1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-21 00:37:46 +01:00
youtube-dl/youtube_dl/extractor/escapist.py

83 lines
2.7 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 21:08:17 +02:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
)
class EscapistIE(InfoExtractor):
_VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
2013-06-27 20:46:46 +02:00
_TEST = {
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'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.",
'uploader': 'the-escapist-presents',
'title': "Breaking Down Baldur's Gate",
2013-06-27 20:46:46 +02:00
}
}
2013-06-23 21:08:17 +02:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
showName = mobj.group('showname')
video_id = mobj.group('id')
2013-06-23 21:08:17 +02:00
self.report_extraction(video_id)
webpage = self._download_webpage(url, video_id)
2013-06-23 21:08:17 +02:00
videoDesc = self._html_search_regex(
r'<meta name="description" content="([^"]*)"',
webpage, 'description', fatal=False)
2013-06-23 21:08:17 +02:00
playerUrl = self._og_search_video_url(webpage, name='player URL')
2013-06-23 21:08:17 +02:00
title = self._html_search_regex(
2013-11-20 07:23:23 +01:00
r'<meta name="title" content="([^"]*)"',
webpage, 'title').split(' : ')[-1]
2013-06-23 21:08:17 +02:00
configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
2013-06-23 21:08:17 +02:00
configUrl = compat_urllib_parse.unquote(configUrl)
formats = []
2013-06-23 21:08:17 +02:00
def _add_format(name, cfgurl, quality):
config = self._download_json(
cfgurl, video_id,
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
transform_source=lambda s: s.replace("'", '"'))
2013-06-23 21:08:17 +02:00
playlist = config['playlist']
formats.append({
'url': playlist[1]['url'],
'format_id': name,
'quality': quality,
})
2013-06-23 21:08:17 +02:00
_add_format('normal', configUrl, quality=0)
2013-11-20 06:55:07 +01:00
hq_url = (configUrl +
('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
try:
_add_format('hq', hq_url, quality=1)
2013-11-20 06:55:07 +01:00
except ExtractorError:
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
2013-06-23 21:08:17 +02:00
'uploader': showName,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2013-06-23 21:08:17 +02:00
'description': videoDesc,
'player_url': playerUrl,
}