Imported Debian patch 2015.11.27.1-1.1

[youtubedl] / youtube_dl / extractor / bilibili.py

diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 2103ed73aad860738bba5108ee27a86fd921d29c..6c66a12368ea0a963d89ef5922c9d83f3019ddfc 100644 (file)
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 import itertools
 import json
 import re
 import itertools
 import json

-import xml.etree.ElementTree as ET

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

+from ..compat import (
+    compat_etree_fromstring,
+)

 from ..utils import (
     int_or_none,
     unified_strdate,
 from ..utils import (
     int_or_none,
     unified_strdate,


@@ -41,8 +43,15 @@ class BiliBiliIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

-        if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
-            raise ExtractorError('The video does not exist or was deleted', expected=True)
+        if '(此视频不存在或被删除)' in webpage:
+            raise ExtractorError(
+                'The video does not exist or was deleted', expected=True)
+
+        if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage:
+            raise ExtractorError(
+                'The video is not available in your region due to copyright reasons',
+                expected=True)
+

         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 
         video_code = self._search_regex(
             r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
 


@@ -81,7 +90,7 @@ class BiliBiliIE(InfoExtractor):
         except ValueError:
             pass
 
         except ValueError:
             pass
 

-        lq_doc = ET.fromstring(lq_page)
+        lq_doc = compat_etree_fromstring(lq_page)

         lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(
         lq_durls = lq_doc.findall('./durl')
 
         hq_doc = self._download_xml(


@@ -105,7 +114,7 @@ class BiliBiliIE(InfoExtractor):
                 'filesize': int_or_none(
                     lq_durl.find('./size'), get_attr='text'),
             }]
                 'filesize': int_or_none(
                     lq_durl.find('./size'), get_attr='text'),
             }]

-            if hq_durl:
+            if hq_durl is not None:

                 formats.append({
                     'format_id': 'hq',
                     'quality': 2,
                 formats.append({
                     'format_id': 'hq',
                     'quality': 2,