目标：爬取安居客网站上前10页北京二手房的数据，包括二手房源的名称、价格、几室几厅、大小、建造年份、联系人、地址、标签等。
网址为：https://beijing.anjuke.com/sale/
BeautifulSoup官网：https://www.crummy.com/software/BeautifulSoup/
直接上代码：
import requests
from bs4 import BeautifulSoup
'''
遇到不懂的问题？Python学习交流群：1136201545满足你的需求，资料都已经上传群文件，可以自行下载！
'''
headers={'user-agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
link='https://beijing.anjuke.com/sale/'
def getHouseInfo(link):
r=requests.get(link,headers=headers)
soup=BeautifulSoup(r.text,'lxml')
house_list=soup.find_all('li',class_='list-item')
for house in house_list:
name=house.find('div',class_='house-title').a.text.strip()
price=house.find('span',class_='price-det').text.strip()
price_area=house.find('span',class_='unit-price').text.strip()#单位面积
no_room=house.find('div',class_='details-item').span.text#几室几厅
area=house.find('div',class_='details-item').contents[3].text
floor=house.find('div',class_='details-item').contents[5].text
year=house.find('div',class_='details-item').contents[7].text
broker=house.find('span',class_='brokername').text
broker=broker[1:]
address=house.find('span',class_='comm-address').text.strip()
address=address.replace('\xa0\xa0\n',' ')
tag_list=house.find_all('span',class_='item-tags')
tags=[i.text for i in tag_list]
print(name,price,price_area,no_room,area,floor,year,broker,address,tags)
for i in range(1,11):
link=link+'/p'+str(i)
print('page'+str(i))
getHouseInfo(link)