Initial backup: folder structure manifest, tree summary, scraper scripts, and text metadata

xhamster/downloader.py

@@ -0,0 +1,48 @@
+import sys
+import re
+from pathlib import Path
+
+# Add parent workspace directory to path to import generic_downloader
+sys.path.append(str(Path(__file__).resolve().parents[1]))
+import generic_downloader
+
+def is_video_link(url):
+    # Match standard xHamster video pages: contains /videos/ and doesn't point to user grids/channels
+    return (
+        "/videos/" in url 
+        and not "/users/" in url 
+        and not "/channels/" in url 
+        and not "/creators/" in url
+    )
+
+if __name__ == "__main__":
+    # JS evaluated in browser context to get the clean uploader name
+    uploader_eval = """() => {
+        // 1. Try channel link
+        const channelLink = document.querySelector('a[href*="/channels/"]');
+        if (channelLink && channelLink.innerText.trim()) {
+            return channelLink.innerText.trim().replace(/\\n/g, ' ').trim();
+        }
+        
+        // 2. Try user link
+        const userLink = document.querySelector('.entity-author-container__name, a[href*="/users/"]');
+        if (userLink && userLink.innerText.trim()) {
+            return userLink.innerText.trim();
+        }
+        
+        // 3. Try creator logo or class
+        const creatorLink = document.querySelector('a[href*="/creators/"] .video-uploader__name, .video-uploader__name');
+        if (creatorLink && creatorLink.innerText.trim()) {
+            return creatorLink.innerText.trim();
+        }
+        
+        return 'unknown';
+    }"""
+    
+    generic_downloader.run(
+        site_name="xHamster",
+        is_video_link_fn=is_video_link,
+        next_page_selector="a:has-text('Next'), .next, a[rel='next']",
+        video_selector="video",
+        uploader_eval_js=uploader_eval
+    )