X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcrunchyroll.py;h=026a9177e754de7d606961e6e4793af86da49fe2;hb=7c360e3a04f09b912f51034c7778eb2297872e86;hp=a20b88f0250279abe35b98a6a887b6be11298ec5;hpb=344400951ccddaaa477738957bdbdb86a704c55b;p=youtube-dl

diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index a20b88f02..026a9177e 100644
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 import base64
 import zlib
 
@@ -85,9 +86,8 @@ class CrunchyrollIE(InfoExtractor):
         return zlib.decompress(decrypted_data)
 
     def _convert_subtitles_to_srt(self, subtitles):
-        i = 1
         output = ''
-        for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+        for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
             start = start.replace('.', ',')
             end = end.replace('.', ',')
             text = clean_html(text)
@@ -95,7 +95,6 @@ class CrunchyrollIE(InfoExtractor):
             if not text:
                 continue
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
-            i += 1
         return output
 
     def _real_extract(self,url):
@@ -113,6 +112,12 @@ class CrunchyrollIE(InfoExtractor):
         if note_m:
             raise ExtractorError(note_m)
 
+        mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
+        if mobj:
+            msg = json.loads(mobj.group('msg'))
+            if msg.get('type') == 'error':
+                raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
+
         video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
         video_title = re.sub(r' {2,}', ' ', video_title)
         video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
@@ -166,7 +171,7 @@ class CrunchyrollIE(InfoExtractor):
             data = base64.b64decode(data)
 
             subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
-            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
+            lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
             subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
@@ -180,4 +185,4 @@ class CrunchyrollIE(InfoExtractor):
             'upload_date': video_upload_date,
             'subtitles':   subtitles,
             'formats':     formats,
-        }
\ No newline at end of file
+        }