【Python爬虫】：selenium下载pdf

关注

转载最新推荐文章于 2026-03-23 09:19:19 发布 991 阅读 AI 写同款· GEO 优化 ›

Selenium下载PDF文件实战 2021-07-21 文章目录文件下载的Selenium配置文件名修改按钮点击出错示例根据`Xpath`获取内容打开所有折叠的session标签获取所有session的论文列表数据保存下载文件&重命名文件下载的Selenium配置由于打开PDF文件网页时，可能会直接打开PDF预览页面，所以需要用： from selenium import webdriver download_dir = r"C:\Users\xxx\Desktop" options = webdriver.ChromeOptions() opti 阅读详情

# -*- coding: utf-8 -*-
import time
import re
import io
from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains

import sys
reload(sys)
sys.setdefaultencoding("utf-8") 

option = webdriver.ChromeOptions()
option.add_experimental_option("excludeSwitches", ['enable-automation'])
option.add_experimental_option('prefs',  {
    "download.default_directory": "D:\\edesk\\outtask\\AIopt\\AIOPTjiaofu\\lunwen",
    "download.prompt_for_download": False,
    "download.directory_upgrade": True,
    "plugins.always_open_pdf_externally": True  #这句配置很重要
    }
) 
driver = webdriver.Chrome(chrome_options=option)  
wait = ui.WebDriverWait(driver,20)


driver.get("https://xxxxx1-s2.0-S2095495621000383-main.pdf") 
time.sleep(10)
driver.set_window_size(width=1000, height=800, windowHandle="current")
flag = False
if not flag:
    #可以手动输入一次密码，后面访问均有cookie
    raw_input('login:')
print "login!!!"
time.sleep(10) 
driver.get("https://xxxxx1-s2.0-S2095495621000383-main.pdf") 
time.sleep(20)  
print "download!!!"
driver.quit()