class WebLinkClickerFrame(wx.Frame):
    def __init__(self):
        super().__init__(parent=None, title='網(wǎng)頁鏈接自動(dòng)點(diǎn)擊截圖工具', size=(900, 700))
        
        # URL輸入框
        self.url_input = wx.TextCtrl(panel, value="https://example.com")
        
        # 瀏覽器選擇
        self.browser_choice = wx.Choice(panel, choices=['Chrome', 'Firefox'])
        
        # 功能選項(xiàng)
        self.headless_cb = wx.CheckBox(panel, label="無頭模式(后臺運(yùn)行)")
        self.full_page_cb = wx.CheckBox(panel, label="完整頁面截圖")
        self.delay_spin = wx.SpinCtrl(panel, value="2", min=1, max=10)
        
        # 進(jìn)度顯示
        self.progress_text = wx.TextCtrl(panel, style=wx.TE_MULTILINE | wx.TE_READONLY)
        self.progress_gauge = wx.Gauge(panel, range=100)

def init_driver(self):
    browser_type = self.browser_choice.GetStringSelection()
    headless = self.headless_cb.GetValue()
    
    if browser_type == 'Chrome':
        options = Options()
        if headless:
            options.add_argument('--headless')
        options.add_argument('--no-sandbox')
        options.add_argument('--window-size=1920,1080')
        
        self.driver = webdriver.Chrome(options=options)
    else:
        options = FirefoxOptions()
        if headless:
            options.add_argument('--headless')
        
        self.driver = webdriver.Firefox(options=options)

def click_care_button(self):
    care_button = None
    
    # 方式1: 通過文本內(nèi)容查找
    try:
        care_button = self.driver.find_element(By.XPATH, "http://*[contains(text(), '進(jìn)入關(guān)懷版')]")
    except:
        pass
    
    # 方式2: 通過鏈接文本查找
    if not care_button:
        try:
            care_button = self.driver.find_element(By.LINK_TEXT, "進(jìn)入關(guān)懷版")
        except:
            pass
    
    # 方式3: 通過部分鏈接文本查找
    if not care_button:
        try:
            care_button = self.driver.find_element(By.PARTIAL_LINK_TEXT, "關(guān)懷版")
        except:
            pass
    
    # 方式4: 遍歷所有按鈕
    if not care_button:
        buttons = self.driver.find_elements(By.TAG_NAME, "button")
        for btn in buttons:
            if "關(guān)懷版" in btn.text:
                care_button = btn
                break
    
    # 點(diǎn)擊按鈕
    if care_button:
        care_button.click()
        time.sleep(2)  # 等待頁面跳轉(zhuǎn)

def extract_links(self, url):
    self.driver.get(url)
    time.sleep(self.delay_spin.GetValue())
    
    # 點(diǎn)擊特定按鈕（如果存在）
    self.click_care_button()
    
    # 解析頁面
    html = self.driver.page_source
    soup = BeautifulSoup(html, 'html.parser')
    base_domain = urlparse(url).netloc
    
    # 提取鏈接
    links = []
    for a_tag in soup.find_all('a', href=True):
        href = a_tag['href']
        full_url = urljoin(url, href)
        
        # 只保留站內(nèi)鏈接
        if urlparse(full_url).netloc == base_domain:
            link_text = a_tag.get_text(strip=True) or '無標(biāo)題'
            links.append({'text': link_text, 'url': full_url})
    
    # 去重
    unique_links = []
    seen_urls = set()
    for link in links:
        if link['url'] not in seen_urls:
            seen_urls.add(link['url'])
            unique_links.append(link)
    
    return unique_links

def take_full_page_screenshot(self, filepath):
    if isinstance(self.driver, webdriver.Chrome):
        # 獲取頁面完整尺寸
        metrics = self.driver.execute_cdp_cmd('Page.getLayoutMetrics', {})
        width = metrics['contentSize']['width']
        height = metrics['contentSize']['height']
        
        # 使用CDP截圖
        screenshot = self.driver.execute_cdp_cmd('Page.captureScreenshot', {
            'clip': {
                'width': width,
                'height': height,
                'x': 0,
                'y': 0,
                'scale': 1
            },
            'captureBeyondViewport': True  # 關(guān)鍵參數(shù)
        })
        
        # 保存截圖
        import base64
        with open(filepath, 'wb') as f:
            f.write(base64.b64decode(screenshot['data']))
    else:
        # Firefox使用標(biāo)準(zhǔn)方法
        self.driver.save_screenshot(filepath)

def generate_excel(self):
    wb = openpyxl.Workbook()
    ws = wb.active
    ws.title = "鏈接截圖報(bào)告"
    
    # 設(shè)置表頭
    headers = ['序號', '按鈕名稱', '鏈接地址', '截圖']
    ws.append(headers)
    
    # 設(shè)置列寬
    ws.column_dimensions['B'].width = 30
    ws.column_dimensions['C'].width = 50
    ws.column_dimensions['D'].width = 60
    
    # 添加數(shù)據(jù)和截圖
    for data in self.links_data:
        row = ws.max_row + 1
        ws.cell(row, 1, data['index'])
        ws.cell(row, 2, data['text'])
        ws.cell(row, 3, data['url'])
        
        # 插入截圖
        if data['screenshot'] and os.path.exists(data['screenshot']):
            img = XLImage(data['screenshot'])
            img.width = 400
            img.height = 300
            ws.add_image(img, f'D{row}')
            ws.row_dimensions[row].height = 225
    
    # 保存文件
    excel_path = os.path.join(self.screenshot_dir, "鏈接報(bào)告.xlsx")
    wb.save(excel_path)

def on_start(self, event):
    self.is_running = True
    thread = threading.Thread(target=self.run_analysis, args=(url,))
    thread.daemon = True
    thread.start()

def run_analysis(self, url):
    try:
        # 初始化瀏覽器
        self.init_driver()
        
        # 提取鏈接
        links = self.extract_links(url)
        
        # 處理每個(gè)鏈接
        for index, link in enumerate(links):
            if not self.is_running:  # 支持中途停止
                break
            
            self.process_link(link, index)
            self.update_progress(int((index / len(links)) * 100))
        
        # 生成報(bào)告
        self.generate_excel()
    finally:
        self.driver.quit()

pip install wxPython selenium beautifulsoup4 openpyxl pillow

# 自動(dòng)管理驅(qū)動(dòng)
pip install webdriver-manager

python web_link_clicker.py

from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.service import Service

service = Service(ChromeDriverManager().install())
self.driver = webdriver.Chrome(service=service, options=options)

from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

wait = WebDriverWait(self.driver, 10)
element = wait.until(EC.presence_of_element_located((By.ID, "content")))

try:
    self.driver.get(url)
except TimeoutException:
    self.log("頁面加載超時(shí)")
except WebDriverException as e:
    self.log(f"瀏覽器錯(cuò)誤: {str(e)}")