python + 高德地图API实现地图找房

python + 高德地图API实现地图找房

项目简介：根据工作地点信息和58同城爬取的租房信息，通过高德地图进行显示，同时利用高德API自动规划房源到工作地点的通勤路线（公交+地铁）
项目仓库：https://github.com/haohaizhi/58house_spiders

一、数据爬取

# 拉取代码
git clone https://github.com/haohaizhi/58house_spiders.git

完整代码如下：

from bs4 import BeautifulSoup
import requests
import csv
import time
import lxml

def main():

    # 1、筛选条件为租金的范围，可自定义修改
    # 2、地点不同则网址二级域名不同,如此时南京：nj.58.com  北京：bj.58.com
    # 3、因为没有做一些动态切换处理，多次运行可能会触发网址防爬机制，此时需要手动访问该网站进行验证
    # 4、使用此程序需要了解一些爬虫基本原理
    url = "https://nj.58.com/pinpaigongyu/pn/{page}/?minprice=2000_4000"

    # 已完成的页数序号，初时为0

    csv_file = open("house.csv", "w", encoding="utf-8")
    csv_writer = csv.writer(csv_file, delimiter=',')

    for page in range(0,20):
        page += 1
        print("正在爬取第" + str(page) + "页信息........")
        print("URL: ", url.format(page=page))
        time.sleep(3)
        response = requests.get(url.format(page=page))
        response.encoding = 'utf-8'
        html = BeautifulSoup(response.text,features="lxml")
        # lxml 4.0版本
        # html = BeautifulSoup(response.text,features="html.parser")
        house_list = html.select(".list > li")

        for house in house_list:
            house_title = house.select("img")[0]["alt"]
            house_url = house.select("a")[0]["href"]
            house_info_list1 = house_title.split('-')

            # 如果第二列是公寓名或者社区则取第一列作为地址
            if "公寓" in house_info_list1[0] or "社区" in house_info_list1[0]:
                house_info_list2 = house_info_list1[0].split(' ')
                house_info_list2 = house_info_list2[0].replace('【','')
                house_info_list2 = house_info_list2.replace('】', '｜')
            else:
                house_info_list2 = house_info_list1[0]
            print(house_info_list2 + " " + house_url)

            house_location = house_info_list2.replace('｜',' ')
            house_info_list = house_location.split(' ')
            print(house_info_list)

            house_url = "https://nj.58.com" + house_url
            csv_writer.writerow([house_info_list[1], house_url])
    csv_file.close()

if __name__ == '__main__':
    main()

根据自身需要进行修改如下url：

# 修改代码中url网址 (地区 价格范围)
# 如: 北京:bj.58.com
#     南京:nj.58.com
# 若想进行更准确的筛选，则需要添加其他参数，具体需要参考58同城
url = "https://nj.58.com/pinpaigongyu/pn/{page}/?minprice=2000_4000"

查看所需数据的标签

#这几行代码就是从网页源码中获取所需数据，这个用到了BeautifulSoup库的select函数，函数具体用法可上网搜索文档，或者在本项目代码仓库的README中查看
		response = requests.get(url.format(page=page))
        response.encoding = 'utf-8'
        html = BeautifulSoup(response.text,features="lxml")
        house_list = html.select(".list > li")

注意：程序运行过程中很大几率会出现中断的情况，基本原因都是爬取网址时出现问题，可能网络波动，可能网站需要人工验证

# 可将部分代码修改成以下方式进行优化
    for page in range(0,20):
     	try:
	        page += 1
	        print("正在爬取第" + str(page) + "页信息........")
	        print("URL: ", url.format(page=page))
	        time.sleep(3)
	        response = requests.get(url.format(page=page))
	        response.encoding = 'utf-8'
	        html = BeautifulSoup(response.text,features="lxml")
	        house_list = html.select(".list > li")
	
	        for house in house_list:
	            house_title = house.select("img")[0]["alt"]
	            house_url = house.select("a")[0]["href"]
	            house_info_list1 = house_title.split('-')
	
	            # 如果第二列是公寓名或者社区则取第一列作为地址
	            if "公寓" in house_info_list1[0] or "社区" in house_info_list1[0]:
	                house_info_list2 = house_info_list1[0].split(' ')
	                house_info_list2 = house_info_list2[0].replace('【','')
	                house_info_list2 = house_info_list2.replace('】', '｜')
	            else:
	                house_info_list2 = house_info_list1[0]
	            print(house_info_list2 + " " + house_url)
	
	            house_location = house_info_list2.replace('｜',' ')
	            house_info_list = house_location.split(' ')
	            print(house_info_list)
	
	            house_url = "https://nj.58.com" + house_url
	            csv_writer.writerow([house_info_list[1], house_url])
        except:
           	pass
    csv_file.close()

刚开始进行调试时可以先尝试只分析某一页的html源码

# 代码如下
from bs4 import BeautifulSoup
import requests
import csv
import time
import lxml

def main():
    url = "https://nj.58.com/pinpaigongyu/pn/1/?minprice=2000_4000"
    response = requests.get(url.format(page=page))
    response.encoding = 'utf-8'
    print(response)
    
if __name__ == '__main__':
    main()

将执行后打印的内容Ctrl + A, Ctrl + C 复制粘贴到临时文件中，如test.txt
然后就可以针对这个临时文件进行后续数据提取的操作，等程序调试的没问题了，在用最最终版的代码

from bs4 import BeautifulSoup
import requests
import csv
import time
import lxml
def main():
	csv_file = open("house.csv", "w", encoding="utf-8")
    csv_writer = csv.writer(csv_file, delimiter=',')
    
	f = open('./test.txt', 'r')
    response = f.read()
    f.close()
	
	html = BeautifulSoup(response,features="lxml")
    house_list = html.select(".list > li")
    for house in house_list:
        house_title = house.select("img")[0]["alt"]
        house_url = house.select("a")[0]["href"]
        house_info_list1 = house_title.split('-')

        # 如果第二列是公寓名或者社区则取第一列作为地址
        if "公寓" in house_info_list1[0] or "社区" in house_info_list1[0]:
            house_info_list2 = house_info_list1[0].split(' ')
            house_info_list2 = house_info_list2[0].replace('【','')
            house_info_list2 = house_info_list2.replace('】', '｜')
        else:
            house_info_list2 = house_info_list1[0]
        print(house_info_list2 + " " + house_url)

        house_location = house_info_list2.replace('｜',' ')
        house_info_list = house_location.split(' ')
        print(house_info_list)

        house_url = "https://nj.58.com" + house_url
        csv_writer.writerow([house_info_list[1], house_url])
    csv_file.close()
    
if __name__ == '__main__':
    main()    

二、高德地图显示

打开该html文件

初始时坐标中心为北京，输入工作地点并回车后会进行跳转

将house.csv文件导入，点击蓝色图标，将自动规划通勤路线

点击房源链接地址后将跳转到指定网址

到此，整个项目已介绍完毕。

已同步发表到个人网站：https://blog.mehoon.com/269.html