Merge tag 'upstream/2016.02.22'

[youtubedl] / youtube_dl / extractor / addanime.py

diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py
index b99d4b96689c23a13379d4392484c3763ce0e36f..e3e6d21137994593d593fbc51313bf38032ce7f8 100644 (file)
--- a/youtube_dl/extractor/addanime.py
+++ b/youtube_dl/extractor/addanime.py
@@ -1,34 +1,40 @@
+from __future__ import unicode_literals
+

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_HTTPError,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_HTTPError,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,

-
+)
+from ..utils import (

     ExtractorError,
     ExtractorError,

+    qualities,

 )
 
 
 class AddAnimeIE(InfoExtractor):
 )
 
 
 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'http://(?:\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',

         }
         }

-    }
+    }, {
+        'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

+        video_id = self._match_id(url)
+

         try:
         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) or \
             webpage = self._download_webpage(url, video_id)
         except ExtractorError as ee:
             if not isinstance(ee.cause, compat_HTTPError) or \


@@ -38,48 +44,50 @@ class AddAnimeIE(InfoExtractor):
             redir_webpage = ee.cause.read().decode('utf-8')
             action = self._search_regex(
                 r'<form id="challenge-form" action="([^"]+)"',
             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="([^"]+)"/>',
             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:
             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 = (
             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 +
+                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,
                 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)
 
             webpage = self._download_webpage(url, video_id)
 

+        FORMATS = ('normal', 'hq')
+        quality = qualities(FORMATS)

         formats = []
         formats = []

-        for format_id in ('normal', 'hq'):
+        for format_id in FORMATS:

             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)

-            video_url = self._search_regex(rex, webpage, u'video file URLx',
+            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,
                                            fatal=False)
             if not video_url:
                 continue
             formats.append({
                 'format_id': format_id,
                 'url': video_url,

+                'quality': quality(format_id),

             })
             })

-        if not formats:
-            raise ExtractorError(u'Cannot find any video format!')
+        self._sort_formats(formats)

         video_title = self._og_search_title(webpage)
         video_description = self._og_search_description(webpage)
 
         return {
             '_type': 'video',
         video_title = self._og_search_title(webpage)
         video_description = self._og_search_description(webpage)
 
         return {
             '_type': 'video',

-            'id':  video_id,
+            'id': video_id,

             'formats': formats,
             'title': video_title,
             'description': video_description
             'formats': formats,
             'title': video_title,
             'description': video_description