diff options
| author | coletdjnz <colethedj@protonmail.com> | 2021-08-30 10:22:57 +1200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-08-29 22:22:57 +0000 |
| commit | 419508eabb5f324143c606b9ba0136d4a40abdf4 (patch) | |
| tree | 87a8d73c932987f440c7bc672ad45107e156f2df | |
| parent | 54153fb71bb6846040823abd3ce3ff0eb96e5b44 (diff) | |
| download | hypervideo-pre-419508eabb5f324143c606b9ba0136d4a40abdf4.tar.lz hypervideo-pre-419508eabb5f324143c606b9ba0136d4a40abdf4.tar.xz hypervideo-pre-419508eabb5f324143c606b9ba0136d4a40abdf4.zip | |
[Motherless] Fix extractor (#809)
Authored-by: coletdjnz
Fixes #806, https://github.com/ytdl-org/youtube-dl/issues/29626
| -rw-r--r-- | yt_dlp/extractor/motherless.py | 30 |
1 files changed, 24 insertions, 6 deletions
diff --git a/yt_dlp/extractor/motherless.py b/yt_dlp/extractor/motherless.py index ef1e081f2..111c7c544 100644 --- a/yt_dlp/extractor/motherless.py +++ b/yt_dlp/extractor/motherless.py @@ -127,9 +127,9 @@ class MotherlessIE(InfoExtractor): comment_count = webpage.count('class="media-comment-contents"') uploader_id = self._html_search_regex( - r'"thumb-member-username">\s+<a href="/m/([^"]+)"', - webpage, 'uploader_id') - + (r'"media-meta-member">\s+<a href="/m/([^"]+)"', + r'<span\b[^>]+\bclass="username">([^<]+)</span>'), + webpage, 'uploader_id', fatal=False) categories = self._html_search_meta('keywords', webpage, default=None) if categories: categories = [cat.strip() for cat in categories.split(',')] @@ -169,7 +169,18 @@ class MotherlessGroupIE(InfoExtractor): 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of ' 'any kind!' }, - 'playlist_mincount': 9, + 'playlist_mincount': 0, + 'expected_warnings': [ + 'This group has no videos.', + ] + }, { + 'url': 'https://motherless.com/g/beautiful_cock', + 'info_dict': { + 'id': 'beautiful_cock', + 'title': 'Beautiful Cock', + 'description': 'Group for lovely cocks yours, mine, a friends anything human', + }, + 'playlist_mincount': 2500, }] @classmethod @@ -209,11 +220,18 @@ class MotherlessGroupIE(InfoExtractor): description = self._html_search_meta( 'description', webpage, fatal=False) page_count = self._int(self._search_regex( - r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT', - webpage, 'page_count'), 'page_count') + r'(\d+)</(?:a|span)><(?:a|span)[^>]+rel="next">', + webpage, 'page_count', default=0), 'page_count') + if not page_count: + message = self._search_regex( + r'class="error-page"[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*', + webpage, 'error_msg', default=None) or 'This group has no videos.' + self.report_warning(message, group_id) PAGE_SIZE = 80 def _get_page(idx): + if not page_count: + return webpage = self._download_webpage( page_url, group_id, query={'page': idx + 1}, note='Downloading page %d/%d' % (idx + 1, page_count) |