From 6bb05b32a990b8fb961971fcb8110d292cf953e7 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 11 Sep 2016 19:22:51 +0800 Subject: [PATCH] [pornhub] Extract categories and tags (closes #10499) --- ChangeLog | 1 + youtube_dl/extractor/pornhub.py | 16 ++++++++++++++++ 2 files changed, 17 insertions(+) diff --git a/ChangeLog b/ChangeLog index a73a35e88..5d6609987 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,6 +1,7 @@ version Extractors ++ [pornhub] Extract categories and tags (#10499) + [foxnews] Support Fox News articles (#10598) * [iwara] Fix extraction after relaunch (#10462, #3215) * [newgrounds] Fix uploader extraction (#10584) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 20976c101..0724efc09 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -15,6 +15,7 @@ from ..compat import ( from ..utils import ( ExtractorError, int_or_none, + js_to_json, orderedSet, sanitized_Request, str_to_int, @@ -48,6 +49,8 @@ class PornHubIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, 'age_limit': 18, + 'tags': list, + 'categories': list, }, }, { # non-ASCII title @@ -63,6 +66,8 @@ class PornHubIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, 'age_limit': 18, + 'tags': list, + 'categories': list, }, 'params': { 'skip_download': True, @@ -183,6 +188,15 @@ class PornHubIE(InfoExtractor): }) self._sort_formats(formats) + page_params = self._parse_json(self._search_regex( + r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P{[^}]+})', + 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(',') + return { 'id': video_id, 'uploader': video_uploader, @@ -195,6 +209,8 @@ class PornHubIE(InfoExtractor): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, + 'tags': tags, + 'categories': categories, } -- 2.40.0