]> gitweb @ CieloNegro.org - youtube-dl.git/commitdiff
[pornhub] Extract categories and tags (closes #10499)
authorYen Chi Hsuan <yan12125@gmail.com>
Sun, 11 Sep 2016 11:22:51 +0000 (19:22 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Sun, 11 Sep 2016 11:22:51 +0000 (19:22 +0800)
ChangeLog
youtube_dl/extractor/pornhub.py

index a73a35e883b4a68d3b88cd8b9892ad2c4949512b..5d6609987386982ce6e40b4453a48ef0ce6b322a 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -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)
index 20976c101d97f53a58b3599ded30f7bfb1d4bcd5..0724efc09963d1f84fc7b24ec99d89b58e1bdfb6 100644 (file)
@@ -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,
         }