一、配置webdriver
下载谷歌浏览器驱动，并配置好
import timeimport randomfrom PIL import Imagefrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECif __name__ == '__main__':options = webdriver.ChromeOptions()options.binary_location = r'C:UsershhhAppDataLocalGoogleChromeApplication谷歌浏览器.exe'# driver=webdriver.Chrome(executable_path=r'D:360Chromechromedriverchromedriver.exe')driver = webdriver.Chrome(options=options)#以java模块为例driver.get('https://www.csdn.net/nav/java')for i in range(1,20):driver.execute_script("window.scrollTo(0, document.body.scrollHeight)")time.sleep(2)二、获取URL
from bs4 import BeautifulSoupfrom lxml import etree
html = etree.HTML(driver.page_source)# soup = BeautifulSoup(html, 'lxml')# soup_herf=soup.find_all("#feedlist_id > li:nth-child(1) > div > div > h2 > a")# soup_herftitle = html.xpath('//*[@id="feedlist_id"]/li/div/div/h2/a/@href')可以看到，一下爬取了很多，速度非常快
三、写入Redis
导入redis包后，配置redis端口和redis数据库，用rpush函数写入
打开redis
import redis
r_link = redis.Redis(port='6379', host='localhost', decode_responses=True, db=1)for u in title:print("准备写入{}".format(u))r_link.rpush("csdn_url", u)print("{}写入成功!".format(u))print('=' * 30, 'n', "共计写入url：{}个".format(len(title)), 'n', '=' * 30)
大功告成！
在Redis Desktop Manager中可以看到，爬取和写入都是非常的快。
要使用只需用rpop出栈就OK
one_url = r_link.rpop("csdn_url)")while one_url:print("{}被弹出！".format(one_url)) 
