上市公司年报爬取（其他公告同理）---仅供学习使用

声明：本程序不存在任何恶意攻击意图，仅供学习练习使用

感谢巨潮资讯提供的信息：http://www.cninfo.com.cn/
教程开始

1. 环境

使用 pip安装 request 1.0.117
模块 os、json、time模块均为python自带环境 Python 3.8.12
代码

2. List item

import os
import requests
import json
import time

print("年报爬取，股票代码，开始时间、结束时间\n退出程序在输入股票代码处输入exit退出\n一次最多100条")

url = "http://www.cninfo.com.cn/new/hisAnnouncement/query"

headers = {
    "Accept": "application/json, text/javascript, */*; q=0.01",
    "Accept-Encoding": "gzip, deflate",
    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
    "Connection": "keep-alive",
    "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
    "Host": "www.cninfo.com.cn",
    "Origin": "http://www.cninfo.com.cn",
    "Referer": "http://www.cninfo.com.cn/new/disclosure/stock?stockCode=000501&orgId=gssz0000501",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.4951.54 Safari/537.36 Edg/101.0.1210.39",
    "X-Requested-With": "XMLHttpRequest"
}
while True:
    number = str(input("请输入代号："))
    if number.__eq__("exit"):
        print("退出程序")
        break
    begin = str(input("请输入开始年份：")) + "-01-01~"
    end = str(input("请输入结束年份：")) + "-12-31"
    data = {
        "stock": number + ",gssz0" + number,
        "tabName": "fulltext",
        "pageSize": 100,
        "pageNum": 1,
        "column": "szse",
        "category": "category_ndbg_szsh;",
        "plate": "sz",
        "seDate": begin + end,
        "searchkey": "",
        "secid": "",
        "sortName": "",
        "sortType": "",
        "isHLtitle": "true"
    }
    print(data)
    res = requests.post(url, data)
    content = res.content
    djson = json.loads(content)

    if not os.path.exists("./pdf/" + number):
        os.mkdir("./pdf/" + number)
    if djson.get("announcements") is None:
        print("你查找的股票在该范围内无公告，请检查股票编号和时间范围")
    else:
        for j in djson.get("announcements"):
            url = str(j.get("adjunctUrl"))
            name = j.get("announcementTitle")
            url = "http://www.cninfo.com.cn/new/announcement/download?" \
                  + "bulletinId=" + url[21:-4] + "&announceTime=" + url[10:20]
            print(name + ":\t" + url)
            response = requests.get(url)
            content = response.content
            file = open("./pdf/" + number + "/" + name + ".pdf", "wb+")
            file.write(content)
            file.close()
            # time.sleep(1)  # 防止被屏蔽
    print(number + "任务完成")

结果图