[Python知识库]爬虫模拟鼠标点击动态下载PDF文件

话不多说直接上代码：

from selenium import webdriver
from selenium.webdriver import ActionChains
import time
import os
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait

#创建浏览器驱动
driver = webdriver.Chrome()
url = 'http://www.*****.com'
driver.get(url)
#按页码进入下载详情页
for i in range(1,9):

    driver.execute_script('window.scrollTo(0,document.body.scrollHeight)')  # 滑到底部
    #睡眠等待进入详情页下载
    time.sleep(1)
    #最大化浏览页面
    driver.maximize_window()
    #进入详情页，鼠标点击事件，下载当前页内PDF
    for j in range(1, 11):
        j = str(j)
        click = WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.XPATH, '/html/body/div[5]/div/div[1]/div[2]/table/tbody/tr[' + j + ']/td[1]/div/a')))
        ActionChains(driver).click(click).perform()
        #定位当前网页
        driver.switch_to.window(driver.window_handles[1])
        time.sleep(3)
        #点击PDF下载按钮
        download = driver.find_element_by_link_text('PDF下载')
        ActionChains(driver).click(download).perform()
        #关闭当前页
        driver.close()
        #返回招标公告首页
        driver.switch_to.window(driver.window_handles[0])
    # if i < 4 and i > 968:
    try:
        input_box = driver.find_element_by_xpath('//*[@id="layui-laypage-'+str(i)+'"]/span[3]/input')

        #清空文本框并输入页码
        input_box.clear()
        input_box.send_keys(i+1)
        my_element = driver.find_element_by_class_name('layui-laypage-btn')
        #下载到i页
        print(i)
        ActionChains(driver).click(my_element).perform()
    except:
        input_box = driver.find_element_by_xpath('//*[@id="layui-laypage-' + str(i) + '"]/span[4]/input')
        # 清空文本框并输入页码
        input_box.clear()
        input_box.send_keys(i + 1)
        my_element = driver.find_element_by_class_name('layui-laypage-btn')
        # 下载到i页
        print(i)
        ActionChains(driver).click(my_element).perform()

根据实际网页具体情况具体分析，灵活替换