2014-01-29 01:55:06 +08:00
from __future__ import unicode_literals
2013-12-05 21:29:08 +08:00
import json
import re
from . common import InfoExtractor
class NineGagIE ( InfoExtractor ) :
IE_NAME = ' 9gag '
_VALID_URL = r ' ^https?://(?:www \ .)?9gag \ .tv/v/(?P<id>[0-9]+) '
_TEST = {
2014-01-29 01:55:06 +08:00
" url " : " http://9gag.tv/v/1912 " ,
" file " : " 1912.mp4 " ,
" info_dict " : {
" description " : " This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!) " ,
" title " : " \" People Are Awesome 2013 \" Is Absolutely Awesome "
2013-12-05 21:29:08 +08:00
} ,
2014-01-29 01:55:06 +08:00
' add_ie ' : [ ' Youtube ' ]
2013-12-05 21:29:08 +08:00
}
def _real_extract ( self , url ) :
mobj = re . match ( self . _VALID_URL , url )
video_id = mobj . group ( ' id ' )
webpage = self . _download_webpage ( url , video_id )
data_json = self . _html_search_regex ( r ''' (?x)
< div \s * id = " tv-video " \s * data - video - source = " youtube " \s *
2014-01-29 01:55:06 +08:00
data - video - meta = " ([^ " ] + ) " ' ' ' , webpage, ' video metadata ' )
2013-12-05 21:29:08 +08:00
data = json . loads ( data_json )
return {
' _type ' : ' url_transparent ' ,
' url ' : data [ ' youtubeVideoId ' ] ,
' ie_key ' : ' Youtube ' ,
' id ' : video_id ,
' title ' : data [ ' title ' ] ,
' description ' : data [ ' description ' ] ,
' view_count ' : int ( data [ ' view_count ' ] ) ,
2013-12-06 01:29:07 +08:00
' like_count ' : int ( data [ ' statistic ' ] [ ' like ' ] ) ,
' dislike_count ' : int ( data [ ' statistic ' ] [ ' dislike ' ] ) ,
2013-12-05 21:29:08 +08:00
' thumbnail ' : data [ ' thumbnail_url ' ] ,
}