1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-16 16:13:35 +01:00
yt-dlp/youtube_dl/extractor/escapist.py

69 lines
2.2 KiB
Python
Raw Normal View History

2013-06-23 21:08:17 +02:00
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
ExtractorError,
)
class EscapistIE(InfoExtractor):
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
webpage, u'description', fatal=False)
imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
webpage, u'thumbnail', fatal=False)
playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
webpage, u'player url')
title = self._html_search_regex('<meta name="title" content="([^"]*)"',
webpage, u'player url').split(' : ')[-1]
configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
configUrl = compat_urllib_parse.unquote(configUrl)
configJSON = self._download_webpage(configUrl, videoId,
u'Downloading configuration',
u'unable to download configuration')
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
videoUrl = playlist[1]['url']
info = {
'id': videoId,
'url': videoUrl,
'uploader': showName,
'upload_date': None,
'title': title,
'ext': 'mp4',
'thumbnail': imgUrl,
'description': videoDesc,
'player_url': playerUrl,
}
return [info]