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

motherless/downloader.py

@@ -0,0 +1,40 @@
+import sys
+import re
+from pathlib import Path
+from urllib.parse import urlparse
+
+# 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 Motherless video URL patterns like:
+    # https://motherless.com/AC493CD
+    # https://motherless.com/g/group_name/AC493CD
+    path = urlparse(url).path.rstrip("/")
+    if not path:
+        return False
+    parts = path.split("/")
+    last_part = parts[-1]
+    # Motherless IDs are typically 7 or 8 characters of uppercase letters and numbers
+    return bool(re.match(r'^[A-Z0-9]{6,9}$', last_part))
+
+if __name__ == "__main__":
+    uploader_eval = """() => {
+        const memberLink = document.querySelector('a[href*="/members/"]');
+        if (memberLink) return memberLink.innerText.trim();
+        const uploadText = document.querySelector('.upload-info');
+        if (uploadText) {
+            const m = uploadText.innerText.match(/by\\s+(\\S+)/i);
+            if (m) return m[1];
+        }
+        return 'unknown';
+    }"""
+    
+    generic_downloader.run(
+        site_name="Motherless",
+        is_video_link_fn=is_video_link,
+        next_page_selector="a:has-text('Next'), a.next, a.pagination-next",
+        video_selector="video",
+        uploader_eval_js=uploader_eval
+    )