Update upstream source from tag 'upstream/2018.09.10'

[youtubedl] / youtube_dl / extractor / aparat.py

diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py
index 74860882628017c5ab7a44f22bd9b05286ad556e..6eb8bbb6e989d0310a0b447ef1928ba081567a6f 100644 (file)
--- a/youtube_dl/extractor/aparat.py
+++ b/youtube_dl/extractor/aparat.py
@@ -1,59 +1,70 @@
-#coding: utf-8
-
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from ..utils import (
 from .common import InfoExtractor
 from ..utils import (

-    ExtractorError,
-    HEADRequest,
+    int_or_none,
+    mimetype2ext,
+    url_or_none,

 )
 
 
 class AparatIE(InfoExtractor):
 )
 
 
 class AparatIE(InfoExtractor):

-    _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'

 
     _TEST = {
         'url': 'http://www.aparat.com/v/wP8On',
 
     _TEST = {
         'url': 'http://www.aparat.com/v/wP8On',

-        'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
+        'md5': '131aca2e14fe7c4dcb3c4877ba300c89',

         'info_dict': {
             'id': 'wP8On',
             'ext': 'mp4',
             'title': 'تیم گلکسی 11 - زومیت',
         'info_dict': {
             'id': 'wP8On',
             'ext': 'mp4',
             'title': 'تیم گلکسی 11 - زومیت',

+            'age_limit': 0,

         },
         # 'skip': 'Extremely unreliable',
     }
 
     def _real_extract(self, url):
         },
         # 'skip': 'Extremely unreliable',
     }
 
     def _real_extract(self, url):

-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
+        video_id = self._match_id(url)

 
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
         # but the URL in there does not work
 
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
         # but the URL in there does not work

-        embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
-                     video_id + '/vt/frame')
-        webpage = self._download_webpage(embed_url, video_id)
-
-        video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
-        for i, video_url in enumerate(video_urls):
-            req = HEADRequest(video_url)
-            res = self._request_webpage(
-                req, video_id, note=u'Testing video URL %d' % i, errnote=False)
-            if res:
-                break
-        else:
-            raise ExtractorError(u'No working video URLs found')
-
-        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+        webpage = self._download_webpage(
+            'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
+            video_id)
+
+        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
+
+        file_list = self._parse_json(
+            self._search_regex(
+                r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage,
+                'file list'),
+            video_id)
+
+        formats = []
+        for item in file_list[0]:
+            file_url = url_or_none(item.get('file'))
+            if not file_url:
+                continue
+            ext = mimetype2ext(item.get('type'))
+            label = item.get('label')
+            formats.append({
+                'url': file_url,
+                'ext': ext,
+                'format_id': label or ext,
+                'height': int_or_none(self._search_regex(
+                    r'(\d+)[pP]', label or '', 'height', default=None)),
+            })
+        self._sort_formats(formats)
+

         thumbnail = self._search_regex(
         thumbnail = self._search_regex(

-            r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+            r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)

 
         return {
             'id': video_id,
             'title': title,
 
         return {
             'id': video_id,
             'title': title,

-            'url': video_url,
-            'ext': 'mp4',

             'thumbnail': thumbnail,
             'thumbnail': thumbnail,

+            'age_limit': self._family_friendly_search(webpage),
+            'formats': formats,

         }
         }