ytdl-nightly/youtube_dl/extractor/escapist.py

101 lines
3.1 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2015-04-27 17:44:13 +02:00
import json
2013-06-23 21:08:17 +02:00
from .common import InfoExtractor
2015-04-27 17:44:13 +02:00
from ..compat import compat_urllib_request
from ..utils import (
2015-04-27 17:44:13 +02:00
determine_ext,
clean_html,
2015-05-04 14:59:22 +02:00
int_or_none,
2013-06-23 21:08:17 +02:00
)
2015-04-27 17:44:13 +02:00
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
2013-06-23 21:08:17 +02:00
class EscapistIE(InfoExtractor):
2015-02-10 15:45:36 +01:00
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
2015-04-27 17:44:13 +02:00
_TESTS = [{
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
2015-04-27 17:44:13 +02:00
'md5': 'c6793dbda81388f4264c1ba18684a74d',
'info_dict': {
'id': '6618',
'ext': 'mp4',
'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
'title': "Breaking Down Baldur's Gate",
'thumbnail': 're:^https?://.*\.jpg$',
2015-02-28 20:52:52 +01:00
'duration': 264,
2013-06-27 20:46:46 +02:00
}
2015-04-27 17:44:13 +02:00
}, {
'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
'md5': 'cf8842a8a46444d241f9a9980d7874f2',
'info_dict': {
'id': '10044',
'ext': 'mp4',
'description': 'This week, Zero Punctuation reviews Evolve.',
'title': 'Evolve - One vs Multiplayer',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 304,
}
}]
2013-06-23 21:08:17 +02:00
def _real_extract(self, url):
2015-02-10 15:45:36 +01:00
video_id = self._match_id(url)
2015-04-27 17:44:13 +02:00
webpage = self._download_webpage(url, video_id)
2015-04-27 18:17:51 +02:00
imsVideo = self._parse_json(
self._search_regex(
r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
video_id)
2015-04-27 17:44:13 +02:00
video_id = imsVideo['videoID']
key = imsVideo['hash']
2015-05-04 14:59:22 +02:00
config_req = compat_urllib_request.Request(
'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')
2013-06-23 21:08:17 +02:00
2015-05-04 14:59:22 +02:00
data = json.loads(_decrypt_config(key, config))
2015-04-27 17:44:13 +02:00
2015-05-04 14:59:22 +02:00
title = clean_html(data['videoData']['title'])
duration = data['videoData']['duration'] / 1000
2015-04-27 17:44:13 +02:00
2015-05-04 14:59:22 +02:00
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)
2015-04-27 17:44:13 +02:00
return {
'id': video_id,
'formats': formats,
2013-06-23 21:08:17 +02:00
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2015-04-27 17:44:13 +02:00
'description': self._og_search_description(webpage),
2015-02-28 20:52:52 +01:00
'duration': duration,
2013-06-23 21:08:17 +02:00
}