wcr/config.py

@@ -15,7 +15,3 @@ def get_db_connection():
         print(f"❌ Failed to connect to DB: {err}")
         return  # don’t continue if DB failed
     return db
-
-def preload_source_urls(cursor):
-    cursor.execute("SELECT source_url FROM videos")
-    return set(row[0] for row in cursor.fetchall())

wcr/crawl_wcr.py

@@ -1,118 +1,135 @@
-import requests, mysql.connector, time
+from config import get_db_connection
+import requests, time, mysql.connector
 from bs4 import BeautifulSoup
 from urllib.parse import urljoin
 from datetime import datetime
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from config import get_db_connection, preload_source_urls
 
-# ────────────────────────────────────────────────────────────────
+
 def insert_video_to_db(data):
-    try:
     db = get_db_connection()
+    
+    try:
         cursor = db.cursor()
-        cursor.execute("""
+        sql = """
-            INSERT IGNORE INTO videos (username, date, embed_link, source_url, created_at)
+        INSERT IGNORE INTO videos (username, url, title, date, embed_link, source_url, created_at)
-            VALUES (%s, %s, %s, %s, NOW())
+        VALUES (%s, %s, %s, %s, %s, %s, NOW())
-        """, (data['username'], data['date'], data['embed_link'], data['source_url']))
+                """
+
+        values = (
+            data['username'],
+            data['url'],
+            data['title'],
+            data['date'],
+            data['embed_link'],
+            data['source_url']
+        )
+        cursor.execute(sql, values)
         db.commit()
-        if cursor.rowcount > 0:
+        print("✅ Inserted into DB!")
-            print(f"✅ New: {data['username']} — {data['date']}")
+
     except mysql.connector.Error as err:
-        print(f"❌ DB insert error: {err}")
+        print(f"❌ Failed to insert: {err}")
+
     finally:
         cursor.close()
         db.close()
 
+def crawl_user_page(base_url, user_path):
+    full_url = urljoin(base_url, user_path)
+    response = requests.get(full_url)
+    if response.status_code != 200:
+        print(f"❌ Failed to load {full_url}")
+        return None
+
+    soup = BeautifulSoup(response.text, "html.parser")
+
+    
 
-# ────────────────────────────────────────────────────────────────
 def parse_data(soup):
-    username = soup.select_one("h1.entry-title")
+    username = user_path.strip("/")
-    username = username.contents[0].strip() if username and username.contents else None
+    title_tag = soup.find("h1", class_="entry-title")
+    title = title_tag.text.strip() if title_tag else "(no title)"
 
-    date_tag = soup.select_one("span.entry-date")
+    date_tag = soup.find("span", class_="entry-date")
     date = date_tag.text.strip() if date_tag else None
+
     if date:
         try:
-            date = datetime.strptime(date, "%d/%m/%Y").strftime("%Y-%m-%d")
+            date_obj = datetime.strptime(date, "%d/%m/%Y")
+            date = date_obj.strftime("%Y-%m-%d")
         except ValueError:
+            print(f"⚠️ Failed to parse date: {date}")
             date = None
 
-    embed_link = next((i["src"] for i in soup.find_all("iframe", src=True) if "xpornium.net" in i["src"]), None)
+        embed_link = None
-    return {"username": username, "date": date, "embed_link": embed_link}
+        for iframe in soup.find_all("iframe", src=True):
+            src = iframe["src"]
+            if "xpornium.net" in src:
+                embed_link = src  # no urljoin needed!
+                break  # stop after finding the first match
 
-# ────────────────────────────────────────────────────────────────
+        # --- print info after crawling this user ---
-def crawl_user_page(url):
+        print(f"\n✅ Scraped {username}: — {date}")
-    try:
-        res = requests.get(url, timeout=15)
-        if res.ok:
-            soup = BeautifulSoup(res.text, "html.parser")
-            data = parse_data(soup)
-            data["source_url"] = url
-            return data if data["embed_link"] else None
-    except Exception:
-        pass
-    return None
 
-# ────────────────────────────────────────────────────────────────
+        # -------------------------------------------
-def crawl_index_page(base_url, page_num, seen, cursor, db):
-    url = f"{base_url}?p={page_num}"
-    print(f"📄 Page {page_num}")
-    try:
-        res = requests.get(url, timeout=15)
-        if not res.ok:
-            return 0
-
-        soup = BeautifulSoup(res.text, "html.parser")
-        links = [urljoin(base_url, a["href"]) for a in soup.select("a.thumbnail-link[href]")]
-        links = [link for link in links if link not in seen]
-        if not links:
-            return 0
-
-        new_count = 0
-        with ThreadPoolExecutor(max_workers=50) as pool:
-            for f in as_completed(pool.submit(crawl_user_page, l) for l in links):
-                data = f.result()
-                if data:
-                    insert_video_to_db(data, cursor, db)
-                    new_count += 1
-        return new_count
-    except Exception:
-        return 0
-
-# ────────────────────────────────────────────────────────────────
-def crawl_all(base_url):
-    db = get_db_connection()
-    cursor = db.cursor()
-    seen = preload_source_urls(cursor)
 
-    QUIT_LOGIC = True
+        return {
+            "username": username,
+            "title": title,
+            "date": date,
+            "embed_link": embed_link,
+        }
+
+def crawl_all(init_url):
+    """Crawl page by page and extract user data as we go."""
+    page = 1
+    all_data = []
 
-    page, total, empty_results = 1000, 0, 0
     while True:
-        batch = range(page, page + 10)
+        url = f"{init_url}?p={page}"
-        print(f"\n🚀 Batch {page}–{page + 9}")
+        print(f"\n🕷️ Crawling index page {page}: {url}")
+        response = requests.get(url)
+        if response.status_code != 200:
+            print(f"❌ Page {page} returned {response.status_code}, stopping.")
+            break
 
-        with ThreadPoolExecutor(max_workers=10) as pool:
+        soup = BeautifulSoup(response.text, "html.parser")
-            results = [f.result() for f in as_completed(pool.submit(crawl_index_page, base_url, p, seen, cursor, db) for p in batch)]
+        user_links = soup.find_all("a", class_="thumbnail-link", href=True)
+        if not user_links:
+            print("⚠️ No user links found — reached end of site.")
+            break
 
-        batch_total = sum(results)
+        for link in user_links:
-        total += batch_total
+            user_path = link["href"]
-        print(f"📦 Batch complete — {batch_total} new videos (total: {total})")
+            user_data = crawl_user_page(init_url, user_path)
+            if not user_data:
+                print("⚠️ Skipping empty user_data.")
+                continue
 
-        if not QUIT_LOGIC:
+            if not user_data["embed_link"]:
-            if batch_total == 0:
+                print(f"⚠️ Skipping {user_data['username']} - no embed link found.")
-                empty_results += 1
+                continue
 
-            if empty_results >= 10:
+            insert_video_to_db(user_data)
-                print("\n🛑 No new videos found for 30 consecutive pages. Stopping.")
+            time.sleep(0.5)
-                break
 
-        page += 10
+        page += 1
+        time.sleep(1)
             
-    cursor.close()
+    print(f"\n✅ Finished crawling all pages. Total users: {len(all_data)}")
-    db.close()
+    return all_data
-    print(f"\n✅ Done! Total new videos: {total}")
 
-# ────────────────────────────────────────────────────────────────
 if __name__ == "__main__":
-    crawl_all("https://webcamrips.to")
+    BASE_URL = "https://webcamrips.to"
+    results = crawl_all(BASE_URL)
+    print("💾 All data saved to users_data.json")
+            
+            
+   
+            
+                
+
+
+
+
+