[snotr] Fix extraction (closes #10338)

diff --git a/ChangeLog b/ChangeLog
index b36e4438cd6a4bbc541f1dbd2e5004e6a657cd3b..13c3d3ffcaed279bbdefd6e2b0450882808accb4 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -7,6 +7,7 @@ Core
 * Fix js_to_json(): correct octal or hexadecimal number detection
 
 Extractors
+* [snotr] Fix extraction (#10338)
 * [n-tv.de] Fix extraction (#10331)
 
 

diff --git a/youtube_dl/extractor/snotr.py b/youtube_dl/extractor/snotr.py
index 0d1ab07f86ac4088b4fd1e56e9d1dfaa52514ddd..3bb78cb84898acf4fddccd556d252a25a8559832 100644 (file)
--- a/youtube_dl/extractor/snotr.py
+++ b/youtube_dl/extractor/snotr.py
@@ -5,9 +5,9 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    float_or_none,
-    str_to_int,
     parse_duration,
+    parse_filesize,
+    str_to_int,
 )
 
 
@@ -17,21 +17,24 @@ class SnotrIE(InfoExtractor):
         'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
         'info_dict': {
             'id': '13708',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Drone flying through fireworks!',
-            'duration': 247,
-            'filesize_approx': 98566144,
+            'duration': 248,
+            'filesize_approx': 40700000,
             'description': 'A drone flying through Fourth of July Fireworks',
-        }
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'expected_warnings': ['description'],
     }, {
         'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
         'info_dict': {
             'id': '530',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'David Letteman - George W. Bush Top 10',
             'duration': 126,
-            'filesize_approx': 8912896,
+            'filesize_approx': 8500000,
             'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
+            'thumbnail': 're:^https?://.*\.jpg$',
         }
     }]
 
@@ -43,26 +46,27 @@ class SnotrIE(InfoExtractor):
         title = self._og_search_title(webpage)
 
         description = self._og_search_description(webpage)
-        video_url = 'http://cdn.videos.snotr.com/%s.flv' % video_id
+        info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
 
         view_count = str_to_int(self._html_search_regex(
-            r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',
+            r'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
             webpage, 'view count', fatal=False))
 
         duration = parse_duration(self._html_search_regex(
-            r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>',
+            r'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
             webpage, 'duration', fatal=False))
 
-        filesize_approx = float_or_none(self._html_search_regex(
-            r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
-            webpage, 'filesize', fatal=False), invscale=1024 * 1024)
+        filesize_approx = parse_filesize(self._html_search_regex(
+            r'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
+            webpage, 'filesize', fatal=False))
 
-        return {
+        info_dict.update({
             'id': video_id,
             'description': description,
             'title': title,
-            'url': video_url,
             'view_count': view_count,
             'duration': duration,
             'filesize_approx': filesize_approx,
-        }
+        })
+
+        return info_dict