python爬虫下载pdf文件 python 下载pdf

1.近期下载一些数据，涉及到pdf文件，因一些原因，需要用到selenium，希望不是在浏览器中打开pdf，而是下载这个文件

chromedrive.exe版本要匹配你当前的chrome浏览器版本（https://npm.taobao.org/mirrors/chromedriver/）

# -*- 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()