[tele5] Fix extraction (closes #24553)
authorSergey M․ <dstftw@gmail.com>
Sun, 5 Apr 2020 19:05:06 +0000 (02:05 +0700)
committerSergey M․ <dstftw@gmail.com>
Sun, 5 Apr 2020 19:05:06 +0000 (02:05 +0700)
youtube_dl/extractor/tele5.py

index 33a72083bff96a74e04020257ba3305d1cfee2ca..364556a1f89d3c1943950c1634bbfae0639a3e7d 100644 (file)
@@ -1,9 +1,19 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
 from .nexx import NexxIE
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    NO_DEFAULT,
+    try_get,
+)
 
 
 class Tele5IE(InfoExtractor):
@@ -44,14 +54,49 @@ class Tele5IE(InfoExtractor):
         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
 
-        if not video_id:
+        NEXX_ID_RE = r'\d{6,}'
+        JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
+
+        def nexx_result(nexx_id):
+            return self.url_result(
+                'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
+                ie=NexxIE.ie_key(), video_id=nexx_id)
+
+        nexx_id = jwplatform_id = None
+
+        if video_id:
+            if re.match(NEXX_ID_RE, video_id):
+                return nexx_result(video_id)
+            elif re.match(JWPLATFORM_ID_RE, video_id):
+                jwplatform_id = video_id
+
+        if not nexx_id:
             display_id = self._match_id(url)
             webpage = self._download_webpage(url, display_id)
-            video_id = self._html_search_regex(
-                (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
-                 r'\s+id\s*=\s*["\']player_(\d{6,})',
-                 r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id')
+
+            def extract_id(pattern, name, default=NO_DEFAULT):
+                return self._html_search_regex(
+                    (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
+                     r'\s+id\s*=\s*["\']player_(%s)' % pattern,
+                     r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
+                    default=default)
+
+            nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
+            if nexx_id:
+                return nexx_result(nexx_id)
+
+            if not jwplatform_id:
+                jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
+
+            media = self._download_json(
+                'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
+                display_id)
+            nexx_id = try_get(
+                media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
+
+            if nexx_id:
+                return nexx_result(nexx_id)
 
         return self.url_result(
-            'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
-            ie=NexxIE.ie_key(), video_id=video_id)
+            'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
+            video_id=jwplatform_id)