yt-dlp/yt_dlp/extractor/adn.py

261 lines
11 KiB
Python
Raw Normal View History

2018-06-02 19:07:36 +02:00
import base64
import binascii
2017-03-31 13:24:23 +02:00
import json
import os
2018-06-02 19:07:36 +02:00
import random
2017-03-31 13:24:23 +02:00
from .common import InfoExtractor
2022-01-31 15:49:33 +01:00
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import (
2021-01-16 13:40:15 +01:00
compat_HTTPError,
compat_b64decode,
)
2017-03-31 13:24:23 +02:00
from ..utils import (
ass_subtitles_timecode,
2017-03-31 13:24:23 +02:00
bytes_to_intlist,
2018-06-02 19:07:36 +02:00
bytes_to_long,
2017-03-31 13:24:23 +02:00
ExtractorError,
float_or_none,
2021-01-16 13:40:15 +01:00
int_or_none,
2017-03-31 13:24:23 +02:00
intlist_to_bytes,
2018-06-02 19:07:36 +02:00
long_to_bytes,
pkcs1pad,
2017-03-31 13:24:23 +02:00
strip_or_none,
2021-01-16 13:40:15 +01:00
try_get,
unified_strdate,
urlencode_postdata,
2017-03-31 13:24:23 +02:00
)
class ADNIE(InfoExtractor):
IE_DESC = 'Animation Digital Network'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
2017-03-31 13:24:23 +02:00
'info_dict': {
'id': '9841',
2017-03-31 13:24:23 +02:00
'ext': 'mp4',
'title': 'Fruits Basket - Episode 1',
'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
'series': 'Fruits Basket',
'duration': 1437,
'release_date': '20190405',
2021-01-16 13:40:15 +01:00
'comment_count': int,
'average_rating': float,
'season_number': 1,
'episode': 'À ce soir !',
2021-01-16 13:40:15 +01:00
'episode_number': 1,
},
'skip': 'Only available in region (FR, ...)',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}]
2021-01-16 13:40:15 +01:00
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.' + _BASE + '/'
2021-01-16 13:40:15 +01:00
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
2021-01-16 13:40:15 +01:00
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
_POS_ALIGN_MAP = {
'start': 1,
'end': 3,
}
_LINE_ALIGN_MAP = {
'middle': 8,
'end': 4,
}
2021-01-16 13:40:15 +01:00
def _get_subtitles(self, sub_url, video_id):
if not sub_url:
2017-03-31 13:24:23 +02:00
return None
enc_subtitles = self._download_webpage(
2021-01-16 13:40:15 +01:00
sub_url, video_id, 'Downloading subtitles location', fatal=False) or '{}'
2019-04-16 14:04:13 +02:00
subtitle_location = (self._parse_json(enc_subtitles, video_id, fatal=False) or {}).get('location')
if subtitle_location:
enc_subtitles = self._download_webpage(
2021-01-16 13:40:15 +01:00
subtitle_location, video_id, 'Downloading subtitles data',
fatal=False, headers={'Origin': 'https://' + self._BASE})
2017-03-31 13:24:23 +02:00
if not enc_subtitles:
return None
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
2022-01-31 15:49:33 +01:00
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + '7fac1178830cfe0c'),
2022-01-31 15:49:33 +01:00
compat_b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
2017-03-31 13:24:23 +02:00
if not subtitles_json:
return None
subtitles = {}
for sub_lang, sub in subtitles_json.items():
ssa = '''[Script Info]
ScriptType:V4.00
[V4 Styles]
Format: Name,Fontname,Fontsize,PrimaryColour,SecondaryColour,TertiaryColour,BackColour,Bold,Italic,BorderStyle,Outline,Shadow,Alignment,MarginL,MarginR,MarginV,AlphaLevel,Encoding
Style: Default,Arial,18,16777215,16777215,16777215,0,-1,0,1,1,0,2,20,20,20,0,0
[Events]
Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
for current in sub:
start, end, text, line_align, position_align = (
2017-03-31 13:24:23 +02:00
float_or_none(current.get('startTime')),
float_or_none(current.get('endTime')),
current.get('text'), current.get('lineAlign'),
current.get('positionAlign'))
2017-03-31 13:24:23 +02:00
if start is None or end is None or text is None:
continue
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
ass_subtitles_timecode(start),
ass_subtitles_timecode(end),
'{\\a%d}' % alignment if alignment != 2 else '',
text.replace('\n', '\\N').replace('<i>', '{\\i1}').replace('</i>', '{\\i0}'))
2017-03-31 13:24:23 +02:00
if sub_lang == 'vostf':
sub_lang = 'fr'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
}, {
'ext': 'ssa',
'data': ssa,
2017-03-31 13:24:23 +02:00
}])
return subtitles
def _perform_login(self, username, password):
try:
access_token = (self._download_json(
self._API_BASE_URL + 'authentication/login', None,
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
data=urlencode_postdata({
'password': password,
'rememberMe': False,
'source': 'Web',
'username': username,
})) or {}).get('accessToken')
if access_token:
self._HEADERS = {'authorization': 'Bearer ' + access_token}
except ExtractorError as e:
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
2017-03-31 13:24:23 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2021-01-16 13:40:15 +01:00
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
player = self._download_json(
video_base_url + 'configuration', video_id,
'Downloading player config JSON metadata',
headers=self._HEADERS)['player']
2021-01-16 13:40:15 +01:00
options = player['options']
user = options['user']
if not user.get('hasAccess'):
self.raise_login_required()
2021-01-16 13:40:15 +01:00
token = self._download_json(
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
video_id, 'Downloading access token', headers={
'x-player-refresh-token': user['refreshToken']
}, data=b'')['token']
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
message = bytes_to_intlist(json.dumps({
'k': self._K,
't': token,
}))
# Sometimes authentication fails for no good reason, retry with
# a different random padding
links_data = None
for _ in range(3):
2018-06-02 19:07:36 +02:00
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
n, e = self._RSA_KEY
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
authorization = base64.b64encode(encrypted_message).decode()
2021-01-16 13:40:15 +01:00
try:
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
})
break
except ExtractorError as e:
if not isinstance(e.cause, compat_HTTPError):
raise e
if e.cause.code == 401:
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message)
2021-01-16 13:40:15 +01:00
else:
raise ExtractorError('Giving up retrying')
links = links_data.get('links') or {}
metas = links_data.get('metadata') or {}
sub_url = (links.get('subtitles') or {}).get('all')
video_info = links_data.get('video') or {}
title = metas['title']
2017-03-31 13:24:23 +02:00
formats = []
2021-01-16 13:40:15 +01:00
for format_id, qualities in (links.get('streaming') or {}).items():
2017-05-26 21:00:44 +02:00
if not isinstance(qualities, dict):
continue
for quality, load_balancer_url in qualities.items():
2017-03-31 13:24:23 +02:00
load_balancer_data = self._download_json(
load_balancer_url, video_id,
'Downloading %s %s JSON metadata' % (format_id, quality),
fatal=False) or {}
2017-03-31 13:24:23 +02:00
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
continue
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False)
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
formats.extend(m3u8_formats)
self._sort_formats(formats)
2021-01-16 13:40:15 +01:00
video = (self._download_json(
self._API_BASE_URL + 'video/%s' % video_id, video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
show = video.get('show') or {}
2017-03-31 13:24:23 +02:00
return {
'id': video_id,
'title': title,
2021-01-16 13:40:15 +01:00
'description': strip_or_none(metas.get('summary') or video.get('summary')),
'thumbnail': video_info.get('image') or player.get('image'),
2017-03-31 13:24:23 +02:00
'formats': formats,
2021-01-16 13:40:15 +01:00
'subtitles': self.extract_subtitles(sub_url, video_id),
'episode': metas.get('subtitle') or video.get('name'),
'episode_number': int_or_none(video.get('shortNumber')),
'series': show.get('title'),
'season_number': int_or_none(video.get('season')),
'duration': int_or_none(video_info.get('duration') or video.get('duration')),
'release_date': unified_strdate(video.get('releaseDate')),
'average_rating': float_or_none(video.get('rating') or metas.get('rating')),
'comment_count': int_or_none(video.get('commentsCount')),
2017-03-31 13:24:23 +02:00
}