X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Faddanime.py;h=5e7c0724e994c1df632cc5d03d565e0e8ddaafdf;hb=3089bc748c0fe72a0361bce3f5e2fbab25175236;hp=490b5af627372199a82f214c8081ef18be4baa44;hpb=3e6a330d38e2bfce12a789c0f51c7d9754f4316e;p=youtube-dl

diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py
index 490b5af62..5e7c0724e 100644
--- a/youtube_dl/extractor/addanime.py
+++ b/youtube_dl/extractor/addanime.py
@@ -1,82 +1,95 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_HTTPError,
     compat_str,
-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
-
+)
+from ..utils import (
     ExtractorError,
-    RegexNotFoundError,
+    qualities,
 )
 
 
 class AddAnimeIE(InfoExtractor):
-
-    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
-    IE_NAME = u'AddAnime'
-    _TEST = {
-        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
-        u'file': u'24MR3YO5SAS9.mp4',
-        u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
-        u'info_dict': {
-            u"description": u"One Piece 606",
-            u"title": u"One Piece 606"
-        }
-    }
+    _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
+    _TESTS = [{
+        'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+        'md5': '72954ea10bc979ab5e2eb288b21425a0',
+        'info_dict': {
+            'id': '24MR3YO5SAS9',
+            'ext': 'mp4',
+            'description': 'One Piece 606',
+            'title': 'One Piece 606',
+        },
+        'skip': 'Video is gone',
+    }, {
+        'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
+        video_id = self._match_id(url)
+
         try:
-            mobj = re.match(self._VALID_URL, url)
-            video_id = mobj.group('video_id')
             webpage = self._download_webpage(url, video_id)
         except ExtractorError as ee:
-            if not isinstance(ee.cause, compat_HTTPError):
+            if not isinstance(ee.cause, compat_HTTPError) or \
+               ee.cause.code != 503:
                 raise
 
             redir_webpage = ee.cause.read().decode('utf-8')
             action = self._search_regex(
                 r'<form id="challenge-form" action="([^"]+)"',
-                redir_webpage, u'Redirect form')
+                redir_webpage, 'Redirect form')
             vc = self._search_regex(
                 r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
-                redir_webpage, u'redirect vc value')
+                redir_webpage, 'redirect vc value')
             av = re.search(
                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
                 redir_webpage)
             if av is None:
-                raise ExtractorError(u'Cannot find redirect math task')
+                raise ExtractorError('Cannot find redirect math task')
             av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
 
             parsed_url = compat_urllib_parse_urlparse(url)
             av_val = av_res + len(parsed_url.netloc)
             confirm_url = (
-                parsed_url.scheme + u'://' + parsed_url.netloc +
-                action + '?' +
-                compat_urllib_parse.urlencode({
+                parsed_url.scheme + '://' + parsed_url.netloc
+                + action + '?'
+                + compat_urllib_parse_urlencode({
                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
             self._download_webpage(
                 confirm_url, video_id,
-                note=u'Confirming after redirect')
+                note='Confirming after redirect')
             webpage = self._download_webpage(url, video_id)
 
-        try:
-            video_url = self._search_regex(r"var hq_video_file = '(.*?)';",
-                                           webpage, u'video file URL')
-        except RegexNotFoundError:
-            video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
-                                           webpage, u'video file URL')
-        
-        video_extension = video_url[-3:]  # mp4 or flv ?
+        FORMATS = ('normal', 'hq')
+        quality = qualities(FORMATS)
+        formats = []
+        for format_id in FORMATS:
+            rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
+            video_url = self._search_regex(rex, webpage, 'video file URLx',
+                                           fatal=False)
+            if not video_url:
+                continue
+            formats.append({
+                'format_id': format_id,
+                'url': video_url,
+                'quality': quality(format_id),
+            })
+        self._sort_formats(formats)
         video_title = self._og_search_title(webpage)
         video_description = self._og_search_description(webpage)
 
         return {
             '_type': 'video',
-            'id':  video_id,
-            'url': video_url,
-            'ext': video_extension,
+            'id': video_id,
+            'formats': formats,
             'title': video_title,
             'description': video_description
         }