cninfo-search-python/PdfListGet.py at master · Poncirus/cninfo-search-python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
#!/usr/bin/python3

from urllib import parse
import http.client
import json
import socket
import os

class PdfListGet:
    def __init__(self, orgId, code, name):
        self.orgId = orgId
        self.code = code
        self.name = name
        self.data = []

    def getPdfList(self, keylist, ban = []):
        for key in keylist:
            self.getPdfListByKey(key, ban)

        print("共获取到", len(self.data), "个链接")
        return self.data

    def getPdfListByKey(self, key, ban):
        print("正在搜索PDF链接 --- " + self.name + " --- " + key)
        print("正在获取PDF链接 --- " + self.name + " --- 沪市")
        self.httpConnect("sse", "shmb", "沪市", key)
        self.jsonDecode(ban)
        print("正在获取PDF链接 --- " + self.name + " --- 深市")
        self.httpConnect("szse", "sz", "深市", key)
        self.jsonDecode(ban)

    def jsonDecode(self, ban):
        if self.jsonMessage != None:
            data = json.loads(self.jsonMessage)
            if data["totalAnnouncement"] > 50:
                print("Warning: 总搜索数大于50，未下载完全")
            announ = data["announcements"]
            for a in announ:
                title = a["announcementTitle"]
                isBan = False
                for b in ban:
                    if title.find(b) != -1:
                        isBan = True  # 查找到禁用字符串
                        break
                if isBan:
                    continue    # 跳过该文件
                info = []
                info.append(a["adjunctUrl"])
                info.append(a["announcementTime"])
                info.append(a["announcementTitle"])
                self.data.append(info)

    # 创建http连接  获取Json字符串
    # ！ 去掉 'accept-encoding': "gzip, deflate", 解除加密
    # ！ 去掉 'content-length' 避免计算长度
    def httpConnect(self, column, plate, platename, key):
        conn = http.client.HTTPConnection("www.cninfo.com.cn")

        payload = (
            "pageNum=1&pageSize=50&tabName=fulltext&column="
            + column
            + "&stock="
            + self.code
            + "%2C"
            + self.orgId
            + "&searchkey=" + parse.quote(key) + "%3B&secid=&plate="
            + plate
            + "&category=&trade=&seDate=2000-01-01+~+2099-03-01"
        )

        headers = {
            "accept": "application/json, text/javascript, */*; q=0.01",
            "accept-language": "zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6",
            "connection": "keep-alive",
            "host": "www.cninfo.com.cn",
            "origin": "http://www.cninfo.com.cn",
            "referer": "http://www.cninfo.com.cn/new/disclosure/stock?orgId="
            + self.orgId
            + "&stockCode="
            + self.code,
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36",
            "x-requested-with": "XMLHttpRequest",
            "content-type": "application/x-www-form-urlencoded",
            "cache-control": "no-cache",
        }

        conn.request("POST", "/new/hisAnnouncement/query", payload, headers)
        try:
            res = conn.getresponse()
            data = res.read()
            self.jsonMessage = data.decode("utf-8")
            return
        except ConnectionResetError:
            print("注意: Http连接错误，" + self.name + "，" + platename)
            os.system("pause")
        self.jsonMessage = None


def main():
    print(parse.quote("重大事项"))

if __name__ == "__main__":
    main()