mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2026-06-12 13:54:28 +00:00
3ba1534fa3
Closes #2623 Closes #2679 Closes #2821 Closes #3416 Closes #4828 Closes #4939 Closes #5421 Closes #7064 Closes #7264 Closes #7654 Closes #8075 Closes #8798 Closes #9313 Closes #9617 Closes #10162 Closes #10252 Closes #10264 Closes #15640 Authored by: doe1080, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>
246 lines
8.4 KiB
Python
246 lines
8.4 KiB
Python
import datetime as dt
|
||
import re
|
||
import time
|
||
|
||
from .common import InfoExtractor
|
||
from ..compat import compat_ord
|
||
from ..utils import (
|
||
ExtractorError,
|
||
determine_ext,
|
||
encode_data_uri,
|
||
int_or_none,
|
||
orderedSet,
|
||
parse_iso8601,
|
||
urshift,
|
||
)
|
||
|
||
|
||
class LeIE(InfoExtractor):
|
||
IE_DESC = '乐视网'
|
||
_VALID_URL = r'https?://(?:www\.le\.com/ptv/vplay|(?:sports\.le|(?:www\.)?lesports)\.com/(?:match|video))/(?P<id>\d+)\.html'
|
||
_GEO_COUNTRIES = ['CN']
|
||
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
|
||
|
||
_TESTS = [{
|
||
'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',
|
||
'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
|
||
},
|
||
'params': {
|
||
'hls_prefer_native': True,
|
||
},
|
||
}, {
|
||
'url': 'http://www.le.com/ptv/vplay/1415246.html',
|
||
'info_dict': {
|
||
'id': '1415246',
|
||
'ext': 'mp4',
|
||
'title': '美人天下01',
|
||
'description': 'md5:28942e650e82ed4fcc8e4de919ee854d',
|
||
},
|
||
'params': {
|
||
'hls_prefer_native': True,
|
||
},
|
||
}, {
|
||
'note': 'This video is available only in Mainland China, thus a proxy is needed',
|
||
'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,
|
||
},
|
||
}, {
|
||
'url': 'http://sports.le.com/video/25737697.html',
|
||
'only_matching': True,
|
||
}, {
|
||
'url': 'http://www.lesports.com/match/1023203003.html',
|
||
'only_matching': True,
|
||
}, {
|
||
'url': 'http://sports.le.com/match/1023203003.html',
|
||
'only_matching': True,
|
||
}]
|
||
|
||
# ror() and calc_time_key() are reversed from a embedded swf file in LetvPlayer.swf
|
||
def ror(self, param1, param2):
|
||
_loc3_ = 0
|
||
while _loc3_ < param2:
|
||
param1 = urshift(param1, 1) + ((param1 & 1) << 31)
|
||
_loc3_ += 1
|
||
return param1
|
||
|
||
def calc_time_key(self, param1):
|
||
_loc2_ = 185025305
|
||
return self.ror(param1, _loc2_ % 17) ^ _loc2_
|
||
|
||
# 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:]
|
||
|
||
_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]
|
||
_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 _check_errors(self, play_json):
|
||
# Check for errors
|
||
playstatus = play_json['msgs']['playstatus']
|
||
if playstatus['status'] == 0:
|
||
flag = playstatus['flag']
|
||
if flag == 1:
|
||
self.raise_geo_restricted()
|
||
else:
|
||
raise ExtractorError('Generic error. flag = %d' % flag, expected=True)
|
||
|
||
def _real_extract(self, url):
|
||
media_id = self._match_id(url)
|
||
page = self._download_webpage(url, media_id)
|
||
|
||
play_json_flash = self._download_json(
|
||
'http://player-pc.le.com/mms/out/video/playJson',
|
||
media_id, 'Downloading flash playJson data', query={
|
||
'id': media_id,
|
||
'platid': 1,
|
||
'splatid': 105,
|
||
'format': 1,
|
||
'source': 1000,
|
||
'tkey': self.calc_time_key(int(time.time())),
|
||
'domain': 'www.le.com',
|
||
'region': 'cn',
|
||
},
|
||
headers=self.geo_verification_headers())
|
||
self._check_errors(play_json_flash)
|
||
|
||
def get_flash_urls(media_url, format_id):
|
||
nodes_data = self._download_json(
|
||
media_url, media_id,
|
||
f'Download JSON metadata for format {format_id}',
|
||
query={
|
||
'm3v': 1,
|
||
'format': 1,
|
||
'expect': 3,
|
||
'tss': 'ios',
|
||
})
|
||
|
||
req = self._request_webpage(
|
||
nodes_data['nodelist'][0]['location'], media_id,
|
||
note=f'Downloading m3u8 information for format {format_id}')
|
||
|
||
m3u8_data = self.decrypt_m3u8(req.read())
|
||
|
||
return {
|
||
'hls': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
|
||
}
|
||
|
||
extracted_formats = []
|
||
formats = []
|
||
playurl = play_json_flash['msgs']['playurl']
|
||
play_domain = playurl['domain'][0]
|
||
|
||
for format_id, format_data in playurl.get('dispatch', []).items():
|
||
if format_id in extracted_formats:
|
||
continue
|
||
extracted_formats.append(format_id)
|
||
|
||
media_url = play_domain + format_data[0]
|
||
for protocol, format_url in get_flash_urls(media_url, format_id).items():
|
||
f = {
|
||
'url': format_url,
|
||
'ext': determine_ext(format_data[1]),
|
||
'format_id': f'{protocol}-{format_id}',
|
||
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
|
||
'quality': int_or_none(format_id),
|
||
}
|
||
|
||
if format_id[-1:] == 'p':
|
||
f['height'] = int_or_none(format_id[:-1])
|
||
|
||
formats.append(f)
|
||
|
||
publish_time = parse_iso8601(self._html_search_regex(
|
||
r'发布时间 ([^<>]+) ', page, 'publish time', default=None),
|
||
delimiter=' ', timezone=dt.timedelta(hours=8))
|
||
description = self._html_search_meta('description', page, fatal=False)
|
||
|
||
return {
|
||
'id': media_id,
|
||
'formats': formats,
|
||
'title': playurl['title'],
|
||
'thumbnail': playurl['pic'],
|
||
'description': description,
|
||
'timestamp': publish_time,
|
||
'_format_sort_fields': ('res', 'quality'),
|
||
}
|
||
|
||
|
||
class LePlaylistIE(InfoExtractor):
|
||
_VALID_URL = r'https?://[a-z]+\.le\.com/(?!video)[a-z]+/(?P<id>[a-z0-9_]+)'
|
||
|
||
_TESTS = [{
|
||
'url': 'http://www.le.com/tv/46177.html',
|
||
'info_dict': {
|
||
'id': '46177',
|
||
'title': '美人天下',
|
||
'description': 'md5:395666ff41b44080396e59570dbac01c',
|
||
},
|
||
'playlist_count': 35,
|
||
}, {
|
||
'url': 'http://tv.le.com/izt/wuzetian/index.html',
|
||
'info_dict': {
|
||
'id': 'wuzetian',
|
||
'title': '武媚娘传奇',
|
||
'description': 'md5:e12499475ab3d50219e5bba00b3cb248',
|
||
},
|
||
# This playlist contains some extra videos other than the drama itself
|
||
'playlist_mincount': 96,
|
||
}, {
|
||
'url': 'http://tv.le.com/pzt/lswjzzjc/index.shtml',
|
||
# This series is moved to http://www.le.com/tv/10005297.html
|
||
'only_matching': True,
|
||
}, {
|
||
'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,
|
||
}]
|
||
|
||
@classmethod
|
||
def suitable(cls, url):
|
||
return False if LeIE.suitable(url) else super().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)
|