diff options
Diffstat (limited to 'yt_dlp/extractor/arte.py')
| -rw-r--r-- | yt_dlp/extractor/arte.py | 42 |
1 files changed, 42 insertions, 0 deletions
diff --git a/yt_dlp/extractor/arte.py b/yt_dlp/extractor/arte.py index 296b169d2..a7ffdc24c 100644 --- a/yt_dlp/extractor/arte.py +++ b/yt_dlp/extractor/arte.py @@ -12,6 +12,7 @@ from ..utils import ( int_or_none, parse_qs, qualities, + strip_or_none, try_get, unified_strdate, url_or_none, @@ -253,3 +254,44 @@ class ArteTVPlaylistIE(ArteTVBaseIE): title = collection.get('title') description = collection.get('shortDescription') or collection.get('teaserText') return self.playlist_result(entries, playlist_id, title, description) + + +class ArteTVCategoryIE(ArteTVBaseIE): + _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$' % ArteTVBaseIE._ARTE_LANGUAGES + _TESTS = [{ + 'url': 'https://www.arte.tv/en/videos/politics-and-society/', + 'info_dict': { + 'id': 'politics-and-society', + 'title': 'Politics and society', + 'description': 'Investigative documentary series, geopolitical analysis, and international commentary', + }, + 'playlist_mincount': 13, + }, + ] + + @classmethod + def suitable(cls, url): + return ( + not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, )) + and super(ArteTVCategoryIE, cls).suitable(url)) + + def _real_extract(self, url): + lang, playlist_id = self._match_valid_url(url).groups() + webpage = self._download_webpage(url, playlist_id) + + items = [] + for video in re.finditer( + r'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/%s/videos/[\w/-]+)(?P=q)' % lang, + webpage): + video = video.group('url') + if video == url: + continue + if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )): + items.append(video) + + title = (self._og_search_title(webpage, default=None) + or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title>', default=None)) + title = strip_or_none(title.rsplit('|', 1)[0]) or self._generic_title(url) + + return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title, + description=self._og_search_description(webpage, default=None)) |