Update dzsecurity.py to use _EMBED_REGEX

yt_dlp/extractor/dzsecurity.py

@@ -1,13 +1,42 @@
-import re
 
+from yt_dlp import traverse_obj
 from yt_dlp.extractor.common import InfoExtractor
-from yt_dlp.utils import ExtractorError
+from yt_dlp.utils import smuggle_url, unsmuggle_url
 
 
 class DzsecurityLiveIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(echoroukonline\.com/live(?:-news)?|ennaharonline\.com/live(?:-news)?|elhayat\.dz/%D8%A7%D9%84%D8%A8%D8%AB-%D8%A7%D9%84%D8%AD%D9%8A)'
+    _VALID_URL = r'https?://live\.dzsecurity\.net/live/player/(?P<id>[\w-]+)'
+    _EMBED_REGEX = [rf'<iframe [^>]*\bsrc\s*=\s*[\'"](?P<url>{_VALID_URL})']
 
-    _TESTS = [{
+    _WEBPAGE_TESTS = [
+        {
+            'url': 'https://www.echoroukonline.com/live',
+            'info_dict': {
+                'id': 'echorouktv',
+                'title': r're:البث الحي لقناة الشروق تي في',
+                'ext': 'mp4',
+                'live_status': 'is_live',
+            },
+        },
+        {
+            'url': 'https://www.echoroukonline.com/live-news',
+            'info_dict': {
+                'id': 'echorouknews',
+                'title': r're:البث الحي لقناة الشروق نيوز - آخر أخبار الجزائر',
+                'ext': 'mp4',
+                'live_status': 'is_live',
+            },
+        },
+        {
+            'url': 'https://elhayat.dz/%D8%A7%D9%84%D8%A8%D8%AB-%D8%A7%D9%84%D8%AD%D9%8A/',
+            'info_dict': {
+                'id': 'elhayattv',
+                'title': r're:البث الحي - الحياة',
+                'ext': 'mp4',
+                'live_status': 'is_live',
+            },
+        },
+        {
             'url': 'https://www.ennaharonline.com/live',
             'info_dict': {
                 'id': 'ennahartv',
@@ -16,55 +45,26 @@ class DzsecurityLiveIE(InfoExtractor):
                 'live_status': 'is_live',
             },
             'skip': 'Geo-restricted to Algeria',
-    }, {
-        'url': 'https://www.echoroukonline.com/live',
-        'info_dict': {
-            'id': 'echorouktv',
-            'title': r're:البث الحي لقناة الشروق تي في',
-            'ext': 'mp4',
-            'live_status': 'is_live',
         },
-    }, {
+    ]
-        'url': 'https://www.echoroukonline.com/live-news',
+
-        'info_dict': {
+    @classmethod
-            'id': 'echorouknews',
+    def _extract_embed_urls(cls, url, webpage):
-            'title': r're:البث الحي لقناة الشروق نيوز - آخر أخبار الجزائر',
+        for embed_url in super()._extract_embed_urls(url, webpage):
-            'ext': 'mp4',
+            yield smuggle_url(embed_url, {'referer': url})
-            'live_status': 'is_live',
-        },
-    }, {
-        'url': 'https://elhayat.dz/%D8%A7%D9%84%D8%A8%D8%AB-%D8%A7%D9%84%D8%AD%D9%8A',
-        'info_dict': {
-            'id': 'elhayattv',
-            'title': r're:البث الحي - الحياة',
-            'ext': 'mp4',
-            'live_status': 'is_live',
-        },
-    }]
 
     def _real_extract(self, url):
-        webpage = self._download_webpage(url, url, impersonate=True)
+        url, smuggled_data = unsmuggle_url(url, {})
 
-        title = self._html_extract_title(webpage, default='Live Stream')
+        stream_id = self._match_id(url)
 
-        player_url, stream_id = self._html_search_regex(
+        title = stream_id
-            r'https://live\.dzsecurity\.net/live/player/([a-zA-Z0-9_-]+)',
+        referer = smuggled_data['referer']
-            webpage,
+        if referer:
-            'player URL',
+            webpage = self._download_webpage(referer, referer)
-            group=(0, 1),
+            title = self._html_extract_title(webpage, default=title)
-        )
 
-        base_url_match = re.match(r'(https?://[^/]+)', url)
+        player_page = self._download_webpage(url, stream_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
-        if not base_url_match:
-            raise ExtractorError('Failed to extract base URL from input URL')
-
-        base_url = base_url_match.group(1)
-
-        headers = {
-            'Referer': base_url,
-        }
-
-        player_page = self._download_webpage(player_url, player_url, headers=headers)
 
         m3u8_url = 'https:' + self._search_regex(
             r'src:\s*location\.protocol\s*\+\s*"(//[^"]+\.m3u8\?[^"]+)"',