[PromoDJ] Add codecs

yt_dlp/extractor/promodj.py

@@ -6,16 +6,17 @@ import urllib.parse
 from .common import InfoExtractor
 from .youtube import YoutubeIE
 from ..utils import (
-    OnDemandPagedList,
     clean_html,
     dict_get,
     extract_attributes,
     ExtractorError,
     get_element_by_class,
+    get_element_html_by_id,
     get_elements_html_by_class,
     int_or_none,
     js_to_json,
     merge_dicts,
+    OnDemandPagedList,
     parse_duration,
     str_or_none,
     traverse_obj,
@@ -65,8 +66,8 @@ class PromoDJBaseIE(InfoExtractor):
     _PAGES = ['featured', 'shop', *_MEDIA_TYPES]
 
     _BASE_URL_RE = r'https?://(?:www\.)?promodj\.com'
-    _NOT_LOGIN_LIST = '|'.join(['radio', *_PAGES])
+    _NOT_LOGIN_LIST = '|'.join(['radio', 'embed', *_PAGES])
-    _LOGIN_RE = rf'(?!{_NOT_LOGIN_LIST})[\w.-]+'
+    _LOGIN_RE = rf'(?!(?:{_NOT_LOGIN_LIST})(?:/|$))[\w.-]+'
 
     def _set_url_page(self, url, page):
         parsed_url = urllib.parse.urlparse(url)
@@ -154,6 +155,8 @@ class PromoDJBaseIE(InfoExtractor):
             'format_id': 'lossy',
             'url': traverse_obj(source, ('URL', {url_or_none})),
             'size': traverse_obj(source, ('size', {int_or_none})),
+            'acodec': 'mp3',
+            'vcodec': 'none',
         } for source in traverse_obj(media_data, ('sources'))]
         thumbnails = [{
             'url': url,
@@ -247,6 +250,10 @@ class PromoDJUserIE(PromoDJBaseIE):
             'id': 'slim96',
         },
         'playlist_count': 0,
+    }, {
+        # login starts with page name
+        'url': 'https://promodj.com/radio.remix',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -288,6 +295,10 @@ class PromoDJUserMediaIE(PromoDJBaseIE):
             'id': 'worobyev-video',
         },
         'playlist_count': 0,
+    }, {
+        # login starts with page name
+        'url': 'https://promodj.com/radio.remix/music',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -378,15 +389,18 @@ class PromoDJUserPageIE(PromoDJBaseIE):
         *PromoDJBaseIE._MEDIA_TYPES,
     ]
     _NOT_USER_PAGE_LIST = '|'.join(_USER_PATHS)
-    _USER_PAGE_RE = rf'(?!{_NOT_USER_PAGE_LIST})[\w-]+'
 
-    _VALID_URL = rf'{PromoDJBaseIE._BASE_URL_RE}/(?P<login>{PromoDJBaseIE._LOGIN_RE})/(?P<slug>{_USER_PAGE_RE})$'
+    _VALID_URL = rf'{PromoDJBaseIE._BASE_URL_RE}/(?P<login>{PromoDJBaseIE._LOGIN_RE})/(?P<slug>(?!(?:{_NOT_USER_PAGE_LIST})$)[\w-]+$)'
     _TESTS = [{
         'url': 'https://promodj.com/djperetse/MaxMixes',
         'info_dict': {
             'id': 'djperetse-MaxMixes',
         },
         'playlist_count': 5,
+    }, {
+        # user page starts with media type (not a real link)
+        'url': 'https://promodj.com/djperetse/remixes-best',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -768,7 +782,7 @@ class PromoDJIE(PromoDJBaseIE):
 
     # examples: MP3, 320 Кбит | MP4, 20157 Кбит | WAV, 1412 Кбит | AVI, 1731 Кбит | ASF, 6905 Кбит | FLAC, 1509 Кбит
     # https://regex101.com/r/2AuaxB/1
-    _FORMATS_RE = r'(?:<a\s+href=\"(?P<url>[^\"]+)\">)?\s*\w+, (?P<bitrate>\d+) Кбит'
+    _FORMATS_RE = r'(?:<a\s+href=\"(?P<url>[^\"]+)\">)?\s*(?P<format>\w+), (?P<bitrate>\d+) Кбит'
     _VIEW_COUNT_RE = r'<b>(?:Прослушиваний|Просмотров):</b>\s*(\d+)'
     # examples: 0:21 | 1:07 | 74:38
     _DURATION_RE = r'<b>Продолжительность:</b>\s*(\d+:\d{2})'
@@ -835,18 +849,19 @@ class PromoDJIE(PromoDJBaseIE):
         # size field describes best quality
         size = self._parse_ru_size(*re.search(self._SIZE_RE, meta_html).groups())
         if type == 'videos':
-            for url, bitrate in formats_from_html:
+            for url, format, bitrate in formats_from_html:
                 if url_or_none(url):
                     metadata['formats'].append({
                         'format_id': 'source',
                         'url': url,
                         'tbr': int(bitrate),
                         'size': size,
+                        'container': format.lower(),
                         'quality': 1,
                     })
         elif not is_paid:
             for i, match in enumerate(formats_from_html):
-                url, bitrate = match
+                url, format, bitrate = match
                 is_last = i == len(formats_from_html) - 1
                 if is_last:
                     metadata['formats'][0]['abr'] = int(bitrate)
@@ -855,6 +870,8 @@ class PromoDJIE(PromoDJBaseIE):
                         'format_id': 'lossless',
                         'url': url,
                         'abr': int(bitrate),
+                        'acodec': format.lower(),
+                        'vcodec': 'none',
                     })
             metadata['formats'][-1]['size'] = size
 
@@ -978,19 +995,55 @@ class PromoDJRadioIE(PromoDJBaseIE):
     _VALID_URL = rf'{PromoDJBaseIE._BASE_URL_RE}/radio#(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://promodj.com/radio#dubstep',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'dubstep',
+            'ext': 'mp3',
+            'title': r're:^Dubstep ',
+            'description': 'Всё лучше под дабстеп',
+            'thumbnail': r're:^https?://',
+            'live_status': 'is_live',
+        },
     }, {
         'url': 'https://promodj.com/radio#oldschool',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'oldschool',
+            'ext': 'mp3',
+            'title': r're:^Old-School ',
+            'description': 'То самое доброе, старое, вечное',
+            'thumbnail': r're:^https?://',
+            'live_status': 'is_live',
+        },
     }]
 
     def _real_extract(self, url):
-        id = self._match_id(url)
+        slug = self._match_id(url)
+        html = self._download_webpage(url, slug)
+        radio_span = get_element_html_by_id(f'radio_{slug}', html)
+        if not radio_span:
+            raise ExtractorError('Radio channel is offline or not exists', expected=True)
+        id = self._search_regex(r'amba="radio:(\d+)"', radio_span, 'id')
+        tooltip_html = self._download_webpage(
+            f'https://promodj.com/ajax/tooltip.html?wtf=radio:{id}', slug,
+            note='Downloading tooltip webpage')
+        title = clean_html(self._search_regex(
+            r'<h1[^>]*><b>([^<]+)</b></h1>', tooltip_html, 'title', default=None))
+        description = clean_html(self._search_regex(
+            r'<div>([^<]+)</div>', tooltip_html, 'description', default=None))
+        thumbnail = self._search_regex(
+            rf'#radio_{slug}:after {{ background-image: url\(([^)]+)\); }}',
+            html, 'thumbnail', default=None)
+
         return {
-            'id': id,
+            'id': slug,
+            'title': title,
+            'description': description,
+            'thumbnail': url_or_none(thumbnail),
             'formats': [{
-                'url': f'https://radio.promodj.com/{id}-192',
+                'url': f'https://radio.promodj.com/{slug}-192',
                 'abr': 192,
+                'ext': 'mp3',
+                'acodec': 'mp3',
+                'vcodec': 'none',
             }],
             'is_live': True,
         }