yt-dlp/youtube_dl/extractor/leeco.py

368 lines
13 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2016-03-02 18:42:19 +00:00
import base64
2015-02-26 00:30:18 +00:00
import datetime
2016-03-02 18:42:19 +00:00
import hashlib
2015-02-24 16:45:11 +00:00
import re
import time
from .common import InfoExtractor
2015-02-26 00:30:18 +00:00
from ..compat import (
compat_ord,
2016-01-30 23:13:21 +00:00
compat_str,
2016-03-02 18:42:19 +00:00
compat_urllib_parse,
2015-02-26 00:30:18 +00:00
)
from ..utils import (
determine_ext,
2016-03-02 18:42:19 +00:00
encode_data_uri,
2015-02-26 00:30:18 +00:00
ExtractorError,
2016-03-02 18:42:19 +00:00
int_or_none,
orderedSet,
2015-02-26 00:30:18 +00:00
parse_iso8601,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
sanitized_Request,
2015-12-20 11:09:45 +00:00
str_or_none,
url_basename,
2015-02-26 00:30:18 +00:00
)
class LeIE(InfoExtractor):
2015-07-10 16:51:26 +00:00
IE_DESC = '乐视网'
_VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
2016-03-02 18:38:41 +00:00
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
_TESTS = [{
2016-03-02 18:38:41 +00:00
'url': 'http://www.le.com/ptv/vplay/22005890.html',
'md5': 'edadcfe5406976f42f9f266057ee5e40',
'info_dict': {
'id': '22005890',
'ext': 'mp4',
'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
2015-02-24 18:10:55 +00:00
'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
},
'params': {
'hls_prefer_native': True,
},
}, {
2016-03-02 18:38:41 +00:00
'url': 'http://www.le.com/ptv/vplay/1415246.html',
'info_dict': {
2015-02-24 18:10:55 +00:00
'id': '1415246',
'ext': 'mp4',
2015-02-24 18:10:55 +00:00
'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
},
'params': {
'hls_prefer_native': True,
},
}, {
'note': 'This video is available only in Mainland China, thus a proxy is needed',
2016-03-02 18:38:41 +00:00
'url': 'http://www.le.com/ptv/vplay/1118082.html',
'md5': '2424c74948a62e5f31988438979c5ad1',
'info_dict': {
'id': '1118082',
'ext': 'mp4',
'title': '与龙共舞 完整版',
'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
},
'params': {
'hls_prefer_native': True,
},
'skip': 'Only available in China',
}]
@staticmethod
def urshift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n
2015-02-26 00:30:18 +00:00
# ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
def ror(self, param1, param2):
_loc3_ = 0
while _loc3_ < param2:
param1 = self.urshift(param1, 1) + ((param1 & 1) << 31)
_loc3_ += 1
return param1
2015-02-26 00:30:18 +00:00
def calc_time_key(self, param1):
_loc2_ = 773625421
_loc3_ = self.ror(param1, _loc2_ % 13)
_loc3_ = _loc3_ ^ _loc2_
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# see M3U8Encryption class in KLetvPlayer.swf
@staticmethod
def decrypt_m3u8(encrypted_data):
if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
return encrypted_data
encrypted_data = encrypted_data[5:]
2016-02-26 16:57:35 +00:00
_loc4_ = bytearray(2 * len(encrypted_data))
for idx, val in enumerate(encrypted_data):
b = compat_ord(val)
_loc4_[2 * idx] = b // 16
_loc4_[2 * idx + 1] = b % 16
idx = len(_loc4_) - 11
_loc4_ = _loc4_[idx:] + _loc4_[:idx]
2016-02-26 16:57:35 +00:00
_loc7_ = bytearray(len(encrypted_data))
for i in range(len(encrypted_data)):
_loc7_[i] = _loc4_[2 * i] * 16 + _loc4_[2 * i + 1]
return bytes(_loc7_)
def _real_extract(self, url):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
params = {
'id': media_id,
'platid': 1,
'splatid': 101,
'format': 1,
2015-02-26 00:30:18 +00:00
'tkey': self.calc_time_key(int(time.time())),
2016-03-02 18:38:41 +00:00
'domain': 'www.le.com'
}
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
play_json_req = sanitized_Request(
2016-03-02 18:38:41 +00:00
'http://api.le.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
)
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
play_json = self._download_json(
play_json_req,
2015-03-17 14:01:31 +00:00
media_id, 'Downloading playJson data')
# Check for errors
playstatus = play_json['playstatus']
if playstatus['status'] == 0:
flag = playstatus['flag']
if flag == 1:
msg = 'Country %s auth error' % playstatus['country']
else:
msg = 'Generic error. flag = %d' % flag
raise ExtractorError(msg, expected=True)
playurl = play_json['playurl']
formats = ['350', '1000', '1300', '720p', '1080p']
dispatch = playurl['dispatch']
urls = []
for format_id in formats:
if format_id in dispatch:
media_url = playurl['domain'][0] + dispatch[format_id][0]
media_url += '&' + compat_urllib_parse.urlencode({
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
})
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id)
req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id,
note='Downloading m3u8 information for format %s' % format_id)
m3u8_data = self.decrypt_m3u8(req.read())
url_info_dict = {
'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
'ext': determine_ext(dispatch[format_id][1]),
'format_id': format_id,
'protocol': 'm3u8',
}
if format_id[-1:] == 'p':
2015-07-24 13:46:45 +00:00
url_info_dict['height'] = int_or_none(format_id[:-1])
urls.append(url_info_dict)
publish_time = parse_iso8601(self._html_search_regex(
r'发布时间&nbsp;([^<>]+) ', page, 'publish time', default=None),
delimiter=' ', timezone=datetime.timedelta(hours=8))
2015-02-24 18:10:55 +00:00
description = self._html_search_meta('description', page, fatal=False)
return {
'id': media_id,
'formats': urls,
'title': playurl['title'],
'thumbnail': playurl['pic'],
2015-02-24 18:10:55 +00:00
'description': description,
'timestamp': publish_time,
}
2015-02-24 16:45:11 +00:00
class LePlaylistIE(InfoExtractor):
_VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
2015-02-24 16:45:11 +00:00
_TESTS = [{
2016-03-02 18:38:41 +00:00
'url': 'http://www.le.com/tv/46177.html',
2015-02-24 16:45:11 +00:00
'info_dict': {
'id': '46177',
'title': '美人天下',
'description': 'md5:395666ff41b44080396e59570dbac01c'
},
'playlist_count': 35
}, {
2016-03-02 18:38:41 +00:00
'url': 'http://tv.le.com/izt/wuzetian/index.html',
2015-02-24 16:45:11 +00:00
'info_dict': {
'id': 'wuzetian',
'title': '武媚娘传奇',
'description': 'md5:e12499475ab3d50219e5bba00b3cb248'
},
2015-02-24 18:10:55 +00:00
# This playlist contains some extra videos other than the drama itself
'playlist_mincount': 96
2015-02-24 16:45:11 +00:00
}, {
2016-03-02 18:38:41 +00:00
'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml',
2015-02-24 16:45:11 +00:00
'info_dict': {
'id': 'lswjzzjc',
2015-02-24 18:10:55 +00:00
# The title should be "劲舞青春", but I can't find a simple way to
# determine the playlist title
2015-02-24 16:45:11 +00:00
'title': '乐视午间自制剧场',
'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489'
},
'playlist_mincount': 7
}, {
'url': 'http://www.le.com/comic/92063.html',
'only_matching': True,
}, {
'url': 'http://list.le.com/listn/c1009_sc532002_d2_p1_o1.html',
'only_matching': True,
2015-02-24 16:45:11 +00:00
}]
2015-12-20 11:09:45 +00:00
@classmethod
def suitable(cls, url):
return False if LeIE.suitable(url) else super(LePlaylistIE, cls).suitable(url)
def _real_extract(self, url):
playlist_id = self._match_id(url)
page = self._download_webpage(url, playlist_id)
# Currently old domain names are still used in playlists
media_ids = orderedSet(re.findall(
r'<a[^>]+href="http://www\.letv\.com/ptv/vplay/(\d+)\.html', page))
entries = [self.url_result(LeIE._URL_TEMPLATE % media_id, ie='Le')
for media_id in media_ids]
title = self._html_search_meta('keywords', page,
fatal=False).split('')[0]
description = self._html_search_meta('description', page, fatal=False)
return self.playlist_result(entries, playlist_id, playlist_title=title,
playlist_description=description)
2015-12-20 11:09:45 +00:00
class LetvCloudIE(InfoExtractor):
# Most of *.letv.com is changed to *.le.com on 2016/01/02
# but yuntv.letv.com is kept, so also keep the extractor name
2015-12-20 11:09:45 +00:00
IE_DESC = '乐视云'
_VALID_URL = r'https?://yuntv\.letv\.com/bcloud.html\?.+'
2015-12-20 11:09:45 +00:00
_TESTS = [{
'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=467623dedf',
'md5': '26450599afd64c513bc77030ad15db44',
'info_dict': {
'id': 'p7jnfw5hw9_467623dedf',
'ext': 'mp4',
'title': 'Video p7jnfw5hw9_467623dedf',
2015-12-20 11:09:45 +00:00
},
}, {
'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=ec93197892&pu=2c7cd40209&auto_play=1&gpcflag=1&width=640&height=360',
2016-01-30 23:13:21 +00:00
'md5': 'e03d9cc8d9c13191e1caf277e42dbd31',
2015-12-20 11:09:45 +00:00
'info_dict': {
'id': 'p7jnfw5hw9_ec93197892',
'ext': 'mp4',
'title': 'Video p7jnfw5hw9_ec93197892',
2015-12-20 11:09:45 +00:00
},
}, {
'url': 'http://yuntv.letv.com/bcloud.html?uu=p7jnfw5hw9&vu=187060b6fd',
2016-01-30 23:13:21 +00:00
'md5': 'cb988699a776b22d4a41b9d43acfb3ac',
2015-12-20 11:09:45 +00:00
'info_dict': {
'id': 'p7jnfw5hw9_187060b6fd',
'ext': 'mp4',
'title': 'Video p7jnfw5hw9_187060b6fd',
2015-12-20 11:09:45 +00:00
},
}]
2016-01-30 23:13:21 +00:00
@staticmethod
def sign_data(obj):
if obj['cf'] == 'flash':
salt = '2f9d6924b33a165a6d8b5d3d42f4f987'
items = ['cf', 'format', 'ran', 'uu', 'ver', 'vu']
elif obj['cf'] == 'html5':
salt = 'fbeh5player12c43eccf2bec3300344'
items = ['cf', 'ran', 'uu', 'bver', 'vu']
input_data = ''.join([item + obj[item] for item in items]) + salt
obj['sign'] = hashlib.md5(input_data.encode('utf-8')).hexdigest()
def _get_formats(self, cf, uu, vu, media_id):
def get_play_json(cf, timestamp):
data = {
'cf': cf,
'ver': '2.2',
'bver': 'firefox44.0',
'format': 'json',
'uu': uu,
'vu': vu,
'ran': compat_str(timestamp),
}
self.sign_data(data)
return self._download_json(
'http://api.letvcloud.com/gpc.php?' + compat_urllib_parse.urlencode(data),
media_id, 'Downloading playJson data for type %s' % cf)
play_json = get_play_json(cf, time.time())
# The server time may be different from local time
if play_json.get('code') == 10071:
play_json = get_play_json(cf, play_json['timestamp'])
2015-12-20 11:09:45 +00:00
if not play_json.get('data'):
if play_json.get('message'):
raise ExtractorError('Letv cloud said: %s' % play_json['message'], expected=True)
elif play_json.get('code'):
raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True)
else:
raise ExtractorError('Letv cloud returned an unknwon error')
def b64decode(s):
return base64.b64decode(s.encode('utf-8')).decode('utf-8')
2016-01-19 19:17:35 +00:00
formats = []
for media in play_json['data']['video_info']['media'].values():
play_url = media['play_url']
url = b64decode(play_url['main_url'])
decoded_url = b64decode(url_basename(url))
2016-01-19 19:17:35 +00:00
formats.append({
'url': url,
'ext': determine_ext(decoded_url),
2016-01-19 19:17:35 +00:00
'format_id': int_or_none(play_url.get('vtype')),
'format_note': str_or_none(play_url.get('definition')),
'width': int_or_none(play_url.get('vwidth')),
'height': int_or_none(play_url.get('vheight')),
})
2016-01-30 23:13:21 +00:00
return formats
def _real_extract(self, url):
uu_mobj = re.search('uu=([\w]+)', url)
vu_mobj = re.search('vu=([\w]+)', url)
if not uu_mobj or not vu_mobj:
raise ExtractorError('Invalid URL: %s' % url, expected=True)
uu = uu_mobj.group(1)
vu = vu_mobj.group(1)
media_id = uu + '_' + vu
formats = self._get_formats('flash', uu, vu, media_id) + self._get_formats('html5', uu, vu, media_id)
2015-12-20 11:09:45 +00:00
self._sort_formats(formats)
return {
'id': media_id,
'title': 'Video %s' % media_id,
2015-12-20 11:09:45 +00:00
'formats': formats,
}