yt-dlc/youtube_dl/extractor/escapist.py

85 lines
2.9 KiB
Python
Raw Normal View History

2013-06-23 19:08:17 +00:00
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>[^/?]+)[/?]?.*$'
2013-06-27 18:46:46 +00:00
_TEST = {
u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
2013-06-27 18:46:46 +00:00
u'info_dict': {
u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
u"uploader": u"the-escapist-presents",
u"title": u"Breaking Down Baldur's Gate"
}
}
2013-06-23 19:08:17 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
videoDesc = self._html_search_regex(
r'<meta name="description" content="([^"]*)"',
2013-06-23 19:08:17 +00:00
webpage, u'description', fatal=False)
2013-11-20 06:23:23 +00:00
playerUrl = self._og_search_video_url(webpage, name=u'player URL')
2013-06-23 19:08:17 +00:00
title = self._html_search_regex(
2013-11-20 06:23:23 +00:00
r'<meta name="title" content="([^"]*)"',
webpage, u'title').split(' : ')[-1]
2013-06-23 19:08:17 +00:00
2013-11-20 05:56:59 +00:00
configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
2013-06-23 19:08:17 +00:00
configUrl = compat_urllib_parse.unquote(configUrl)
formats = []
2013-06-23 19:08:17 +00:00
def _add_format(name, cfgurl):
configJSON = self._download_webpage(
cfgurl, videoId,
u'Downloading ' + name + ' configuration',
u'Unable to download ' + name + ' configuration')
2013-06-23 19:08:17 +00:00
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
2013-06-23 19:08:17 +00:00
try:
config = json.loads(configJSON)
except (ValueError,) as err:
raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
formats.append({
'url': playlist[1]['url'],
'format_id': name,
})
2013-06-23 19:08:17 +00:00
_add_format(u'normal', configUrl)
2013-11-20 05:55:07 +00:00
hq_url = (configUrl +
('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
try:
2013-11-20 05:55:07 +00:00
_add_format(u'hq', hq_url)
except ExtractorError:
pass # That's fine, we'll just use normal quality
return {
2013-06-23 19:08:17 +00:00
'id': videoId,
'formats': formats,
2013-06-23 19:08:17 +00:00
'uploader': showName,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
2013-06-23 19:08:17 +00:00
'description': videoDesc,
'player_url': playerUrl,
}