python网络爬虫练习关于房屋信息爬取的例子模块:
#-*- coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
resp = requests.get('https://wuzhong.anjuke.com/sale/litong/?from=SearchBar')
soup = BeautifulSoup(resp.text, 'lxml')
# find_all()方法,
# 注意class是Python关键词,后面要加下划线_:
alldiv = soup.find_all('div', class_='house-title')
for a in alldiv:
names = a.find('a')['title']
print(names)
allp = soup.find_all('div', class_='pro-price')
for p in allp:
authors1 = p.select('span')[0].get_text()#选择p节点的第一、二个span元素,并获取span中的文字
authors2 = p.select('span')[1].get_text()
print(authors1)
print(authors2)