diff options
| author | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-11 19:22:51 +0800 | 
|---|---|---|
| committer | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-11 19:22:51 +0800 | 
| commit | 6bb05b32a990b8fb961971fcb8110d292cf953e7 (patch) | |
| tree | 80631d743f269a88895eb78f6c0b77150a88e727 | |
| parent | fea74acad8e8ebc1fda1d24a10c085c6771a71be (diff) | |
[pornhub] Extract categories and tags (closes #10499)
| -rw-r--r-- | ChangeLog | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 16 | 
2 files changed, 17 insertions, 0 deletions
@@ -1,6 +1,7 @@  version <unreleased>  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<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(',') +          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,          }  | 
