yt-dlp/yt_dlp/extractor/youku.py

291 lines
11 KiB
Python
Raw Normal View History

2015-12-31 06:05:46 +01:00
import random
2016-06-08 17:45:46 +02:00
import re
2015-12-31 06:05:46 +01:00
import string
import time
2013-06-23 22:01:02 +02:00
from .common import InfoExtractor
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 17:18:17 +01:00
from ..utils import (
ExtractorError,
clean_html,
2017-05-26 15:59:16 +02:00
get_element_by_class,
js_to_json,
str_or_none,
2017-05-26 15:59:16 +02:00
strip_jsonp,
)
2015-06-15 16:41:24 +02:00
2013-06-23 22:01:02 +02:00
class YoukuIE(InfoExtractor):
2015-05-28 11:00:09 +02:00
IE_NAME = 'youku'
2015-07-10 18:58:13 +02:00
IE_DESC = '优酷'
2014-09-25 09:58:09 +02:00
_VALID_URL = r'''(?x)
(?:
https?://(
(?:v|play(?:er)?)\.(?:youku|tudou)\.com/(?:v_show/id_|player\.php/sid/)|
video\.tudou\.com/v/)|
2014-09-25 09:58:09 +02:00
youku:)
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
2015-05-28 11:00:09 +02:00
2015-06-15 17:36:28 +02:00
_TESTS = [{
'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
'only_matching': True,
2015-08-31 18:19:58 +02:00
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'note': 'Video protected with password',
'info_dict': {
'id': 'XNjA1NzA2Njgw',
2017-05-26 08:15:46 +02:00
'ext': 'mp4',
2015-09-01 18:26:17 +02:00
'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
'duration': 7264.5,
'thumbnail': r're:^https?://.*',
'uploader': 'FoxJin1006',
'uploader_id': '322014285',
'uploader_url': 'http://i.youku.com/u/UMTI4ODA1NzE0MA==',
'tags': list,
'skip': '404',
2015-08-31 18:19:58 +02:00
},
'params': {
'videopassword': '100600',
},
}, {
# /play/get.json contains streams with "channel_type":"tail"
'url': 'http://v.youku.com/v_show/id_XOTUxMzg4NDMy.html',
'info_dict': {
'id': 'XOTUxMzg4NDMy',
2017-05-26 08:15:46 +02:00
'ext': 'mp4',
'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
'duration': 702.08,
'thumbnail': r're:^https?://.*',
'uploader': '明月庄主moon',
'uploader_id': '38465621',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UMTUzODYyNDg0',
'tags': list,
},
}, {
'url': 'https://v.youku.com/v_show/id_XNTA2NTA0MjA1Mg==.html',
'info_dict': {
'id': 'XNTA2NTA0MjA1Mg',
'ext': 'mp4',
'title': 'Minecraft我的世界建造超大巨型航空飞机菜鸟vs高手vs黑客',
'duration': 542.13,
'thumbnail': r're:^https?://.*',
'uploader': '波哥游戏解说',
'uploader_id': '156688084',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjI2NzUyMzM2',
'tags': list,
},
}, {
'url': 'https://v.youku.com/v_show/id_XNTE1MzczOTg4MA==.html',
'info_dict': {
'id': 'XNTE1MzczOTg4MA',
'ext': 'mp4',
'title': '国产超A特工片',
'duration': 362.97,
'thumbnail': r're:^https?://.*',
'uploader': '陈晓娟说历史',
'uploader_id': '1640913339',
'uploader_url': 'https://www.youku.com/profile/index/?uid=UNjU2MzY1MzM1Ng==',
'tags': list,
},
}, {
'url': 'https://play.tudou.com/v_show/id_XNjAxNjI2OTU3Ng==.html?',
'info_dict': {
'id': 'XNjAxNjI2OTU3Ng',
'ext': 'mp4',
'title': '阿斯塔意识到哈里杀了人,自己被骗了',
'thumbnail': 'https://m.ykimg.com/0541010164F732752794D4D7B70331D1',
'uploader_id': '88758207',
'tags': [],
'uploader_url': 'https://www.youku.com/profile/index/?uid=UMzU1MDMyODI4',
'uploader': '英美剧场',
'duration': 72.91,
},
2015-06-15 17:36:28 +02:00
}]
2013-06-27 20:25:46 +02:00
2015-12-31 06:05:46 +01:00
@staticmethod
def get_ysuid():
return '%d%s' % (int(time.time()), ''.join(
random.choices(string.ascii_letters, k=3)))
2015-12-31 06:05:46 +01:00
2015-05-30 04:03:32 +02:00
def get_format_name(self, fm):
_dict = {
2015-06-15 16:41:24 +02:00
'3gp': 'h6',
'3gphd': 'h5',
'flv': 'h4',
2015-12-12 08:24:58 +01:00
'flvhd': 'h4',
2015-06-15 16:41:24 +02:00
'mp4': 'h3',
'mp4hd': 'h3',
2015-12-12 08:24:58 +01:00
'mp4hd2': 'h4',
'mp4hd3': 'h4',
2015-12-12 08:24:58 +01:00
'hd2': 'h2',
'hd3': 'h1',
2015-05-30 04:03:32 +02:00
}
2017-05-26 08:15:46 +02:00
return _dict.get(fm)
2015-05-30 04:03:32 +02:00
2013-06-23 22:01:02 +02:00
def _real_extract(self, url):
2015-06-15 17:31:30 +02:00
video_id = self._match_id(url)
2013-06-23 22:01:02 +02:00
2015-12-31 06:05:46 +01:00
self._set_cookie('youku.com', '__ysuid', self.get_ysuid())
2017-05-26 08:15:46 +02:00
self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
2015-12-31 06:05:46 +01:00
2017-05-26 08:15:46 +02:00
_, urlh = self._download_webpage_handle(
'https://log.mmstat.com/eg.js', video_id, 'Retrieving cna info')
# The etag header is '"foobar"'; let's remove the double quotes
cna = urlh.headers['etag'][1:-1]
2017-05-26 08:15:46 +02:00
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0524',
2017-05-26 08:15:46 +02:00
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,
}
video_password = self.get_param('videopassword')
2015-08-31 18:19:58 +02:00
if video_password:
2017-05-26 08:15:46 +02:00
basic_data_params['password'] = video_password
2015-09-01 05:07:47 +02:00
2017-05-26 08:15:46 +02:00
headers = {
'Referer': url,
}
headers.update(self.geo_verification_headers())
data = self._download_json(
'https://ups.youku.com/ups/get.json', video_id,
'Downloading JSON metadata',
query=basic_data_params, headers=headers)['data']
2014-09-25 09:58:09 +02:00
2015-12-12 04:26:15 +01:00
error = data.get('error')
if error:
error_note = error.get('note')
if error_note is not None and '因版权原因无法观看此视频' in error_note:
2015-06-15 17:54:55 +02:00
raise ExtractorError(
'Youku said: Sorry, this video is available in China only', expected=True)
elif error_note and '该视频被设为私密' in error_note:
raise ExtractorError(
'Youku said: Sorry, this video is private', expected=True)
2015-06-15 17:54:55 +02:00
else:
msg = 'Youku server reported error %i' % error.get('code')
2015-12-17 12:51:50 +01:00
if error_note is not None:
msg += ': ' + clean_html(error_note)
2015-06-15 17:54:55 +02:00
raise ExtractorError(msg)
2015-05-28 11:00:09 +02:00
2015-12-12 07:41:53 +01:00
# get video title
video_data = data['video']
title = video_data['title']
2015-05-28 11:00:09 +02:00
2017-05-26 08:15:46 +02:00
formats = [{
'url': stream['m3u8_url'],
'format_id': self.get_format_name(stream.get('stream_type')),
'ext': 'mp4',
'protocol': 'm3u8_native',
'filesize': int(stream.get('size')),
'width': stream.get('width'),
'height': stream.get('height'),
} for stream in data['stream'] if stream.get('channel_type') != 'tail']
2015-05-28 11:00:09 +02:00
return {
'id': video_id,
'title': title,
2017-05-26 08:15:46 +02:00
'formats': formats,
'duration': video_data.get('seconds'),
'thumbnail': video_data.get('logo'),
'uploader': video_data.get('username'),
'uploader_id': str_or_none(video_data.get('userid')),
'uploader_url': data.get('uploader', {}).get('homepage'),
'tags': video_data.get('tags'),
}
2016-06-08 17:45:46 +02:00
class YoukuShowIE(InfoExtractor):
2017-05-26 15:59:16 +02:00
_VALID_URL = r'https?://list\.youku\.com/show/id_(?P<id>[0-9a-z]+)\.html'
2016-06-08 17:45:46 +02:00
IE_NAME = 'youku:show'
_TESTS = [{
2017-05-26 15:59:16 +02:00
'url': 'http://list.youku.com/show/id_zc7c670be07ff11e48b3f.html',
2016-06-08 17:45:46 +02:00
'info_dict': {
'id': 'zc7c670be07ff11e48b3f',
'title': '花千骨 DVD版',
2017-05-26 15:59:16 +02:00
'description': 'md5:a1ae6f5618571bbeb5c9821f9c81b558',
2016-06-08 17:45:46 +02:00
},
'playlist_count': 50,
}, {
# Episode number not starting from 1
'url': 'http://list.youku.com/show/id_zefbfbd70efbfbd780bef.html',
'info_dict': {
'id': 'zefbfbd70efbfbd780bef',
'title': '超级飞侠3',
'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
},
'playlist_count': 24,
}, {
# Ongoing playlist. The initial page is the last one
'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
'only_matching': True,
}, {
# No data-id value.
'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html',
'only_matching': True,
}, {
# Wrong number of reload_id.
'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html',
'only_matching': True,
}]
2016-06-08 17:45:46 +02:00
def _extract_entries(self, playlist_data_url, show_id, note, query):
query['callback'] = 'cb'
playlist_data = self._download_json(
playlist_data_url, show_id, query=query, note=note,
transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html')
if playlist_data is None:
return [None, None]
drama_list = (get_element_by_class('p-drama-grid', playlist_data)
or get_element_by_class('p-drama-half-row', playlist_data))
if drama_list is None:
raise ExtractorError('No episodes found')
video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
return playlist_data, [
self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
for video_url in video_urls]
2016-06-08 17:45:46 +02:00
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = []
2017-05-26 15:59:16 +02:00
page_config = self._parse_json(self._search_regex(
r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
show_id, transform_source=js_to_json)
first_page, initial_entries = self._extract_entries(
'http://list.youku.com/show/module', show_id,
note='Downloading initial playlist data page',
query={
'id': page_config['showid'],
'tab': 'showInfo',
})
first_page_reload_id = self._html_search_regex(
r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
# The first reload_id has the same items as first_page
reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
entries.extend(initial_entries)
for idx, reload_id in enumerate(reload_ids):
if reload_id == first_page_reload_id:
continue
_, new_entries = self._extract_entries(
'http://list.youku.com/show/episode', show_id,
note='Downloading playlist data page %d' % (idx + 1),
query={
2017-05-26 15:59:16 +02:00
'id': page_config['showid'],
'stage': reload_id,
})
if new_entries is not None:
entries.extend(new_entries)
2017-05-26 15:59:16 +02:00
desc = self._html_search_meta('description', webpage, fatal=False)
playlist_title = desc.split(',')[0] if desc else None
detail_li = get_element_by_class('p-intro', webpage)
playlist_description = get_element_by_class(
'intro-more', detail_li) if detail_li else None
return self.playlist_result(
entries, show_id, playlist_title, playlist_description)