[izlesene] extract info using api request

youtube_dl/extractor/izlesene.py

@@ -6,11 +6,7 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
-    determine_ext,
-    float_or_none,
-    get_element_by_id,
     int_or_none,
-    parse_iso8601,
     str_to_int,
 )
 
@@ -28,13 +24,8 @@ class IzleseneIE(InfoExtractor):
                 'id': '7599694',
                 'ext': 'mp4',
                 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
-                'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
-                'uploader_id': 'pelikzzle',
+                'duration': 95395,
-                'timestamp': int,
-                'upload_date': '20140702',
-                'duration': 95.395,
-                'age_limit': 0,
             }
         },
         {
@@ -44,13 +35,8 @@ class IzleseneIE(InfoExtractor):
                 'id': '17997',
                 'ext': 'mp4',
                 'title': 'Tarkan Dortmund 2006 Konseri',
-                'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
-                'uploader_id': 'parlayankiz',
+                'duration': 253666,
-                'timestamp': int,
-                'upload_date': '20061112',
-                'duration': 253.666,
-                'age_limit': 0,
             }
         },
     ]
@@ -58,65 +44,37 @@ class IzleseneIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        url = 'http://www.izlesene.com/video/%s' % video_id
+        api_data = self._download_json('http://panel.izlesene.com/api/playerJson/izlesene/%s' % video_id, video_id)
-        webpage = self._download_webpage(url, video_id)
 
-        title = self._og_search_title(webpage)
+        title = api_data['videoname']
-        description = self._og_search_description(webpage)
+        thumbnail = api_data.get('thumbnail')
-        thumbnail = self._proto_relative_url(
+        duration = int_or_none(api_data.get('videoduration'))
-            self._og_search_thumbnail(webpage), scheme='http:')
+        view_count = int_or_none(str_to_int(api_data.get('views')))
-
-        uploader = self._html_search_regex(
-            r"adduserUsername\s*=\s*'([^']+)';",
-            webpage, 'uploader', fatal=False)
-        timestamp = parse_iso8601(self._html_search_meta(
-            'uploadDate', webpage, 'upload date'))
-
-        duration = float_or_none(self._html_search_regex(
-            r'"videoduration"\s*:\s*"([^"]+)"',
-            webpage, 'duration', fatal=False), scale=1000)
-
-        view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
-        comment_count = self._html_search_regex(
-            r'comment_count\s*=\s*\'([^\']+)\';',
-            webpage, 'comment_count', fatal=False)
-
-        content_url = self._html_search_meta(
-            'contentURL', webpage, 'content URL', fatal=False)
-        ext = determine_ext(content_url, 'mp4')
 
         # Might be empty for some videos.
-        streams = self._html_search_regex(
+        streams = api_data.get('qualitylevel')
-            r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='')
 
         formats = []
+        # TODO: extract formats from dash manifest
         if streams:
             for stream in streams.split('|'):
                 quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
                 formats.append({
                     'format_id': '%sp' % quality if quality else 'sd',
-                    'url': compat_urllib_parse_unquote(url),
+                    'url': url,
-                    'ext': ext,
                 })
         else:
-            stream_url = self._search_regex(
+            stream_url = api_data.get('streamurl')
-                r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL')
             formats.append({
                 'format_id': 'sd',
-                'url': compat_urllib_parse_unquote(stream_url),
+                'url': stream_url,
-                'ext': ext,
             })
 
         return {
             'id': video_id,
             'title': title,
-            'description': description,
             'thumbnail': thumbnail,
-            'uploader_id': uploader,
-            'timestamp': timestamp,
             'duration': duration,
-            'view_count': int_or_none(view_count),
+            'view_count': view_count,
-            'comment_count': int_or_none(comment_count),
-            'age_limit': self._family_friendly_search(webpage),
             'formats': formats,
         }