2013-08-22 18:37:34 +08:00
# coding: utf-8
2014-02-09 01:43:12 +08:00
from __future__ import unicode_literals
2013-08-18 22:11:47 +08:00
import json
import re
from . common import InfoExtractor
2013-10-07 20:33:23 +08:00
2013-08-18 22:11:47 +08:00
class JeuxVideoIE ( InfoExtractor ) :
_VALID_URL = r ' http://.*? \ .jeuxvideo \ .com/.*/(.*?)- \ d+ \ .htm '
2013-08-22 18:37:34 +08:00
_TEST = {
2014-02-09 01:43:12 +08:00
' url ' : ' http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm ' ,
' md5 ' : ' 046e491afb32a8aaac1f44dd4ddd54ee ' ,
' info_dict ' : {
' id ' : ' 5182 ' ,
' ext ' : ' mp4 ' ,
' title ' : ' GC 2013 : Tearaway nous présente ses papiers d \' identité ' ,
' description ' : ' Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s \' attendre à un résultat original et fort attrayant. \n ' ,
2013-08-22 18:37:34 +08:00
} ,
}
2013-08-18 22:11:47 +08:00
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
2013-11-20 13:27:48 +08:00
title = mobj . group ( 1 )
2013-08-18 22:11:47 +08:00
webpage = self . _download_webpage ( url , title )
2013-10-07 20:33:23 +08:00
xml_link = self . _html_search_regex (
r ' <param name= " flashvars " value= " config=(.*?) " /> ' ,
2014-02-09 01:43:12 +08:00
webpage , ' config URL ' )
2013-08-18 22:11:47 +08:00
2013-10-07 20:33:23 +08:00
video_id = self . _search_regex (
r ' http://www \ .jeuxvideo \ .com/config/ \ w+/ \ d+/(.*?)/ \ d+_player \ .xml ' ,
2014-02-09 01:43:12 +08:00
xml_link , ' video ID ' )
2013-08-18 22:11:47 +08:00
2013-11-27 01:48:52 +08:00
config = self . _download_xml (
2014-02-09 01:43:12 +08:00
xml_link , title , ' Downloading XML config ' )
2013-11-27 01:48:52 +08:00
info_json = config . find ( ' format.json ' ) . text
2013-10-07 20:33:23 +08:00
info = json . loads ( info_json ) [ ' versions ' ] [ 0 ]
2013-08-18 22:11:47 +08:00
video_url = ' http://video720.jeuxvideo.com/ ' + info [ ' file ' ]
2013-10-07 20:33:23 +08:00
return {
' id ' : video_id ,
' title ' : config . find ( ' titre_video ' ) . text ,
' ext ' : ' mp4 ' ,
' url ' : video_url ,
' description ' : self . _og_search_description ( webpage ) ,
' thumbnail ' : config . find ( ' image ' ) . text ,
}