苏州吴江所有二手楼盘导出EXCEL表

最新推荐文章于 2024-10-05 08:53:18 发布

yuwhich

最新推荐文章于 2024-10-05 08:53:18 发布

阅读量116

点赞数

文章标签：爬虫 python xpath

本文链接：https://blog.csdn.net/yuwhich/article/details/99682259

版权

import requests
from lxml import etree
import csv

class JuAnKe():
    def __init__(self):
        self.url_temp = "https://suzhou.anjuke.com/sale/p{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"}

    def get_url_list(self):
        return [self.url_temp.format(i) for i in range(1, 3)] #这里爬取1-3页。

    def pase_url(self, url):
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def get_content_list(self, html_str):
        html = etree.HTML(html_str)
        content_list = []
        div_list = html.xpath('//ul[@id="houselist-mod-new"]/li')
        for div in div_list:
            item = {}
            item["标题"] = div.xpath(
                './/div[@class="house-title"]/a/text()')
            item["标题"] = item["标题"][0].strip()
            item["楼盘名称"] = div.xpath(
                './/div[@class="details-item"]/span[@class="comm-address"]/text()')
            item["楼盘名称"] = item['楼盘名称'][0].split("\xa0")[0].strip()
            item["地址"] = div.xpath(
                './/div[@class="details-item"]/span[@class="comm-address"]/text()')
            item["地址"] = item['地址'][0].split("\xa0")[-1].strip()
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):
        headers = ["标题","楼盘名称","地址"]
        with open("信息.csv","w",encoding="utf-8-sig", newline="") as fp:
            writer = csv.DictWriter(fp, headers)
            writer.writeheader()
            writer.writerows(content_list)

        # for i in content_list:
        #     print(i["title"])


    def run(self):
        url_list = self.get_url_list()
        for url in url_list:
            html_str = self.pase_url(url)
            content_list = self.get_content_list(html_str)
            self.save_content_list(content_list)

if __name__ == '__main__':
    juanke = JuAnKe()
    juanke.run()