2014-02-24 04:28:22 +11:00
# encoding: utf-8
from __future__ import unicode_literals
2014-01-31 04:26:50 +11:00
from . common import InfoExtractor
from . . utils import (
unified_strdate ,
)
2014-02-24 04:28:22 +11:00
2014-01-31 04:26:50 +11:00
class NormalbootsIE ( InfoExtractor ) :
2015-02-03 09:04:39 +11:00
_VALID_URL = r ' http://(?:www \ .)?normalboots \ .com/video/(?P<id>[0-9a-z-]*)/?$ '
2014-01-31 07:01:35 +11:00
_TEST = {
2014-02-24 04:28:22 +11:00
' url ' : ' http://normalboots.com/video/home-alone-games-jontron/ ' ,
' md5 ' : ' 8bf6de238915dd501105b44ef5f1e0f6 ' ,
' info_dict ' : {
' id ' : ' home-alone-games-jontron ' ,
' ext ' : ' mp4 ' ,
' title ' : ' Home Alone Games - JonTron - NormalBoots ' ,
' description ' : ' Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘ Tense Battle Theme’ : \xa0 http://www.youtube.com/Kiamet/ ' ,
' uploader ' : ' JonTron ' ,
' upload_date ' : ' 20140125 ' ,
2015-01-05 23:59:49 +11:00
} ,
' params ' : {
# rtmp download
' skip_download ' : True ,
} ,
2014-01-31 07:01:35 +11:00
}
2014-02-24 04:28:22 +11:00
2014-01-31 04:26:50 +11:00
def _real_extract ( self , url ) :
2015-02-03 09:04:39 +11:00
video_id = self . _match_id ( url )
2014-01-31 04:26:50 +11:00
webpage = self . _download_webpage ( url , video_id )
2014-02-24 04:28:22 +11:00
2015-02-03 09:04:39 +11:00
video_uploader = self . _html_search_regex (
r ' Posted \ sby \ s<a \ shref= " [A-Za-z0-9/]* " >(?P<uploader>[A-Za-z]*) \ s</a> ' ,
webpage , ' uploader ' , fatal = False )
video_upload_date = unified_strdate ( self . _html_search_regex (
r ' <span style= " text-transform:uppercase; font-size:inherit; " >[A-Za-z]+, (?P<date>.*)</span> ' ,
webpage , ' date ' , fatal = False ) )
player_url = self . _html_search_regex (
r ' <iframe \ swidth= " [0-9]+ " \ sheight= " [0-9]+ " \ ssrc= " (?P<url>[ \ S]+) " ' ,
webpage , ' player url ' )
2014-01-31 04:26:50 +11:00
player_page = self . _download_webpage ( player_url , video_id )
2015-02-03 09:04:39 +11:00
video_url = self . _html_search_regex (
r " file: \ s ' (?P<file>[^ ' ]+ \ .mp4) ' " , player_page , ' file ' )
2014-02-24 04:28:22 +11:00
return {
' id ' : video_id ,
' url ' : video_url ,
' title ' : self . _og_search_title ( webpage ) ,
' description ' : self . _og_search_description ( webpage ) ,
' thumbnail ' : self . _og_search_thumbnail ( webpage ) ,
' uploader ' : video_uploader ,
' upload_date ' : video_upload_date ,
}