yt_dlp/extractor/promodj.py

@@ -114,6 +114,10 @@ class PromoDJBaseIE(InfoExtractor):
             if YoutubeIE.suitable(iframe_url):
                 yield self.url_result(iframe_url, YoutubeIE)
 
+    def _get_playlist_page_size(self, url):
+        is_default_playlist = '/groups/' not in url
+        return 30 if is_default_playlist else 20
+
     def _get_current_page(self, html):
         return int(clean_html(get_element_by_class('NavigatorCurrentPage', html)) or '1')
 
@@ -155,11 +159,10 @@ class PromoDJBaseIE(InfoExtractor):
                 })
             }
 
-        formats = [{
+        formats = [traverse_obj(source, {
-            'format_id': 'lossy',
+            'url': ('URL', {url_or_none}),
-            'url': traverse_obj(source, ('URL', {url_or_none})),
+            'size': ('size', {int_or_none}),
-            'size': traverse_obj(source, ('size', {int_or_none})),
+        }) for source in traverse_obj(media_data, ('sources'))]
-        } for source in traverse_obj(media_data, ('sources'))]
         thumbnails = [{
             'url': url,
         } for url in traverse_obj(media_data, ('coverURL', ('600', '1200', '2000'))) if url_or_none(url)]
@@ -379,7 +382,6 @@ class PromoDJUserPageIE(PromoDJBaseIE):
         'blog',
         'feedback',
         'contact',
-        'uenno',
         *PromoDJBaseIE._MEDIA_TYPES,
     ]
     _NOT_USER_PAGE_RE = '|'.join(_USER_PAGES)
@@ -445,11 +447,8 @@ class PromoDJBlogPageIE(PromoDJBaseIE):
 
 
 class PromoDJPlaylistIE(PromoDJBaseIE):
-    _PLAYLIST_TYPES = ['uenno', *PromoDJBaseIE._MEDIA_TYPES]
-    _PLAYLIST_TYPES_RE = '|'.join(_PLAYLIST_TYPES)
-
     _VALID_URL = [
-        rf'{PromoDJBaseIE._BASE_URL_RE}/(?P<login>{PromoDJBaseIE._LOGIN_RE})/(?P<type>{_PLAYLIST_TYPES_RE})$',
+        rf'{PromoDJBaseIE._BASE_URL_RE}/(?P<login>{PromoDJBaseIE._LOGIN_RE})/(?P<type>{PromoDJBaseIE._MEDIA_TYPES_RE})$',
         rf'{PromoDJBaseIE._BASE_URL_RE}/(?P<login>{PromoDJBaseIE._LOGIN_RE})/(?P<type>groups)/(?P<id>\d+)(?:/(?P<slug>\w+))?',
     ]
     _TESTS = [{
@@ -508,36 +507,20 @@ class PromoDJPlaylistIE(PromoDJBaseIE):
         # 900+ items
         'url': 'https://promodj.com/fonarev/groups/17350/Digital_Emotions_Podcast',
         'only_matching': True,
-    }, {
-        # user's best music and video
-        'url': 'https://promodj.com/djbaribyn/uenno',
-        'info_dict': {
-            'id': 'djbaribyn-uenno',
-        },
-        'playlist_count': 15,
-        'params': {
-            'playlistend': 15,
-        }
     }]
 
     _ALLOWED_MEDIA_CATS = ['music', 'video']
 
-    def _get_page_size(self, type):
-        if type == 'uenno':
-            return 15
-        if type == 'groups':
-            return 20
-        return 30
-
     def _real_extract(self, url):
         match = self._match_valid_url(url)
         login = match.group('login')
         type = match.group('type')
         playlist_id = f'{login}-{type}' if len(match.groups()) == 2 else f'{login}-{type}-{match.group("id")}'
+        page_size = self._get_playlist_page_size(url)
 
         entries = OnDemandPagedList(
             functools.partial(self._fetch_page, url, self._ALLOWED_MEDIA_CATS, playlist_id),
-            self._get_page_size(type))
+            page_size)
         return self.playlist_result(entries, playlist_id=playlist_id)
 
 
@@ -770,6 +753,7 @@ class PromoDJIE(PromoDJBaseIE):
         },
     }]
 
+    _IS_PAID_RE = r'<b>Цена:</b>'
     # 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'
@@ -777,7 +761,7 @@ class PromoDJIE(PromoDJBaseIE):
     # examples: 0:21 | 1:07 | 74:38
     _DURATION_RE = r'<b>Продолжительность:</b>\s*(\d+:\d{2})'
     # examples: 818.4 Кб | 12.9 Мб | 4 Гб | 1.76 Гб | 1001.5 Мб
-    _SIZE_RE = r'<b>Размер:</b>\s*(?P<size>\d+(?:\.\d+)?)\s*(?P<unit>Б|Кб|Мб|Гб|Тб)'
+    _SIZE_RE = r'<b>Размер:</b>\s*(?P<size>\d+(?:\.\d+)?)\s*(?P<unit>Кб|Мб|Гб)'
     # examples: сегодня 2:55 | вчера 23:17 | 1 июня 2016 3:46
     _TIMESTAMP_RE = r'<b>Публикация:</b>\s*(?P<day>вчера|сегодня|\d{1,2})(?: (?P<month>[а-я]+) (?P<year>\d{4}))?\s*(?P<hours>\d{1,2}):(?P<minutes>\d{2})'
     _TAGS_RE = r'<span\s+class=\"styles\">([^\n]+)</span>'
@@ -787,8 +771,9 @@ class PromoDJIE(PromoDJBaseIE):
     # https://regex101.com/r/b9utBf/1
     _VIDEO_DATA_REGEX = r'({\"video\":true,\"config\":[^\n]+)\);'
 
-    def _parse_ru_date(self, day, month, year, hours, minutes):
+    def _parse_ru_date(self, raw_date):
         RU_MONTHS = ['января', 'февраля', 'марта', 'апреля', 'мая', 'июня', 'июля', 'августа', 'сентября', 'октября', 'ноября', 'декабря']
+        day, month, year, hours, minutes = raw_date
         if day == 'сегодня':
             d = datetime.date.today()
             day = d.day
@@ -805,9 +790,10 @@ class PromoDJIE(PromoDJBaseIE):
             year = int(year)
         return datetime.datetime(year, month, day, int(hours), int(minutes)).timestamp()
 
-    def _parse_ru_size(self, size, unit):
+    def _parse_ru_size(self, raw_size):
-        RU_SIZE_UNITS = ['Б', 'Кб', 'Мб', 'Гб', 'Тб']
+        RU_SIZE_UNITS = ['Б', 'Кб', 'Мб', 'Гб']
-        return int(float(size) * pow(1024, RU_SIZE_UNITS.index(unit)))
+        size, size_unit = raw_size
+        return int(float(size) * pow(1024, RU_SIZE_UNITS.index(size_unit)))
 
     # music: always have lossy format (mp3), sometimes have lossless (wav or flac) format
     # video: sometimes have source format (mp4, avi, asf), always have converted for web format (mp4)
@@ -835,9 +821,9 @@ class PromoDJIE(PromoDJBaseIE):
         # download links can be missing
         # best quality format always comes first
         formats_from_html = re.findall(self._FORMATS_RE, meta_html)
-        is_paid = '<b>Цена:</b>' in meta_html
+        is_paid = re.search(self._IS_PAID_RE, meta_html)
         # size field describes best quality
-        size = self._parse_ru_size(*re.search(self._SIZE_RE, meta_html).groups())
+        size = self._parse_ru_size(re.search(self._SIZE_RE, meta_html).groups())
         if type == 'videos':
             for url, bitrate in formats_from_html:
                 if url_or_none(url):
@@ -848,15 +834,14 @@ class PromoDJIE(PromoDJBaseIE):
                         'size': size,
                         'quality': 1,
                     })
-        elif not is_paid:
+        else:
             for i, match in enumerate(formats_from_html):
                 url, bitrate = match
                 is_last = i == len(formats_from_html) - 1
                 if is_last:
                     metadata['formats'][0]['abr'] = int(bitrate)
-                elif url_or_none(url):
+                elif url_or_none(url) and not is_paid:
                     metadata['formats'].append({
-                        'format_id': 'lossless',
                         'url': url,
                         'abr': int(bitrate),
                     })
@@ -866,7 +851,7 @@ class PromoDJIE(PromoDJBaseIE):
             'title': clean_html(get_element_by_class('file_title', html)),
             'view_count': int_or_none(self._search_regex(self._VIEW_COUNT_RE, meta_html, 'view_count', default=None)),
             'duration': parse_duration(self._search_regex(self._DURATION_RE, meta_html, 'duration')),
-            'timestamp': self._parse_ru_date(*re.search(self._TIMESTAMP_RE, meta_html).groups()),
+            'timestamp': self._parse_ru_date(re.search(self._TIMESTAMP_RE, meta_html).groups()),
             'tags': self._html_search_regex(self._TAGS_RE, meta_html, 'tags').split(', '),
         })