add get_embeded_stream_url to searx.utils

searx/engines/brave.py

@@ -123,7 +123,6 @@ from typing import Any, TYPE_CHECKING
 from urllib.parse import (
     urlencode,
     urlparse,
-    parse_qs,
 )
 
 from dateutil import parser
@@ -137,6 +136,7 @@ from searx.utils import (
     eval_xpath_list,
     eval_xpath_getindex,
     js_variable_to_python,
+    get_embeded_stream_url,
 )
 from searx.enginelib.traits import EngineTraits
 
@@ -311,7 +311,7 @@ def _parse_search(resp):
             # In my tests a video tag in the WEB search was most often not a
             # video, except the ones from youtube ..
 
-            iframe_src = _get_iframe_src(url)
+            iframe_src = get_embeded_stream_url(url)
             if iframe_src:
                 item['iframe_src'] = iframe_src
                 item['template'] = 'videos.html'
@@ -328,15 +328,6 @@ def _parse_search(resp):
     return result_list
 
 
-def _get_iframe_src(url):
-    parsed_url = urlparse(url)
-    if parsed_url.path == '/watch' and parsed_url.query:
-        video_id = parse_qs(parsed_url.query).get('v', [])  # type: ignore
-        if video_id:
-            return 'https://www.youtube-nocookie.com/embed/' + video_id[0]  # type: ignore
-    return None
-
-
 def _parse_news(json_resp):
     result_list = []
 
@@ -392,7 +383,7 @@ def _parse_videos(json_resp):
         if result['thumbnail'] is not None:
             item['thumbnail'] = result['thumbnail']['src']
 
-        iframe_src = _get_iframe_src(url)
+        iframe_src = get_embeded_stream_url(url)
         if iframe_src:
             item['iframe_src'] = iframe_src
 

searx/engines/duckduckgo_extra.py

@@ -7,6 +7,7 @@ DuckDuckGo Extra (images, videos, news)
 from datetime import datetime
 from typing import TYPE_CHECKING
 from urllib.parse import urlencode
+from searx.utils import get_embeded_stream_url
 
 from searx.engines.duckduckgo import fetch_traits  # pylint: disable=unused-import
 from searx.engines.duckduckgo import (
@@ -108,7 +109,7 @@ def _video_result(result):
         'title': result['title'],
         'content': result['description'],
         'thumbnail': result['images'].get('small') or result['images'].get('medium'),
-        'iframe_src': result['embed_url'],
+        'iframe_src': get_embeded_stream_url(result['content']),
         'source': result['provider'],
         'length': result['duration'],
         'metadata': result.get('uploader'),

searx/engines/google_videos.py

@@ -34,6 +34,7 @@ from searx.engines.google import (
     detect_google_sorry,
 )
 from searx.enginelib.traits import EngineTraits
+from searx.utils import get_embeded_stream_url
 
 if TYPE_CHECKING:
     import logging
@@ -125,6 +126,7 @@ def response(resp):
                 'content': content,
                 'author': pub_info,
                 'thumbnail': thumbnail,
+                'iframe_src': get_embeded_stream_url(url),
                 'template': 'videos.html',
             }
         )

searx/engines/qwant.py

@@ -57,6 +57,7 @@ from searx.utils import (
     eval_xpath,
     eval_xpath_list,
     extract_text,
+    get_embeded_stream_url,
 )
 
 traits: EngineTraits
@@ -297,6 +298,7 @@ def parse_web_api(resp):
                         'title': title,
                         'url': res_url,
                         'content': content,
+                        'iframe_src': get_embeded_stream_url(res_url),
                         'publishedDate': pub_date,
                         'thumbnail': thumbnail,
                         'template': 'videos.html',