debian/NEWS: Add link to my webpage to give more details.

[youtubedl] / youtube_dl / extractor / youku.py

diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py
index ed43f42be59faa0cc1ec61b12767b19463529f3b..a8fd40c833fb7707eb1cd8760c288da5f2299025 100644 (file)
--- a/youtube_dl/extractor/youku.py
+++ b/youtube_dl/extractor/youku.py
@@ -1,3 +1,5 @@
+# coding: utf-8
+

 import json
 import math
 import random
 import json
 import math
 import random


@@ -11,7 +13,17 @@ from ..utils import (
 
 
 class YoukuIE(InfoExtractor):
 
 
 class YoukuIE(InfoExtractor):

-    _VALID_URL =  r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
+    _VALID_URL =  r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)'
+    _TEST =   {
+        u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
+        u"file": u"XNDgyMDQ2NTQw_part00.flv",
+        u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
+        u"params": {u"test": False},
+        u"info_dict": {
+            u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
+        }
+    }
+

 
     def _gen_sid(self):
         nowTime = int(time.time() * 1000)
 
     def _gen_sid(self):
         nowTime = int(time.time() * 1000)


@@ -25,8 +37,8 @@ class YoukuIE(InfoExtractor):
         source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890")
         seed = float(seed)
         for i in range(len(source)):
         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) )
+            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)
             mixed.append(source[int(index)])
             source.remove(source[int(index)])
         #return ''.join(mixed)


@@ -54,6 +66,12 @@ class YoukuIE(InfoExtractor):
         self.report_extraction(video_id)
         try:
             config = json.loads(jsondata)
         self.report_extraction(video_id)
         try:
             config = json.loads(jsondata)

+            error_code = config['data'][0].get('error_code')
+            if error_code:
+                # -8 means blocked outside China.
+                error = config['data'][0].get('error')  # Chinese and English, separated by newline.
+                raise ExtractorError(error or u'Server reported error %i' % error_code,
+                    expected=True)

 
             video_title =  config['data'][0]['title']
             seed = config['data'][0]['seed']
 
             video_title =  config['data'][0]['title']
             seed = config['data'][0]['seed']


@@ -77,6 +95,7 @@ class YoukuIE(InfoExtractor):
 
             fileid = config['data'][0]['streamfileids'][format]
             keys = [s['k'] for s in config['data'][0]['segs'][format]]
 
             fileid = config['data'][0]['streamfileids'][format]
             keys = [s['k'] for s in config['data'][0]['segs'][format]]

+            # segs is usually a dictionary, but an empty *list* if an error occured.

         except (UnicodeDecodeError, ValueError, KeyError):
             raise ExtractorError(u'Unable to extract info section')
 
         except (UnicodeDecodeError, ValueError, KeyError):
             raise ExtractorError(u'Unable to extract info section')