ytdl/youtube_dl/extractor/myvideo.py

177 lines
6.1 KiB
Python
Raw Normal View History

2014-03-09 18:58:34 +01:00
from __future__ import unicode_literals
2013-06-23 20:48:32 +02:00
import binascii
import base64
import hashlib
import re
import json
2013-06-23 20:48:32 +02:00
from .common import InfoExtractor
from ..compat import (
2013-06-23 20:48:32 +02:00
compat_ord,
compat_urllib_parse,
compat_urllib_parse_unquote,
)
from ..utils import (
2013-06-23 20:48:32 +02:00
ExtractorError,
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
sanitized_Request,
2013-06-23 20:48:32 +02:00
)
class MyVideoIE(InfoExtractor):
2014-03-09 18:58:34 +01:00
_VALID_URL = r'http://(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/(?P<id>[0-9]+)/[^?/]+.*'
IE_NAME = 'myvideo'
2013-06-27 20:46:46 +02:00
_TEST = {
2014-03-09 18:58:34 +01:00
'url': 'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
'md5': '2d2753e8130479ba2cb7e0a37002053e',
'info_dict': {
'id': '8229274',
'ext': 'flv',
'title': 'bowling-fail-or-win',
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 20:48:32 +02:00
# Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
# Released into the Public Domain by Tristan Fischer on 2013-05-19
# https://github.com/rg3/youtube-dl/pull/842
2014-11-23 20:41:03 +01:00
def __rc4crypt(self, data, key):
2013-06-23 20:48:32 +02:00
x = 0
box = list(range(256))
for i in list(range(256)):
x = (x + box[i] + compat_ord(key[i % len(key)])) % 256
box[i], box[x] = box[x], box[i]
x = 0
y = 0
out = ''
for char in data:
x = (x + 1) % 256
y = (y + box[x]) % 256
box[x], box[y] = box[y], box[x]
out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256])
return out
2014-11-23 20:41:03 +01:00
def __md5(self, s):
2013-06-23 20:48:32 +02:00
return hashlib.md5(s).hexdigest().encode()
2014-11-23 20:41:03 +01:00
def _real_extract(self, url):
2013-06-23 20:48:32 +02:00
mobj = re.match(self._VALID_URL, url)
2014-03-09 18:58:34 +01:00
video_id = mobj.group('id')
2013-06-23 20:48:32 +02:00
GK = (
2014-11-23 22:21:46 +01:00
b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3'
b'TnpsbA0KTVRkbU1tSTRNdz09'
2013-06-23 20:48:32 +02:00
)
# Get video webpage
webpage_url = 'http://www.myvideo.de/watch/%s' % video_id
webpage = self._download_webpage(webpage_url, video_id)
mobj = re.search('source src=\'(.+?)[.]([^.]+)\'', webpage)
if mobj is not None:
self.report_extraction(video_id)
video_url = mobj.group(1) + '.flv'
video_title = self._html_search_regex('<title>([^<]+)</title>',
2014-11-23 21:39:15 +01:00
webpage, 'title')
2013-06-23 20:48:32 +02:00
2014-03-09 18:58:34 +01:00
return {
'id': video_id,
'url': video_url,
'title': video_title,
}
2013-06-23 20:48:32 +02:00
mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
if mobj is not None:
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
request = sanitized_Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
response = self._download_webpage(request, video_id,
2014-03-09 18:58:34 +01:00
'Downloading video info')
info = json.loads(base64.b64decode(response).decode('utf-8'))
2014-03-09 18:58:34 +01:00
return {
'id': video_id,
'title': info['title'],
'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
'play_path': info['filename'],
'ext': 'flv',
'thumbnail': info['thumbnail'][0]['url'],
}
2013-06-23 20:48:32 +02:00
# try encxml
mobj = re.search('var flashvars={(.+?)}', webpage)
if mobj is None:
2014-03-09 18:58:34 +01:00
raise ExtractorError('Unable to extract video')
2013-06-23 20:48:32 +02:00
params = {}
encxml = ''
sec = mobj.group(1)
for (a, b) in re.findall('(.+?):\'(.+?)\',?', sec):
if not a == '_encxml':
params[a] = b
else:
encxml = compat_urllib_parse_unquote(b)
2013-06-23 20:48:32 +02:00
if not params.get('domain'):
params['domain'] = 'www.myvideo.de'
xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
if 'flash_playertype=MTV' in xmldata_url:
2014-03-09 18:58:34 +01:00
self._downloader.report_warning('avoiding MTV player')
2013-06-23 20:48:32 +02:00
xmldata_url = (
'http://www.myvideo.de/dynamic/get_player_video_xml.php'
'?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
) % video_id
# get enc data
enc_data = self._download_webpage(xmldata_url, video_id).split('=')[1]
enc_data_b = binascii.unhexlify(enc_data)
sk = self.__md5(
base64.b64decode(base64.b64decode(GK)) +
self.__md5(
str(video_id).encode('utf-8')
)
)
dec_data = self.__rc4crypt(enc_data_b, sk)
# extracting infos
self.report_extraction(video_id)
video_url = None
mobj = re.search('connectionurl=\'(.*?)\'', dec_data)
if mobj:
video_url = compat_urllib_parse_unquote(mobj.group(1))
2013-06-23 20:48:32 +02:00
if 'myvideo2flash' in video_url:
self.report_warning(
2014-03-09 18:58:34 +01:00
'Rewriting URL to use unencrypted rtmp:// ...',
video_id)
video_url = video_url.replace('rtmpe://', 'rtmp://')
2013-06-23 20:48:32 +02:00
if not video_url:
# extract non rtmp videos
mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
if mobj is None:
2014-03-09 18:58:34 +01:00
raise ExtractorError('unable to extract url')
video_url = compat_urllib_parse_unquote(mobj.group(1)) + compat_urllib_parse_unquote(mobj.group(2))
2013-06-23 20:48:32 +02:00
2014-03-09 18:58:34 +01:00
video_file = self._search_regex('source=\'(.*?)\'', dec_data, 'video file')
video_file = compat_urllib_parse_unquote(video_file)
2013-06-23 20:48:32 +02:00
if not video_file.endswith('f4m'):
ppath, prefix = video_file.split('.')
video_playpath = '%s:%s' % (prefix, ppath)
else:
video_playpath = ''
2014-03-09 18:58:34 +01:00
video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
video_swfobj = compat_urllib_parse_unquote(video_swfobj)
2013-06-23 20:48:32 +02:00
video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
2014-11-23 21:39:15 +01:00
webpage, 'title')
2014-03-09 18:58:34 +01:00
return {
'id': video_id,
'url': video_url,
'tc_url': video_url,
'title': video_title,
'ext': 'flv',
'play_path': video_playpath,
'player_url': video_swfobj,
}