diff options
| author | JChris246 <chris.401@live.com> | 2019-02-04 13:33:54 -0400 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2019-02-05 23:08:49 +0700 |
| commit | d2d970d07ec82f648b62bff8b15ac0b57d0d0496 (patch) | |
| tree | 2ecc09b60ce4e8f205137eacf1986a5ae0ece462 | |
| parent | 48fb963b2f9495922a4acf751608167cbc273693 (diff) | |
| download | youtube-dl-d2d970d07ec82f648b62bff8b15ac0b57d0d0496.tar.xz | |
[pornhub] Fix tags and categories extraction (closes #13720)
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 20 |
1 files changed, 11 insertions, 9 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index be93d5d48..428324ef0 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper from ..utils import ( ExtractorError, int_or_none, - js_to_json, orderedSet, remove_quotes, str_to_int, @@ -303,14 +302,17 @@ class PornHubIE(PornHubBaseIE): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') - page_params = self._parse_json(self._search_regex( - r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', - webpage, 'page parameters', group='data', default='{}'), - video_id, transform_source=js_to_json, fatal=False) - tags = categories = None - if page_params: - tags = page_params.get('tags', '').split(',') - categories = page_params.get('categories', '').split(',') + def _get_items(class_name): + div = self._search_regex( + r'<div class="' + class_name + '">([\S\s]+?)</div>', + webpage, class_name, default=None) + if div: + return [a for a in re.findall(r'<a href=[^>]+>([^<]+)', div)] + else: + return None + + categories = _get_items('categoriesWrapper') + tags = _get_items('tagsWrapper') return { 'id': video_id, |