Crawler/wcr/crawl_wcr.py

from config import get_db_connection
import requests, time, mysql.connector
from bs4 import BeautifulSoup
from urllib.parse import urljoin
from datetime import datetime


def insert_video_to_db(data):
    db = get_db_connection()
    
    try:
        cursor = db.cursor()
        sql = """
        INSERT IGNORE INTO videos (username, url, title, date, embed_link, source_url, created_at)
        VALUES (%s, %s, %s, %s, %s, %s, NOW())
                """

        values = (
            data['username'],
            data['url'],
            data['title'],
            data['date'],
            data['embed_link'],
            data['source_url']
        )
        cursor.execute(sql, values)
        db.commit()
        print("✅ Inserted into DB!")

    except mysql.connector.Error as 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 = user_path.strip("/")
    title_tag = soup.find("h1", class_="entry-title")
    title = title_tag.text.strip() if title_tag else "(no title)"

    date_tag = soup.find("span", class_="entry-date")
    date = date_tag.text.strip() if date_tag else None

    if date:
        try:
            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 = None
        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 ---
        print(f"\n✅ Scraped {username}: — {date}")

        # -------------------------------------------

        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 = []

    while True:
        url = f"{init_url}?p={page}"
        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

        soup = BeautifulSoup(response.text, "html.parser")
        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

        for link in user_links:
            user_path = link["href"]
            user_data = crawl_user_page(init_url, user_path)
            if not user_data:
                print("⚠️ Skipping empty user_data.")
                continue

            if not user_data["embed_link"]:
                print(f"⚠️ Skipping {user_data['username']} - no embed link found.")
                continue

            insert_video_to_db(user_data)
            time.sleep(0.5)

        page += 1
        time.sleep(1)
            
    print(f"\n✅ Finished crawling all pages. Total users: {len(all_data)}")
    return all_data

if __name__ == "__main__":
    BASE_URL = "https://webcamrips.to"
    results = crawl_all(BASE_URL)
    print("💾 All data saved to users_data.json")