Compare commits
12 Commits
12509f2df1
...
2383b69870
Author | SHA1 | Date |
---|---|---|
Nick Lai | 2383b69870 | |
dirkf | 668332b973 | |
dirkf | 0b2ce3685e | |
dirkf | c2766cb80e | |
dirkf | eb38665438 | |
dirkf | e0727e4ab6 | |
Ori Avtalion | 4ea59c6107 | |
Nick Lai | 5e7738a0df | |
Nick Lai | 67db51cdfe | |
Nick Lai | 292be92987 | |
Nick Lai | 5416301787 | |
Nick Lai | 05698ebf9b |
|
@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
gettestcases,
|
||||
|
@ -122,7 +123,10 @@ def generator(test_case, tname):
|
|||
params['outtmpl'] = tname + '_' + params['outtmpl']
|
||||
if is_playlist and 'playlist' not in test_case:
|
||||
params.setdefault('extract_flat', 'in_playlist')
|
||||
params.setdefault('playlistend', test_case.get('playlist_mincount'))
|
||||
params.setdefault('playlistend',
|
||||
test_case['playlist_maxcount'] + 1
|
||||
if test_case.get('playlist_maxcount')
|
||||
else test_case.get('playlist_mincount'))
|
||||
params.setdefault('skip_download', True)
|
||||
|
||||
ydl = YoutubeDL(params, auto_init=False)
|
||||
|
@ -190,6 +194,14 @@ def generator(test_case, tname):
|
|||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_maxcount' in test_case:
|
||||
assertLessEqual(
|
||||
self,
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_maxcount'],
|
||||
'Expected at most %d in playlist %s, but got %d' % (
|
||||
test_case['playlist_maxcount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_count' in test_case:
|
||||
self.assertEqual(
|
||||
len(res_dict['entries']),
|
||||
|
|
|
@ -688,6 +688,10 @@ from .metacritic import MetacriticIE
|
|||
from .mgoon import MgoonIE
|
||||
from .mgtv import MGTVIE
|
||||
from .miaopai import MiaoPaiIE
|
||||
from .microsoftstream import (
|
||||
MicrosoftStreamIE,
|
||||
MicrosoftStreamChannelIE
|
||||
)
|
||||
from .microsoftvirtualacademy import (
|
||||
MicrosoftVirtualAcademyIE,
|
||||
MicrosoftVirtualAcademyCourseIE,
|
||||
|
@ -1653,7 +1657,15 @@ from .younow import (
|
|||
YouNowChannelIE,
|
||||
YouNowMomentIE,
|
||||
)
|
||||
from .youporn import YouPornIE
|
||||
from .youporn import (
|
||||
YouPornIE,
|
||||
YouPornCategoryIE,
|
||||
YouPornChannelIE,
|
||||
YouPornCollectionIE,
|
||||
YouPornStarIE,
|
||||
YouPornTagIE,
|
||||
YouPornVideosIE,
|
||||
)
|
||||
from .yourporn import YourPornIE
|
||||
from .yourupload import YourUploadIE
|
||||
from .youtube import (
|
||||
|
|
|
@ -0,0 +1,317 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (ExtractorError, update_url_query, merge_dicts)
|
||||
|
||||
|
||||
class MicrosoftStreamBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'https://web.microsoftstream.com/?noSignUpCheck=1' # expect redirection
|
||||
_ACCESS_TOKEN = None # A JWT token
|
||||
_API_GATEWAY = None
|
||||
|
||||
def is_logged_in(self, webpage):
|
||||
"""
|
||||
This test is based on the fact that Microsoft Stream will redirect unauthenticated users
|
||||
"""
|
||||
return '<title>Microsoft Stream</title>' in webpage
|
||||
|
||||
def _real_initialize(self):
|
||||
username, password = self._get_login_info()
|
||||
|
||||
if username is not None or password is not None:
|
||||
raise ExtractorError('MicrosoftStream Extractor does not support username/password log-in at the moment. Please use cookies log-in instead. See https://github.com/ytdl-org/youtube-dl/blob/master/README.md#how-do-i-pass-cookies-to-youtube-dl for more information')
|
||||
|
||||
"""
|
||||
Extraction Helper
|
||||
"""
|
||||
|
||||
def _extract_access_token(self, webpage):
|
||||
"""
|
||||
Extract the JWT access token with Regex
|
||||
"""
|
||||
self._ACCESS_TOKEN = self._html_search_regex(r"\"AccessToken\":\"(?P<AccessToken>.+?)\"", webpage, 'AccessToken')
|
||||
return self._ACCESS_TOKEN
|
||||
|
||||
def _extract_api_gateway(self, webpage):
|
||||
"""
|
||||
Extract the API gateway with Regex
|
||||
"""
|
||||
self._API_GATEWAY = self._html_search_regex(r"\"ApiGatewayUri\":\"(?P<APIGateway>.+?)\"", webpage, 'APIGateway')
|
||||
return self._API_GATEWAY
|
||||
|
||||
"""
|
||||
Common getters
|
||||
"""
|
||||
@property
|
||||
def api_gateway(self):
|
||||
"""
|
||||
Return the start of an API endoint, like "https://aaea-1.api.microsoftstream.com/api/"
|
||||
"""
|
||||
if self._API_GATEWAY is None:
|
||||
raise ExtractorError('API gateway is None. Did you forget to call "_extract_api_gateway"?')
|
||||
return self._API_GATEWAY
|
||||
|
||||
@property
|
||||
def access_token(self):
|
||||
if self._ACCESS_TOKEN is None:
|
||||
raise ExtractorError('Access token is None. Did you forget to call "_extract_access_token"?')
|
||||
return self._ACCESS_TOKEN
|
||||
|
||||
@property
|
||||
def headers(self):
|
||||
return {'Authorization': 'Bearer %s' % self.access_token}
|
||||
|
||||
"""
|
||||
Utils function
|
||||
"""
|
||||
|
||||
def _determine_protocol(self, mime):
|
||||
"""
|
||||
A switch board for the MIME type provided from the API endpoint.
|
||||
"""
|
||||
if mime in ['application/dash+xml']:
|
||||
return 'http_dash_segments'
|
||||
elif mime in ['application/vnd.apple.mpegurl']:
|
||||
return 'm3u8'
|
||||
else:
|
||||
return None
|
||||
|
||||
"""
|
||||
Remapper
|
||||
|
||||
Remap data into correct field
|
||||
"""
|
||||
|
||||
def _remap_thumbnails(self, thumbnail_dict_list):
|
||||
output = []
|
||||
preference_index = ['extraSmall', 'small', 'medium', 'large']
|
||||
|
||||
for _, key in enumerate(thumbnail_dict_list):
|
||||
output.append({
|
||||
'preference': preference_index.index(key),
|
||||
'url': thumbnail_dict_list.get(key).get('url')
|
||||
})
|
||||
return output
|
||||
|
||||
def _remap_playback(self, master_playlist_urls, video_id=None):
|
||||
"""
|
||||
A parser for the HLS and MPD playlists from the API endpoint.
|
||||
"""
|
||||
output = []
|
||||
|
||||
for master_playlist_url in master_playlist_urls:
|
||||
protocol = self._determine_protocol(master_playlist_url['mimeType'])
|
||||
# Handle HLS Master playlist
|
||||
if protocol == 'm3u8':
|
||||
varient_playlists = self._extract_m3u8_formats(master_playlist_url['playbackUrl'], video_id=video_id, headers=self.headers)
|
||||
|
||||
# For MPEG-DASH Master playlists
|
||||
elif protocol == 'http_dash_segments':
|
||||
varient_playlists = self._extract_mpd_formats(master_playlist_url['playbackUrl'], video_id=video_id, headers=self.headers)
|
||||
|
||||
# For other Master playlists (like Microsoft Smooth Streaming)
|
||||
else:
|
||||
self.to_screen('Found unresolvable stream with format: %s' % master_playlist_url['mimeType'])
|
||||
continue
|
||||
|
||||
# Patching the "Authorization" header
|
||||
for varient_playlist in varient_playlists:
|
||||
varient_playlist['http_headers'] = self.headers
|
||||
output.append(varient_playlist)
|
||||
return output
|
||||
|
||||
def _remap_subtitle(self, tracks, video_id, is_auto_generated):
|
||||
"""
|
||||
An internal method for filtering and remapping text tracks
|
||||
"""
|
||||
if type(is_auto_generated) is not bool:
|
||||
raise ExtractorError('Unexpected variable "is_auto_generated" type: must be a Boolean')
|
||||
|
||||
subtitle_subset = {}
|
||||
|
||||
for track in tracks:
|
||||
track_language = track.get('language') # The track language must have a language code.
|
||||
|
||||
if track.get('autoGenerated') is is_auto_generated:
|
||||
if track_language not in subtitle_subset:
|
||||
subtitle_subset[track_language] = [] # Scaffold an empty list for the object to insert into
|
||||
|
||||
# Since the subtitle is token protected, a get request will fire here.
|
||||
data = self._download_webpage(url_or_request=track.get('url'), video_id=video_id, headers=self.headers)
|
||||
subtitle_subset[track_language].append({'data': data, "ext": "vtt"})
|
||||
|
||||
return subtitle_subset
|
||||
|
||||
def _remap_video(self, video):
|
||||
return {
|
||||
'id': video['id'],
|
||||
'title': video['name'],
|
||||
'description': video.get('description'),
|
||||
'uploader': video.get('creator').get('name'),
|
||||
'thumbnails': self._remap_thumbnails(video.get('posterImage') or []),
|
||||
'formats': self._remap_playback(video['playbackUrls'], video_id=video['id']),
|
||||
'is_live': False
|
||||
}
|
||||
"""
|
||||
Formatter
|
||||
"""
|
||||
|
||||
def _format_texttrack_endpoint(self, video_id):
|
||||
return "%s/videos/%s/texttracks?api-version=1.4-private" % (self.api_gateway, video_id)
|
||||
|
||||
def _request_texttracks(self, video_id):
|
||||
"""
|
||||
Make an additional request to Microsoft Stream for the subtitle and auto-caption
|
||||
"""
|
||||
self._TEXTTRACKS_RESPONSE = self._download_json(self._format_texttrack_endpoint(video_id), video_id, headers=self.headers).get('value')
|
||||
return self._TEXTTRACKS_RESPONSE
|
||||
|
||||
|
||||
class MicrosoftStreamIE(MicrosoftStreamBaseIE):
|
||||
"""
|
||||
Extractor for single Microsoft Stream video
|
||||
"""
|
||||
IE_NAME = 'microsoftstream'
|
||||
_VALID_URL = r'https?://(?:(?:web|www)\.)?microsoftstream\.com/video/(?P<id>[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})' # https://regex101.com/r/K1mlgK/1/
|
||||
_NETRC_MACHINE = 'microsoftstream'
|
||||
_TEXTTRACKS_RESPONSE = None
|
||||
_VIDEO_ID = None
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://web.microsoftstream.com/video/c883c6a5-9895-4900-9a35-62f4b5d506c9',
|
||||
'info_dict': {
|
||||
'id': 'c883c6a5-9895-4900-9a35-62f4b5d506c9',
|
||||
'ext': 'mp4',
|
||||
'title': 'Webinar for Researchers: Use of GitLab',
|
||||
'thumbnail': r're:^https?://.*$'
|
||||
},
|
||||
'skip': 'Requires Microsoft 365 account credentials',
|
||||
}, {
|
||||
'url': 'https://www.microsoftstream.com/video/1541f3f9-7fed-4901-ae70-0f7cb775679f',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
"""
|
||||
Getters
|
||||
|
||||
The following getters include helpful message to prompt developers for potential errors.
|
||||
"""
|
||||
|
||||
@property
|
||||
def video_id(self):
|
||||
if self._VIDEO_ID is None:
|
||||
raise('Variable "_VIDEO_ID" is not defined. Did you make the main extraction call?')
|
||||
return self._VIDEO_ID
|
||||
|
||||
@property
|
||||
def media_info_endpoint(self):
|
||||
return "%s/videos/%s?$expand=creator,tokens,status,liveEvent,extensions&api-version=1.4-private" % (self.api_gateway, self.video_id)
|
||||
|
||||
def _get_subtitles(self, tracks=None): # Fulfill abstract method
|
||||
tracks = self._TEXTTRACKS_RESPONSE if tracks is None else tracks
|
||||
return self._remap_subtitle(tracks, is_auto_generated=False, video_id=self.video_id)
|
||||
|
||||
def _get_automatic_captions(self, tracks=None): # Fulfill abstract method
|
||||
tracks = self._TEXTTRACKS_RESPONSE if tracks is None else tracks
|
||||
return self._remap_subtitle(tracks, is_auto_generated=True, video_id=self.video_id)
|
||||
|
||||
def _real_extract(self, url):
|
||||
self._VIDEO_ID = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, self.video_id)
|
||||
if not self.is_logged_in(webpage):
|
||||
return self.raise_login_required()
|
||||
|
||||
# Extract access token from webpage
|
||||
self._extract_access_token(webpage)
|
||||
self._extract_api_gateway(webpage)
|
||||
|
||||
# "GET" api for video information
|
||||
video = self._download_json(self.media_info_endpoint, self.video_id, headers=self.headers)
|
||||
texttracks = self._request_texttracks(self.video_id)
|
||||
|
||||
return merge_dicts(self._remap_video(video), {
|
||||
'subtitles': self._get_subtitles(texttracks),
|
||||
'automatic_captions': self._get_automatic_captions(texttracks),
|
||||
})
|
||||
|
||||
|
||||
class MicrosoftStreamChannelIE(MicrosoftStreamBaseIE):
|
||||
"""
|
||||
Extractor for single channel of Microsoft Stream video
|
||||
"""
|
||||
IE_NAME = 'microsoftstream:channel'
|
||||
_VALID_URL = r'https?://(?:(?:web|www)\.)?microsoftstream\.com/channel/(?P<id>[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})' # https://regex101.com/r/K1mlgK/1/
|
||||
_NETRC_MACHINE = 'microsoftstream'
|
||||
_CHANNEL_ID = None
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://web.microsoftstream.com/channel/c883c6a5-9895-4900-9a35-62f4b5d506c9',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.microsoftstream.com/channel/0ceffe58-07b1-4098-8ed9-a15f4e8231f7',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _format_channel_video_endpoint(self, skip=0, top=100):
|
||||
parameters = {
|
||||
'$top': top,
|
||||
'$skip': skip,
|
||||
'$expand': 'creator,events',
|
||||
'$orderby': 'created asc',
|
||||
'api-version': '1.4-private'
|
||||
}
|
||||
|
||||
return update_url_query('%schannels/%s/videos' % (self.api_gateway, self._CHANNEL_ID), parameters)
|
||||
|
||||
def _iterate_video(self, video):
|
||||
subtitle_dict = {}
|
||||
|
||||
if (self._downloader.params.get('writesubtitles', False)
|
||||
or self._downloader.params.get('writeautomaticsub', False)
|
||||
or self._downloader.params.get('listsubtitles')):
|
||||
texttracks = self._request_texttracks(video['id'])
|
||||
|
||||
if (self._downloader.params.get('writesubtitles', False)
|
||||
or self._downloader.params.get('listsubtitles')):
|
||||
subtitle_dict['subtitles'] = self._remap_subtitle(texttracks, video_id=video['id'], is_auto_generated=False)
|
||||
|
||||
if (self._downloader.params.get('writeautomaticsub', False)
|
||||
or self._downloader.params.get('listsubtitles')):
|
||||
subtitle_dict['automatic_captions'] = self._remap_subtitle(texttracks, video_id=video['id'], is_auto_generated=False)
|
||||
|
||||
return merge_dicts(self._remap_video(video), subtitle_dict)
|
||||
|
||||
def _fetch_video(self):
|
||||
found_all_video = False
|
||||
current_skip = 0
|
||||
top = 100
|
||||
all_video = []
|
||||
|
||||
while found_all_video is False:
|
||||
video_info_endpoint = self._format_channel_video_endpoint(current_skip, top)
|
||||
channel_video_subset = self._download_json(video_info_endpoint, self._CHANNEL_ID, headers=self.headers)['value']
|
||||
|
||||
for video in channel_video_subset:
|
||||
all_video.append(self._iterate_video(video)) # Remap the video
|
||||
|
||||
found_all_video = bool(len(channel_video_subset) < top) # Break out from the iteration if all content is downloaded.
|
||||
current_skip += top # Adjust starting position
|
||||
|
||||
return all_video
|
||||
|
||||
def _real_extract(self, url):
|
||||
self._CHANNEL_ID = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, self._CHANNEL_ID)
|
||||
if not self.is_logged_in(webpage):
|
||||
return self.raise_login_required()
|
||||
|
||||
# Extract access token from webpage
|
||||
self._extract_access_token(webpage)
|
||||
self._extract_api_gateway(webpage)
|
||||
|
||||
entries = self._fetch_video()
|
||||
|
||||
return {'_type': 'playlist',
|
||||
'entries': entries}
|
|
@ -1,20 +1,38 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
import re
|
||||
from time import sleep
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
get_element_by_class,
|
||||
get_element_by_id,
|
||||
int_or_none,
|
||||
str_to_int,
|
||||
merge_dicts,
|
||||
parse_count,
|
||||
parse_qs,
|
||||
T,
|
||||
traverse_obj,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class YouPornIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
|
||||
_VALID_URL = (
|
||||
r'youporn:(?P<id>\d+)',
|
||||
r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)
|
||||
(?:/(?:(?P<display_id>[^/?#&]+)/?)?)?(?:[#?]|$)
|
||||
'''
|
||||
)
|
||||
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)']
|
||||
_TESTS = [{
|
||||
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
'md5': '3744d24c50438cf5b6f6d59feb5055c2',
|
||||
|
@ -34,7 +52,7 @@ class YouPornIE(InfoExtractor):
|
|||
'tags': list,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'skip': 'This video has been disabled',
|
||||
'skip': 'This video has been deactivated',
|
||||
}, {
|
||||
# Unknown uploader
|
||||
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
|
||||
|
@ -66,57 +84,104 @@ class YouPornIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/',
|
||||
'info_dict': {
|
||||
'id': '16290308',
|
||||
'age_limit': 18,
|
||||
'categories': [],
|
||||
'description': None, # SEO spam using title removed
|
||||
'display_id': 'tinderspecial-trailer1',
|
||||
'duration': 298.0,
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20201123',
|
||||
'uploader': 'Ersties',
|
||||
'tags': [],
|
||||
'thumbnail': 'https://fi1.ypncdn.com/m=eaSaaTbWx/202011/23/16290308/original/3.jpg',
|
||||
'timestamp': 1606147564,
|
||||
'title': 'Tinder In Real Life',
|
||||
'view_count': int,
|
||||
}
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
|
||||
webpage)
|
||||
@classmethod
|
||||
def _extract_urls(cls, webpage):
|
||||
def yield_urls():
|
||||
for p in cls._EMBED_REGEX:
|
||||
for m in re.finditer(p, webpage):
|
||||
yield m.group('url')
|
||||
|
||||
return list(yield_urls())
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
# A different video ID (data-video-id) is hidden in the page but
|
||||
# never seems to be used
|
||||
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
|
||||
url = 'http://www.youporn.com/watch/%s' % (video_id,)
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
definitions = self._download_json(
|
||||
'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
|
||||
display_id)
|
||||
watchable = self._search_regex(
|
||||
r'''(<div\s[^>]*\bid\s*=\s*('|")?watch-container(?(2)\2|(?!-)\b)[^>]*>)''',
|
||||
webpage, 'watchability', default=None)
|
||||
if not watchable:
|
||||
msg = re.split(r'\s{4}', clean_html(get_element_by_id(
|
||||
'mainContent', webpage)) or '')[0]
|
||||
raise ExtractorError(
|
||||
('%s says: %s' % (self.IE_NAME, msg))
|
||||
if msg else 'Video unavailable: no reason found',
|
||||
expected=True)
|
||||
# internal ID ?
|
||||
# video_id = extract_attributes(watchable).get('data-video-id')
|
||||
|
||||
playervars = self._search_json(
|
||||
r'\bplayervars\s*:', webpage, 'playervars', video_id)
|
||||
|
||||
def get_fmt(x):
|
||||
v_url = url_or_none(x.get('videoUrl'))
|
||||
if v_url:
|
||||
x['videoUrl'] = v_url
|
||||
return (x['format'], x)
|
||||
|
||||
defs_by_format = dict(traverse_obj(playervars, (
|
||||
'mediaDefinitions', lambda _, v: v.get('format'), T(get_fmt))))
|
||||
|
||||
def get_format_data(f):
|
||||
if f not in defs_by_format:
|
||||
return []
|
||||
return self._download_json(
|
||||
defs_by_format[f]['videoUrl'], video_id, '{0}-formats'.format(f))
|
||||
|
||||
formats = []
|
||||
for definition in definitions:
|
||||
if not isinstance(definition, dict):
|
||||
continue
|
||||
video_url = url_or_none(definition.get('videoUrl'))
|
||||
if not video_url:
|
||||
continue
|
||||
f = {
|
||||
'url': video_url,
|
||||
'filesize': int_or_none(definition.get('videoSize')),
|
||||
}
|
||||
height = int_or_none(definition.get('quality'))
|
||||
# Try to extract only the actual master m3u8 first, avoiding the duplicate single resolution "master" m3u8s
|
||||
for hls_url in traverse_obj(
|
||||
get_format_data('hls'),
|
||||
(lambda _, v: not isinstance(v['defaultQuality'], bool), 'videoUrl'),
|
||||
(Ellipsis, 'videoUrl')):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls',
|
||||
entry_protocol='m3u8_native'))
|
||||
|
||||
for f in traverse_obj(get_format_data('mp4'), (
|
||||
lambda _, v: v.get('videoUrl'), {
|
||||
'url': ('videoUrl', T(url_or_none)),
|
||||
'filesize': ('videoSize', T(int_or_none)),
|
||||
'height': ('quality', T(int_or_none)),
|
||||
}, T(lambda x: x.get('videoUrl') and x))):
|
||||
# Video URL's path looks like this:
|
||||
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
|
||||
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
|
||||
# We will benefit from it by extracting some metadata
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
|
||||
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', f['videoUrl'])
|
||||
if mobj:
|
||||
if not height:
|
||||
height = int(mobj.group('height'))
|
||||
bitrate = int(mobj.group('bitrate'))
|
||||
f.update({
|
||||
'format_id': '%dp-%dk' % (height, bitrate),
|
||||
'tbr': bitrate,
|
||||
})
|
||||
f['height'] = height
|
||||
if not f.get('height'):
|
||||
f['height'] = int(mobj.group('height'))
|
||||
f['tbr'] = int(mobj.group('bitrate'))
|
||||
f['format_id'] = '%dp-%dk' % (f['height'], f['tbr'])
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://www.youporn.com/watch/%s' % video_id, display_id,
|
||||
headers={'Cookie': 'age_verified=1'})
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
|
||||
webpage, 'title', default=None) or self._og_search_title(
|
||||
|
@ -131,8 +196,10 @@ class YouPornIE(InfoExtractor):
|
|||
thumbnail = self._search_regex(
|
||||
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
|
||||
webpage, 'thumbnail', fatal=False, group='thumbnail')
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'duration', fatal=False))
|
||||
duration = traverse_obj(playervars, ('duration', T(int_or_none)))
|
||||
if duration is None:
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'duration', fatal=False))
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
|
||||
|
@ -148,11 +215,11 @@ class YouPornIE(InfoExtractor):
|
|||
|
||||
view_count = None
|
||||
views = self._search_regex(
|
||||
r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
|
||||
'views', default=None)
|
||||
r'(<div\s[^>]*\bdata-value\s*=[^>]+>)\s*<label>Views:</label>',
|
||||
webpage, 'views', default=None)
|
||||
if views:
|
||||
view_count = str_to_int(extract_attributes(views).get('data-value'))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
view_count = parse_count(extract_attributes(views).get('data-value'))
|
||||
comment_count = parse_count(self._search_regex(
|
||||
r'>All [Cc]omments? \(([\d,.]+)\)',
|
||||
webpage, 'comment count', default=None))
|
||||
|
||||
|
@ -168,7 +235,10 @@ class YouPornIE(InfoExtractor):
|
|||
r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
|
||||
'tags')
|
||||
|
||||
return {
|
||||
data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False) or {}
|
||||
data.pop('url', None)
|
||||
|
||||
result = merge_dicts(data, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
|
@ -183,4 +253,442 @@ class YouPornIE(InfoExtractor):
|
|||
'tags': tags,
|
||||
'age_limit': age_limit,
|
||||
'formats': formats,
|
||||
}
|
||||
})
|
||||
# Remove promotional non-description
|
||||
if result.get('description', '').startswith(
|
||||
'Watch %s online' % (result['title'],)):
|
||||
del result['description']
|
||||
return result
|
||||
|
||||
|
||||
class YouPornListBase(InfoExtractor):
|
||||
# pattern in '.title-text' element of page section containing videos
|
||||
_PLAYLIST_TITLEBAR_RE = r'\s+[Vv]ideos\s*$'
|
||||
_PAGE_RETRY_COUNT = 0 # ie, no retry
|
||||
_PAGE_RETRY_DELAY = 2 # seconds
|
||||
|
||||
def _get_next_url(self, url, pl_id, html):
|
||||
return urljoin(url, self._search_regex(
|
||||
r'''<a\s[^>]*?\bhref\s*=\s*("|')(?P<url>(?:(?!\1)[^>])+)\1''',
|
||||
get_element_by_id('next', html) or '', 'next page',
|
||||
group='url', default=None))
|
||||
|
||||
@classmethod
|
||||
def _get_title_from_slug(cls, title_slug):
|
||||
return re.sub(r'[_-]', ' ', title_slug)
|
||||
|
||||
def _entries(self, url, pl_id, html=None, page_num=None):
|
||||
|
||||
# separates page sections
|
||||
PLAYLIST_SECTION_RE = (
|
||||
r'''<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?title-bar(?:\s+[\w$-]+|\s)*\1[^>]*>'''
|
||||
)
|
||||
# contains video link
|
||||
VIDEO_URL_RE = r'''(?x)
|
||||
<div\s[^>]*\bdata-video-id\s*=\s*('|")\d+\1[^>]*>\s*
|
||||
(?:<div\b[\s\S]+?</div>\s*)*
|
||||
<a\s[^>]*\bhref\s*=\s*('|")(?P<url>(?:(?!\2)[^>])+)\2
|
||||
'''
|
||||
|
||||
def yield_pages(url, html=html, page_num=page_num):
|
||||
fatal = not html
|
||||
for pnum in itertools.count(start=page_num or 1):
|
||||
if not html:
|
||||
html = self._download_webpage(
|
||||
url, pl_id, note='Downloading page %d' % pnum,
|
||||
fatal=fatal)
|
||||
if not html:
|
||||
break
|
||||
fatal = False
|
||||
yield (url, html, pnum)
|
||||
# explicit page: extract just that page
|
||||
if page_num is not None:
|
||||
break
|
||||
next_url = self._get_next_url(url, pl_id, html)
|
||||
if not next_url or next_url == url:
|
||||
break
|
||||
url, html = next_url, None
|
||||
|
||||
def retry_page(msg, tries_left, page_data):
|
||||
if tries_left <= 0:
|
||||
return
|
||||
self.report_warning(msg, pl_id)
|
||||
sleep(self._PAGE_RETRY_DELAY)
|
||||
return next(
|
||||
yield_pages(page_data[0], page_num=page_data[2]), None)
|
||||
|
||||
def yield_entries(html):
|
||||
for frag in re.split(PLAYLIST_SECTION_RE, html):
|
||||
if not frag:
|
||||
continue
|
||||
t_text = get_element_by_class('title-text', frag or '')
|
||||
if not (t_text and re.search(self._PLAYLIST_TITLEBAR_RE, t_text)):
|
||||
continue
|
||||
for m in re.finditer(VIDEO_URL_RE, frag):
|
||||
video_url = urljoin(url, m.group('url'))
|
||||
if video_url:
|
||||
yield self.url_result(video_url)
|
||||
|
||||
last_first_url = None
|
||||
for page_data in yield_pages(url, html=html, page_num=page_num):
|
||||
# page_data: url, html, page_num
|
||||
first_url = None
|
||||
tries_left = self._PAGE_RETRY_COUNT + 1
|
||||
while tries_left > 0:
|
||||
tries_left -= 1
|
||||
for from_ in yield_entries(page_data[1]):
|
||||
# may get the same page twice instead of empty page
|
||||
# or (site bug) intead of actual next page
|
||||
if not first_url:
|
||||
first_url = from_['url']
|
||||
if first_url == last_first_url:
|
||||
# sometimes (/porntags/) the site serves the previous page
|
||||
# instead but may provide the correct page after a delay
|
||||
page_data = retry_page(
|
||||
'Retrying duplicate page...', tries_left, page_data)
|
||||
if page_data:
|
||||
first_url = None
|
||||
break
|
||||
continue
|
||||
yield from_
|
||||
else:
|
||||
if not first_url and 'no-result-paragarph1' in page_data[1]:
|
||||
page_data = retry_page(
|
||||
'Retrying empty page...', tries_left, page_data)
|
||||
if page_data:
|
||||
continue
|
||||
else:
|
||||
# success/failure
|
||||
break
|
||||
# may get an infinite (?) sequence of empty pages
|
||||
if not first_url:
|
||||
break
|
||||
last_first_url = first_url
|
||||
|
||||
def _real_extract(self, url, html=None):
|
||||
# exceptionally, id may be None
|
||||
m_dict = self._match_valid_url(url).groupdict()
|
||||
pl_id, page_type, sort = (m_dict.get(k) for k in ('id', 'type', 'sort'))
|
||||
|
||||
qs = parse_qs(url)
|
||||
for q, v in qs.items():
|
||||
if v:
|
||||
qs[q] = v[-1]
|
||||
else:
|
||||
del qs[q]
|
||||
|
||||
base_id = pl_id or 'YouPorn'
|
||||
title = self._get_title_from_slug(base_id)
|
||||
if page_type:
|
||||
title = '%s %s' % (page_type.capitalize(), title)
|
||||
base_id = [base_id.lower()]
|
||||
if sort is None:
|
||||
title += ' videos'
|
||||
else:
|
||||
title = '%s videos by %s' % (title, re.sub(r'[_-]', ' ', sort))
|
||||
base_id.append(sort)
|
||||
if qs:
|
||||
ps = ['%s=%s' % item for item in sorted(qs.items())]
|
||||
title += ' (%s)' % ','.join(ps)
|
||||
base_id.extend(ps)
|
||||
pl_id = '/'.join(base_id)
|
||||
|
||||
return self.playlist_result(
|
||||
self._entries(url, pl_id, html=html,
|
||||
page_num=int_or_none(qs.get('page'))),
|
||||
playlist_id=pl_id, playlist_title=title)
|
||||
|
||||
|
||||
class YouPornCategoryIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn category, with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>category)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>popular|views|rating|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/category/lingerie/popular/',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/popular',
|
||||
'title': 'Category lingerie videos by popular',
|
||||
},
|
||||
'playlist_mincount': 39,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/category/lingerie/duration/?min_minutes=10',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/duration/min_minutes=10',
|
||||
'title': 'Category lingerie videos by duration (min_minutes=10)',
|
||||
},
|
||||
'playlist_maxcount': 30,
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/category/lingerie/popular?page=1',
|
||||
'info_dict': {
|
||||
'id': 'lingerie/popular/page=1',
|
||||
'title': 'Category lingerie videos by popular (page=1)',
|
||||
},
|
||||
'playlist_count': 30,
|
||||
}]
|
||||
|
||||
|
||||
class YouPornChannelIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn channel, with sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>channel)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/channel/x-feeds/',
|
||||
'info_dict': {
|
||||
'id': 'x-feeds',
|
||||
'title': 'Channel X-Feeds videos',
|
||||
},
|
||||
'playlist_mincount': 37,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/channel/x-feeds/duration?page=1',
|
||||
'info_dict': {
|
||||
'id': 'x-feeds/duration/page=1',
|
||||
'title': 'Channel X-Feeds videos by duration (page=1)',
|
||||
},
|
||||
'playlist_count': 24,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return re.sub(r'_', ' ', title_slug).title()
|
||||
|
||||
|
||||
class YouPornCollectionIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>collection)s/videos/(?P<id>\d+)
|
||||
(?:/(?P<sort>rating|views|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+in\s'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/collections/videos/33044251/',
|
||||
'info_dict': {
|
||||
'id': '33044251',
|
||||
'title': 'Collection Sexy Lips videos',
|
||||
'uploader': 'ph-littlewillyb',
|
||||
},
|
||||
'playlist_mincount': 50,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/collections/videos/33044251/time?page=1',
|
||||
'info_dict': {
|
||||
'id': '33044251/time/page=1',
|
||||
'title': 'Collection Sexy Lips videos by time (page=1)',
|
||||
'uploader': 'ph-littlewillyb',
|
||||
},
|
||||
'playlist_count': 20,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
pl_id = self._match_id(url)
|
||||
html = self._download_webpage(url, pl_id)
|
||||
playlist = super(YouPornCollectionIE, self)._real_extract(url, html=html)
|
||||
infos = re.sub(r'\s+', ' ', clean_html(get_element_by_class(
|
||||
'collection-infos', html)) or '')
|
||||
title, uploader = self._search_regex(
|
||||
r'^\s*Collection: (?P<title>.+?) \d+ VIDEOS \d+ VIEWS \d+ days LAST UPDATED From: (?P<uploader>[\w_-]+)',
|
||||
infos, 'title/uploader', group=('title', 'uploader'), default=(None, None))
|
||||
|
||||
return merge_dicts({
|
||||
'title': playlist['title'].replace(playlist['id'].split('/')[0], title),
|
||||
'uploader': uploader,
|
||||
}, playlist) if title else playlist
|
||||
|
||||
|
||||
class YouPornTagIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
porn(?P<type>tag)s/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>views|rating|time|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+tagged\s'
|
||||
_PAGE_RETRY_COUNT = 1
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/porntags/austrian',
|
||||
'info_dict': {
|
||||
'id': 'austrian',
|
||||
'title': 'Tag austrian videos',
|
||||
},
|
||||
'playlist_mincount': 35,
|
||||
'expected_warnings': ['Retrying duplicate page'],
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/porntags/austrian/duration/?min_minutes=10',
|
||||
'info_dict': {
|
||||
'id': 'austrian/duration/min_minutes=10',
|
||||
'title': 'Tag austrian videos by duration (min_minutes=10)',
|
||||
},
|
||||
# number of videos per page is (row x col) 2x3 + 6x4 + 2, or + 3,
|
||||
# or more, varying with number of ads; let's set max as 9x4
|
||||
# NB col 1 may not be shown in non-JS page with site CSS and zoom 100%
|
||||
'playlist_maxcount': 32,
|
||||
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/porntags/austrian/?page=1',
|
||||
'info_dict': {
|
||||
'id': 'austrian/page=1',
|
||||
'title': 'Tag austrian videos (page=1)',
|
||||
},
|
||||
'playlist_mincount': 32,
|
||||
'playlist_maxcount': 34,
|
||||
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
|
||||
}]
|
||||
|
||||
# YP tag navigation is broken, loses sort
|
||||
def _get_next_url(self, url, pl_id, html):
|
||||
next_url = super(YouPornTagIE, self)._get_next_url(url, pl_id, html)
|
||||
if next_url:
|
||||
n = self._match_valid_url(next_url)
|
||||
if n:
|
||||
s = n.groupdict().get('sort')
|
||||
if s:
|
||||
u = self._match_valid_url(url)
|
||||
if u:
|
||||
u = u.groupdict().get('sort')
|
||||
if s and not u:
|
||||
n = n.end('sort')
|
||||
next_url = next_url[:n] + '/' + u + next_url[n:]
|
||||
return next_url
|
||||
|
||||
|
||||
class YouPornStarIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?P<type>pornstar)/(?P<id>[^/?#&]+)
|
||||
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+[fF]eaturing\s'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination',
|
||||
'url': 'https://www.youporn.com/pornstar/daynia/',
|
||||
'info_dict': {
|
||||
'id': 'daynia',
|
||||
'title': 'Pornstar Daynia videos',
|
||||
'description': r're:Daynia Rank \d+ Videos \d+ Views [\d,.]+ .+ Subscribers \d+',
|
||||
},
|
||||
'playlist_mincount': 45,
|
||||
}, {
|
||||
'note': 'Single page of full list (no filters here)',
|
||||
'url': 'https://www.youporn.com/pornstar/daynia/?page=1',
|
||||
'info_dict': {
|
||||
'id': 'daynia/page=1',
|
||||
'title': 'Pornstar Daynia videos (page=1)',
|
||||
'description': 're:.{180,}',
|
||||
},
|
||||
'playlist_count': 26,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return re.sub(r'_', ' ', title_slug).title()
|
||||
|
||||
def _real_extract(self, url):
|
||||
pl_id = self._match_id(url)
|
||||
html = self._download_webpage(url, pl_id)
|
||||
playlist = super(YouPornStarIE, self)._real_extract(url, html=html)
|
||||
INFO_ELEMENT_RE = r'''(?x)
|
||||
<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?pornstar-info-wrapper(?:\s+[\w$-]+|\s)*\1[^>]*>
|
||||
(?P<info>[\s\S]+?)(?:</div>\s*){6,}
|
||||
'''
|
||||
|
||||
infos = self._search_regex(INFO_ELEMENT_RE, html, 'infos', group='info', default='')
|
||||
if infos:
|
||||
infos = re.sub(
|
||||
r'(?:\s*nl=nl)+\s*', ' ',
|
||||
re.sub(r'(?u)\s+', ' ', clean_html(
|
||||
re.sub('\n', 'nl=nl', infos)))).replace('ribe Subsc', '')
|
||||
|
||||
return merge_dicts({
|
||||
'description': infos.strip() or None,
|
||||
}, playlist)
|
||||
|
||||
|
||||
class YouPornVideosIE(YouPornListBase):
|
||||
IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?youporn\.com/
|
||||
(?:(?P<id>browse)/)?
|
||||
(?P<sort>(?(id)
|
||||
(?:duration|rating|time|views)|
|
||||
(?:most_(?:favou?rit|view)ed|recommended|top_rated)?))
|
||||
(?:[/#?]|$)
|
||||
'''
|
||||
_PLAYLIST_TITLEBAR_RE = r'\s+(?:[Vv]ideos|VIDEOS)\s*$'
|
||||
_TESTS = [{
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/',
|
||||
'info_dict': {
|
||||
'id': 'youporn',
|
||||
'title': 'YouPorn videos',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/recommended',
|
||||
'info_dict': {
|
||||
'id': 'youporn/recommended',
|
||||
'title': 'YouPorn videos by recommended',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/top_rated',
|
||||
'info_dict': {
|
||||
'id': 'youporn/top_rated',
|
||||
'title': 'YouPorn videos by top rated',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Full list with pagination (too long for test)',
|
||||
'url': 'https://www.youporn.com/browse/time',
|
||||
'info_dict': {
|
||||
'id': 'browse/time',
|
||||
'title': 'YouPorn videos by time',
|
||||
},
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with single page result',
|
||||
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=2',
|
||||
'info_dict': {
|
||||
'id': 'youporn/most_favorited/max_minutes=2/res=VR',
|
||||
'title': 'YouPorn videos by most favorited (max_minutes=2,res=VR)',
|
||||
},
|
||||
'playlist_mincount': 10,
|
||||
'playlist_maxcount': 28,
|
||||
}, {
|
||||
'note': 'Filtered paginated list with several pages',
|
||||
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=5',
|
||||
'info_dict': {
|
||||
'id': 'youporn/most_favorited/max_minutes=5/res=VR',
|
||||
'title': 'YouPorn videos by most favorited (max_minutes=5,res=VR)',
|
||||
},
|
||||
'playlist_mincount': 45,
|
||||
}, {
|
||||
'note': 'Single page of full list',
|
||||
'url': 'https://www.youporn.com/browse/time?page=1',
|
||||
'info_dict': {
|
||||
'id': 'browse/time/page=1',
|
||||
'title': 'YouPorn videos by time (page=1)',
|
||||
},
|
||||
'playlist_count': 36,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_title_from_slug(title_slug):
|
||||
return 'YouPorn' if title_slug == 'browse' else title_slug
|
||||
|
|
|
@ -74,8 +74,11 @@ class FFmpegPostProcessor(PostProcessor):
|
|||
return FFmpegPostProcessor(downloader)._versions
|
||||
|
||||
def _determine_executables(self):
|
||||
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
|
||||
# ordered to match prefer_ffmpeg!
|
||||
convs = ['ffmpeg', 'avconv']
|
||||
probes = ['ffprobe', 'avprobe']
|
||||
prefer_ffmpeg = True
|
||||
programs = convs + probes
|
||||
|
||||
def get_ffmpeg_version(path):
|
||||
ver = get_exe_version(path, args=['-version'])
|
||||
|
@ -127,10 +130,13 @@ class FFmpegPostProcessor(PostProcessor):
|
|||
(p, get_ffmpeg_version(self._paths[p])) for p in programs)
|
||||
if x[1] is not None)
|
||||
|
||||
for p in ('ffmpeg', 'avconv')[::-1 if prefer_ffmpeg is False else 1]:
|
||||
if self._versions.get(p):
|
||||
self.basename = self.probe_basename = p
|
||||
break
|
||||
basenames = [None, None]
|
||||
for i, progs in enumerate((convs, probes)):
|
||||
for p in progs[::-1 if prefer_ffmpeg is False else 1]:
|
||||
if self._versions.get(p):
|
||||
basenames[i] = p
|
||||
break
|
||||
self.basename, self.probe_basename = basenames
|
||||
|
||||
@property
|
||||
def available(self):
|
||||
|
|
|
@ -2371,15 +2371,24 @@ def make_HTTPS_handler(params, **kwargs):
|
|||
return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
|
||||
|
||||
|
||||
def bug_reports_message():
|
||||
def bug_reports_message(before=';'):
|
||||
if ytdl_is_updateable():
|
||||
update_cmd = 'type youtube-dl -U to update'
|
||||
else:
|
||||
update_cmd = 'see https://yt-dl.org/update on how to update'
|
||||
msg = '; please report this issue on https://yt-dl.org/bug .'
|
||||
msg += ' Make sure you are using the latest version; %s.' % update_cmd
|
||||
msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
|
||||
return msg
|
||||
update_cmd = 'see https://github.com/ytdl-org/youtube-dl/#user-content-installation on how to update'
|
||||
|
||||
msg = (
|
||||
'please report this issue on https://github.com/ytdl-org/youtube-dl/issues ,'
|
||||
' using the appropriate issue template.'
|
||||
' Make sure you are using the latest version; %s.'
|
||||
' Be sure to call youtube-dl with the --verbose option and include the complete output.'
|
||||
) % update_cmd
|
||||
|
||||
before = (before or '').rstrip()
|
||||
if not before or before.endswith(('.', '!', '?')):
|
||||
msg = msg[0].title() + msg[1:]
|
||||
|
||||
return (before + ' ' if before else '') + msg
|
||||
|
||||
|
||||
class YoutubeDLError(Exception):
|
||||
|
|
Loading…
Reference in New Issue