最近项目上有个需求，获取特定区域的POI信息，先在地图上初始化一个矩形，然后用该矩形从特定区域的左下角一直移动到右上角的位置，移动过程中，矩形所覆盖的区域的POI即为需要的信息。该方式主要是为了将地图进行网格化，以获取最小单位的信息，特记录一下，以便自己后续查看。
完整代码：
# coding=UTF-8
import requests
import time
import random
import csv
import sys
ty=sys.getfilesystemencoding()
class Yn_School(object):
def __init__(self):
self.base_url= 'http://api.map.baidu.com/place/v2/search?query={}&scope=2&bounds={}&page_size=20&page_num={}&output=json&ak=您的ak'
self.user_agent_list = [
{'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1"},
{'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0"},
{'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50"},
{'User-Agent':"Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50"},
{'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'},
{'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1'},
{'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12'},
{'User-Agent':'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)'},
{'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11'},
{'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16'},
{'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER '},
{'User-Agent':'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400) '},
{'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0 '},
{'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3'},
{'User-Agent':'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11'},
]
self.lat_1 = 24.390894
self.lon_1 = 102.174112
self.lat_2 = 26.548645
self.lon_2 = 103.678942
self.las_lat = 1
self.las_lon = 1 # 给las一个值1
self.ak = '您的ak'
self.url0 = 'http://api.map.baidu.com/place/v2/search?'
self.lat_count = int((self.lat_2 - self.lat_1) / self.las_lat + 1)
self.lon_count = int((self.lon_2 - self.lon_1) / self.las_lon + 1)
# self.user_ip_list =[{"http":"//116.7.176.75:8118"},{"http":"//119.179.60.117:8118"}]
self.data_list=[]
self.type=['酒店']
# self.type=['美食','酒店','购物','生活服务','旅游景点','休闲娱乐','运动健身','教育培训','文化传媒','医疗','汽车服务','交通设施','金融','房地产','公司企业'
# ,'政府机构']
# 1、取完整URL
def get_url_list(self):
url_list = []
for i in self.type:
for lat_c in range(0, self.lat_count):
lat_b1 = self.lat_1 + self.las_lat * lat_c
for lon_c in range(0, self.lon_count):
lon_b1 = self.lon_1 + self.las_lon * lon_c
lan_all = str(lat_b1)+','+str(lon_b1)+','+str(lat_b1+self.las_lat)+','+str(lon_b1+self.las_lon)
for j in range(0, 1): # 网页数 需修改
url_list.append(self.base_url.format(i,lan_all,j))
return url_list
# 2、发请求
def send_request(self,url):
headers = random.choice(self.user_agent_list)
print(headers)
# proxy = random.choice(self.user_ip_list)
# print(proxy)
time.sleep(random.random() * 3) # 随机访问间隔
html = requests.get(url,headers=headers) # 获取网页信息
data = html.json() # 获取网页信息的json格式数据
print("正在爬取 %s" % url)
return data
# 3、解析数据
def parse_data(self,data):
# print(len(data['results']))
if len(data['results']) > 0:
for item in data['results']:
data_dict = {}
data_dict['一级分类'] = item['detail_info']['tag'].split(';')[0]
data_dict['二级分类'] = item['detail_info']['tag'].split(';')[1]
data_dict['名称'] = item['name']
data_dict['经度'] = item['location']['lng']
data_dict['纬度'] = item['location']['lat']
data_dict['城市'] = item['city']
data_dict['区域'] = item['area']
data_dict['地址'] = item['address']
if "telephone" in item:
data_dict['电话'] = item["telephone"].replace(',', ' ')
else:
data_dict['电话'] = ''
self.data_list.append(data_dict)
print(data_dict)
else:
print('空数据')
# print(self.data_list)
# 4、保存数据
def save_data(self):
csv_file = open('BD_POI.csv', 'w', encoding='gbk', newline='')
# 添加csv标题
if len(self.data_list)>0:
sheet_title = self.data_list[0].keys()
sheet_content = []
for data in self.data_list:
sheet_content.append(data.values())
writer = csv.writer(csv_file)
writer.writerow(sheet_title)
writer.writerows(sheet_content)
csv_file.close()
else:
print('空数据')
print("写入成功")
# 5、统筹调用
def run(self):
url_list = self.get_url_list()
for url in url_list:
data = self.send_request(url)
self.parse_data(data)
self.save_data()
Yn_School().run()
网友评论