Update upstream source from tag 'upstream/2019.06.08'

[youtubedl] / youtube_dl / extractor / izlesene.py

diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py
index 79e8430b5e6a85d59ede8490eac5405950c5dabc..f8fca6c8f47c9978e78d1c2c76d0dcb84a8d7f9d 100644 (file)
--- a/youtube_dl/extractor/izlesene.py
+++ b/youtube_dl/extractor/izlesene.py
@@ -1,86 +1,106 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)

 from ..utils import (
 from ..utils import (

-    get_element_by_id,
-    parse_iso8601,

     determine_ext,
     determine_ext,

+    float_or_none,
+    get_element_by_id,

     int_or_none,
     int_or_none,

+    parse_iso8601,

     str_to_int,
 )
 
 
 class IzleseneIE(InfoExtractor):
     str_to_int,
 )
 
 
 class IzleseneIE(InfoExtractor):

-    _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',
-            '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,
-        }
-    }
+    _VALID_URL = r'''(?x)
+        https?://(?:(?:www|m)\.)?izlesene\.com/
+        (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
+        '''
+    _TESTS = [
+        {
+            'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
+            'md5': '4384f9f0ea65086734b881085ee05ac2',
+            'info_dict': {
+                'id': '7599694',
+                'ext': 'mp4',
+                'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+                'description': 'md5:253753e2655dde93f59f74b572454f6d',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'uploader_id': 'pelikzzle',
+                'timestamp': int,
+                'upload_date': '20140702',
+                'duration': 95.395,
+                'age_limit': 0,
+            }
+        },
+        {
+            'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
+            'md5': '97f09b6872bffa284cb7fa4f6910cb72',
+            'info_dict': {
+                'id': '17997',
+                'ext': 'mp4',
+                'title': 'Tarkan Dortmund 2006 Konseri',
+                'thumbnail': r're:^https://.*\.jpg',
+                'uploader_id': 'parlayankiz',
+                'timestamp': int,
+                'upload_date': '20061112',
+                'duration': 253.666,
+                'age_limit': 0,
+            }
+        },
+    ]

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.izlesene.com/video/%s' % video_id
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage('http://www.izlesene.com/video/%s' % video_id, video_id)
+
+        video = self._parse_json(
+            self._search_regex(
+                r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'),
+            video_id)

 
 

-        webpage = self._download_webpage(url, video_id)
+        title = video.get('videoTitle') or self._og_search_title(webpage)
+
+        formats = []
+        for stream in video['media']['level']:
+            source_url = stream.get('source')
+            if not source_url or not isinstance(source_url, compat_str):
+                continue
+            ext = determine_ext(url, 'mp4')
+            quality = stream.get('value')
+            height = int_or_none(quality)
+            formats.append({
+                'format_id': '%sp' % quality if quality else 'sd',
+                'url': compat_urllib_parse_unquote(source_url),
+                'ext': ext,
+                'height': height,
+            })
+        self._sort_formats(formats)

 
 

-        title = self._og_search_title(webpage)
-        description = self._og_search_description(webpage)
-        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage, default=None)
+        thumbnail = video.get('posterURL') or self._proto_relative_url(
+            self._og_search_thumbnail(webpage), scheme='http:')

 
         uploader = self._html_search_regex(
 
         uploader = self._html_search_regex(

-            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
+            r"adduserUsername\s*=\s*'([^']+)';",
+            webpage, 'uploader', fatal=False)

         timestamp = parse_iso8601(self._html_search_meta(
         timestamp = parse_iso8601(self._html_search_meta(

-            'uploadDate', webpage, 'upload date', fatal=False))
+            'uploadDate', webpage, 'upload date'))

 
 

-        duration = int_or_none(self._html_search_regex(
-            r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
-        if duration:
-            duration /= 1000.0
+        duration = float_or_none(video.get('duration') or self._html_search_regex(
+            r'videoduration["\']?\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            webpage, 'duration', fatal=False, group='value'), scale=1000)

 
         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
         comment_count = self._html_search_regex(
 
         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
         comment_count = self._html_search_regex(

-            r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
-
-        family_friendly = self._html_search_meta(
-            'isFamilyFriendly', webpage, 'age limit', 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.
-        qualities = self._html_search_regex(
-            r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
-
-        formats = []
-        for quality in qualities.split('|'):
-            json = self._download_json(
-                self._STREAM_URL.format(id=video_id, format=quality), video_id,
-                note='Getting video URL for "%s" quality' % quality,
-                errnote='Failed to get video URL for "%s" quality' % quality
-            )
-            formats.append({
-                'url': json.get('streamurl'),
-                'ext': ext,
-                'format_id': '%sp' % quality if quality else 'sd',
-            })
+            r'comment_count\s*=\s*\'([^\']+)\';',
+            webpage, 'comment_count', fatal=False)

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


@@ -92,6 +112,6 @@ class IzleseneIE(InfoExtractor):
             'duration': duration,
             'view_count': int_or_none(view_count),
             'comment_count': int_or_none(comment_count),
             'duration': duration,
             'view_count': int_or_none(view_count),
             'comment_count': int_or_none(comment_count),

-            'age_limit': 18 if family_friendly == 'False' else 0,
+            'age_limit': self._family_friendly_search(webpage),

             'formats': formats,
         }
             'formats': formats,
         }