又到了每周一次的CSDN时刻,用博客记录我漫漫Python路的每一步第一次,2019年3月8日作业:用Python实现爬虫,爬取安居客租房信息,以下是我的代码过程:
'''
#爬取安居客租房信息
'''
#导入需要的模块
import requests
from lxml import etree
import csv
import time
import random
from pip._vendor.msgpack.fallback import newlist_hint
#定义抓取函数
def spider():
headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3514.0 Safari/537.36'}
prefix_url='https://xa.zu.anjuke.com/fangyuan/l2/?pi'
for i in range(1,2):
url = prefix_url+str(i) # 拼出完整的url
html = requests.get(url,headers=headers) # 获取页面
selector = etree.HTML(html.text) # 获取selector