17python链家济南市全网数据爬取（也可稍加改动用于全国各城市）

#仅需修改这个地方https://jn.lianjia.com/ershoufang/pg{}rs/   将jn换成你所在城市的拼写首字母小写
import requests
from lxml import etree
import time
import random
import csv

class LianjiaSpider(object):
    def __init__(self):
        self.url = "https://jn.lianjia.com/ershoufang/pg{}rs/"


        self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1"}

    def get_page(self,url):
        res = requests.get(url =url ,headers = self.headers)
        res.encoding ="utf-8"
        html = res.text
        #调用解析函数
        self.parse_page(html)

    def parse_page(self,html):
        parse_html = etree.HTML(html)
        house_dict = {}
        house_list = parse_html.xpath("//div//ul[@class='sellListContent']//li")
        for house in house_list:
            house_dict["name"] = house.xpath(".//div[@class='title']/a//text()")[0]
            house_dict["totalprice"] = house.xpath(".//div[@class='totalPrice']/span//text()")[0]
            house_dict["uniteprice"] = house.xpath(".//div[@class='unitPrice']/span//text()")[0]
            house_dict["houseInfo"] = house.xpath(".//div[@class='houseInfo']/text()")[0]
            house_dict["positionInfoShequ"] = house.xpath(".//div[@class='positionInfo']/a[1]//text()")[0]
            house_dict["positionInfoJiedao"] = house.xpath(".//div[@class='positionInfo']/a[2]//text()")[0]
            house_dict["followInfo"] = house.xpath(".//div[@class='followInfo']/text()")[0]
            print(house_dict)
            with open('F:/top250/lianjia.csv', 'a', newline='', encoding='utf-8')as f:
                write = csv.writer(f)
               # write.writerow([house_dict["name"],house_dict["totalprice"],house_dict["uniteprice"],house_dict["info"]])
                write.writerow([house_dict["name"], house_dict["totalprice"], house_dict["uniteprice"],house_dict["houseInfo"],house_dict["positionInfoShequ"],house_dict["positionInfoJiedao"],house_dict["followInfo"]])
            f.close()

    def main(self):
        try:
            for i in range(1,2000):
                time.sleep(random.randint(3,5))
                url = self.url.format(i)
                self.get_page(url)
        except:
            self.main()

if __name__ == '__main__':
    start = time.time()
    spider = LianjiaSpider()
    spider.main()
    end = time.time()
    print("执行时间：%.2f" %(end-start))