yt-dlp/youtube_dl/extractor/youku.py

209 lines
6.9 KiB
Python
Raw Normal View History

2013-06-27 18:32:02 +00:00
# coding: utf-8
2014-09-25 07:58:09 +00:00
from __future__ import unicode_literals
2016-06-08 15:45:46 +00:00
import itertools
2015-12-31 05:05:46 +00:00
import random
2016-06-08 15:45:46 +00:00
import re
2015-12-31 05:05:46 +00:00
import string
import time
2013-06-23 20:01:02 +00:00
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 16:18:17 +00:00
from ..utils import (
ExtractorError,
2016-06-08 15:45:46 +00:00
get_element_by_attribute,
)
2015-06-15 14:41:24 +00:00
2013-06-23 20:01:02 +00:00
class YoukuIE(InfoExtractor):
2015-05-28 09:00:09 +00:00
IE_NAME = 'youku'
2015-07-10 16:58:13 +00:00
IE_DESC = '优酷'
2014-09-25 07:58:09 +00:00
_VALID_URL = r'''(?x)
(?:
http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
youku:)
(?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
'''
2015-05-28 09:00:09 +00:00
2015-06-15 15:36:28 +00:00
_TESTS = [{
2015-12-12 06:48:46 +00:00
# MD5 is unstable
2015-06-15 14:41:24 +00:00
'url': 'http://v.youku.com/v_show/id_XMTc1ODE5Njcy.html',
'info_dict': {
2017-05-26 06:15:46 +00:00
'id': 'XMTc1ODE5Njcy',
2015-06-15 14:41:24 +00:00
'title': '★Smile﹗♡ Git Fresh -Booty Music舞蹈.',
2017-05-26 06:15:46 +00:00
'ext': 'mp4',
2015-06-15 14:41:24 +00:00
}
2015-06-15 15:36:28 +00:00
}, {
'url': 'http://player.youku.com/player.php/sid/XNDgyMDQ2NTQw/v.swf',
'only_matching': True,
}, {
'url': 'http://v.youku.com/v_show/id_XODgxNjg1Mzk2_ev_1.html',
'info_dict': {
'id': 'XODgxNjg1Mzk2',
2017-05-26 06:15:46 +00:00
'ext': 'mp4',
'title': '武媚娘传奇 85',
},
}, {
'url': 'http://v.youku.com/v_show/id_XMTI1OTczNDM5Mg==.html',
'info_dict': {
'id': 'XMTI1OTczNDM5Mg',
2017-05-26 06:15:46 +00:00
'ext': 'mp4',
'title': '花千骨 04',
},
2015-08-31 16:19:58 +00:00
}, {
'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html',
'note': 'Video protected with password',
'info_dict': {
'id': 'XNjA1NzA2Njgw',
2017-05-26 06:15:46 +00:00
'ext': 'mp4',
2015-09-01 16:26:17 +00:00
'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起',
2015-08-31 16:19:58 +00:00
},
'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 06:15:46 +00:00
'ext': 'mp4',
'title': '我的世界☆明月庄主☆车震猎杀☆杀人艺术Minecraft',
},
2015-06-15 15:36:28 +00:00
}]
2013-06-27 18:25:46 +00:00
2015-12-31 05:05:46 +00:00
@staticmethod
def get_ysuid():
return '%d%s' % (int(time.time()), ''.join([
random.choice(string.ascii_letters) for i in range(3)]))
2015-05-30 02:03:32 +00:00
def get_format_name(self, fm):
_dict = {
2015-06-15 14:41:24 +00:00
'3gp': 'h6',
'3gphd': 'h5',
'flv': 'h4',
2015-12-12 07:24:58 +00:00
'flvhd': 'h4',
2015-06-15 14:41:24 +00:00
'mp4': 'h3',
'mp4hd': 'h3',
2015-12-12 07:24:58 +00:00
'mp4hd2': 'h4',
'mp4hd3': 'h4',
2015-12-12 07:24:58 +00:00
'hd2': 'h2',
'hd3': 'h1',
2015-05-30 02:03:32 +00:00
}
2017-05-26 06:15:46 +00:00
return _dict.get(fm)
2015-05-30 02:03:32 +00:00
2013-06-23 20:01:02 +00:00
def _real_extract(self, url):
2015-06-15 15:31:30 +00:00
video_id = self._match_id(url)
2013-06-23 20:01:02 +00:00
2015-12-31 05:05:46 +00:00
self._set_cookie('youku.com', '__ysuid', self.get_ysuid())
2017-05-26 06:15:46 +00:00
self._set_cookie('youku.com', 'xreferrer', 'http://www.youku.com')
2015-12-31 05:05:46 +00:00
2017-05-26 06:15:46 +00:00
_, 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 06:15:46 +00:00
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0401',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,
}
video_password = self._downloader.params.get('videopassword')
2015-08-31 16:19:58 +00:00
if video_password:
2017-05-26 06:15:46 +00:00
basic_data_params['password'] = video_password
2015-09-01 03:07:47 +00:00
2017-05-26 06:15:46 +00:00
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 07:58:09 +00:00
2015-12-12 03:26:15 +00:00
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 15:54:55 +00:00
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 15:54:55 +00:00
else:
msg = 'Youku server reported error %i' % error.get('code')
2015-12-17 11:51:50 +00:00
if error_note is not None:
msg += ': ' + error_note
2015-06-15 15:54:55 +00:00
raise ExtractorError(msg)
2015-05-28 09:00:09 +00:00
2015-12-12 06:41:53 +00:00
# get video title
2015-12-12 03:26:15 +00:00
title = data['video']['title']
2015-05-28 09:00:09 +00:00
2017-05-26 06:15:46 +00:00
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']
self._sort_formats(formats)
2015-05-28 09:00:09 +00:00
return {
'id': video_id,
'title': title,
2017-05-26 06:15:46 +00:00
'formats': formats,
}
2016-06-08 15:45:46 +00:00
class YoukuShowIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youku\.com/show_page/id_(?P<id>[0-9a-z]+)\.html'
IE_NAME = 'youku:show'
_TEST = {
'url': 'http://www.youku.com/show_page/id_zc7c670be07ff11e48b3f.html',
'info_dict': {
'id': 'zc7c670be07ff11e48b3f',
'title': '花千骨 未删减版',
'description': 'md5:578d4f2145ae3f9128d9d4d863312910',
},
'playlist_count': 50,
}
_PAGE_SIZE = 40
def _find_videos_in_page(self, webpage):
videos = re.findall(
r'<li><a[^>]+href="(?P<url>https?://v\.youku\.com/[^"]+)"[^>]+title="(?P<title>[^"]+)"', webpage)
return [
self.url_result(video_url, YoukuIE.ie_key(), title)
for video_url, title in videos]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = self._find_videos_in_page(webpage)
playlist_title = self._html_search_regex(
r'<span[^>]+class="name">([^<]+)</span>', webpage, 'playlist title', fatal=False)
detail_div = get_element_by_attribute('class', 'detail', webpage) or ''
playlist_description = self._html_search_regex(
r'<span[^>]+style="display:none"[^>]*>([^<]+)</span>',
detail_div, 'playlist description', fatal=False)
for idx in itertools.count(1):
episodes_page = self._download_webpage(
'http://www.youku.com/show_episode/id_%s.html' % show_id,
show_id, query={'divid': 'reload_%d' % (idx * self._PAGE_SIZE + 1)},
note='Downloading episodes page %d' % idx)
new_entries = self._find_videos_in_page(episodes_page)
entries.extend(new_entries)
if len(new_entries) < self._PAGE_SIZE:
break
return self.playlist_result(entries, show_id, playlist_title, playlist_description)