python爬取URL 详解用python实现爬取CSDN热门评论URL并存入redis

import time
import random
from PIL import Image
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
if __name__ == '__main__':
  options = webdriver.ChromeOptions()
  options.binary_location = r'C:\Users\hhh\AppData\Local\Google\Chrome\Application\谷歌浏览器.exe'
  # driver=webdriver.Chrome(executable_path=r'D:\360Chrome\chromedriver\chromedriver.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)

from bs4 import BeautifulSoup
from 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_herf
title = html.xpath('//*[@id="feedlist_id"]/li/div/div/h2/a/@href')

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)

one_url = r_link.rpop("csdn_url)")
while one_url:
  print("{}被弹出！".format(one_url))