链家数据爬取

import requests
import re
import json
import time
def get_one_page(url):
    headers={
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36‘

    }
    response=requests.get(url,headers=headers)
    if response.status_code==200:
        return response.text
    return None
def parse_one_page(html):
    pattern=re.compile(‘<li.*?LOGCLICKDATA.*?class="info clear".*?title.*?<a.*?>(.*?)</a>.*?houseInfo.*?region.*?>(.*?)</a>(.*?)</div>.*?positionIcon.*?</span>(.*?)<a.*?>(.*?)</a>.*?starIcon.*?</span>(.*?)</div>.*?class="totalPrice"><span>(.*?)</span>(.*?)</div>.*?unitPrice.*?<span>(.*?)</span>‘)
    items=re.findall(pattern,html)
    for item in items:
        yield{
        ‘title‘:item[0],
        ‘address‘:item[1],
        ‘houseIcon‘:item[2],
        ‘flood‘:item[3].strip()+item[4].strip(),
        ‘personStar‘:item[5],
        ‘price‘:item[6]+item[7]
        }
def write_file(content):
    with open(‘result12.json‘,‘a‘,encoding=‘utf8‘)as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content,ensure_ascii=False)+‘\n‘)
def main(offset):
    url=‘https://hz.lianjia.com/ershoufang/pg‘+str(offset)
    html=get_one_page(url)
    for item in parse_one_page(html):
        write_file(item)
if __name__ == ‘__main__‘:
    for i in range(101):
        main(offset=i)
        time.sleep(1)