[ie/joqrag] Fix download test; add only_matching tests

Co-authored-by: garret <garret1317@yandex.com>

yt_dlp/extractor/joqrag.py

@@ -1,21 +1,21 @@
 import urllib.parse
 
 from .common import InfoExtractor
+from ..utils import clean_html, urljoin
 
 
 class JoqrAgIE(InfoExtractor):
     IE_DESC = '超!A&G+ 文化放送 Nippon Cultural Broadcasting, Inc. (JOQR)'
-    _VALID_URL = r'''(?x)
+    _VALID_URL = [r'https?://www\.uniqueradio\.jp/agplayer5/player\.php',
-                    (https?://www\.uniqueradio\.jp/agplayer5/player\.php)|
+                  r'https?://www\.uniqueradio\.jp/agplayer5/inc-player-hls\.php',
-                    (https?://www\.uniqueradio\.jp/agplayer5/inc-player-hls\.php)|
+                  r'https?://(?:www\.)?joqr\.co\.jp/ag/',
-                    (https?://(?:www\.)?joqr\.co\.jp/ag/)|
+                  r'https?://(?:www\.)?joqr\.co\.jp/qr/(?:agdailyprogram|agregularprogram)/']
-                    (https?://(?:www\.)?joqr\.co\.jp/qr/(?:agdailyprogram|agregularprogram)/)
-                    '''
     _TESTS = [{
         'url': 'https://www.uniqueradio.jp/agplayer5/player.php',
         'info_dict': {
             'id': 'live',
             'title': str,
+            'channel': '超!A&G+',
             'description': str,
             'live_status': 'is_live',
         },
@@ -23,6 +23,18 @@ class JoqrAgIE(InfoExtractor):
             'skip_download': True,
             'ignore_no_formats_error': True,
         },
+    }, {
+        'url': 'https://www.uniqueradio.jp/agplayer5/inc-player-hls.php',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.joqr.co.jp/ag/article/103760/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.joqr.co.jp/qr/agdailyprogram/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.joqr.co.jp/qr/agregularprogram/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -31,10 +43,10 @@ class JoqrAgIE(InfoExtractor):
         metadata = self._download_webpage(
             'https://www.uniqueradio.jp/aandg', video_id,
             note='Downloading metadata', errnote='Failed to download metadata')
-        title = urllib.parse.unquote_plus(
+        title = clean_html(urllib.parse.unquote_plus(
-            self._search_regex(r'var\s+Program_name\s*=\s*["\']([^"\']+)["\']', metadata, 'program title'))
+            self._search_regex(r'var\s+Program_name\s*=\s*["\']([^"\']+)["\']', metadata, 'program title')))
-        desc = urllib.parse.unquote_plus(
+        desc = clean_html(urllib.parse.unquote_plus(
-            self._search_regex(r'var\s+Program_text\s*=\s*["\']([^"\']+)["\']', metadata, 'program description'))
+            self._search_regex(r'var\s+Program_text\s*=\s*["\']([^"\']+)["\']', metadata, 'program description')))
 
         m3u8_path = self._search_regex(
             r'<source\s[^>]*\bsrc="([^"]+)"',
@@ -43,11 +55,12 @@ class JoqrAgIE(InfoExtractor):
                 note='Downloading player data', errnote='Failed to download player data'),
             'm3u8 url')
         formats = self._extract_m3u8_formats(
-            f'https://www.uniqueradio.jp/{m3u8_path}', video_id, fatal=False)
+            urljoin('https://www.uniqueradio.jp/', m3u8_path), video_id, fatal=False)
 
         return {
             'id': video_id,
-            'title': f'{title} - 超!A&G+',
+            'title': title,
+            'channel': '超!A&G+',
             'description': desc,
             'formats': formats,
             'live_status': 'is_live',