[ie/matchtv] Fix extractor (#10190)

[yt-dlp.git] / yt_dlp / extractor / glomex.py

diff --git a/yt_dlp/extractor/glomex.py b/yt_dlp/extractor/glomex.py
index d9ef4338fc1a2eedcab8e4d7bd84f5d988dd3755..35ffad56c2c56ef18f8d295a697e7c9b63ea345f 100644 (file)
--- a/yt_dlp/extractor/glomex.py
+++ b/yt_dlp/extractor/glomex.py
@@ -1,14 +1,11 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import re
 import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     determine_ext,
     extract_attributes,
-    ExtractorError,
     int_or_none,
     parse_qs,
     smuggle_url,
@@ -52,15 +49,15 @@ def _download_api_data(self, video_id, integration, current_url=None):
         video_id_type = self._get_videoid_type(video_id)
         return self._download_json(
             self._API_URL,
-            video_id, 'Downloading %s JSON' % video_id_type,
-            'Unable to download %s JSON' % video_id_type,
+            video_id, f'Downloading {video_id_type} JSON',
+            f'Unable to download {video_id_type} JSON',
             query=query)
 
     def _download_and_extract_api_data(self, video_id, integration, current_url):
         api_data = self._download_api_data(video_id, integration, current_url)
         videos = api_data['videos']
         if not videos:
-            raise ExtractorError('no videos found for %s' % video_id)
+            raise ExtractorError(f'no videos found for {video_id}')
         videos = [self._extract_api_data(video, video_id) for video in videos]
         return videos[0] if len(videos) == 1 else self.playlist_result(videos, video_id)
 
@@ -85,7 +82,6 @@ def _extract_api_data(self, video, video_id):
         if video.get('language'):
             for fmt in formats:
                 fmt['language'] = video['language']
-        self._sort_formats(formats)
 
         images = (video.get('images') or []) + [video.get('image') or {}]
         thumbnails = [{
@@ -177,7 +173,7 @@ def build_player_url(cls, video_id, integration, origin_url=None):
         return cls._smuggle_origin_url(f'https:{cls._BASE_PLAYER_URL}?{query_string}', origin_url)
 
     @classmethod
-    def _extract_urls(cls, webpage, origin_url):
+    def _extract_embed_urls(cls, url, webpage):
         # https://docs.glomex.com/publisher/video-player-integration/javascript-api/
         quot_re = r'["\']'
 
@@ -186,9 +182,9 @@ def _extract_urls(cls, webpage, origin_url):
                 (?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=q)).)+
             )(?P=q)'''
         for mobj in re.finditer(regex, webpage):
-            url = unescapeHTML(mobj.group('url'))
-            if cls.suitable(url):
-                yield cls._smuggle_origin_url(url, origin_url)
+            embed_url = unescapeHTML(mobj.group('url'))
+            if cls.suitable(embed_url):
+                yield cls._smuggle_origin_url(embed_url, url)
 
         regex = fr'''(?x)
             <glomex-player [^>]+?>|
@@ -196,7 +192,7 @@ def _extract_urls(cls, webpage, origin_url):
         for mobj in re.finditer(regex, webpage):
             attrs = extract_attributes(mobj.group(0))
             if attrs.get('data-integration-id') and attrs.get('data-playlist-id'):
-                yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], origin_url)
+                yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], url)
 
         # naive parsing of inline scripts for hard-coded integration parameters
         regex = fr'''(?x)
@@ -209,7 +205,7 @@ def _extract_urls(cls, webpage, origin_url):
                 continue
             playlist_id = re.search(regex % 'playlistId', script)
             if playlist_id:
-                yield cls.build_player_url(playlist_id, integration_id, origin_url)
+                yield cls.build_player_url(playlist_id, integration_id, url)
 
     def _real_extract(self, url):
         url, origin_url = self._unsmuggle_origin_url(url)