youtube-dl/youtube_dl/extractor/escapist.py

107 lines
3.3 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2015-04-28 00:44:13 +09:00
import json
2013-06-24 04:08:17 +09:00
from .common import InfoExtractor
from ..utils import (
2015-04-28 00:44:13 +09:00
determine_ext,
clean_html,
2015-05-04 21:59:22 +09:00
int_or_none,
2015-05-04 22:04:49 +09:00
float_or_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
2015-11-22 01:18:17 +09:00
sanitized_Request,
2013-06-24 04:08:17 +09:00
)
2015-04-28 00:44:13 +09:00
def _decrypt_config(key, string):
a = ''
i = ''
r = ''
while len(a) < (len(string) / 2):
a += key
a = a[0:int(len(string) / 2)]
t = 0
while t < len(string):
i += chr(int(string[t] + string[t + 1], 16))
t += 2
icko = [s for s in i]
for t, c in enumerate(a):
r += chr(ord(c) ^ ord(icko[t]))
return r
2013-06-24 04:08:17 +09:00
class EscapistIE(InfoExtractor):
2015-05-04 22:01:08 +09:00
_VALID_URL = r'https?://?(?:www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
2015-04-28 00:44:13 +09:00
_TESTS = [{
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
2015-05-04 22:00:34 +09:00
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
'info_dict': {
'id': '6618',
'ext': 'mp4',
'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
'title': "Breaking Down Baldur's Gate",
'thumbnail': 're:^https?://.*\.jpg$',
2015-03-01 04:52:52 +09:00
'duration': 264,
2015-05-04 22:06:07 +09:00
'uploader': 'The Escapist',
2013-06-28 03:46:46 +09:00
}
2015-04-28 00:44:13 +09:00
}, {
'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
2015-05-04 22:00:34 +09:00
'md5': '9e8c437b0dbb0387d3bd3255ca77f6bf',
2015-04-28 00:44:13 +09:00
'info_dict': {
'id': '10044',
'ext': 'mp4',
'description': 'This week, Zero Punctuation reviews Evolve.',
'title': 'Evolve - One vs Multiplayer',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 304,
2015-05-04 22:06:07 +09:00
'uploader': 'The Escapist',
2015-04-28 00:44:13 +09:00
}
}]
2013-06-24 04:08:17 +09:00
def _real_extract(self, url):
2015-02-10 23:45:36 +09:00
video_id = self._match_id(url)
2015-04-28 00:44:13 +09:00
webpage = self._download_webpage(url, video_id)
2015-05-04 22:04:49 +09:00
ims_video = self._parse_json(
2015-04-28 01:17:51 +09:00
self._search_regex(
r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
video_id)
2015-05-04 22:04:49 +09:00
video_id = ims_video['videoID']
key = ims_video['hash']
2015-04-28 00:44:13 +09:00
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
2015-11-22 01:18:17 +09:00
config_req = sanitized_Request(
2015-05-04 21:59:22 +09:00
'http://www.escapistmagazine.com/videos/'
'vidconfig.php?videoID=%s&hash=%s' % (video_id, key))
config_req.add_header('Referer', url)
config = self._download_webpage(config_req, video_id, 'Downloading video config')
2013-06-24 04:08:17 +09:00
2015-05-04 21:59:22 +09:00
data = json.loads(_decrypt_config(key, config))
2015-04-28 00:44:13 +09:00
2015-05-04 22:04:49 +09:00
video_data = data['videoData']
title = clean_html(video_data['title'])
duration = float_or_none(video_data.get('duration'), 1000)
uploader = video_data.get('publisher')
2015-04-28 00:44:13 +09:00
2015-05-04 21:59:22 +09:00
formats = [{
'url': video['src'],
'format_id': '%s-%sp' % (determine_ext(video['src']), video['res']),
'height': int_or_none(video.get('res')),
} for video in data['files']['videos']]
self._sort_formats(formats)
2015-04-28 00:44:13 +09:00
return {
'id': video_id,
'formats': formats,
2013-06-24 04:08:17 +09:00
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2015-04-28 00:44:13 +09:00
'description': self._og_search_description(webpage),
2015-03-01 04:52:52 +09:00
'duration': duration,
2015-05-04 22:04:49 +09:00
'uploader': uploader,
2013-06-24 04:08:17 +09:00
}