Prepare for upload.

[youtubedl] / youtube_dl / extractor / xuite.py

diff --git a/youtube_dl/extractor/xuite.py b/youtube_dl/extractor/xuite.py
index 4971965f9d090cce61a2e8b6d1486fadc873b4dc..e0818201a2b9ff122904fcbbf7a775a770c5dc5c 100644 (file)
--- a/youtube_dl/extractor/xuite.py
+++ b/youtube_dl/extractor/xuite.py
@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8

 from __future__ import unicode_literals
 
 import base64
 from __future__ import unicode_literals
 
 import base64


@@ -13,17 +13,18 @@ from ..utils import (
 
 
 class XuiteIE(InfoExtractor):
 
 
 class XuiteIE(InfoExtractor):

+    IE_DESC = '隨意窩Xuite影音'

     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
     _TESTS = [{
         # Audio
         'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',
     _REGEX_BASE64 = r'(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?'
     _VALID_URL = r'https?://vlog\.xuite\.net/(?:play|embed)/(?P<id>%s)' % _REGEX_BASE64
     _TESTS = [{
         # Audio
         'url': 'http://vlog.xuite.net/play/RGkzc1ZULTM4NjA5MTQuZmx2',

-        'md5': '63a42c705772aa53fd4c1a0027f86adf',
+        'md5': 'e79284c87b371424885448d11f6398c8',

         'info_dict': {
             'id': '3860914',
             'ext': 'mp3',
             'title': '孤單南半球-歐德陽',
         'info_dict': {
             'id': '3860914',
             'ext': 'mp3',
             'title': '孤單南半球-歐德陽',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'duration': 247.246,
             'timestamp': 1314932940,
             'upload_date': '20110902',
             'duration': 247.246,
             'timestamp': 1314932940,
             'upload_date': '20110902',


@@ -33,19 +34,20 @@ class XuiteIE(InfoExtractor):
         },
     }, {
         # Video with only one format
         },
     }, {
         # Video with only one format

-        'url': 'http://vlog.xuite.net/play/TkRZNjhULTM0NDE2MjkuZmx2',
-        'md5': 'c45737fc8ac5dc8ac2f92ecbcecf505e',
+        'url': 'http://vlog.xuite.net/play/WUxxR2xCLTI1OTI1MDk5LmZsdg==',
+        'md5': '21f7b39c009b5a4615b4463df6eb7a46',

         'info_dict': {
         'info_dict': {

-            'id': '3441629',
+            'id': '25925099',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': '孫燕姿 - 眼淚成詩',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'duration': 217.399,
-            'timestamp': 1299383640,
-            'upload_date': '20110306',
-            'uploader': 'Valen',
-            'uploader_id': '10400126',
-            'categories': ['影視娛樂'],
+            'title': 'BigBuckBunny_320x180',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 596.458,
+            'timestamp': 1454242500,
+            'upload_date': '20160131',
+            'uploader': 'yan12125',
+            'uploader_id': '12158353',
+            'categories': ['個人短片'],
+            'description': 'http://download.blender.org/peach/bigbuckbunny_movies/BigBuckBunny_320x180.mp4',

         },
     }, {
         # Video with two formats
         },
     }, {
         # Video with two formats


@@ -56,7 +58,7 @@ class XuiteIE(InfoExtractor):
             'ext': 'mp4',
             'title': '暗殺教室 02',
             'description': '字幕:【極影字幕社】',
             'ext': 'mp4',
             'title': '暗殺教室 02',
             'description': '字幕:【極影字幕社】',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'duration': 1384.907,
             'timestamp': 1421481240,
             'upload_date': '20150117',
             'duration': 1384.907,
             'timestamp': 1421481240,
             'upload_date': '20150117',


@@ -64,23 +66,45 @@ class XuiteIE(InfoExtractor):
             'uploader_id': '242127761',
             'categories': ['電玩動漫'],
         },
             'uploader_id': '242127761',
             'categories': ['電玩動漫'],
         },

+        'skip': 'Video removed',
+    }, {
+        # Video with encoded media id
+        # from http://forgetfulbc.blogspot.com/2016/06/date.html
+        'url': 'http://vlog.xuite.net/embed/cE1xbENoLTI3NDQ3MzM2LmZsdg==?ar=0&as=0',
+        'info_dict': {
+            'id': 'cE1xbENoLTI3NDQ3MzM2LmZsdg==',
+            'ext': 'mp4',
+            'title': '男女平權只是口號？專家解釋約會時男生是否該幫女生付錢 (中字)',
+            'description': 'md5:f0abdcb69df300f522a5442ef3146f2a',
+            'timestamp': 1466160960,
+            'upload_date': '20160617',
+            'uploader': 'B.C. & Lowy',
+            'uploader_id': '232279340',
+        },

     }, {
         'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
         'only_matching': True,
     }]
 
     }, {
         'url': 'http://vlog.xuite.net/play/S1dDUjdyLTMyOTc3NjcuZmx2/%E5%AD%AB%E7%87%95%E5%A7%BF-%E7%9C%BC%E6%B7%9A%E6%88%90%E8%A9%A9',
         'only_matching': True,
     }]
 

-    def _extract_flv_config(self, media_id):
-        base64_media_id = base64.b64encode(media_id.encode('utf-8')).decode('utf-8')
+    @staticmethod
+    def base64_decode_utf8(data):
+        return base64.b64decode(data.encode('utf-8')).decode('utf-8')
+
+    @staticmethod
+    def base64_encode_utf8(data):
+        return base64.b64encode(data.encode('utf-8')).decode('utf-8')
+
+    def _extract_flv_config(self, encoded_media_id):

         flv_config = self._download_xml(
         flv_config = self._download_xml(

-            'http://vlog.xuite.net/flash/player?media=%s' % base64_media_id,
+            'http://vlog.xuite.net/flash/player?media=%s' % encoded_media_id,

             'flv config')
         prop_dict = {}
         for prop in flv_config.findall('./property'):
             'flv config')
         prop_dict = {}
         for prop in flv_config.findall('./property'):

-            prop_id = base64.b64decode(prop.attrib['id']).decode('utf-8')
+            prop_id = self.base64_decode_utf8(prop.attrib['id'])

             # CDATA may be empty in flv config
             if not prop.text:
                 continue
             # CDATA may be empty in flv config
             if not prop.text:
                 continue

-            encoded_content = base64.b64decode(prop.text).decode('utf-8')
+            encoded_content = self.base64_decode_utf8(prop.text)

             prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
         return prop_dict
 
             prop_dict[prop_id] = compat_urllib_parse_unquote(encoded_content)
         return prop_dict
 


@@ -97,9 +121,14 @@ class XuiteIE(InfoExtractor):
                 '%s returned error: %s' % (self.IE_NAME, error_msg),
                 expected=True)
 
                 '%s returned error: %s' % (self.IE_NAME, error_msg),
                 expected=True)
 

-        video_id = self._html_search_regex(
-            r'data-mediaid="(\d+)"', webpage, 'media id')
-        flv_config = self._extract_flv_config(video_id)
+        encoded_media_id = self._search_regex(
+            r'attributes\.name\s*=\s*"([^"]+)"', webpage,
+            'encoded media id', default=None)
+        if encoded_media_id is None:
+            video_id = self._html_search_regex(
+                r'data-mediaid="(\d+)"', webpage, 'media id')
+            encoded_media_id = self.base64_encode_utf8(video_id)
+        flv_config = self._extract_flv_config(encoded_media_id)

 
         FORMATS = {
             'audio': 'mp3',
 
         FORMATS = {
             'audio': 'mp3',