爬虫-招标信息()

这个写的很舒服

#!/usr/bin/env python3
# -*- coding: utf-8  -*-

import requests
import re
import json
import random
from time import sleep
from datetime import date
from functools import reduce


class Province(object):
    def NJT(self, provinceCode, provinceNames, startDate, endDate):
        response = requests.post(
            url='https://ct-mss.com/MSS-PORTAL/announcementjoin/list.do',
            params={
                "provinceJT": "NJT"
            },
            headers={
                "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
                "Accept-Encoding": "gzip, deflate, br",
                "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
                "Cache-Control": "max-age=0",
                "Connection": "keep-alive",
                "Content-Length": "961",
                "Content-Type": "application/x-www-form-urlencoded",
                "Cookie": "BIGipServerld_wbmhap_pool=1464051904.31267.0000; JSESSIONID=00002wTXO7ynkEzAXBqdSAzGbuI:18djc0j4k",
                "Host": "ct-mss.com",
                "Origin": "https://ct-mss.com",
                "Referer": "https://ct-mss.com/MSS-PORTAL/announcementjoin/list.do?provinceJT=NJT",
                "Upgrade-Insecure-Requests": "1",
                "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
            },
            data={
                "provinceJT": "NJT",
                "docTitle": "",
                "docCode": "",
                "provinceCode": provinceCode,
                "provinceNames": provinceNames,
                "startDate": startDate,
                "endDate": endDate,
                "docType": "TenderAnnouncement",
                "paging.start": "1",
                "paging.pageSize": "50",
                "pageNum": "",
                "goPageNum": "1"
            },
            verify=False
        )

        info_regex = re.compile(r'<a href="#" onclick="view\S\S(\d*).*>(.*)</a>')
        info_list = info_regex.findall(response.text)
        hp = 'https://ct-mss.com/MSS-PORTAL/tenderannouncement/viewHome.do?id='
        messages = [message for message in
                    map(lambda m, n: n + '\r\n' + hp + m + '\r\n', [x[0] for x in info_list],
                        [y[1] for y in info_list])]
        return messages

    def JT(self, startDate, endDate):
        response = requests.post(
            url='https://ct-mss.com/MSS-PORTAL/announcementjoin/list.do',
            params={
                "provinceJT": "JT"
            },
            headers={
                "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
                "Accept-Encoding": "gzip, deflate, br",
                "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
                "Cache-Control": "max-age=0",
                "Connection": "keep-alive",
                "Content-Length": "253",
                "Content-Type": "application/x-www-form-urlencoded",
                "Cookie": "JSESSIONID=00002NnohCjtLkuBB8kPBUDUpi8:18djc0j4k; BIGipServerld_wbmhap_pool=1480829120.31267.0000",
                "Host": "ct-mss.com",
                "Origin": "https://ct-mss.com",
                "Referer": "https://ct-mss.com/MSS-PORTAL/announcementjoin/list.do?provinceJT=JT",
                "Upgrade-Insecure-Requests": "1",
                "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
            },
            data={
                "provinceJT": "JT",
                "docTitle": "",
                "docCode": "",
                "provinceCode": "",
                "startDate": startDate,
                "endDate": endDate,
                "docType": "TenderAnnouncement",
                "paging.start": "1",
                "paging.pageSize": "20",
                "pageNum": "10",
                "goPageNum": "1"
            },
            verify=False
        )

        info_regex = re.compile(r'<a href="#" onclick="view\S\S(\d*).*>(.*)</a>')
        info_list = info_regex.findall(response.text)
        hp = 'https://ct-mss.com/MSS-PORTAL/tenderannouncement/viewHome.do?id='
        messages = [message for message in
                    map(lambda m, n: n + '\r\n' + hp + m + '\r\n', [x[0] for x in info_list],
                        [y[1] for y in info_list])]
        return messages


def a_token():
    params = {'corpid': 'wwb1783c01ce91f3c2',
              'corpsecret': r'Jn0o32cISUIZDecxNDPnic42gjrjlOfKZ0rYa2EF9kA'
              }
    url = 'https://qyapi.weixin.qq.com/cgi-bin/gettoken'
    r = requests.get(url=url, params=params)
    token = json.loads(r.text)['access_token']
    return token


def send_message(totag, msg, token):
    data = {  # "touser": "@all",
        #"toparty": "",
        "totag": totag,
        "msgtype": "text",
        "agentid": '1000005',
        "text": {"content": "%s" % (msg)},
        "safe": 0
    }
    value = json.dumps(data)
    url = 'https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token=%s' % (token)
    requests.post(url, data=value)


def send(provinceCode, provinceNames, totag, token):
    today = str(date.today())
    startDate = today + ' 00:00:00'
    endDate = today + ' 20:00:00'
    province = Province()
    mlist = province.NJT(provinceCode, provinceNames, startDate, endDate) + province.JT(startDate, endDate)
    mlst = ['日期:' + today + '\r\n'] + mlist if mlist else [provinceNames + ': ' + today + '无招标信息']
    msg = reduce(lambda a, b: a + b, mlst)
    send_message(totag, msg, token)


if __name__ == '__main__':
    access_token = a_token()

    send("03", "上海", "1", access_token)
    sleep(10 + random.randint(5, 60))
    send("02", "浙江", "1", access_token)
  • 0
    点赞
  • 7
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值