Webtoon scraper

main.py

import os
from sys import platform

try:
    import requests
    from bs4 import BeautifulSoup
    from PIL import Image
except (ModuleNotFoundError, ImportError):
    if platform == "win32":
        os.system("pip install requests bs4 Pillow")
    else:
        os.system("pip3 install requests bs4 Pillow")
finally:
    import requests
    from bs4 import BeautifulSoup
    from PIL import Image

def print_author_info():
    print("=" * 60)
    print("✨  Webtoon Scraper  ✨")
    print("-" * 60)
    print("Author  : Xnuvers007")
    print("GitHub  : https://github.com/Xnuvers007")
    print("Email   : Gosah kepo")
    print("Instagram: Gosah Kepo")
    print("-" * 60)
    print("This tool allows you to scrape Webtoon content")
    print("with ease and download episodes as PDF files.")
    print("=" * 60)
    print()

class WebtoonScraper:
    def main():
        genres = input("Masukkan genre webtoon (Example: action): ")
        url = f"https://www.webtoons.com/id/{genres}"

        headers = {
            "User-Agent": "Mozilla/5.0",
            "Referer": "https://www.webtoons.com/"
        }

        response = requests.get(url, headers=headers)

        if response.status_code == 200:
            soup = BeautifulSoup(response.text, "html.parser")
            
            items = soup.find_all("li")
            count_series = soup.find('div', class_='series_count')

            if count_series:
                print(f"📚 Jumlah Webtoon: {count_series.text.strip()}")
            else:
                print("❌ Tidak ditemukan jumlah webtoon.")

            for idx, item in enumerate(items, start=1):
                a_tag = item.find("a", class_="link _genre_title_a")
                if not a_tag:
                    continue

                title_tag = item.find("strong", class_="title")
                author_tag = item.find("div", class_="author")
                view_tag = item.find("div", class_="view_count")
                img_tag = item.find("img")

                title = title_tag.get_text(strip=True) if title_tag else "N/A"
                author = author_tag.get_text(strip=True) if author_tag else "N/A"
                view = view_tag.get_text(strip=True) if view_tag else "N/A"
                image = img_tag["src"] if img_tag else "N/A"
                link = a_tag["href"] if a_tag else "N/A"

                print(f"{idx}. Judul       : {title}")
                print(f"   Penulis     : {author}")
                print(f"   View        : {view}")
                print(f"   Gambar      : {image}")
                print(f"   Link Webtoon: {link}")
                print("-" * 50)
        else:
            print(f"Gagal mengakses halaman. Status code: {response.status_code}")

    def episodeList():
        get_link = input("Masukkan link webtoon (Example: https://www.webtoons.com/id/slice-of-life/wee/list?title_no=3085): ").strip()
        print("\n\n")
        headers = {
            "User-Agent": "Mozilla/5.0",
            "Referer": "https://www.webtoons.com/"
        }
        response_eps = requests.get(get_link, headers=headers)
        soup = BeautifulSoup(response_eps.text, "html.parser")
        unordered_list = soup.find("ul", id="_listUl")

        for li in unordered_list.find_all("li"):
            a = li.find('a')
            if a and a.has_attr('href'):
                print(a['href'])

        print("\n\n📄 Pagination Links:")

        if "&page=" in get_link:
            base_url = get_link.split("&page=")[0]
        else:
            base_url = get_link

        page_div = soup.find("div", class_="paginate")
        printed_pages = set()

        if page_div:
            for link in page_div.find_all("a"):
                href = link.get("href")
                if href == "#":
                    page_number = 1
                else:
                    split_parts = href.split("page=")
                    page_number = int(split_parts[1]) if len(split_parts) > 1 else 1

                if page_number not in printed_pages:
                    full_url = f"{base_url}&page={page_number}"
                    print(full_url)
                    printed_pages.add(page_number)

    def get_content():
        get_link = input("Masukkan link episode webtoon (example: https://www.webtoons.com/id/slice-of-life/wee/episode-363/viewer?title_no=3085&episode_no=366): ").strip()
        folder_name = input("Masukkan nama folder penyimpanan (judul/episode): ").strip()

        headers = {
            "User-Agent": "Mozilla/5.0",
            "Referer": "https://www.webtoons.com/"
        }

        response_eps = requests.get(get_link, headers=headers)
        soup = BeautifulSoup(response_eps.text, "html.parser")

        image_list_div = soup.find("div", id="_imageList")
        if not image_list_div:
            print("❌ Tidak ditemukan konten gambar dalam halaman ini.")
            return

        image_tags = image_list_div.find_all("img", class_="_images")
        if not image_tags:
            print("❌ Tidak ada gambar ditemukan.")
            return

        if not os.path.exists(folder_name):
            os.makedirs(folder_name)

        print(f"\n🖼️ Ditemukan {len(image_tags)} gambar. Mulai mengunduh...\n")

        for idx, img in enumerate(image_tags, start=1):
            img_url = img.get("data-url")
            if not img_url:
                continue

            ext = img_url.split("?")[0].split(".")[-1]
            filename = f"{idx:03d}.{ext}"
            filepath = os.path.join(folder_name, filename)

            try:
                img_data = requests.get(img_url, headers=headers).content
                with open(filepath, "wb") as f:
                    f.write(img_data)
                print(f"✅ Gambar {idx} berhasil disimpan: {filepath}")
            except Exception as e:
                print(f"❌ Gagal menyimpan gambar {idx}: {e}")

        print(f"\n✅ Semua gambar selesai diunduh ke folder: {folder_name}")
        WebtoonScraper.convert_to_pdf(folder_name)
    
    def convert_to_pdf(folder_name):
        print(f"\n📄 Menggabungkan gambar di folder '{folder_name}' menjadi PDF...")

        images = []
        for filename in sorted(os.listdir(folder_name)):
            if filename.lower().endswith((".png", ".jpg", ".jpeg")):
                img_path = os.path.join(folder_name, filename)
                img = Image.open(img_path).convert("RGB")
                images.append(img)

        if images:
            pdf_path = os.path.join(folder_name, f"{folder_name}.pdf")
            try:
                images[0].save(pdf_path, save_all=True, append_images=images[1:])
                print(f"✅ PDF berhasil dibuat: {pdf_path}")
            except Exception as e:
                print(f"❌ Gagal membuat PDF: {e}")
        else:
            print("❌ Tidak ada gambar yang bisa digabungkan.")


if __name__ == "__main__":
    try:
        print_author_info()
        WebtoonScraper.main()
        WebtoonScraper.episodeList()
        WebtoonScraper.get_content()
    except Exception as e:
        print(f"❌ Terjadi kesalahan: {e}")
        print("❌ Mohon coba lagi.")
        exit(1)
    except KeyboardInterrupt:
        print("\n❌ Pengguna membatalkan operasi.")
        exit(0)