[extractor/common] Add support for AMP tags in _parse_html5_media_entries

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index afeb4c5daa839cefc8385f5ced2fd4874d5af314..daa10885fb27a583773e2f9b8421448309346ac7 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -2132,15 +2132,18 @@ class InfoExtractor(object):
             return is_plain_url, formats
 
         entries = []
+        # amp-video and amp-audio are very similar to their HTML5 counterparts
+        # so we wll include them right here (see
+        # https://www.ampproject.org/docs/reference/components/amp-video)
         media_tags = [(media_tag, media_type, '')
                       for media_tag, media_type
-                      in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
+                      in re.findall(r'(?s)(<(?:amp-)?(video|audio)[^>]*/>)', webpage)]
         media_tags.extend(re.findall(
             # We only allow video|audio followed by a whitespace or '>'.
             # Allowing more characters may end up in significant slow down (see
             # https://github.com/rg3/youtube-dl/issues/11979, example URL:
             # http://www.porntrex.com/maps/videositemap.xml).
-            r'(?s)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
+            r'(?s)(<(?P<tag>(?:amp-)?(?:video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
         for media_tag, media_type, media_content in media_tags:
             media_info = {
                 'formats': [],

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 95c38698d6404be54be3c5c378f8b2e4f350685f..919f4f987eb6f5af3963656329ca9fc1c540d9a8 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -1770,6 +1770,16 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': [MediasetIE.ie_key()],
         },
+        {
+            # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
+            'url': 'https://tvrain.ru/amp/418921/',
+            'md5': 'cc00413936695987e8de148b67d14f1d',
+            'info_dict': {
+                'id': '418921',
+                'ext': 'mp4',
+                'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
+            },
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject