assignment01_scraper.py

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
import time
import os

def init_driver():
    options = webdriver.ChromeOptions() # 設定 Chrome 瀏覽器的選項
    options.add_argument('--start-maximized') # 啟動時最大化視窗
    options.add_argument('--incognito') # 無痕模式
    options.add_argument('--disable-popup-blocking') # 停用彈窗阻擋功能
    options.add_experimental_option('excludeSwitches',['enable-automation']) # 移除 Chrome 被 Selenium 控制時的一些提示標記
    options.add_experimental_option('useAutomationExtension',False) # 關閉 Selenium 自帶的自動化擴充功能。
    options.add_argument('--user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36') # 假裝自己是一般使用者
    options.add_argument('disable-blink-features=AutomationControlled') # 避免被視為機器人

    driver = webdriver.Chrome(options=options) # 這行跑完，會看到一個 Chrome 視窗彈出來
    return driver

def open_url(driver, url):
    driver.get(url)
    print("Page Title:", driver.title)

    # 點擊「免費閱讀」按鈕
    button = driver.find_element(By.CSS_SELECTOR,'button.open-viewer.book-begin.ga')
    button.click()

    time.sleep(2)

    # 切換到新開啟的標籤頁
    driver.switch_to.window(driver.window_handles[-1])
    
    # 點擊「立即閱讀」按鈕
    read_now = driver.find_element(By.PARTIAL_LINK_TEXT,'すぐに読む')
    read_now.click()

def get_manga_images(driver, folder_name='manga_images'):
    if not os.path.exists(folder_name):
        os.makedirs(folder_name)
        print(f'已建立資料夾: {folder_name}')

    wait_element = WebDriverWait(driver, 10)
    total_image_count = 0

    while True:
        image_elements = driver.find_elements(By.CSS_SELECTOR,'div.page_image img.image')

        for img_element in image_elements:
            if img_element.is_displayed():
                file_path = os.path.join(folder_name, f"manga_page_{total_image_count}.png")

                img_element.screenshot(file_path)
                print(f"成功擷取 {total_image_count} 頁並儲存為: {file_path}")
                
                total_image_count += 1

        try: # 嘗試尋找並點擊「下一頁」按鈕
            next_page = wait_element.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'div.flip.flip-left')))

            next_page.click() # 點擊下一頁按鈕

            print("已點擊下一頁，等待畫面載入...")
            time.sleep(2)
        
        except TimeoutException: # Break Condition
            print("【系統提示】找不到下一頁按鈕，已達最後一頁，結束爬取迴圈。")
            break
        

if __name__ == "__main__":
    mangaz_url = "https://www.mangaz.com/book/detail/157901"
    
    my_driver = init_driver()
    
    try:
        open_url(my_driver, mangaz_url)
        get_manga_images(my_driver)

    except Exception as e:
        print(f"發生錯誤: {e}")

    finally:
        print("程式即將關閉...")
        time.sleep(5)
        my_driver.quit()