【python爬虫】邮政包裹物流查询

• 目标网站 ems 邮政快递包裹查询:

https://www.ems.com.cn/

• 截图

• 接口预览
  

  • getPic请求滑动验证码的背景图片和滑块图片，返回的是base64编码的图片

  • getLogisticsTestFlag发送验证码的验证信息

    

    • xpos为滑动的距离，本站没有验证轨迹一说，属于验证码简单的一类
    • waybillNoList为需要查询的单号

  • queryTrack为查询物流的api

    

  • 请求头的加密参数

    

    • ticket、time必须校验
    • user-sign没有校验

• 解决思路

  • 滑动验证码采取ddddocr识别
  • 逆向ticket、time请求头参数即可

• js调试

  

  • 上图显示了这两个加密参数的加密逻辑

  • h()跟进去看是MD5

  • p.encode()是base64

  • 需要注意的是querytrack那个接口的l参数不一样，如下

    

  • 另外，请求前需要获取一个服务器时间，穿插在每次请求前，这个是为了让获取的信息更加实时

• 代码实现

import requests
import base64
import ddddocr
import hashlib
import json
from loguru import logger
logger.info("技术交流qq群:{}",529528142)
det = ddddocr.DdddOcr(det=False, ocr=False, show_ad=False)
headers = {
    'authority': 'www.ems.com.cn',
    'accept': 'application/json, text/plain, */*',
    'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
    # 'content-length': '0',
    'origin': 'https://www.ems.com.cn',
    'referer': 'https://www.ems.com.cn/',
    'sec-ch-ua': '"Not/A)Brand";v="99", "Google Chrome";v="115", "Chromium";v="115"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"Windows"',
    'sec-fetch-dest': 'empty',
    'sec-fetch-mode': 'cors',
    'sec-fetch-site': 'same-origin',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36',
}


def query_time():
    response = requests.post('https://www.ems.com.cn/ems-web/currentTime/queryTime', headers=headers)
    return response.json()["value"]


def getPic():
    response = requests.post('https://www.ems.com.cn/ems-web/cutPic/getPic', headers=headers).json()
    return response["value"]["capcode"], response["value"]["backImage"], response["value"]["slidingImage"], \
        response["value"]["yHeight"]


def verify(_ticket, _time, _xpos, _capcode):
    __headers = {
        'authority': 'www.ems.com.cn',
        'accept': 'application/json, text/plain, */*',
        'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'content-type': 'application/json;charset=UTF-8',
        'origin': 'https://www.ems.com.cn',
        'referer': 'https://www.ems.com.cn/',
        'sec-ch-ua': '"Not/A)Brand";v="99", "Google Chrome";v="115", "Chromium";v="115"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'empty',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'ticket': _ticket,
        'time': _time,
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36',
    }

    json_data = {
        'value': {
            'customerIP': '你的ip',
            'phoneNum': '',
            'waybillNoList': [
                consult_code,
            ],
            'xpos': _xpos,
            'capcode': _capcode,
        },
    }
    response = requests.post('https://www.ems.com.cn/ems-web/trackTestQuery/getLogisticsTestFlag', headers=__headers,
                             json=json_data)
    # print(response.json())
    if response.json()["success"]:
        logger.info("验证成功")
    else:
        logger.error("验证失败")


def ddocr_get_pos(_slide, _bg):
    _slide_bytes = base64.b64decode(_slide)
    _bg_bytes = base64.b64decode(_bg)

    with open('./slide.png', 'wb') as f:
        f.write(_slide_bytes)

    with open('./bg.jpg', 'wb') as f:
        f.write(_bg_bytes)

    _res = det.slide_match(_slide_bytes, _bg_bytes)
    return _res


def get_ticket_(_time, _capcode, _type):
    o = _time
    n = o[0:3]
    r = o[3:]
    l = ""
    if _type == "verify":
        l = "1163FA15CC9A425EA4B65B2A218FF5F8"
    elif _type == "track":
        l = "053B245CB1B74EBBB5FBB4A5889D66B8"
    else:
        pass
    c = _capcode
    u = consult_code + n + l + r + c
    g = hashlib.md5(u.encode('utf-8')).hexdigest().upper()
    d = hashlib.md5(g.encode('utf-8')).hexdigest().upper()
    m = base64.b64encode(d.encode('utf-8')).decode('utf-8')
    return m


def query_track(_ticket, _time, _xpos, _capcode):
    headers_ = {
        'authority': 'www.ems.com.cn',
        'accept': 'application/json, text/plain, */*',
        'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
        'content-type': 'application/json;charset=UTF-8',
        'origin': 'https://www.ems.com.cn',
        'referer': 'https://www.ems.com.cn/',
        'sec-ch-ua': '"Not/A)Brand";v="99", "Google Chrome";v="115", "Chromium";v="115"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'empty',
        'sec-fetch-mode': 'cors',
        'sec-fetch-site': 'same-origin',
        'ticket': _ticket,
        'time': _time,
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36',
    }

    json_data = {
        'value': [
            {
                'ip': '你的ip',
                'xpos': _xpos,
                'capcode': _capcode,
                'mailStatus': 'a',
                'orderNum': [
                    consult_code,
                ],
                'orderType': '1',
                'noRulesNum': [],
                'appleFlag': None,
            },
        ],
        'list': [
            consult_code,
        ],
    }

    response = requests.post('https://www.ems.com.cn/ems-web/mailTrack/queryTrack', headers=headers_, json=json_data)
    return response.json()


if __name__ == "__main__":
    consult_code = "12121212121"
    capCode, bg, slide, yheight = getPic()
    time_ = query_time()
    xpos_ = ddocr_get_pos(slide, bg)['target'][0] - 3
    logger.info("ddddocr->{}", xpos_)
    ticket_ = get_ticket_(_time=str(time_), _capcode=capCode, _type="verify")
    verify(_ticket=ticket_, _time=str(time_), _xpos=xpos_, _capcode=capCode)
    time_ = query_time()
    ticket_ = get_ticket_(_time=str(time_), _capcode=capCode, _type="track")
    info = query_track(_ticket=ticket_, _time=str(time_), _xpos=xpos_, _capcode=capCode)
    logger.info(info)

• 运行截图

技术交流群:529528142