一、配置webdriver
下載谷歌瀏覽器驅動，并配置好
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\谷歌瀏覽器.exe'
# driver=webdriver.Chrome(executable_path=r'D:\360Chrome\chromedriver\chromedriver.exe')
driver = webdriver.Chrome(options=options)
#以java模塊為例
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、獲取URL
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')
可以看到，一下爬取了很多，速度非常快
三、寫入Redis
匯入redis包后，配置redis埠和redis資料庫，用rpush函式寫入
打開redis
import redis
r_link = redis.Redis(port='6379', host='localhost', decode_responses=True, db=1)
for u in title:
print("準備寫入{}".format(u))
r_link.rpush("csdn_url", u)
print("{}寫入成功!".format(u))
print('=' * 30, '\n', "共計寫入url：{}個".format(len(title)), '\n', '=' * 30)
大功告成！
在Redis Desktop Manager中可以看到，爬取和寫入都是非常的快，
要使用只需用rpop出堆疊就OK
one_url = r_link.rpop("csdn_url)")
while one_url:
print("{}被彈出！".format(one_url))
轉載請註明出處，本文鏈接：https://www.uj5u.com/houduan/271580.html
標籤：python
上一篇：快捷生成HTML代碼的實作
下一篇：詳解僵尸行程、行程等待