[extractor/wordpress:mb.miniAudioPlayer] Add embed extractor (#5087)

Closes https://github.com/yt-dlp/yt-dlp/issues/4994

Authored by: coletdjnz

diff --git a/test/test_utils.py b/test/test_utils.py
index 90085a9c0d904c87d2dceeb53b921ac1d3c04804..df23f1f47b1564f75541a57390be110303c8ef2e 100644 (file)
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1679,6 +1679,9 @@ def test_get_elements_text_and_html_by_attribute(self):
         self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'foo', html)), [])
         self.assertEqual(list(get_elements_text_and_html_by_attribute('class', 'no-such-foo', html)), [])
 
+        self.assertEqual(list(get_elements_text_and_html_by_attribute(
+            'class', 'foo', '<a class="foo">nice</a><span class="foo">nice</span>', tag='a')), [('nice', '<a class="foo">nice</a>')])
+
     GET_ELEMENT_BY_TAG_TEST_STRING = '''
     random text lorem ipsum</p>
     <div>

diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py
index 75cb3fcab9c4eeff4fbf4898db809fcea0066037..e5be3571645df04365ebb561aa2e8828bd1a9b98 100644 (file)
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@@ -2165,7 +2165,10 @@
     WistiaPlaylistIE,
     WistiaChannelIE,
 )
-from .wordpress import WordpressPlaylistEmbedIE
+from .wordpress import (
+    WordpressPlaylistEmbedIE,
+    WordpressMiniAudioPlayerEmbedIE,
+)
 from .worldstarhiphop import WorldStarHipHopIE
 from .wppilot import (
     WPPilotIE,

diff --git a/yt_dlp/extractor/wordpress.py b/yt_dlp/extractor/wordpress.py
index e90ae6c1e10769ab8e387447ef81bda1cae53191..53820b57a907d6c69e50cd9fbdbc312b8e6b340f 100644 (file)
--- a/yt_dlp/extractor/wordpress.py
+++ b/yt_dlp/extractor/wordpress.py
@@ -1,6 +1,10 @@
+import re
+
 from .common import InfoExtractor
 from ..utils import (
+    extract_attributes,
     get_elements_by_class,
+    get_elements_text_and_html_by_attribute,
     int_or_none,
     parse_duration,
     traverse_obj,
@@ -67,3 +71,84 @@ def _extract_from_webpage(self, url, webpage):
                 'width': int_or_none(traverse_obj(track, ('dimensions', 'original', 'width'))),
             } for track in traverse_obj(playlist_json, ('tracks', ...), expected_type=dict)]
             yield self.playlist_result(entries, self._generic_id(url) + f'-wp-playlist-{i+1}', 'Wordpress Playlist')
+
+
+class WordpressMiniAudioPlayerEmbedIE(InfoExtractor):
+    # WordPress MB Mini Player Plugin
+    # https://wordpress.org/plugins/wp-miniaudioplayer/
+    # Note: This is for the WordPress plugin version only.
+    _VALID_URL = False
+    IE_NAME = 'wordpress:mb.miniAudioPlayer'
+    _WEBPAGE_TESTS = [{
+        # Version 1.8.10: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.8.10
+        'url': 'https://news.samsung.com/global/over-the-horizon-the-evolution-of-the-samsung-galaxy-brand-sound',
+        'info_dict': {
+            'id': 'over-the-horizon-the-evolution-of-the-samsung-galaxy-brand-sound',
+            'title': 'Over the Horizon: The Evolution of the Samsung Galaxy Brand Sound',
+            'age_limit': 0,
+            'thumbnail': 'https://img.global.news.samsung.com/global/wp-content/uploads/2015/04/OTH_Main_Title-e1429612467870.jpg',
+            'description': 'md5:bc3dd738d1f11d9232e94e6629983bf7',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'over_the_horizon_2013',
+                'ext': 'mp3',
+                'title': 'Over the Horizon 2013',
+                'url': 'http://news.samsung.com/global/wp-content/uploads/ringtones/over_the_horizon_2013.mp3'
+            }
+        }],
+        'playlist_count': 6,
+        'params': {'skip_download': True}
+    }, {
+        # Version 1.9.3: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.9.3
+        'url': 'https://www.booksontape.com/collections/audiobooks-with-teacher-guides/',
+        'info_dict': {
+            'id': 'audiobooks-with-teacher-guides',
+            'title': 'Audiobooks with Teacher Guides | Books on Tape',
+            'age_limit': 0,
+            'thumbnail': 'https://www.booksontape.com/wp-content/uploads/2016/09/bot-logo-1200x630.jpg',
+        },
+        'playlist_mincount': 12
+    }, {
+        # Version 1.9.7: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.9.7
+        # But has spaces around href filter
+        'url': 'https://www.estudiords.com.br/temas/',
+        'info_dict': {
+            'id': 'temas',
+            'title': 'Temas Variados',
+            'age_limit': 0,
+            'timestamp': float,
+            'upload_date': str,
+            'thumbnail': 'https://www.estudiords.com.br/wp-content/uploads/2021/03/LOGO-TEMAS.png',
+            'description': 'md5:ab24d6a7ed0312ad2d466e721679f5a0',
+        },
+        'playlist_mincount': 30
+    }]
+
+    def _extract_from_webpage(self, url, webpage):
+        # Common function for the WordPress plugin version only.
+        mb_player_params = self._search_regex(
+            r'function\s*initializeMiniAudioPlayer\(\){[^}]+jQuery([^;]+)\.mb_miniPlayer',
+            webpage, 'mb player params', default=None)
+        if not mb_player_params:
+            return
+        # v1.55 - 1.9.3 has "a[href*='.mp3'] ,a[href*='.m4a']"
+        # v1.9.4+ has "a[href*='.mp3']" only
+        file_exts = re.findall(r'a\[href\s*\*=\s*\'\.([a-zA-Z\d]+)\'', mb_player_params)
+        if not file_exts:
+            return
+
+        candidates = get_elements_text_and_html_by_attribute(
+            'href', rf'(?:[^\"\']+\.(?:{"|".join(file_exts)}))', webpage, escape_value=False, tag='a')
+
+        for title, html in candidates:
+            attrs = extract_attributes(html)
+            # XXX: not tested - have not found any example of it being used
+            if any(c in (attrs.get('class') or '') for c in re.findall(r'\.not\("\.([^"]+)', mb_player_params)):
+                continue
+            href = attrs['href']
+            yield {
+                'id': self._generic_id(href),
+                'title': title or self._generic_title(href),
+                'url': href,
+            }

diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py
index cb14908c7fff790bb7498a6341f7717e381541ec..5a88a928d6ac8f4452e5d01df717e0d2dc3c4d88 100644 (file)
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@@ -408,7 +408,7 @@ def get_elements_html_by_attribute(*args, **kwargs):
     return [whole for _, whole in get_elements_text_and_html_by_attribute(*args, **kwargs)]
 
 
-def get_elements_text_and_html_by_attribute(attribute, value, html, escape_value=True):
+def get_elements_text_and_html_by_attribute(attribute, value, html, *, tag=r'[\w:.-]+', escape_value=True):
     """
     Return the text (content) and the html (whole) of the tag with the specified
     attribute in the passed HTML document
@@ -419,7 +419,7 @@ def get_elements_text_and_html_by_attribute(attribute, value, html, escape_value
     value = re.escape(value) if escape_value else value
 
     partial_element_re = rf'''(?x)
-        <(?P<tag>[a-zA-Z0-9:._-]+)
+        <(?P<tag>{tag})
          (?:\s(?:[^>"']|"[^"]*"|'[^']*')*)?
          \s{re.escape(attribute)}\s*=\s*(?P<_q>['"]{quote})(?-x:{value})(?P=_q)
         '''