[extractor/rule34video] Add view count

yt_dlp/extractor/rule34video.py

@@ -5,7 +5,6 @@ from ..utils import (
     extract_attributes,
     get_element_by_attribute,
     get_element_by_class,
-    get_element_by_id,
     get_element_html_by_class,
     get_elements_by_class,
     int_or_none,
@@ -13,7 +12,9 @@ from ..utils import (
     parse_duration,
     remove_end,
     str_to_int,
+    traverse_obj,
     unescapeHTML,
+    url_or_none,
 )
 from .common import InfoExtractor
 
@@ -31,14 +32,16 @@ class Rule34VideoIE(InfoExtractor):
                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065157/preview.jpg',
                 'duration': 347.0,
                 'age_limit': 18,
+                'view_count': int,
                 'like_count': int,
                 'comment_count': int,
+                'timestamp': 1639872000,
                 'description': 'https://discord.gg/aBqPrHSHvv',
-                'creator': None,
+                'upload_date': '20211219',
                 'uploader': 'Sweet HMV',
                 'uploader_url': 'https://rule34video.com/members/22119/',
                 'categories': ['3D', 'MMD', 'iwara'],
-                'tags': 'count:14'
+                'tags': 'mincount:10'
             }
         },
         {
@@ -51,14 +54,17 @@ class Rule34VideoIE(InfoExtractor):
                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065296/preview.jpg',
                 'duration': 938.0,
                 'age_limit': 18,
+                'view_count': int,
                 'like_count': int,
                 'comment_count': int,
-                'description': None,
+                'timestamp': 1640131200,
+                'description': '',
                 'creator': 'WildeerStudio',
+                'upload_date': '20211222',
                 'uploader': 'CerZule',
                 'uploader_url': 'https://rule34video.com/members/36281/',
                 'categories': ['3D', 'Tomb Raider'],
-                'tags': 'count:50'
+                'tags': 'mincount:40'
             }
         },
     ]
@@ -77,21 +83,18 @@ class Rule34VideoIE(InfoExtractor):
                 'quality': quality,
             })
 
-        title = self._html_extract_title(webpage)
+        json_ld = self._search_json_ld(webpage, video_id, default={})
-        thumbnail = self._html_search_regex(r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None)
+
-        duration = self._html_search_regex(r'"icon-clock"></i>\s+<span>((?:\d+:?)+)', webpage, 'duration', default=None)
+        title = self._html_extract_title(webpage) or json_ld.get('title')
-        like_count = str_to_int(remove_end(get_element_by_class('voters count', webpage), ' likes'))
+        thumbnail = (self._html_search_regex(r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None)
+                     or traverse_obj(json_ld.get('thumbnails'), (0, 'url'), expected_type=url_or_none))
+        duration = parse_duration(self._html_search_regex(r'"icon-clock"></i>\s+<span>((?:\d+:?)+)', webpage, 'duration', default=None)) or json_ld.get('duration')
+        view_count = int_or_none(self._html_search_regex(r'"icon-eye"></i>\s+<span>([ \d]+)', webpage, 'views', default='').replace(' ', '')) or json_ld.get('view_count')
+        like_count = str_to_int(remove_end(get_element_by_class('voters count', webpage), ' likes')) or json_ld.get('like_count')
         comment_count = int_or_none(self._search_regex(r'[^(]+\((\d+)\)', get_element_by_attribute(
             'href', '#tab_comments', webpage), 'comment count', fatal=False))
-
+        timestamp = json_ld.get('timestamp')
-        description = None
+        description = json_ld.get('description')
-        video_info_element = get_element_by_id('tab_video_info', webpage)
-        info_labels = get_elements_by_class('label', video_info_element)
-        for label in info_labels:
-            label_clean = label.strip(' \n\t')
-            if label_clean.startswith('Description:'):
-                description = clean_html(label_clean[len('Description:'):])
-                break
 
         categories = None
         creator = None
@@ -111,10 +114,12 @@ class Rule34VideoIE(InfoExtractor):
             'formats': formats,
             'title': title,
             'thumbnail': thumbnail,
-            'duration': parse_duration(duration),
+            'duration': duration,
             'age_limit': 18,
+            'view_count': view_count,
             'like_count': like_count,
             'comment_count': comment_count,
+            'timestamp': timestamp,
             'description': description,
             'creator': creator,
             'uploader': uploader,