python爬取链家网_python - 爬虫入门练习 爬取链家网二手房信息

import requests

from bs4 import BeautifulSoup

import sqlite3

conn = sqlite3.connect("test.db")

c = conn.cursor()

for num in range(1,101):

url = "https://cs.lianjia.com/ershoufang/pg%s/"%num

headers = {

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)Chrome/64.0.3282.140 Safari/537.36',

}

req = requests.session()

response = req.get(url, headers=headers, verify=False)

info = response.text

f1 = BeautifulSoup(info,'lxml')

f2 = f1.find(class_='sellListContent')

f3 = f2.find_all(class_='clear LOGCLICKDATA')

for i in f3:

data_id = i.find(class_="noresultRecommend").get('data-housecode')

href = i.find( class_ =