使用PYTHON采集船舶MMSI数据

新项目开发AIS设备，需要用到MMSI信息。自己用python写了个简易的爬虫！

目标网站的接口数据是JSON，省去麻烦直接采集入库代码如下！

import sys
import time
import pymysql
import requests

# mysql
db = pymysql.connect(host='127.0.0.1',
                     user='root',
                     password='root',
                     database='bms_company_ship')
cursor = db.cursor()


def get_html(url) -> dict:
    try:
        headers = {
            'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                          "Chrome/97.0.4692.99 Safari/537.36 Edg/97.0.1072.69",
        }

        r = requests.get(url=url, headers=headers)
        r.encoding = 'utf-8'
        content = r.json()
        return content
    except:
        s = sys.exc_info()
        print("Error '%s' happened on line %d" % (s[1], s[2].tb_lineno))
        return {'type': 'Error'}


def execute_mysql(sql) -> bool:
    try:
        cursor.execute(sql)
        db.commit()
        return True
    except:
        db.rollback()
        return False


def main():
    page = 1
    while page < 1994:
        htmldata = get_html('https://www.hifleet.com/particulars/getShipData?offset=%d&limit=100' % page)
        data = htmldata['data']
        for i in data:
            sql = "INSERT INTO `bms_company_ship` (`shipname`, `mmsi`, `callsign`, `imo`) VALUES ('%s', '%s', '%s', '%s');" % (
                i['ShipName'], i['mmsi'], i['callsign'], i['imo'])
            execute_mysql(sql)
        print("采集海事数据 第%d页" % page)
        page += 1
        time.sleep(0.5)
    db.close()


if __name__ == "__main__":
    main()

如果有需要现成数据的可以去下载：

全球船舶MMSIIMOnamecallsign19万+数据-MySQL文档类资源-CSDN下载包含MMSIIMOnamecallsign数据sql文件直接导入mysql就能用更多下载资源、学习资料请访问CSDN下载频道.https://download.csdn.net/download/weixin_42258479/84991683