2013-06-23 12:08:17 -07:00
import json
import re
from . common import InfoExtractor
from . . utils import (
compat_str ,
compat_urllib_parse ,
ExtractorError ,
)
class EscapistIE ( InfoExtractor ) :
2013-11-19 21:47:50 -08:00
_VALID_URL = r ' ^https?://?(www \ .)?escapistmagazine \ .com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$ '
2013-06-27 11:46:46 -07:00
_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 ' ,
2013-11-19 21:47:50 -08:00
u ' md5 ' : u ' ab3a706c681efca53f0a35f1415cf0d1 ' ,
2013-06-27 11:46:46 -07:00
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 12:08:17 -07:00
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 )
2013-11-19 21:47:50 -08:00
videoDesc = self . _html_search_regex (
r ' <meta name= " description " content= " ([^ " ]*) " ' ,
2013-06-23 12:08:17 -07:00
webpage , u ' description ' , fatal = False )
2013-11-19 22:23:23 -08:00
playerUrl = self . _og_search_video_url ( webpage , name = u ' player URL ' )
2013-06-23 12:08:17 -07:00
2013-11-19 21:47:50 -08:00
title = self . _html_search_regex (
2013-11-19 22:23:23 -08:00
r ' <meta name= " title " content= " ([^ " ]*) " ' ,
webpage , u ' title ' ) . split ( ' : ' ) [ - 1 ]
2013-06-23 12:08:17 -07:00
2013-11-19 21:56:59 -08:00
configUrl = self . _search_regex ( ' config=(.*)$ ' , playerUrl , u ' config URL ' )
2013-06-23 12:08:17 -07:00
configUrl = compat_urllib_parse . unquote ( configUrl )
2013-11-19 21:47:50 -08:00
formats = [ ]
2013-06-23 12:08:17 -07:00
2013-11-19 21:47:50 -08:00
def _add_format ( name , cfgurl ) :
configJSON = self . _download_webpage (
cfgurl , videoId ,
u ' Downloading ' + name + ' configuration ' ,
u ' Unable to download ' + name + ' configuration ' )
2013-06-23 12:08:17 -07:00
2013-11-19 21:47:50 -08:00
# Technically, it's JavaScript, not JSON
configJSON = configJSON . replace ( " ' " , ' " ' )
2013-06-23 12:08:17 -07:00
2013-11-19 21:47:50 -08:00
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 12:08:17 -07:00
2013-11-19 21:47:50 -08:00
_add_format ( u ' normal ' , configUrl )
2013-11-19 21:55:07 -08:00
hq_url = ( configUrl +
( ' &hq=1 ' if ' ? ' in configUrl else configUrl + ' ?hq=1 ' ) )
2013-11-19 21:47:50 -08:00
try :
2013-11-19 21:55:07 -08:00
_add_format ( u ' hq ' , hq_url )
except ExtractorError :
pass # That's fine, we'll just use normal quality
2013-11-19 21:47:50 -08:00
return {
2013-06-23 12:08:17 -07:00
' id ' : videoId ,
2013-11-19 21:47:50 -08:00
' formats ' : formats ,
2013-06-23 12:08:17 -07:00
' uploader ' : showName ,
' title ' : title ,
2013-07-12 10:00:19 -07:00
' thumbnail ' : self . _og_search_thumbnail ( webpage ) ,
2013-06-23 12:08:17 -07:00
' description ' : videoDesc ,
' player_url ' : playerUrl ,
}