import requests #想要爬必须引
from lxml import html #这个是用于页面爬取
import xlsxwriter#操作Excel表格库
 
workbook = xlsxwriter.Workbook('E:/test/test.xlsx')# 新建的Excel表格文档路径
worksheet = workbook.add_worksheet() # 建立sheet， 可以work.add_worksheet('employee')来指定sheet名，但中文名会报UnicodeDecodeErro的错误
i = 1;# 作用于Excel表格第几行数与接口第几页
#写一个死循环让他一直爬取数据
while (True):
 import json# 这里这么引入json是因为不这么引入当循环到第二次就会报没有引入json的错，所以循环引入了
 #接口str(i)表示第几页一定要转为字符串格式，要不会报不是字符串的错
 url = "https://www.amap.com/service/poiInfo"+str(i)+"&qii=true&cluster_state=5&need_utd=true&utd_sceneid=1000&div=PC1000&addr_poi_merge=true&is_classify=true&zoom=14.81&city=110000&geoobj=115.7|39.4|117.4|41.6&keywords=水果店" 
 # 将cookies字符串组装为字典 
 cookies_str = "guid=f86f-79f2-5b0b-69a3; UM_distinctid=16386a114ca143-07312d6ae4d5af8-47534130-1fa400-16386a114ccb85; CNZZDATA1255626299=1778515027-1526967763-https%253A%252F%252Fwww.baidu.com%252F%7C1527219534; cna=5hWHEx7lRkECAXL4l+2LMAfU; isg=BGBg3rAqL6QOz5OkNN5wbxWiMm7ywUxc_zvQMtpxLHsO1QD_gnkUwzbHaf3V_vwL; _uab_collina=152697209566826431413694; key=bfe31f4e0fb231d29e1d3ce951e2c780" 
 cookies_dict = {} 
 for cookie in cookies_str.split(";"): 
  k, v = cookie.split("=", 1) 
  cookies_dict[k.strip()] = v.strip() 
 pass
 # 其他请求头参数 
 headers = { 
  'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0' 
 }
 
 # 让服务器认为你是通过浏览器访问页面 
 page = requests.get(url=url,cookies=cookies_dict,headers=headers);
 # 转json
 json = json.loads(page.text);
 # 判断这个字段如果为未找到相关信息则跳出死循环
 if json['data']['lqii']['change_query_tip'] == '未找到"水果店"相关结果':
 break;
 pass
 # 获取json长度用于添加Excel第几行
 length = len(json['data']['poi_list']);
 # 循环json数据向Excel表格添加
 for index,j in enumerate(json['data']['poi_list']):
 worksheet.write(index+(i-1)*length,0,j['disp_name'])
 worksheet.write(index+(i-1)*length,1,j['tel'])
 worksheet.write(index+(i-1)*length,2,j['address'])
 pass
 i+=1
pass
workbook.close()#最后关闭Excel表格 注意事项，当Excel表格正在打开的情况下会报没有关闭的错所以请关闭Excel再运行此程序