地理编码 如何在10分钟内将25万个地址绑定到坐标？

• 背景

• 批量地理编码

• 选择数据包地址解析器提供商

• Python服务指南

• 完整批次类别说明

• 结果分析

背景

1. 用于大学的地理编码Web应用程序；
2. 根据地理编码器的REST API编写脚本。

批量地理编码

1. 准备数据集，以便服务无误地接受它；
2. 设置工作结果的参数（选择列，分隔符...）；
3. 将文件上传到云；
4. 等待处理完成；
5. 下载完成的文件。

选择批处理地理编码服务提供商

• 谷歌地图
• HERE Technologies；
• 地图框
• 汤姆汤姆
• ESRI。

• 每月对地理编码服务的请求数量是免费的；
• 每天交易数量的限制；
• 批量地理编码服务的可用性；
• 可以在免费计划中使用数据包地址解析器。

谷歌地图

这里技术

地图框

汤姆

Yandex技术

ESRI

到底要选择什么？

Python服务指南

import requests
import json
import time
import zipfile
import io
from bs4 import BeautifulSoup

class Batch:

    SERVICE_URL = "https://batch.geocoder.ls.hereapi.com/6.2/jobs"
    jobId = None

    def __init__(self, apikey="your_api_key"):
        self.apikey = apikey

   recId; searchText
   1; -, . , 6
   2; ,  1,  -., 72
   3; 425 W Randolph St Chicago IL 60606
   4; , DJ106 20-30, Sibiu 557260
   5; 200 S Mathilda Ave Sunnyvale CA 94086
  

def start(self, filename, indelim=";", outdelim=";"):
        
        file = open(filename, 'rb')

        params = {
            "action": "run",
            "apiKey": self.apikey,
            "politicalview":"RUS",
            "gen": 9,
            "maxresults": "1",
            "header": "true",
            "indelim": indelim,
            "outdelim": outdelim,
            "outcols": "displayLatitude,displayLongitude,locationLabel,houseNumber,street,district,city,postalCode,county,state,country",
            "outputcombined": "true",
        }

        response = requests.post(self.SERVICE_URL, params=params, data=file)
        self.__stats (response)
        file.close()

• “操作”：“运行”-开始地址处理；
• “politicalView”: “RUS” – . ( );
• “gen”: 9 – ( );
• “maxresults”: 1 – ;
• “header”: true – ;
• “indelim”: “;” – , ;
• “outdelim”: “;” – ;
• “outcols”: “” – , ;
• “outcombined”: true – .

    def status (self, jobId = None):

        if jobId is not None:
            self.jobId = jobId
        
        statusUrl = self.SERVICE_URL + "/" + self.jobId
        
        params = {
            "action": "status",
            "apiKey": self.apikey,
        }
        
        response = requests.get(statusUrl, params=params)
        self.__stats (response)

    def result (self, jobId = None):

        if jobId is not None:
            self.jobId = jobId
        
        print("Requesting result data ...")
        
        resultUrl = self.SERVICE_URL + "/" + self.jobId + "/result"
        
        params = {
            "apiKey": self.apikey
        }
        
        response = requests.get(resultUrl, params=params, stream=True)
        
        if (response.ok):    
            zipResult = zipfile.ZipFile(io.BytesIO(response.content))
            zipResult.extractall()
            print("File saved successfully")
        
        else:
            print("Error")
            print(response.text)

    def __stats (self, response):
        if (response.ok):
            parsedXMLResponse = BeautifulSoup(response.text, "lxml")

            self.jobId = parsedXMLResponse.find('requestid').get_text()
            
            for stat in parsedXMLResponse.find('response').findChildren():
                if(len(stat.findChildren()) == 0):
                    print("{name}: {data}".format(name=stat.name, data=stat.get_text()))

        else:
            print(response.text)

>>> from geocoder import Batch
>>> service = Batch(apikey="   REST API")
>>> service.start("big_data_addresses.csv", indelim=";", outdelim=";")

requestid: "  Id "
status: accepted
totalcount: 0
validcount: 0
invalidcount: 0
processedcount: 0
pendingcount: 0
successcount: 0
errorcount: 0

>>> service.status()

requestid: "  Id "
status: completed
jobstarted: 2020-04-27T10:09:58.000Z
jobfinished: 2020-04-27T10:17:18.000Z
totalcount: 249999
validcount: 249999
invalidcount: 0
processedcount: 249999
pendingcount: 0
successcount: 249978
errorcount: 21

>>> service.result()
Requesting result data ...
File saved successfully

完整批次类别说明

import requests
import json
import time
import zipfile
import io
from bs4 import BeautifulSoup

class Batch:

    SERVICE_URL = "https://batch.geocoder.ls.hereapi.com/6.2/jobs"
    jobId = None

    def __init__(self, apikey="   REST API "):
        self.apikey = apikey
        
            
    def start(self, filename, indelim=";", outdelim=";"):
        
        file = open(filename, 'rb')

        params = {
            "action": "run",
            "apiKey": self.apikey,
            "politicalview":"RUS",
            "gen": 9,
            "maxresults": "1",
            "header": "true",
            "indelim": indelim,
            "outdelim": outdelim,
            "outcols": "displayLatitude,displayLongitude,locationLabel,houseNumber,street,district,city,postalCode,county,state,country",
            "outputcombined": "true",
        }

        response = requests.post(self.SERVICE_URL, params=params, data=file)
        self.__stats (response)
        file.close()
    

    def status (self, jobId = None):

        if jobId is not None:
            self.jobId = jobId
        
        statusUrl = self.SERVICE_URL + "/" + self.jobId
        
        params = {
            "action": "status",
            "apiKey": self.apikey,
        }
        
        response = requests.get(statusUrl, params=params)
        self.__stats (response)
        

    def result (self, jobId = None):

        if jobId is not None:
            self.jobId = jobId
        
        print("Requesting result data ...")
        
        resultUrl = self.SERVICE_URL + "/" + self.jobId + "/result"
        
        params = {
            "apiKey": self.apikey
        }
        
        response = requests.get(resultUrl, params=params, stream=True)
        
        if (response.ok):    
            zipResult = zipfile.ZipFile(io.BytesIO(response.content))
            zipResult.extractall()
            print("File saved successfully")
        
        else:
            print("Error")
            print(response.text)
    

    
    def __stats (self, response):
        if (response.ok):
            parsedXMLResponse = BeautifulSoup(response.text, "lxml")

            self.jobId = parsedXMLResponse.find('requestid').get_text()
            
            for stat in parsedXMLResponse.find('response').findChildren():
                if(len(stat.findChildren()) == 0):
                    print("{name}: {data}".format(name=stat.name, data=stat.get_text()))

        else:
            print(response.text)

结果分析