Merge pull request #398 from tempname/master

diff --git a/youtube-dl b/youtube-dl
index f2268af227b0eee8548aa6d106861cc508879931..448b2cd2667738716d7fc05e26f35ef59554fcb2 100755 (executable)
Binary files a/youtube-dl and b/youtube-dl differ

diff --git a/youtube-dl.exe b/youtube-dl.exe
index 2aa052ccf569ae513f627910c18e55675effe844..b7123fc168c815f3d01964db2aaa9de755b9b44f 100755 (executable)
Binary files a/youtube-dl.exe and b/youtube-dl.exe differ

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 32c52cc08542a10588a5adeb444b6d3e6b7c3d64..2b313966fd35a69f338f9d8ee1024c4bdbaa3064 100644 (file)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -13,6 +13,8 @@ import urllib
 import urllib2
 import email.utils
 import xml.etree.ElementTree
+import random
+import math
 from urlparse import parse_qs
 
 try:
@@ -95,7 +97,7 @@ class InfoExtractor(object):
 class YoutubeIE(InfoExtractor):
        """Information extractor for youtube.com."""
 
-       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
+       _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$'
        _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
        _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en'
        _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
@@ -2956,6 +2958,129 @@ class MTVIE(InfoExtractor):
 
                return [info]
 
+
+class YoukuIE(InfoExtractor):
+
+       _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
+       IE_NAME = u'Youku'
+
+       def __init__(self, downloader=None):
+               InfoExtractor.__init__(self, downloader)
+
+       def report_download_webpage(self, file_id):
+               """Report webpage download."""
+               self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id)
+
+       def report_extraction(self, file_id):
+               """Report information extraction."""
+               self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id)
+
+       def _gen_sid(self):
+               nowTime = int(time.time() * 1000)
+               random1 = random.randint(1000,1998)
+               random2 = random.randint(1000,9999)
+
+               return "%d%d%d" %(nowTime,random1,random2)
+
+       def _get_file_ID_mix_string(self, seed):
+               mixed = []
+               source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
+               seed = float(seed)
+               for i in range(len(source)):
+                       seed  =  (seed * 211 + 30031 ) % 65536
+                       index  =  math.floor(seed / 65536 * len(source) )
+                       mixed.append(source[int(index)])
+                       source.remove(source[int(index)])
+               #return ''.join(mixed)
+               return mixed
+
+       def _get_file_id(self, fileId, seed):
+               mixed = self._get_file_ID_mix_string(seed)
+               ids = fileId.split('*')
+               realId = []
+               for ch in ids:
+                       if ch:
+                               realId.append(mixed[int(ch)])
+               return ''.join(realId)
+
+       def _real_extract(self, url):
+               mobj = re.match(self._VALID_URL, url)
+               if mobj is None:
+                       self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+                       return
+               video_id = mobj.group('ID')
+
+               info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
+
+               request = urllib2.Request(info_url, None, std_headers)
+               try:
+                       self.report_download_webpage(video_id)
+                       jsondata = urllib2.urlopen(request).read()
+               except (urllib2.URLError, httplib.HTTPException, socket.error) as err:
+                       self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
+                       return
+
+               self.report_extraction(video_id)
+               try:
+                       config = json.loads(jsondata)
+
+                       video_title =  config['data'][0]['title']
+                       seed = config['data'][0]['seed']
+
+                       format = self._downloader.params.get('format', None)
+                       supported_format = config['data'][0]['streamfileids'].keys()
+
+                       if format is None or format == 'best':
+                               if 'hd2' in supported_format:
+                                       format = 'hd2'
+                               else:
+                                       format = 'flv'
+                               ext = u'flv'
+                       elif format == 'worst':
+                               format = 'mp4'
+                               ext = u'mp4'
+                       else:
+                               format = 'flv'
+                               ext = u'flv'
+
+
+                       fileid = config['data'][0]['streamfileids'][format]
+                       seg_number = len(config['data'][0]['segs'][format])
+
+                       keys=[]
+                       for i in xrange(seg_number):
+                               keys.append(config['data'][0]['segs'][format][i]['k'])
+
+                       #TODO check error
+                       #youku only could be viewed from mainland china
+               except:
+                       self._downloader.trouble(u'ERROR: unable to extract info section')
+                       return
+
+               files_info=[]
+               sid = self._gen_sid()
+               fileid = self._get_file_id(fileid, seed)
+
+               #column 8,9 of fileid represent the segment number
+               #fileid[7:9] should be changed
+               for index, key in enumerate(keys):
+
+                       temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
+                       download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+
+                       info = {
+                               'id': '%s_part%02d' % (video_id, index),
+                               'url': download_url,
+                               'uploader': None,
+                               'title': video_title,
+                               'ext': ext,
+                               'format': u'NA'
+                       }
+                       files_info.append(info)
+
+               return files_info
+
+
 class XNXXIE(InfoExtractor):
        """Information extractor for xnxx.com"""
 

diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 0a6a5d35c2e4428460d8d5e20174de694394e621..f49f126720dea7096a474d5e22712e750f65523c 100644 (file)
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -351,6 +351,7 @@ def gen_extractors():
                MixcloudIE(),
                StanfordOpenClassroomIE(),
                MTVIE(),
+               YoukuIE(),
                XNXXIE(),
 
                GenericIE()

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 2853ba50f228bb1f87900aa78a256b1637fcee2b..922e17eccfac611a1d90bf83e913383c9afce30d 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -223,7 +223,7 @@ def encodeFilename(s):
 
        assert type(s) == type(u'')
 
-       if sys.platform == 'win32' and sys.getwindowsversion().major >= 5:
+       if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
                # Pass u'' directly to use Unicode APIs on Windows 2000 and up
                # (Detecting Windows NT 4 is tricky because 'major >= 4' would
                # match Windows 9x series as well. Besides, NT 4 is obsolete.)