[ie/Rule34Video] Extract more metadata (#7416)

Closes #7233
Authored by: gmes78

yt_dlp/extractor/rule34video.py

@@ -1,7 +1,20 @@
 import re
 
-from ..utils import parse_duration, unescapeHTML
 from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_attribute,
+    get_element_by_class,
+    get_element_html_by_class,
+    get_elements_by_class,
+    int_or_none,
+    join_nonempty,
+    parse_count,
+    parse_duration,
+    unescapeHTML,
+)
+from ..utils.traversal import traverse_obj
 
 
 class Rule34VideoIE(InfoExtractor):
@@ -17,7 +30,16 @@ class Rule34VideoIE(InfoExtractor):
                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065157/preview.jpg',
                 'duration': 347.0,
                 'age_limit': 18,
-                'tags': 'count:14'
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'timestamp': 1639872000,
+                'description': 'https://discord.gg/aBqPrHSHvv',
+                'upload_date': '20211219',
+                'uploader': 'Sweet HMV',
+                'uploader_url': 'https://rule34video.com/members/22119/',
+                'categories': ['3D', 'MMD', 'iwara'],
+                'tags': 'mincount:10'
             }
         },
         {
@@ -30,7 +52,17 @@ class Rule34VideoIE(InfoExtractor):
                 'thumbnail': 'https://rule34video.com/contents/videos_screenshots/3065000/3065296/preview.jpg',
                 'duration': 938.0,
                 'age_limit': 18,
-                'tags': 'count:50'
+                'view_count': int,
+                'like_count': int,
+                'comment_count': int,
+                'timestamp': 1640131200,
+                'description': '',
+                'creator': 'WildeerStudio',
+                'upload_date': '20211222',
+                'uploader': 'CerZule',
+                'uploader_url': 'https://rule34video.com/members/36281/',
+                'categories': ['3D', 'Tomb Raider'],
+                'tags': 'mincount:40'
             }
         },
     ]
@@ -49,17 +81,44 @@ def _real_extract(self, url):
                 'quality': quality,
             })
 
-        title = self._html_extract_title(webpage)
-        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)
+        categories, creator, uploader, uploader_url = [None] * 4
+        for col in get_elements_by_class('col', webpage):
+            label = clean_html(get_element_by_class('label', col))
+            if label == 'Categories:':
+                categories = list(map(clean_html, get_elements_by_class('item', col)))
+            elif label == 'Artist:':
+                creator = join_nonempty(*map(clean_html, get_elements_by_class('item', col)), delim=', ')
+            elif label == 'Uploaded By:':
+                uploader = clean_html(get_element_by_class('name', col))
+                uploader_url = extract_attributes(get_element_html_by_class('name', col) or '').get('href')
 
         return {
+            **traverse_obj(self._search_json_ld(webpage, video_id, default={}), ({
+                'title': 'title',
+                'view_count': 'view_count',
+                'like_count': 'like_count',
+                'duration': 'duration',
+                'timestamp': 'timestamp',
+                'description': 'description',
+                'thumbnail': ('thumbnails', 0, 'url'),
+            })),
             'id': video_id,
             'formats': formats,
-            'title': title,
-            'thumbnail': thumbnail,
-            'duration': parse_duration(duration),
+            'title': self._html_extract_title(webpage),
+            'thumbnail': self._html_search_regex(
+                r'preview_url:\s+\'([^\']+)\'', webpage, 'thumbnail', default=None),
+            'duration': parse_duration(self._html_search_regex(
+                r'"icon-clock"></i>\s+<span>((?:\d+:?)+)', webpage, 'duration', default=None)),
+            'view_count': int_or_none(self._html_search_regex(
+                r'"icon-eye"></i>\s+<span>([ \d]+)', webpage, 'views', default='').replace(' ', '')),
+            'like_count': parse_count(get_element_by_class('voters count', webpage)),
+            'comment_count': int_or_none(self._search_regex(
+                r'[^(]+\((\d+)\)', get_element_by_attribute('href', '#tab_comments', webpage), 'comment count', fatal=False)),
             'age_limit': 18,
+            'creator': creator,
+            'uploader': uploader,
+            'uploader_url': uploader_url,
+            'categories': categories,
             'tags': list(map(unescapeHTML, re.findall(
                 r'<a class="tag_item"[^>]+\bhref="https://rule34video\.com/tags/\d+/"[^>]*>(?P<tag>[^>]*)</a>', webpage))),
         }