网页版爬虫
#爬取requests/BeautifulSoup
import requests
import MySQLdb
from bs4 import BeautifulSoup
url = 'https://bj.lianjia.com/zufang/'#浏览器获取url
def get_page(url):
response = requests.get(url)
soup = BeautifulSoup(response.text,'lxml')
return soup
#封装成函数,作用是获取列表下面所有租房页面的链接,返回一个链接列表;
def get_links(link_url):
soup = get_page(link_url)
links_div = soup.find_all('div',class_ = "content__list--item")
links =