, pc, mobile, i, metadata):
return self._extract_info(
try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
metadata)
class LimelightMediaIE(LimelightBaseIE): class LimelightMediaIE(LimelightBaseIE):
IE_NAME = 'limelight' IE_NAME = 'limelight'
@ -251,8 +231,6 @@ class LimelightMediaIE(LimelightBaseIE):
'description': 'md5:8005b944181778e313d95c1237ddb640', 'description': 'md5:8005b944181778e313d95c1237ddb640',
'thumbnail': r're:^https?://.*\.jpeg$', 'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 144.23, 'duration': 144.23,
'timestamp': 1244136834,
'upload_date': '20090604',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -268,30 +246,29 @@ class LimelightMediaIE(LimelightBaseIE):
'title': '3Play Media Overview Video', 'title': '3Play Media Overview Video',
'thumbnail': r're:^https?://.*\.jpeg$', 'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 78.101, 'duration': 78.101,
'timestamp': 1338929955, # TODO: extract all languages that were accessible via API
'upload_date': '20120605', # 'subtitles': 'mincount:9',
'subtitles': 'mincount:9', 'subtitles': 'mincount:1',
}, },
}, { }, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452', 'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
'only_matching': True, 'only_matching': True,
}] }]
_PLAYLIST_SERVICE_PATH = 'media' _PLAYLIST_SERVICE_PATH = 'media'
_API_PATH = 'media'
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url) video_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
self._initialize_geo_bypass({ self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'), 'countries': smuggled_data.get('geo_countries'),
}) })
pc, mobile, metadata = self._extract( pc, mobile = self._extract(
video_id, 'getPlaylistByMediaId', video_id, 'getPlaylistByMediaId',
'getMobilePlaylistByMediaId', 'properties', 'getMobilePlaylistByMediaId', source_url)
smuggled_data.get('source_url'))
return self._extract_info_helper(pc, mobile, 0, metadata) return self._extract_info(pc, mobile, 0, source_url)
class LimelightChannelIE(LimelightBaseIE): class LimelightChannelIE(LimelightBaseIE):
@ -313,6 +290,7 @@ class LimelightChannelIE(LimelightBaseIE):
'info_dict': { 'info_dict': {
'id': 'ab6a524c379342f9b23642917020c082', 'id': 'ab6a524c379342f9b23642917020c082',
'title': 'Javascript Sample Code', 'title': 'Javascript Sample Code',
'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
}, },
'playlist_mincount': 3, 'playlist_mincount': 3,
}, { }, {
@ -320,22 +298,23 @@ class LimelightChannelIE(LimelightBaseIE):
'only_matching': True, 'only_matching': True,
}] }]
_PLAYLIST_SERVICE_PATH = 'channel' _PLAYLIST_SERVICE_PATH = 'channel'
_API_PATH = 'channels'
def _real_extract(self, url): def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {}) url, smuggled_data = unsmuggle_url(url, {})
channel_id = self._match_id(url) channel_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
pc, mobile, medias = self._extract( pc, mobile = self._extract(
channel_id, 'getPlaylistByChannelId', channel_id, 'getPlaylistByChannelId',
'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
'media', smuggled_data.get('source_url')) source_url)
entries = [ entries = [
self._extract_info_helper(pc, mobile, i, medias['media_list'][i]) self._extract_info(pc, mobile, i, source_url)
for i in range(len(medias['media_list']))] for i in range(len(pc['playlistItems']))]
return self.playlist_result(entries, channel_id, pc['title']) return self.playlist_result(
entries, channel_id, pc.get('title'), mobile.get('description'))
class LimelightChannelListIE(LimelightBaseIE): class LimelightChannelListIE(LimelightBaseIE):
@ -368,10 +347,12 @@ class LimelightChannelListIE(LimelightBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
channel_list_id = self._match_id(url) channel_list_id = self._match_id(url)
channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById') channel_list = self._call_playlist_service(
channel_list_id, 'getMobileChannelListById')
entries = [ entries = [
self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel') self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel')
for channel in channel_list['channelList']] for channel in channel_list['channelList']]
return self.playlist_result(entries, channel_list_id, channel_list['title']) return self.playlist_result(
entries, channel_list_id, channel_list['title'])

12
youtube_dl/extractor/pokemon.py
View file

@ -20,20 +20,16 @@ class PokemonIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Ol’ Raise and Switch!', 'title': 'The Ol’ Raise and Switch!',
'description': 'md5:7db77f7107f98ba88401d3adc80ff7af', 'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
'timestamp': 1511824728,
'upload_date': '20171127',
}, },
'add_id': ['LimelightMedia'], 'add_id': ['LimelightMedia'],
}, { }, {
# no data-video-title # no data-video-title
'url': 'https://www.pokemon.com/us/pokemon-episodes/pokemon-movies/pokemon-the-rise-of-darkrai-2008', 'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
'info_dict': { 'info_dict': {
'id': '99f3bae270bf4e5097274817239ce9c8', 'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Pokémon: The Rise of Darkrai', 'title': "Pokémon : L'ascension de Darkrai",
'description': 'md5:ea8fbbf942e1e497d54b19025dd57d9d', 'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
'timestamp': 1417778347,
'upload_date': '20141205',
}, },
'add_id': ['LimelightMedia'], 'add_id': ['LimelightMedia'],
'params': { 'params': {

2
youtube_dl/extractor/telequebec.py
View file

@ -38,8 +38,6 @@ class TeleQuebecIE(TeleQuebecBaseIE):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Un petit choc et puis repart!', 'title': 'Un petit choc et puis repart!',
'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374', 'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
'upload_date': '20180222',
'timestamp': 1519326631,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,

6
youtube_dl/extractor/tfo.py
View file

@ -17,14 +17,12 @@ class TFOIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon', 'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
'md5': '47c987d0515561114cf03d1226a9d4c7', 'md5': 'cafbe4f47a8dae0ca0159937878100d6',
'info_dict': { 'info_dict': {
'id': '100463871', 'id': '7da3d50e495c406b8fc0b997659cc075',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Video Game Hackathon', 'title': 'Video Game Hackathon',
'description': 'md5:558afeba217c6c8d96c60e5421795c07', 'description': 'md5:558afeba217c6c8d96c60e5421795c07',
'upload_date': '20160212',
'timestamp': 1455310233,
} }
} }