mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into pr/6698
bashonly
4 months ago
commit
cf828cc90a
@ -1,8 +1,5 @@
|
||||
blank_issues_enabled: false
|
||||
contact_links:
|
||||
- name: Get help from the community on Discord
|
||||
- name: Get help on Discord
|
||||
url: https://discord.gg/H5MNcFW63r
|
||||
about: Join the yt-dlp Discord for community-powered support!
|
||||
- name: Matrix Bridge to the Discord server
|
||||
url: https://matrix.to/#/#yt-dlp:matrix.org
|
||||
about: For those who do not want to use Discord
|
||||
about: Join the yt-dlp Discord server for support and discussion
|
||||
|
||||
@ -0,0 +1,10 @@
|
||||
from yt_dlp.extractor.common import InfoExtractor
|
||||
|
||||
|
||||
class NormalPluginIE(InfoExtractor):
|
||||
_VALID_URL = 'normal'
|
||||
REPLACED = True
|
||||
|
||||
|
||||
class _IgnoreUnderscorePluginIE(InfoExtractor):
|
||||
pass
|
||||
@ -0,0 +1,5 @@
|
||||
from yt_dlp.postprocessor.common import PostProcessor
|
||||
|
||||
|
||||
class NormalPluginPP(PostProcessor):
|
||||
REPLACED = True
|
||||
@ -0,0 +1,5 @@
|
||||
from yt_dlp.extractor.generic import GenericIE
|
||||
|
||||
|
||||
class OverrideGenericIE(GenericIE, plugin_name='override'):
|
||||
TEST_FIELD = 'override'
|
||||
@ -0,0 +1,5 @@
|
||||
from yt_dlp.extractor.generic import GenericIE
|
||||
|
||||
|
||||
class _UnderscoreOverrideGenericIE(GenericIE, plugin_name='underscore-override'):
|
||||
SECONDARY_TEST_FIELD = 'underscore-override'
|
||||
@ -0,0 +1,50 @@
|
||||
import hashlib
|
||||
import random
|
||||
import threading
|
||||
|
||||
from .common import FileDownloader
|
||||
from . import HlsFD
|
||||
from ..networking import Request
|
||||
from ..networking.exceptions import network_exceptions
|
||||
|
||||
|
||||
class BunnyCdnFD(FileDownloader):
|
||||
"""
|
||||
Downloads from BunnyCDN with required pings
|
||||
Note, this is not a part of public API, and will be removed without notice.
|
||||
DO NOT USE
|
||||
"""
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
self.to_screen(f'[{self.FD_NAME}] Downloading from BunnyCDN')
|
||||
|
||||
fd = HlsFD(self.ydl, self.params)
|
||||
|
||||
stop_event = threading.Event()
|
||||
ping_thread = threading.Thread(target=self.ping_thread, args=(stop_event,), kwargs=info_dict['_bunnycdn_ping_data'])
|
||||
ping_thread.start()
|
||||
|
||||
try:
|
||||
return fd.real_download(filename, info_dict)
|
||||
finally:
|
||||
stop_event.set()
|
||||
|
||||
def ping_thread(self, stop_event, url, headers, secret, context_id):
|
||||
# Site sends ping every 4 seconds, but this throttles the download. Pinging every 2 seconds seems to work.
|
||||
ping_interval = 2
|
||||
# Hard coded resolution as it doesn't seem to matter
|
||||
res = 1080
|
||||
paused = 'false'
|
||||
current_time = 0
|
||||
|
||||
while not stop_event.wait(ping_interval):
|
||||
current_time += ping_interval
|
||||
|
||||
time = current_time + round(random.random(), 6)
|
||||
md5_hash = hashlib.md5(f'{secret}_{context_id}_{time}_{paused}_{res}'.encode()).hexdigest()
|
||||
ping_url = f'{url}?hash={md5_hash}&time={time}&paused={paused}&resolution={res}'
|
||||
|
||||
try:
|
||||
self.ydl.urlopen(Request(ping_url, headers=headers)).read()
|
||||
except network_exceptions as e:
|
||||
self.to_screen(f'[{self.FD_NAME}] Ping failed: {e}')
|
||||
@ -0,0 +1,178 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import HEADRequest
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
parse_qs,
|
||||
smuggle_url,
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
urlhandle_detect_ext,
|
||||
)
|
||||
from ..utils.traversal import find_element, traverse_obj
|
||||
|
||||
|
||||
class BunnyCdnIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:iframe\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
|
||||
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL}[^\'"]*)[\'"]']
|
||||
_TESTS = [{
|
||||
'url': 'https://iframe.mediadelivery.net/embed/113933/e73edec1-e381-4c8b-ae73-717a140e0924',
|
||||
'info_dict': {
|
||||
'id': 'e73edec1-e381-4c8b-ae73-717a140e0924',
|
||||
'ext': 'mp4',
|
||||
'title': 'mistress morgana (3).mp4',
|
||||
'description': '',
|
||||
'timestamp': 1693251673,
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/e73edec1-e381-4c8b-ae73-717a140e0924/thumbnail\.jpg',
|
||||
'duration': 7.0,
|
||||
'upload_date': '20230828',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
'url': 'https://iframe.mediadelivery.net/play/136145/32e34c4b-0d72-437c-9abb-05e67657da34',
|
||||
'info_dict': {
|
||||
'id': '32e34c4b-0d72-437c-9abb-05e67657da34',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1691145748,
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
|
||||
'duration': 106.0,
|
||||
'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
|
||||
'upload_date': '20230804',
|
||||
'title': 'Sanela ist Teil der #arbeitsmarktkraft',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
# Stream requires activation and pings
|
||||
'url': 'https://iframe.mediadelivery.net/embed/200867/2e8545ec-509d-4571-b855-4cf0235ccd75',
|
||||
'info_dict': {
|
||||
'id': '2e8545ec-509d-4571-b855-4cf0235ccd75',
|
||||
'ext': 'mp4',
|
||||
'timestamp': 1708497752,
|
||||
'title': 'netflix part 1',
|
||||
'duration': 3959.0,
|
||||
'description': '',
|
||||
'upload_date': '20240221',
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
_WEBPAGE_TESTS = [{
|
||||
# Stream requires Referer
|
||||
'url': 'https://conword.io/',
|
||||
'info_dict': {
|
||||
'id': '3a5d863e-9cd6-447e-b6ef-e289af50b349',
|
||||
'ext': 'mp4',
|
||||
'title': 'Conword bei der Stadt Köln und Stadt Dortmund',
|
||||
'description': '',
|
||||
'upload_date': '20231031',
|
||||
'duration': 31.0,
|
||||
'thumbnail': 'https://video.watchuh.com/3a5d863e-9cd6-447e-b6ef-e289af50b349/thumbnail.jpg',
|
||||
'timestamp': 1698783879,
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
# URL requires token and expires
|
||||
'url': 'https://www.stockphotos.com/video/moscow-subway-the-train-is-arriving-at-the-park-kultury-station-10017830',
|
||||
'info_dict': {
|
||||
'id': '0b02fa20-4e8c-4140-8f87-f64d820a3386',
|
||||
'ext': 'mp4',
|
||||
'thumbnail': r're:^https?://.*\.b-cdn\.net/0b02fa20-4e8c-4140-8f87-f64d820a3386/thumbnail\.jpg',
|
||||
'title': 'Moscow subway. The train is arriving at the Park Kultury station.',
|
||||
'upload_date': '20240531',
|
||||
'duration': 18.0,
|
||||
'timestamp': 1717152269,
|
||||
'description': '',
|
||||
},
|
||||
'params': {'skip_download': True},
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def _extract_embed_urls(cls, url, webpage):
|
||||
for embed_url in super()._extract_embed_urls(url, webpage):
|
||||
yield smuggle_url(embed_url, {'Referer': url})
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
|
||||
webpage = self._download_webpage(
|
||||
f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
|
||||
headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
|
||||
query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
|
||||
|
||||
if html_title := self._html_extract_title(webpage, default=None) == '403':
|
||||
raise ExtractorError(
|
||||
'This video is inaccessible. Setting a Referer header '
|
||||
'might be required to access the video', expected=True)
|
||||
elif html_title == '404':
|
||||
raise ExtractorError('This video does not exist', expected=True)
|
||||
|
||||
headers = {'Referer': url}
|
||||
|
||||
info = traverse_obj(self._parse_html5_media_entries(url, webpage, video_id, _headers=headers), 0) or {}
|
||||
formats = info.get('formats') or []
|
||||
subtitles = info.get('subtitles') or {}
|
||||
|
||||
original_url = self._search_regex(
|
||||
r'(?:var|const|let)\s+originalUrl\s*=\s*["\']([^"\']+)["\']', webpage, 'original url', default=None)
|
||||
if url_or_none(original_url):
|
||||
urlh = self._request_webpage(
|
||||
HEADRequest(original_url), video_id=video_id, note='Checking original',
|
||||
headers=headers, fatal=False, expected_status=(403, 404))
|
||||
if urlh and urlh.status == 200:
|
||||
formats.append({
|
||||
'url': original_url,
|
||||
'format_id': 'source',
|
||||
'quality': 1,
|
||||
'http_headers': headers,
|
||||
'ext': urlhandle_detect_ext(urlh, default='mp4'),
|
||||
'filesize': int_or_none(urlh.get_header('Content-Length')),
|
||||
})
|
||||
|
||||
# MediaCage Streams require activation and pings
|
||||
src_url = self._search_regex(
|
||||
r'\.setAttribute\([\'"]src[\'"],\s*[\'"]([^\'"]+)[\'"]\)', webpage, 'src url', default=None)
|
||||
activation_url = self._search_regex(
|
||||
r'loadUrl\([\'"]([^\'"]+/activate)[\'"]', webpage, 'activation url', default=None)
|
||||
ping_url = self._search_regex(
|
||||
r'loadUrl\([\'"]([^\'"]+/ping)[\'"]', webpage, 'ping url', default=None)
|
||||
secret = traverse_obj(parse_qs(src_url), ('secret', 0))
|
||||
context_id = traverse_obj(parse_qs(src_url), ('contextId', 0))
|
||||
ping_data = {}
|
||||
if src_url and activation_url and ping_url and secret and context_id:
|
||||
self._download_webpage(
|
||||
activation_url, video_id, headers=headers, note='Downloading activation data')
|
||||
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
src_url, video_id, 'mp4', headers=headers, m3u8_id='hls', fatal=False)
|
||||
for fmt in fmts:
|
||||
fmt.update({
|
||||
'protocol': 'bunnycdn',
|
||||
'http_headers': headers,
|
||||
})
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
|
||||
ping_data = {
|
||||
'_bunnycdn_ping_data': {
|
||||
'url': ping_url,
|
||||
'headers': headers,
|
||||
'secret': secret,
|
||||
'context_id': context_id,
|
||||
},
|
||||
}
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(webpage, ({find_element(id='main-video', html=True)}, {extract_attributes}, {
|
||||
'title': ('data-plyr-config', {json.loads}, 'title', {str}),
|
||||
'thumbnail': ('data-poster', {url_or_none}),
|
||||
})),
|
||||
**ping_data,
|
||||
**self._search_json_ld(webpage, video_id, fatal=False),
|
||||
}
|
||||
@ -0,0 +1,84 @@
|
||||
import json
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
jwt_decode_hs256,
|
||||
parse_iso8601,
|
||||
url_or_none,
|
||||
variadic,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class CanalsurmasIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?canalsurmas\.es/videos/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.canalsurmas.es/videos/44006-el-gran-queo-1-lora-del-rio-sevilla-20072014',
|
||||
'md5': '861f86fdc1221175e15523047d0087ef',
|
||||
'info_dict': {
|
||||
'id': '44006',
|
||||
'ext': 'mp4',
|
||||
'title': 'Lora del Río (Sevilla)',
|
||||
'description': 'md5:3d9ee40a9b1b26ed8259e6b71ed27b8b',
|
||||
'thumbnail': 'https://cdn2.rtva.interactvty.com/content_cards/00f3e8f67b0a4f3b90a4a14618a48b0d.jpg',
|
||||
'timestamp': 1648123182,
|
||||
'upload_date': '20220324',
|
||||
},
|
||||
}]
|
||||
_API_BASE = 'https://api-rtva.interactvty.com'
|
||||
_access_token = None
|
||||
|
||||
@staticmethod
|
||||
def _is_jwt_expired(token):
|
||||
return jwt_decode_hs256(token)['exp'] - time.time() < 300
|
||||
|
||||
def _call_api(self, endpoint, video_id, fields=None):
|
||||
if not self._access_token or self._is_jwt_expired(self._access_token):
|
||||
self._access_token = self._download_json(
|
||||
f'{self._API_BASE}/jwt/token/', None,
|
||||
'Downloading access token', 'Failed to download access token',
|
||||
headers={'Content-Type': 'application/json'},
|
||||
data=json.dumps({
|
||||
'username': 'canalsur_demo',
|
||||
'password': 'dsUBXUcI',
|
||||
}).encode())['access']
|
||||
|
||||
return self._download_json(
|
||||
f'{self._API_BASE}/api/2.0/contents/{endpoint}/{video_id}/', video_id,
|
||||
f'Downloading {endpoint} API JSON', f'Failed to download {endpoint} API JSON',
|
||||
headers={'Authorization': f'jwtok {self._access_token}'},
|
||||
query={'optional_fields': ','.join(variadic(fields))} if fields else None)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_info = self._call_api('content', video_id, fields=[
|
||||
'description', 'image', 'duration', 'created_at', 'tags',
|
||||
])
|
||||
stream_info = self._call_api('content_resources', video_id, 'media_url')
|
||||
|
||||
formats, subtitles = [], {}
|
||||
for stream_url in traverse_obj(stream_info, ('results', ..., 'media_url', {url_or_none})):
|
||||
if determine_ext(stream_url) == 'm3u8':
|
||||
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
||||
stream_url, video_id, m3u8_id='hls', fatal=False)
|
||||
formats.extend(fmts)
|
||||
self._merge_subtitles(subs, target=subtitles)
|
||||
else:
|
||||
formats.append({'url': stream_url})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
**traverse_obj(video_info, {
|
||||
'title': ('name', {str.strip}),
|
||||
'description': ('description', {str}),
|
||||
'thumbnail': ('image', {url_or_none}),
|
||||
'duration': ('duration', {float_or_none}),
|
||||
'timestamp': ('created_at', {parse_iso8601}),
|
||||
'tags': ('tags', ..., {str}),
|
||||
}),
|
||||
}
|
||||
@ -1,142 +0,0 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
orderedSet,
|
||||
)
|
||||
|
||||
|
||||
class DeezerBaseInfoExtractor(InfoExtractor):
|
||||
def get_data(self, url):
|
||||
if not self.get_param('test'):
|
||||
self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
|
||||
|
||||
mobj = self._match_valid_url(url)
|
||||
data_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, data_id)
|
||||
geoblocking_msg = self._html_search_regex(
|
||||
r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
|
||||
default=None)
|
||||
if geoblocking_msg is not None:
|
||||
raise ExtractorError(
|
||||
f'Deezer said: {geoblocking_msg}', expected=True)
|
||||
|
||||
data_json = self._search_regex(
|
||||
(r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
|
||||
r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
|
||||
webpage, 'data JSON')
|
||||
data = json.loads(data_json)
|
||||
return data_id, webpage, data
|
||||
|
||||
|
||||
class DeezerPlaylistIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.deezer.com/playlist/176747451',
|
||||
'info_dict': {
|
||||
'id': '176747451',
|
||||
'title': 'Best!',
|
||||
'uploader': 'anonymous',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 29,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id, webpage, data = self.get_data(url)
|
||||
|
||||
playlist_title = data.get('DATA', {}).get('TITLE')
|
||||
playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
|
||||
playlist_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
|
||||
'playlist thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': playlist_id,
|
||||
'title': playlist_title,
|
||||
'uploader': playlist_uploader,
|
||||
'thumbnail': playlist_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
||||
|
||||
|
||||
class DeezerAlbumIE(DeezerBaseInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.deezer.com/fr/album/67505622',
|
||||
'info_dict': {
|
||||
'id': '67505622',
|
||||
'title': 'Last Week',
|
||||
'uploader': 'Home Brew',
|
||||
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
|
||||
},
|
||||
'playlist_count': 7,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
album_id, webpage, data = self.get_data(url)
|
||||
|
||||
album_title = data.get('DATA', {}).get('ALB_TITLE')
|
||||
album_uploader = data.get('DATA', {}).get('ART_NAME')
|
||||
album_thumbnail = self._search_regex(
|
||||
r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
|
||||
'album thumbnail')
|
||||
|
||||
entries = []
|
||||
for s in data.get('SONGS', {}).get('data'):
|
||||
formats = [{
|
||||
'format_id': 'preview',
|
||||
'url': s.get('MEDIA', [{}])[0].get('HREF'),
|
||||
'preference': -100, # Only the first 30 seconds
|
||||
'ext': 'mp3',
|
||||
}]
|
||||
artists = ', '.join(
|
||||
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
|
||||
entries.append({
|
||||
'id': s.get('SNG_ID'),
|
||||
'duration': int_or_none(s.get('DURATION')),
|
||||
'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
|
||||
'uploader': s.get('ART_NAME'),
|
||||
'uploader_id': s.get('ART_ID'),
|
||||
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
|
||||
'formats': formats,
|
||||
'track': s.get('SNG_TITLE'),
|
||||
'track_number': int_or_none(s.get('TRACK_NUMBER')),
|
||||
'track_id': s.get('SNG_ID'),
|
||||
'artist': album_uploader,
|
||||
'album': album_title,
|
||||
'album_artist': album_uploader,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': album_id,
|
||||
'title': album_title,
|
||||
'uploader': album_uploader,
|
||||
'thumbnail': album_thumbnail,
|
||||
'entries': entries,
|
||||
}
|
||||
@ -0,0 +1,130 @@
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import clean_html, int_or_none, traverse_obj, url_or_none, urlencode_postdata
|
||||
|
||||
|
||||
class DigiviewIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?ladigitale\.dev/digiview/#/v/(?P<id>[0-9a-f]+)'
|
||||
_TESTS = [{
|
||||
# normal video
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8e50aee2ec',
|
||||
'info_dict': {
|
||||
'id': '67a8e50aee2ec',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny 60fps 4K - Official Blender Foundation Short Film',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 635,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 635,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 0,
|
||||
'availability': 'public',
|
||||
},
|
||||
}, {
|
||||
# cut video
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8e51d0dd58',
|
||||
'info_dict': {
|
||||
'id': '67a8e51d0dd58',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny 60fps 4K - Official Blender Foundation Short Film',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 10,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 5,
|
||||
'availability': 'public',
|
||||
},
|
||||
}, {
|
||||
# changed title
|
||||
'url': 'https://ladigitale.dev/digiview/#/v/67a8ea5644d7a',
|
||||
'info_dict': {
|
||||
'id': '67a8ea5644d7a',
|
||||
'ext': 'mp4',
|
||||
'title': 'Big Buck Bunny (with title changed)',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/aqz-KE-bpKQ/hqdefault.jpg',
|
||||
'upload_date': '20141110',
|
||||
'playable_in_embed': True,
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'channel': 'Blender',
|
||||
'license': 'Creative Commons Attribution license (reuse allowed)',
|
||||
'like_count': int,
|
||||
'tags': 'count:8',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'channel_follower_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSMOQeBJ2RAnuFungnQOxLg',
|
||||
'uploader_id': '@BlenderOfficial',
|
||||
'description': 'md5:8f3ed18a53a1bb36cbb3b70a15782fd0',
|
||||
'categories': ['Film & Animation'],
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'section_end': 15,
|
||||
'uploader': 'Blender',
|
||||
'timestamp': 1415628355,
|
||||
'uploader_url': 'https://www.youtube.com/@BlenderOfficial',
|
||||
'age_limit': 0,
|
||||
'section_start': 10,
|
||||
'availability': 'public',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json(
|
||||
'https://ladigitale.dev/digiview/inc/recuperer_video.php', video_id,
|
||||
data=urlencode_postdata({'id': video_id}))
|
||||
|
||||
clip_id = video_data['videoId']
|
||||
return self.url_result(
|
||||
f'https://www.youtube.com/watch?v={clip_id}',
|
||||
YoutubeIE, video_id, url_transparent=True,
|
||||
**traverse_obj(video_data, {
|
||||
'section_start': ('debut', {int_or_none}),
|
||||
'section_end': ('fin', {int_or_none}),
|
||||
'description': ('description', {clean_html}, filter),
|
||||
'title': ('titre', {str}),
|
||||
'thumbnail': ('vignette', {url_or_none}),
|
||||
'view_count': ('vues', {int_or_none}),
|
||||
}),
|
||||
)
|
||||
@ -0,0 +1,51 @@
|
||||
from .brightcove import BrightcoveNewIE
|
||||
from .common import InfoExtractor
|
||||
from ..utils import url_or_none
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class DrTalksIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?drtalks\.com/videos/(?P<id>[\w-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://drtalks.com/videos/six-pillars-of-resilience-tools-for-managing-stress-and-flourishing/',
|
||||
'info_dict': {
|
||||
'id': '6366193757112',
|
||||
'ext': 'mp4',
|
||||
'uploader_id': '6314452011001',
|
||||
'tags': ['resilience'],
|
||||
'description': 'md5:9c6805aee237ee6de8052461855b9dda',
|
||||
'timestamp': 1734546659,
|
||||
'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/12/Episode-82-Eva-Selhub-DrTalks-Thumbs.jpg',
|
||||
'title': 'Six Pillars of Resilience: Tools for Managing Stress and Flourishing',
|
||||
'duration': 2800.682,
|
||||
'upload_date': '20241218',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://drtalks.com/videos/the-pcos-puzzle-mastering-metabolic-health-with-marcelle-pick/',
|
||||
'info_dict': {
|
||||
'id': '6364699891112',
|
||||
'ext': 'mp4',
|
||||
'title': 'The PCOS Puzzle: Mastering Metabolic Health with Marcelle Pick',
|
||||
'description': 'md5:e87cbe00ca50135d5702787fc4043aaa',
|
||||
'thumbnail': 'https://drtalks.com/wp-content/uploads/2024/11/Episode-34-Marcelle-Pick-OBGYN-NP-DrTalks.jpg',
|
||||
'duration': 3515.2,
|
||||
'tags': ['pcos'],
|
||||
'upload_date': '20241114',
|
||||
'timestamp': 1731592119,
|
||||
'uploader_id': '6314452011001',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
next_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']['video']
|
||||
|
||||
return self.url_result(
|
||||
next_data['videos']['brightcoveVideoLink'], BrightcoveNewIE, video_id,
|
||||
url_transparent=True,
|
||||
**traverse_obj(next_data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('videos', 'summury', {str}),
|
||||
'thumbnail': ('featuredImage', 'node', 'sourceUrl', {url_or_none}),
|
||||
}))
|
||||
@ -0,0 +1,155 @@
|
||||
import secrets
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class EggsBaseIE(InfoExtractor):
|
||||
_API_HEADERS = {
|
||||
'Accept': '*/*',
|
||||
'apVersion': '8.2.00',
|
||||
'deviceName': 'Android',
|
||||
}
|
||||
|
||||
def _real_initialize(self):
|
||||
self._API_HEADERS['deviceId'] = secrets.token_hex(8)
|
||||
|
||||
def _call_api(self, endpoint, video_id):
|
||||
return self._download_json(
|
||||
f'https://app-front-api.eggs.mu/v1/{endpoint}', video_id,
|
||||
headers=self._API_HEADERS)
|
||||
|
||||
def _extract_music_info(self, data):
|
||||
if yt_url := traverse_obj(data, ('youtubeUrl', {url_or_none})):
|
||||
return self.url_result(yt_url, ie=YoutubeIE)
|
||||
|
||||
artist_name = traverse_obj(data, ('artist', 'artistName', {str_or_none}))
|
||||
music_id = traverse_obj(data, ('musicId', {str_or_none}))
|
||||
webpage_url = None
|
||||
if artist_name and music_id:
|
||||
webpage_url = f'https://eggs.mu/artist/{artist_name}/song/{music_id}'
|
||||
|
||||
return {
|
||||
'id': music_id,
|
||||
'vcodec': 'none',
|
||||
'webpage_url': webpage_url,
|
||||
'extractor_key': EggsIE.ie_key(),
|
||||
'extractor': EggsIE.IE_NAME,
|
||||
**traverse_obj(data, {
|
||||
'title': ('musicTitle', {str}),
|
||||
'url': ('musicDataPath', {url_or_none}),
|
||||
'uploader': ('artist', 'displayName', {str}),
|
||||
'uploader_id': ('artist', 'artistId', {str_or_none}),
|
||||
'thumbnail': ('imageDataPath', {url_or_none}),
|
||||
'view_count': ('numberOfMusicPlays', {int_or_none}),
|
||||
'like_count': ('numberOfLikes', {int_or_none}),
|
||||
'comment_count': ('numberOfComments', {int_or_none}),
|
||||
'composers': ('composer', {str}, all),
|
||||
'tags': ('tags', ..., {str}),
|
||||
'timestamp': ('releaseDate', {parse_iso8601}),
|
||||
'artist': ('artist', 'displayName', {str}),
|
||||
})}
|
||||
|
||||
|
||||
class EggsIE(EggsBaseIE):
|
||||
IE_NAME = 'eggs:single'
|
||||
_VALID_URL = r'https?://eggs\.mu/artist/[^/?#]+/song/(?P<id>[\da-f-]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://eggs.mu/artist/32_sunny_girl/song/0e95fd1d-4d61-4d5b-8b18-6092c551da90',
|
||||
'info_dict': {
|
||||
'id': '0e95fd1d-4d61-4d5b-8b18-6092c551da90',
|
||||
'ext': 'm4a',
|
||||
'title': 'シネマと信号',
|
||||
'uploader': 'Sunny Girl',
|
||||
'thumbnail': r're:https?://.*\.jpg(?:\?.*)?$',
|
||||
'uploader_id': '1607',
|
||||
'like_count': int,
|
||||
'timestamp': 1731327327,
|
||||
'composers': ['橘高連太郎'],
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'artists': ['Sunny Girl'],
|
||||
'upload_date': '20241111',
|
||||
'tags': ['SunnyGirl', 'シネマと信号'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://eggs.mu/artist/KAMO_3pband/song/1d4bc45f-1af6-47a9-8b30-a70cae350b4f',
|
||||
'info_dict': {
|
||||
'id': '80cLKA2wnoA',
|
||||
'ext': 'mp4',
|
||||
'title': 'KAMO「いい女だから」Audio',
|
||||
'uploader': 'KAMO',
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCsHLBw2__5Q9y55skXPotOg',
|
||||
'channel_follower_count': int,
|
||||
'description': 'md5:d260da711ecbec3e720293dc11401b87',
|
||||
'availability': 'public',
|
||||
'uploader_id': '@KAMO_band',
|
||||
'upload_date': '20240925',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/80cLKA2wnoA/maxresdefault.jpg',
|
||||
'comment_count': int,
|
||||
'channel_url': 'https://www.youtube.com/channel/UCsHLBw2__5Q9y55skXPotOg',
|
||||
'view_count': int,
|
||||
'duration': 151,
|
||||
'like_count': int,
|
||||
'channel': 'KAMO',
|
||||
'playable_in_embed': True,
|
||||
'uploader_url': 'https://www.youtube.com/@KAMO_band',
|
||||
'tags': [],
|
||||
'timestamp': 1727271121,
|
||||
'age_limit': 0,
|
||||
'categories': ['People & Blogs'],
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
'params': {'skip_download': 'Youtube'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
song_id = self._match_id(url)
|
||||
json_data = self._call_api(f'musics/{song_id}', song_id)
|
||||
return self._extract_music_info(json_data)
|
||||
|
||||
|
||||
class EggsArtistIE(EggsBaseIE):
|
||||
IE_NAME = 'eggs:artist'
|
||||
_VALID_URL = r'https?://eggs\.mu/artist/(?P<id>\w+)/?(?:[?#&]|$)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://eggs.mu/artist/32_sunny_girl',
|
||||
'info_dict': {
|
||||
'id': '32_sunny_girl',
|
||||
'thumbnail': 'https://image-pro.eggs.mu/profile/1607.jpeg?updated_at=2024-04-03T20%3A06%3A00%2B09%3A00',
|
||||
'description': 'Muddy Mine / 東京高田馬場CLUB PHASE / Gt.Vo 橘高 連太郎 / Ba.Cho 小野 ゆうき / Dr 大森 りゅうひこ',
|
||||
'title': 'Sunny Girl',
|
||||
},
|
||||
'playlist_mincount': 18,
|
||||
}, {
|
||||
'url': 'https://eggs.mu/artist/KAMO_3pband',
|
||||
'info_dict': {
|
||||
'id': 'KAMO_3pband',
|
||||
'description': '川崎発３ピースバンド',
|
||||
'thumbnail': 'https://image-pro.eggs.mu/profile/35217.jpeg?updated_at=2024-11-27T16%3A31%3A50%2B09%3A00',
|
||||
'title': 'KAMO',
|
||||
},
|
||||
'playlist_mincount': 2,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
artist_id = self._match_id(url)
|
||||
artist_data = self._call_api(f'artists/{artist_id}', artist_id)
|
||||
song_data = self._call_api(f'artists/{artist_id}/musics', artist_id)
|
||||
return self.playlist_result(
|
||||
traverse_obj(song_data, ('data', ..., {dict}, {self._extract_music_info})),
|
||||
playlist_id=artist_id, **traverse_obj(artist_data, {
|
||||
'title': ('displayName', {str}),
|
||||
'description': ('profile', {str}),
|
||||
'thumbnail': ('imageDataPath', {url_or_none}),
|
||||
}))
|
||||
@ -1,28 +1,37 @@
|
||||
import contextlib
|
||||
import inspect
|
||||
import os
|
||||
|
||||
from ..plugins import load_plugins
|
||||
from ..globals import LAZY_EXTRACTORS
|
||||
from ..globals import extractors as _extractors_context
|
||||
|
||||
# NB: Must be before other imports so that plugins can be correctly injected
|
||||
_PLUGIN_CLASSES = load_plugins('extractor', 'IE')
|
||||
_CLASS_LOOKUP = None
|
||||
if os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
|
||||
LAZY_EXTRACTORS.value = False
|
||||
else:
|
||||
try:
|
||||
from .lazy_extractors import _CLASS_LOOKUP
|
||||
LAZY_EXTRACTORS.value = True
|
||||
except ImportError:
|
||||
LAZY_EXTRACTORS.value = None
|
||||
|
||||
_LAZY_LOADER = False
|
||||
if not os.environ.get('YTDLP_NO_LAZY_EXTRACTORS'):
|
||||
with contextlib.suppress(ImportError):
|
||||
from .lazy_extractors import * # noqa: F403
|
||||
from .lazy_extractors import _ALL_CLASSES
|
||||
_LAZY_LOADER = True
|
||||
if not _CLASS_LOOKUP:
|
||||
from . import _extractors
|
||||
|
||||
if not _LAZY_LOADER:
|
||||
from ._extractors import * # noqa: F403
|
||||
_ALL_CLASSES = [ # noqa: F811
|
||||
klass
|
||||
for name, klass in globals().items()
|
||||
_CLASS_LOOKUP = {
|
||||
name: value
|
||||
for name, value in inspect.getmembers(_extractors)
|
||||
if name.endswith('IE') and name != 'GenericIE'
|
||||
]
|
||||
_ALL_CLASSES.append(GenericIE) # noqa: F405
|
||||
}
|
||||
_CLASS_LOOKUP['GenericIE'] = _extractors.GenericIE
|
||||
|
||||
globals().update(_PLUGIN_CLASSES)
|
||||
_ALL_CLASSES[:0] = _PLUGIN_CLASSES.values()
|
||||
# We want to append to the main lookup
|
||||
_current = _extractors_context.value
|
||||
for name, ie in _CLASS_LOOKUP.items():
|
||||
_current.setdefault(name, ie)
|
||||
|
||||
from .common import _PLUGIN_OVERRIDES # noqa: F401
|
||||
|
||||
def __getattr__(name):
|
||||
value = _CLASS_LOOKUP.get(name)
|
||||
if not value:
|
||||
raise AttributeError(f'module {__name__} has no attribute {name}')
|
||||
return value
|
||||
|
||||
@ -0,0 +1,87 @@
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FrancaisFacileIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://francaisfacile\.rfi\.fr/[a-z]{2}/(?:actualit%C3%A9|podcasts/[^/#?]+)/(?P<id>[^/#?]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250305-r%C3%A9concilier-les-jeunes-avec-la-lecture-gr%C3%A2ce-aux-r%C3%A9seaux-sociaux',
|
||||
'md5': '4f33674cb205744345cc835991100afa',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ58952-FLE-FR-20250305',
|
||||
'display_id': '20250305-réconcilier-les-jeunes-avec-la-lecture-grâce-aux-réseaux-sociaux',
|
||||
'title': 'Réconcilier les jeunes avec la lecture grâce aux réseaux sociaux',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/05/6b6af52a-f9ba-11ef-a1f8-005056a97652.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:b903c63d8585bd59e8cc4d5f80c4272d',
|
||||
'duration': 103.15,
|
||||
'timestamp': 1741177984,
|
||||
'upload_date': '20250305',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250307-argentine-le-sac-d-un-alpiniste-retrouv%C3%A9-40-ans-apr%C3%A8s-sa-mort',
|
||||
'md5': 'b8c3a63652d4ae8e8092dda5700c1cd9',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ59102-FLE-FR-20250307',
|
||||
'display_id': '20250307-argentine-le-sac-d-un-alpiniste-retrouvé-40-ans-après-sa-mort',
|
||||
'title': 'Argentine: le sac d\'un alpiniste retrouvé 40 ans après sa mort',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/07/8edf4082-fb46-11ef-8a37-005056bf762b.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:7fd088fbdf4a943bb68cf82462160dca',
|
||||
'duration': 117.74,
|
||||
'timestamp': 1741352789,
|
||||
'upload_date': '20250307',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://francaisfacile.rfi.fr/fr/podcasts/un-mot-une-histoire/20250317-le-mot-de-david-foenkinos-peut-%C3%AAtre',
|
||||
'md5': 'db83c2cc2589b4c24571c6b6cf14f5f1',
|
||||
'info_dict': {
|
||||
'id': 'WBMZ59441-FLE-FR-20250317',
|
||||
'display_id': '20250317-le-mot-de-david-foenkinos-peut-être',
|
||||
'title': 'Le mot de David Foenkinos: «peut-être» - Un mot, une histoire',
|
||||
'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/17/4ca6cbbe-0315-11f0-a85b-005056a97652.mp3',
|
||||
'ext': 'mp3',
|
||||
'description': 'md5:3fe35fae035803df696bfa7af2496e49',
|
||||
'duration': 198.96,
|
||||
'timestamp': 1742210897,
|
||||
'upload_date': '20250317',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = urllib.parse.unquote(self._match_id(url))
|
||||
|
||||
try: # yt-dlp's default user-agents are too old and blocked by the site
|
||||
webpage = self._download_webpage(url, display_id, headers={
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
|
||||
})
|
||||
except ExtractorError as e:
|
||||
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
|
||||
raise
|
||||
# Retry with impersonation if hardcoded UA is insufficient
|
||||
webpage = self._download_webpage(url, display_id, impersonate=True)
|
||||
|
||||
data = self._search_json(
|
||||
r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
|
||||
webpage, 'audio data', display_id)
|
||||
|
||||
return {
|
||||
'id': data['mediaId'],
|
||||
'display_id': display_id,
|
||||
'vcodec': 'none',
|
||||
'title': self._html_extract_title(webpage),
|
||||
**self._search_json_ld(webpage, display_id, fatal=False),
|
||||
**traverse_obj(data, {
|
||||
'title': ('title', {str}),
|
||||
'url': ('sources', ..., 'url', {url_or_none}, any),
|
||||
'duration': ('sources', ..., 'duration', {float_or_none}, any),
|
||||
}),
|
||||
}
|
||||
@ -1,349 +0,0 @@
|
||||
import random
|
||||
import re
|
||||
import string
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking.exceptions import HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
join_nonempty,
|
||||
js_to_json,
|
||||
make_archive_id,
|
||||
orderedSet,
|
||||
qualities,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
try_get,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class FunimationBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'funimation'
|
||||
_REGION = None
|
||||
_TOKEN = None
|
||||
|
||||
def _get_region(self):
|
||||
region_cookie = self._get_cookies('https://www.funimation.com').get('region')
|
||||
region = region_cookie.value if region_cookie else self.get_param('geo_bypass_country')
|
||||
return region or traverse_obj(
|
||||
self._download_json(
|
||||
'https://geo-service.prd.funimationsvc.com/geo/v1/region/check', None, fatal=False,
|
||||
note='Checking geo-location', errnote='Unable to fetch geo-location information'),
|
||||
'region') or 'US'
|
||||
|
||||
def _perform_login(self, username, password):
|
||||
if self._TOKEN:
|
||||
return
|
||||
try:
|
||||
data = self._download_json(
|
||||
'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
|
||||
None, 'Logging in', data=urlencode_postdata({
|
||||
'username': username,
|
||||
'password': password,
|
||||
}))
|
||||
FunimationBaseIE._TOKEN = data['token']
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
|
||||
error = self._parse_json(e.cause.response.read().decode(), None)['error']
|
||||
raise ExtractorError(error, expected=True)
|
||||
raise
|
||||
|
||||
|
||||
class FunimationPageIE(FunimationBaseIE):
|
||||
IE_NAME = 'funimation:page'
|
||||
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?:(?P<lang>[^/]+)/)?(?:shows|v)/(?P<show>[^/]+)/(?P<episode>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
|
||||
'info_dict': {
|
||||
'id': '210050',
|
||||
'ext': 'mp4',
|
||||
'title': 'Broadcast Dub Preview',
|
||||
# Other metadata is tested in FunimationIE
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
'add_ie': ['Funimation'],
|
||||
}, {
|
||||
# Not available in US
|
||||
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# with lang code
|
||||
'url': 'https://www.funimation.com/en/shows/hacksign/role-play/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.funimation.com/v/a-certain-scientific-railgun/super-powered-level-5',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._REGION:
|
||||
FunimationBaseIE._REGION = self._get_region()
|
||||
|
||||
def _real_extract(self, url):
|
||||
locale, show, episode = self._match_valid_url(url).group('lang', 'show', 'episode')
|
||||
|
||||
video_id = traverse_obj(self._download_json(
|
||||
f'https://title-api.prd.funimationsvc.com/v1/shows/{show}/episodes/{episode}',
|
||||
f'{show}_{episode}', query={
|
||||
'deviceType': 'web',
|
||||
'region': self._REGION,
|
||||
'locale': locale or 'en',
|
||||
}), ('videoList', ..., 'id'), get_all=False)
|
||||
|
||||
return self.url_result(f'https://www.funimation.com/player/{video_id}', FunimationIE.ie_key(), video_id)
|
||||
|
||||
|
||||
class FunimationIE(FunimationBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?funimation\.com/player/(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.funimation.com/player/210051',
|
||||
'info_dict': {
|
||||
'id': '210050',
|
||||
'display_id': 'broadcast-dub-preview',
|
||||
'ext': 'mp4',
|
||||
'title': 'Broadcast Dub Preview',
|
||||
'thumbnail': r're:https?://.*\.(?:jpg|png)',
|
||||
'episode': 'Broadcast Dub Preview',
|
||||
'episode_id': '210050',
|
||||
'season': 'Extras',
|
||||
'season_id': '166038',
|
||||
'season_number': 99,
|
||||
'series': 'Attack on Titan: Junior High',
|
||||
'description': '',
|
||||
'duration': 155,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
},
|
||||
}, {
|
||||
'note': 'player_id should be extracted with the relevent compat-opt',
|
||||
'url': 'https://www.funimation.com/player/210051',
|
||||
'info_dict': {
|
||||
'id': '210051',
|
||||
'display_id': 'broadcast-dub-preview',
|
||||
'ext': 'mp4',
|
||||
'title': 'Broadcast Dub Preview',
|
||||
'thumbnail': r're:https?://.*\.(?:jpg|png)',
|
||||
'episode': 'Broadcast Dub Preview',
|
||||
'episode_id': '210050',
|
||||
'season': 'Extras',
|
||||
'season_id': '166038',
|
||||
'season_number': 99,
|
||||
'series': 'Attack on Titan: Junior High',
|
||||
'description': '',
|
||||
'duration': 155,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'm3u8',
|
||||
'compat_opts': ['seperate-video-versions'],
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _get_experiences(episode):
|
||||
for lang, lang_data in episode.get('languages', {}).items():
|
||||
for video_data in lang_data.values():
|
||||
for version, f in video_data.items():
|
||||
yield lang, version.title(), f
|
||||
|
||||
def _get_episode(self, webpage, experience_id=None, episode_id=None, fatal=True):
|
||||
""" Extract the episode, season and show objects given either episode/experience id """
|
||||
show = self._parse_json(
|
||||
self._search_regex(
|
||||
r'show\s*=\s*({.+?})\s*;', webpage, 'show data', fatal=fatal),
|
||||
experience_id, transform_source=js_to_json, fatal=fatal) or []
|
||||
for season in show.get('seasons', []):
|
||||
for episode in season.get('episodes', []):
|
||||
if episode_id is not None:
|
||||
if str(episode.get('episodePk')) == episode_id:
|
||||
return episode, season, show
|
||||
continue
|
||||
for _, _, f in self._get_experiences(episode):
|
||||
if f.get('experienceId') == experience_id:
|
||||
return episode, season, show
|
||||
if fatal:
|
||||
raise ExtractorError('Unable to find episode information')
|
||||
else:
|
||||
self.report_warning('Unable to find episode information')
|
||||
return {}, {}, {}
|
||||
|
||||
def _real_extract(self, url):
|
||||
initial_experience_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
url, initial_experience_id, note=f'Downloading player webpage for {initial_experience_id}')
|
||||
episode, season, show = self._get_episode(webpage, experience_id=int(initial_experience_id))
|
||||
episode_id = str(episode['episodePk'])
|
||||
display_id = episode.get('slug') or episode_id
|
||||
|
||||
formats, subtitles, thumbnails, duration = [], {}, [], 0
|
||||
requested_languages, requested_versions = self._configuration_arg('language'), self._configuration_arg('version')
|
||||
language_preference = qualities((requested_languages or [''])[::-1])
|
||||
source_preference = qualities((requested_versions or ['uncut', 'simulcast'])[::-1])
|
||||
only_initial_experience = 'seperate-video-versions' in self.get_param('compat_opts', [])
|
||||
|
||||
for lang, version, fmt in self._get_experiences(episode):
|
||||
experience_id = str(fmt['experienceId'])
|
||||
if ((only_initial_experience and experience_id != initial_experience_id)
|
||||
or (requested_languages and lang.lower() not in requested_languages)
|
||||
or (requested_versions and version.lower() not in requested_versions)):
|
||||
continue
|
||||
thumbnails.append({'url': fmt.get('poster')})
|
||||
duration = max(duration, fmt.get('duration', 0))
|
||||
format_name = f'{version} {lang} ({experience_id})'
|
||||
self.extract_subtitles(
|
||||
subtitles, experience_id, display_id=display_id, format_name=format_name,
|
||||
episode=episode if experience_id == initial_experience_id else episode_id)
|
||||
|
||||
headers = {}
|
||||
if self._TOKEN:
|
||||
headers['Authorization'] = f'Token {self._TOKEN}'
|
||||
page = self._download_json(
|
||||
f'https://www.funimation.com/api/showexperience/{experience_id}/',
|
||||
display_id, headers=headers, expected_status=403, query={
|
||||
'pinst_id': ''.join(random.choices(string.digits + string.ascii_letters, k=8)),
|
||||
}, note=f'Downloading {format_name} JSON')
|
||||
sources = page.get('items') or []
|
||||
if not sources:
|
||||
error = try_get(page, lambda x: x['errors'][0], dict)
|
||||
if error:
|
||||
self.report_warning('{} said: Error {} - {}'.format(
|
||||
self.IE_NAME, error.get('code'), error.get('detail') or error.get('title')))
|
||||
else:
|
||||
self.report_warning('No sources found for format')
|
||||
|
||||
current_formats = []
|
||||
for source in sources:
|
||||
source_url = source.get('src')
|
||||
source_type = source.get('videoType') or determine_ext(source_url)
|
||||
if source_type == 'm3u8':
|
||||
current_formats.extend(self._extract_m3u8_formats(
|
||||
source_url, display_id, 'mp4', m3u8_id='{}-{}'.format(experience_id, 'hls'), fatal=False,
|
||||
note=f'Downloading {format_name} m3u8 information'))
|
||||
else:
|
||||
current_formats.append({
|
||||
'format_id': f'{experience_id}-{source_type}',
|
||||
'url': source_url,
|
||||
})
|
||||
for f in current_formats:
|
||||
# TODO: Convert language to code
|
||||
f.update({
|
||||
'language': lang,
|
||||
'format_note': version,
|
||||
'source_preference': source_preference(version.lower()),
|
||||
'language_preference': language_preference(lang.lower()),
|
||||
})
|
||||
formats.extend(current_formats)
|
||||
if not formats and (requested_languages or requested_versions):
|
||||
self.raise_no_formats(
|
||||
'There are no video formats matching the requested languages/versions', expected=True, video_id=display_id)
|
||||
self._remove_duplicate_formats(formats)
|
||||
|
||||
return {
|
||||
'id': episode_id,
|
||||
'_old_archive_ids': [make_archive_id(self, initial_experience_id)],
|
||||
'display_id': display_id,
|
||||
'duration': duration,
|
||||
'title': episode['episodeTitle'],
|
||||
'description': episode.get('episodeSummary'),
|
||||
'episode': episode.get('episodeTitle'),
|
||||
'episode_number': int_or_none(episode.get('episodeId')),
|
||||
'episode_id': episode_id,
|
||||
'season': season.get('seasonTitle'),
|
||||
'season_number': int_or_none(season.get('seasonId')),
|
||||
'season_id': str_or_none(season.get('seasonPk')),
|
||||
'series': show.get('showTitle'),
|
||||
'formats': formats,
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'_format_sort_fields': ('lang', 'source'),
|
||||
}
|
||||
|
||||
def _get_subtitles(self, subtitles, experience_id, episode, display_id, format_name):
|
||||
if isinstance(episode, str):
|
||||
webpage = self._download_webpage(
|
||||
f'https://www.funimation.com/player/{experience_id}/', display_id,
|
||||
fatal=False, note=f'Downloading player webpage for {format_name}')
|
||||
episode, _, _ = self._get_episode(webpage, episode_id=episode, fatal=False)
|
||||
|
||||
for _, version, f in self._get_experiences(episode):
|
||||
for source in f.get('sources'):
|
||||
for text_track in source.get('textTracks'):
|
||||
if not text_track.get('src'):
|
||||
continue
|
||||
sub_type = text_track.get('type').upper()
|
||||
sub_type = sub_type if sub_type != 'FULL' else None
|
||||
current_sub = {
|
||||
'url': text_track['src'],
|
||||
'name': join_nonempty(version, text_track.get('label'), sub_type, delim=' '),
|
||||
}
|
||||
lang = join_nonempty(text_track.get('language', 'und'),
|
||||
version if version != 'Simulcast' else None,
|
||||
sub_type, delim='_')
|
||||
if current_sub not in subtitles.get(lang, []):
|
||||
subtitles.setdefault(lang, []).append(current_sub)
|
||||
return subtitles
|
||||
|
||||
|
||||
class FunimationShowIE(FunimationBaseIE):
|
||||
IE_NAME = 'funimation:show'
|
||||
_VALID_URL = r'(?P<url>https?://(?:www\.)?funimation(?:\.com|now\.uk)/(?P<locale>[^/]+)?/?shows/(?P<id>[^/?#&]+))/?(?:[?#]|$)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.funimation.com/en/shows/sk8-the-infinity',
|
||||
'info_dict': {
|
||||
'id': '1315000',
|
||||
'title': 'SK8 the Infinity',
|
||||
},
|
||||
'playlist_count': 13,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# without lang code
|
||||
'url': 'https://www.funimation.com/shows/ouran-high-school-host-club/',
|
||||
'info_dict': {
|
||||
'id': '39643',
|
||||
'title': 'Ouran High School Host Club',
|
||||
},
|
||||
'playlist_count': 26,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._REGION:
|
||||
FunimationBaseIE._REGION = self._get_region()
|
||||
|
||||
def _real_extract(self, url):
|
||||
base_url, locale, display_id = self._match_valid_url(url).groups()
|
||||
|
||||
show_info = self._download_json(
|
||||
'https://title-api.prd.funimationsvc.com/v2/shows/{}?region={}&deviceType=web&locale={}'.format(
|
||||
display_id, self._REGION, locale or 'en'), display_id)
|
||||
items_info = self._download_json(
|
||||
'https://prod-api-funimationnow.dadcdigital.com/api/funimation/episodes/?limit=99999&title_id={}'.format(
|
||||
show_info.get('id')), display_id)
|
||||
|
||||
vod_items = traverse_obj(items_info, ('items', ..., lambda k, _: re.match(r'(?i)mostRecent[AS]vod', k), 'item'))
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': str_or_none(show_info['id']),
|
||||
'title': show_info['name'],
|
||||
'entries': orderedSet(
|
||||
self.url_result(
|
||||
'{}/{}'.format(base_url, vod_item.get('episodeSlug')), FunimationPageIE.ie_key(),
|
||||
vod_item.get('episodeId'), vod_item.get('episodeName'))
|
||||
for vod_item in sorted(vod_items, key=lambda x: x.get('episodeOrder', -1))),
|
||||
}
|
||||
@ -1,19 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class GigyaBaseIE(InfoExtractor):
|
||||
def _gigya_login(self, auth_data):
|
||||
auth_info = self._download_json(
|
||||
'https://accounts.eu1.gigya.com/accounts.login', None,
|
||||
note='Logging in', errnote='Unable to log in',
|
||||
data=urlencode_postdata(auth_data))
|
||||
|
||||
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
|
||||
if error_message:
|
||||
raise ExtractorError(
|
||||
f'Unable to login: {error_message}', expected=True)
|
||||
return auth_info
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue