使用Selenium爬取数据时遭遇NoAlertPresentException错误求助

问题描述 #

爬取https://mspotrace.org.my/Sccs_list时频繁出现NoAlertPresentException，错误信息如下：

NoAlertPresentException: no alert open
  (Session info: chrome=109.0.5414.121)
  (Driver info: chromedriver=2.35.528161 (5b82f2d2aae0ca24b877009200ced9065a772e73),platform=Windows NT 10.0.19045 x86_64)

调整time.sleep时长后问题仍未解决，原代码如下：

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait    
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import pandas as pd
import time

driver = webdriver.Chrome()
driver.get('https://mspotrace.org.my/Sccs_list')
time.sleep(20)

# Get list of elements
elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[@title='View on Map']")))

# Loop through element popups and pull details of facilities into DF
pos = 0
df = pd.DataFrame(columns=['facility_name','other_details','gmaps_url'])
df_out = pd.DataFrame(columns=['facility_name','other_details','gmaps_url'])

for iii in range(1,10): # testing with 10 pages
    for element in elements:
        try: 
            data = []
            element.click()
            time.sleep(10)
            facility_name = driver.find_element_by_xpath('//h4[@class="modal-title"]').text
            other_details = driver.find_element_by_xpath('//div[@class="modal-body"]').text
            map_url = driver.find_element_by_xpath("//a[contains(@href,'https://maps.google.com/maps?ll=')]")
            gmaps_url = str(map_url.get_attribute('href'))
            time.sleep(20)
            data.append(facility_name)
            data.append(other_details)
            data.append(gmaps_url)
            df.loc[pos] = data
            WebDriverWait(driver,1).until(EC.element_to_be_clickable((By.CSS_SELECTOR, "button[aria-label='Close'] > span"))).click() # close popup window
            print("Scraping info for",facility_name,"")
            time.sleep(10)
            pos+=1

        except Exception:
            alert = driver.switch_to.alert
            print("No geo location information")
            alert.accept()
            pass
      
    # click next
    btnNext = driver.find_element(By.XPATH,'//*[@id="dTable_next"]/a')
    driver.execute_script("arguments[0].scrollIntoView();", btnNext)
    driver.execute_script("arguments[0].click();", btnNext)
    time.sleep(5)
    
    # create outputs in df_out
    df_out = df_out.append(df)
    
    # Get list of elements again
    elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[@title='View on Map']")))

    # Resetting vars again
    pos = 0
    df = pd.DataFrame(columns=['facility_name','other_details','gmaps_url'])

解决方案 #

1. 修复异常捕获逻辑，避免盲目切换Alert #

原代码用except Exception:捕获所有异常，随后直接尝试切换Alert，导致无Alert时触发NoAlertPresentException。需分场景捕获特定异常：

• 先捕获元素查找失败的异常（比如找不到地图链接时可能触发Alert）
• 单独捕获NoAlertPresentException，避免无效切换

2. 用显式等待判断Alert是否存在 #

不要直接调用driver.switch_to.alert，而是用WebDriverWait等待Alert出现，超时则判定无Alert：

from selenium.common.exceptions import NoAlertPresentException, TimeoutException

try:
    alert = WebDriverWait(driver, 3).until(EC.alert_is_present())
    alert.accept()
    print("No geo location information")
except (TimeoutException, NoAlertPresentException):
    pass

3. 匹配Chrome与ChromeDriver版本 #

你的Chrome版本是109，但ChromeDriver是2.35，版本严重不兼容，这会导致包括Alert识别在内的各种异常。下载对应Chrome版本的ChromeDriver（Chrome 109对应ChromeDriver 109.x系列），确保版本一致。

4. 替换过时API，用显式等待替代固定sleep #

原代码中find_element_by_xpath是过时API，改用find_element(By.XPATH, ...)；同时减少time.sleep，用显式等待等待元素加载，提升稳定性：
比如点击元素后等待modal标题出现：

element.click()
# 等待modal标题加载
facility_name = WebDriverWait(driver, 10).until(
    EC.visibility_of_element_located((By.XPATH, '//h4[@class="modal-title"]'))
).text

修改后的完整代码 #

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait    
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import NoAlertPresentException, TimeoutException, NoSuchElementException
import pandas as pd

driver = webdriver.Chrome()
driver.get('https://mspotrace.org.my/Sccs_list')
# 等待页面加载完成
WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[@title='View on Map']")))

df_out = pd.DataFrame(columns=['facility_name','other_details','gmaps_url'])

for iii in range(1,10): # testing with 10 pages
    # 重新获取当前页的元素列表
    elements = WebDriverWait(driver, 20).until(EC.presence_of_all_elements_located((By.XPATH, "//a[@title='View on Map']")))
    df = pd.DataFrame(columns=['facility_name','other_details','gmaps_url'])
    pos = 0
    
    for element in elements:
        try: 
            data = []
            element.click()
            
            # 等待modal标题可见
            facility_name = WebDriverWait(driver, 10).until(
                EC.visibility_of_element_located((By.XPATH, '//h4[@class="modal-title"]'))
            ).text
            # 等待modal内容加载
            other_details = WebDriverWait(driver, 10).until(
                EC.visibility_of_element_located((By.XPATH, '//div[@class="modal-body"]'))
            ).text
            
            try:
                # 尝试获取地图链接
                map_url = WebDriverWait(driver, 5).until(
                    EC.presence_of_element_located((By.XPATH, "//a[contains(@href,'https://maps.google.com/maps?ll=')]"))
                )
                gmaps_url = map_url.get_attribute('href')
            except (TimeoutException, NoSuchElementException):
                # 找不到地图链接时检查Alert
                try:
                    alert = WebDriverWait(driver, 3).until(EC.alert_is_present())
                    alert.accept()
                    print(f"No geo location information for {facility_name}")
                    gmaps_url = None
                except (TimeoutException, NoAlertPresentException):
                    gmaps_url = None
            
            data.extend([facility_name, other_details, gmaps_url])
            df.loc[pos] = data
            
            # 关闭modal
            close_btn = WebDriverWait(driver, 10).until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, "button[aria-label='Close'] > span"))
            )
            close_btn.click()
            print(f"Scraping info for {facility_name}")
            pos += 1

        except Exception as e:
            print(f"Error processing element: {str(e)}")
            # 尝试关闭可能存在的modal或Alert
            try:
                alert = driver.switch_to.alert
                alert.accept()
            except NoAlertPresentException:
                pass
            try:
                close_btn = driver.find_element(By.CSS_SELECTOR, "button[aria-label='Close'] > span")
                if close_btn.is_displayed():
                    close_btn.click()
            except:
                pass
            continue
      
    # 点击下一页
    try:
        btnNext = WebDriverWait(driver, 10).until(
            EC.element_to_be_clickable((By.XPATH, '//*[@id="dTable_next"]/a'))
        )
        driver.execute_script("arguments[0].scrollIntoView();", btnNext)
        btnNext.click()
        # 等待下一页加载完成
        WebDriverWait(driver, 10).until(
            EC.staleness_of(elements[0])  # 等待上一页元素失效，说明页面已刷新
        )
    except Exception as e:
        print(f"Failed to click next page: {str(e)}")
        break
    
    # 合并数据
    df_out = pd.concat([df_out, df], ignore_index=True)

# 保存结果
df_out.to_csv('facilities.csv', index=False)
driver.quit()

内容的提问来源于stack exchange，提问作者Funkeh-Monkeh