[extractor/common] Check validity of direct URLs

[youtube-dl] / youtube_dl / extractor / common.py

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 5684227dcfca770be68d1feea28616a5e0d84e57..b928e24beed9cd161b2fa84c9b410980268c0061 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -39,6 +39,7 @@ from ..utils import (
     RegexNotFoundError,
     sanitize_filename,
     unescapeHTML,
+    unified_strdate,
     url_basename,
     xpath_text,
     xpath_with_ns,
@@ -1044,6 +1045,7 @@ class InfoExtractor(object):
         video_id = os.path.splitext(url_basename(smil_url))[0]
         title = None
         description = None
+        upload_date = None
         for meta in smil.findall(self._xpath_ns('./head/meta', namespace)):
             name = meta.attrib.get('name')
             content = meta.attrib.get('content')
@@ -1053,6 +1055,8 @@ class InfoExtractor(object):
                 title = content
             elif not description and name in ('description', 'abstract'):
                 description = content
+            elif not upload_date and name == 'date':
+                upload_date = unified_strdate(content)
 
         thumbnails = [{
             'id': image.get('type'),
@@ -1065,6 +1069,7 @@ class InfoExtractor(object):
             'id': video_id,
             'title': title or video_id,
             'description': description,
+            'upload_date': upload_date,
             'thumbnails': thumbnails,
             'formats': formats,
             'subtitles': subtitles,
@@ -1140,7 +1145,7 @@ class InfoExtractor(object):
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds'))
                 continue
 
-            if src_url.startswith('http'):
+            if src_url.startswith('http') and self._is_valid_url(src, video_id):
                 http_count += 1
                 formats.append({
                     'url': src_url,