1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-05 22:57:54 +01:00
youtube-dl/youtube_dl/extractor/gdcvault.py

189 lines
7.1 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
HEADRequest,
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,
smuggle_url,
urlencode_postdata,
)
class GDCVaultIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)(?:/(?P<name>[\w-]+))?'
_NETRC_MACHINE = 'gdcvault'
_TESTS = [
{
'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
'md5': '7ce8388f544c88b7ac11c7ab1b593704',
'info_dict': {
'id': '201311826596_AWNY',
2015-04-24 16:43:33 +02:00
'display_id': 'Doki-Doki-Universe-Sweet-Simple',
'ext': 'mp4',
'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
}
},
2014-02-27 11:32:31 +01:00
{
'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
'info_dict': {
'id': '201203272_1330951438328RSXR',
2015-04-24 16:43:33 +02:00
'display_id': 'Embracing-the-Dark-Art-of',
'ext': 'flv',
'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
},
'params': {
'skip_download': True, # Requires rtmpdump
2014-02-27 11:32:31 +01:00
}
},
{
'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
'md5': 'a5eb77996ef82118afbbe8e48731b98e',
'info_dict': {
'id': '1015301',
2015-04-24 16:43:33 +02:00
'display_id': 'Thexder-Meets-Windows-95-or',
'ext': 'flv',
'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
},
'skip': 'Requires login',
},
{
'url': 'http://gdcvault.com/play/1020791/',
'only_matching': True,
},
{
# Hard-coded hostname
'url': 'http://gdcvault.com/play/1023460/Tenacious-Design-and-The-Interface',
'md5': 'a8efb6c31ed06ca8739294960b2dbabd',
'info_dict': {
'id': '840376_BQRC',
'ext': 'mp4',
'display_id': 'Tenacious-Design-and-The-Interface',
'title': 'Tenacious Design and The Interface of \'Destiny\'',
},
},
{
# Multiple audios
'url': 'http://www.gdcvault.com/play/1014631/Classic-Game-Postmortem-PAC',
'info_dict': {
'id': '12396_1299111843500GMPX',
'ext': 'mp4',
'title': 'How to Create a Good Game - From My Experience of Designing Pac-Man',
},
# 'params': {
# 'skip_download': True, # Requires rtmpdump
# 'format': 'jp', # The japanese audio
# }
},
{
# gdc-player.html
'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
'info_dict': {
'id': '9350_1238021887562UHXB',
'display_id': 'An-American-engine-in-Tokyo',
'ext': 'mp4',
'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
},
},
{
# Kaltura Embed
'url': 'https://www.gdcvault.com/play/1026180/Mastering-the-Apex-of-Scaling',
'info_dict': {
'id': '0_h1fg8j3p',
'ext': 'mp4',
'title': 'Mastering the Apex of Scaling Game Servers (Presented by Multiplay)',
'timestamp': 1554401811,
'upload_date': '20190404',
'uploader_id': 'joe@blazestreaming.com',
},
'params': {
'format': 'mp4-408',
},
},
]
2015-04-24 16:43:33 +02:00
def _login(self, webpage_url, display_id):
username, password = self._get_login_info()
2014-02-27 11:32:31 +01:00
if username is None or password is None:
self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
2014-02-27 11:32:31 +01:00
return None
mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
login_url = mobj.group('root_url') + 'api/login.php'
logout_url = mobj.group('root_url') + 'logout'
login_form = {
'email': username,
'password': password,
}
request = sanitized_Request(login_url, urlencode_postdata(login_form))
2014-02-27 11:32:31 +01:00
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
2015-04-24 16:43:33 +02:00
self._download_webpage(request, display_id, 'Logging in')
start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
self._download_webpage(logout_url, display_id, 'Logging out')
2014-02-27 11:32:31 +01:00
return start_page
def _real_extract(self, url):
video_id, name = re.match(self._VALID_URL, url).groups()
display_id = name or video_id
2015-04-24 16:43:33 +02:00
webpage_url = 'http://www.gdcvault.com/play/' + video_id
2015-04-24 16:43:33 +02:00
start_page = self._download_webpage(webpage_url, display_id)
direct_url = self._search_regex(
r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
start_page, 'url', default=None)
if direct_url:
title = self._html_search_regex(
r'<td><strong>Session Name:?</strong></td>\s*<td>(.*?)</td>',
start_page, 'title')
video_url = 'http://www.gdcvault.com' + direct_url
# resolve the url so that we can detect the correct extension
video_url = self._request_webpage(
HEADRequest(video_url), video_id).geturl()
return {
'id': video_id,
2015-04-24 16:43:33 +02:00
'display_id': display_id,
'url': video_url,
'title': title,
}
2014-02-27 11:32:31 +01:00
embed_url = KalturaIE._extract_url(start_page)
if embed_url:
embed_url = smuggle_url(embed_url, {'source_url': url})
ie_key = 'Kaltura'
else:
PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
xml_root = self._html_search_regex(
PLAYER_REGEX, start_page, 'xml root', default=None)
if xml_root is None:
# Probably need to authenticate
login_res = self._login(webpage_url, display_id)
if login_res is None:
self.report_warning('Could not login.')
else:
start_page = login_res
# Grab the url from the authenticated page
xml_root = self._html_search_regex(
PLAYER_REGEX, start_page, 'xml root')
xml_name = self._html_search_regex(
r'<iframe src=".*?\?xml(?:=|URL=xml/)(.+?\.xml).*?".*?</iframe>',
start_page, 'xml filename')
embed_url = '%s/xml/%s' % (xml_root, xml_name)
ie_key = 'DigitallySpeaking'
return {
'_type': 'url_transparent',
'id': video_id,
2015-04-24 16:43:33 +02:00
'display_id': display_id,
'url': embed_url,
'ie_key': ie_key,
}