[izlesene] Minor changes

youtube_dl/extractor/izlesene.py

@@ -4,25 +4,31 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import get_element_by_id, parse_iso8601, determine_ext, int_or_none
+from ..utils import (
+    get_element_by_id,
+    parse_iso8601,
+    determine_ext,
+    int_or_none,
+    str_to_int,
+)
 
 
 class IzleseneIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.|m\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
     _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
     _TEST = {
         'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
         'md5': '4384f9f0ea65086734b881085ee05ac2',
         'info_dict': {
             'id': '7599694',
-            'title': u'Sevinçten Çıldırtan Doğum Günü Hediyesi',
-            'upload_date': '20140702',
-            'uploader_id': 'pelikzzle',
-            'description': u'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
-            'timestamp': 1404298698,
-            'duration': 95,
             'ext': 'mp4',
+            'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+            'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
             'thumbnail': 're:^http://.*\.jpg',
+            'uploader_id': 'pelikzzle',
+            'timestamp': 1404298698,
+            'upload_date': '20140702',
+            'duration': 95.395,
             'age_limit': 0,
         }
     }
@@ -37,58 +43,55 @@ class IzleseneIE(InfoExtractor):
         title = self._og_search_title(webpage)
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
-        duration = int(
+
-            self._html_search_regex(
+        uploader = self._html_search_regex(
-                r'"videoduration"\s?:\s?"([^"]+)"', webpage, 'duration',
+            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
-                fatal=False, default='0')
+        timestamp = parse_iso8601(self._html_search_meta(
-            ) / 1000
+            'uploadDate', webpage, 'upload date', fatal=False))
-        view_count = get_element_by_id('videoViewCount',
+
-                                       webpage).replace('.', '')
+        duration = int_or_none(self._html_search_regex(
-        timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage,
+            r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
-                                  'upload date', fatal=False))
+        if duration:
-        family_friendly = self._html_search_meta('isFamilyFriendly', webpage,
+            duration /= 1000.0
-                                                 'age limit', fatal=False)
+
-        uploader = self._html_search_regex(r"adduserUsername\s?=\s?'([^']+)';",
+        view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
-                                           webpage, 'uploader', fatal=False,
-                                           default='')
         comment_count = self._html_search_regex(
-            r'comment_count\s?=\s?\'([^\']+)\';',
+            r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
-            webpage, 'uploader', fatal=False)
 
-        content_url = self._html_search_meta('contentURL', webpage,
+        family_friendly = self._html_search_meta(
-                                             'content URL', fatal=False)
+            'isFamilyFriendly', webpage, 'age limit', fatal=False)
-        ext = determine_ext(content_url)
+
+        content_url = self._html_search_meta(
+            'contentURL', webpage, 'content URL', fatal=False)
+        ext = determine_ext(content_url, 'mp4')
 
         # Might be empty for some videos.
-        qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"',
+        qualities = self._html_search_regex(
-                                            webpage, 'qualities', fatal=False,
+            r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
-                                            default='')
 
         formats = []
         for quality in qualities.split('|'):
             json = self._download_json(
                 self._STREAM_URL.format(id=video_id, format=quality), video_id,
-                note=u'Getting video URL for "%s" quality' % quality,
+                note='Getting video URL for "%s" quality' % quality,
-                errnote=u'Failed to get video URL for "%s" quality' % quality
+                errnote='Failed to get video URL for "%s" quality' % quality
             )
-            video_format = '%sp' % quality if quality else 'sd'
             formats.append({
                 'url': json.get('streamurl'),
                 'ext': ext,
-                'format': video_format,
+                'format_id': '%sp' % quality if quality else 'sd',
-                'format_id': video_format,
             })
 
         return {
             'id': video_id,
             'title': title,
-            'formats': formats,
             'description': description,
             'thumbnail': thumbnail,
+            'uploader_id': uploader,
+            'timestamp': timestamp,
             'duration': duration,
             'view_count': int_or_none(view_count),
-            'timestamp': timestamp,
-            'age_limit': 18 if family_friendly == 'False' else 0,
-            'uploader_id': uploader,
             'comment_count': int_or_none(comment_count),
+            'age_limit': 18 if family_friendly == 'False' else 0,
+            'formats': formats,
         }

youtube_dl/utils.py

@@ -852,6 +852,8 @@ def unified_strdate(date_str):
     return upload_date
 
 def determine_ext(url, default_ext=u'unknown_video'):
+    if url is None:
+        return default_ext
     guess = url.partition(u'?')[0].rpartition(u'.')[2]
     if re.match(r'^[A-Za-z0-9]+$', guess):
         return guess