2015-12-13 19:15:45 +08:00
# coding: utf-8
2014-01-29 22:34:35 +08:00
from __future__ import unicode_literals
2013-06-24 03:14:19 +08:00
import base64
from . common import InfoExtractor
2015-12-13 19:15:45 +08:00
from . . compat import (
compat_urllib_parse_unquote ,
compat_parse_qs ,
)
from . . utils import determine_ext
2013-06-24 03:14:19 +08:00
class InfoQIE ( InfoExtractor ) :
2015-06-25 21:54:44 +08:00
_VALID_URL = r ' https?://(?:www \ .)?infoq \ .com/(?:[^/]+/)+(?P<id>[^/]+) '
2014-04-20 07:01:37 +08:00
2015-06-25 21:54:44 +08:00
_TESTS = [ {
2014-04-21 08:55:35 +08:00
' url ' : ' http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things ' ,
2014-04-21 09:21:34 +08:00
' md5 ' : ' b5ca0e0a8c1fed93b0e65e48e462f9a2 ' ,
2014-04-21 08:55:35 +08:00
' info_dict ' : {
2015-12-13 19:15:45 +08:00
' id ' : ' A-Few-of-My-Favorite-Python-Things ' ,
2014-04-21 08:55:35 +08:00
' ext ' : ' mp4 ' ,
' description ' : ' Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience. ' ,
' title ' : ' A Few of My Favorite [Python] Things ' ,
2013-06-28 02:27:08 +08:00
} ,
2015-06-25 21:54:44 +08:00
} , {
' url ' : ' http://www.infoq.com/fr/presentations/changez-avis-sur-javascript ' ,
' only_matching ' : True ,
2015-12-13 19:15:45 +08:00
} , {
' url ' : ' http://www.infoq.com/cn/presentations/openstack-continued-delivery ' ,
' md5 ' : ' 4918d0cca1497f2244572caf626687ef ' ,
' info_dict ' : {
' id ' : ' openstack-continued-delivery ' ,
' title ' : ' OpenStack持续交付之路 ' ,
' ext ' : ' flv ' ,
' description ' : ' md5:308d981fb28fa42f49f9568322c683ff ' ,
} ,
2015-06-25 21:54:44 +08:00
} ]
2013-06-24 03:14:19 +08:00
2015-12-13 19:15:45 +08:00
def _extract_bokecc_videos ( self , webpage , video_id ) :
# TODO: bokecc.com is a Chinese video cloud platform
# It should have an independent extractor but I don't have other
# examples using bokecc
player_params_str = self . _html_search_regex (
r ' <script[^>]+src= " http://p \ .bokecc \ .com/player \ ?([^ " ]+) ' ,
webpage , ' player params ' , default = None )
2013-06-24 03:14:19 +08:00
2015-12-13 19:15:45 +08:00
player_params = compat_parse_qs ( player_params_str )
info_xml = self . _download_xml (
' http://p.bokecc.com/servlet/playinfo?uid= %s &vid= %s &m=1 ' % (
player_params [ ' siteid ' ] [ 0 ] , player_params [ ' vid ' ] [ 0 ] ) , video_id )
return [ {
' format_id ' : ' bokecc ' ,
' url ' : quality . find ( ' ./copy ' ) . attrib [ ' playurl ' ] ,
' preference ' : int ( quality . attrib [ ' value ' ] ) ,
} for quality in info_xml . findall ( ' ./video/quality ' ) ]
2013-06-24 03:14:19 +08:00
2015-12-13 19:15:45 +08:00
def _extract_rtmp_videos ( self , webpage ) :
2014-04-20 07:10:30 +08:00
# The server URL is hardcoded
2014-04-20 07:01:37 +08:00
video_url = ' rtmpe://video.infoq.com/cfx/st/ '
2014-04-20 07:10:30 +08:00
# Extract video URL
2014-04-21 09:21:34 +08:00
encoded_id = self . _search_regex (
2015-12-13 19:15:45 +08:00
r " jsclassref \ s*= \ s* ' ([^ ' ]*) ' " , webpage , ' encoded id ' , default = None )
2015-07-18 01:39:54 +08:00
real_id = compat_urllib_parse_unquote ( base64 . b64decode ( encoded_id . encode ( ' ascii ' ) ) . decode ( ' utf-8 ' ) )
2014-04-20 07:10:30 +08:00
playpath = ' mp4: ' + real_id
2013-06-24 03:14:19 +08:00
2015-12-13 19:15:45 +08:00
return [ {
' format_id ' : ' rtmp ' ,
' url ' : video_url ,
' ext ' : determine_ext ( playpath ) ,
' play_path ' : playpath ,
} ]
2013-06-24 03:14:19 +08:00
2015-12-13 19:15:45 +08:00
def _extract_http_videos ( self , webpage ) :
2015-12-13 17:29:27 +08:00
http_video_url = self . _search_regex ( r ' P \ .s \ s*= \ s* \' ([^ \' ]+) \' ' , webpage , ' video URL ' )
policy = self . _search_regex ( r ' InfoQConstants.scp \ s*= \ s* \' ([^ \' ]+) \' ' , webpage , ' policy ' )
signature = self . _search_regex ( r ' InfoQConstants.scs \ s*= \ s* \' ([^ \' ]+) \' ' , webpage , ' signature ' )
key_pair_id = self . _search_regex ( r ' InfoQConstants.sck \ s*= \ s* \' ([^ \' ]+) \' ' , webpage , ' key-pair-id ' )
2014-04-21 09:21:34 +08:00
2015-12-13 19:15:45 +08:00
return [ {
2014-04-21 09:21:34 +08:00
' format_id ' : ' http ' ,
2015-12-13 17:29:27 +08:00
' url ' : http_video_url ,
' http_headers ' : {
' Cookie ' : ' CloudFront-Policy= %s ; CloudFront-Signature= %s ; CloudFront-Key-Pair-Id= %s ' % (
policy , signature , key_pair_id ) ,
} ,
2014-04-21 09:21:34 +08:00
} ]
2015-12-13 19:15:45 +08:00
def _real_extract ( self , url ) :
video_id = self . _match_id ( url )
webpage = self . _download_webpage ( url , video_id )
video_title = self . _html_search_regex ( r ' <title>(.*?)</title> ' , webpage , ' title ' )
video_description = self . _html_search_meta ( ' description ' , webpage , ' description ' )
if ' /cn/ ' in url :
# for China videos, HTTP video URL exists but always fails with 403
formats = self . _extract_bokecc_videos ( webpage , video_id )
else :
formats = self . _extract_rtmp_videos ( webpage ) + self . _extract_http_videos ( webpage )
2014-04-21 09:21:34 +08:00
self . _sort_formats ( formats )
2014-04-21 08:55:35 +08:00
return {
2013-06-24 03:14:19 +08:00
' id ' : video_id ,
' title ' : video_title ,
' description ' : video_description ,
2014-04-21 09:21:34 +08:00
' formats ' : formats ,
2014-04-21 08:55:35 +08:00
}