之前研究了一下OpenCD的签到方式，签到地址是这个，可以自行查看并分析其逻辑

1
https://open.cd/plugin_sign-in.php

界面逻辑还是很简单的，另外验证码也很干净

那么我们只需要用到自建的ddddocr-fastapi+脚本就能做到自动识别验证码后签到了，存档一下完整代码：

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
104
105
106
import base64
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

BASE_URL = "https://open.cd/"
SIGNIN_PAGE = "plugin_sign-in.php"
SIGNIN_POST = "plugin_sign-in.php?cmd=signin"
#自己填OCR服务，用的ddddocr-fastapi
OCR_API = "http://127.0.0.1:8000/ocr"

HEADERS = {
    # 自己填
}

COOKIES = {
    # 自己填
}

def get_imagehash_and_img(session):
    r = session.get(urljoin(BASE_URL, SIGNIN_PAGE))
    r.raise_for_status()

    soup = BeautifulSoup(r.text, "lxml")

    imagehash = soup.find("input", {"name": "imagehash"})["value"]
    img_src = soup.find("img")["src"]

    img_url = urljoin(BASE_URL, img_src)
    return imagehash, img_url

def download_captcha(session, img_url):
    r = session.get(img_url)
    r.raise_for_status()
    return r.content

def image_to_base64(img_bytes):
    # print(base64.b64encode(img_bytes).decode("utf-8"))
    return base64.b64encode(img_bytes).decode("utf-8")

def ocr_image(image_b64):
    files = {
        "image": (None, image_b64),
        "probability": (None, "false"),
        "charsets": (None, ""),
        "png_fix": (None, "false"),
    }

    headers = {
        "Accept": "application/json",
    }

    r = requests.post(OCR_API, files=files, headers=headers, timeout=20)
    r.raise_for_status()

    data = r.json()
    if data.get("code") != 200:
        raise RuntimeError(f"OCR failed: {data}")

    return data["data"]

def post_signin(session, imagehash, imagestring):
    data = {
        "imagehash": imagehash,
        "imagestring": imagestring,
    }

    r = session.post(urljoin(BASE_URL, SIGNIN_POST), files={
    "imagehash": (None, imagehash),
    "imagestring": (None, imagestring)
})
    print(data)
    # print(r.request.headers)
    # print(r.request.body)
    r.raise_for_status()
    return r.text

def main():
    session = requests.Session()
    session.headers.update(HEADERS)
    session.cookies.update(COOKIES)

    max_retry = 5

    for i in range(max_retry):
        print(f"[*] 第 {i+1} 次尝试")

        imagehash, img_url = get_imagehash_and_img(session)
        img_bytes = download_captcha(session, img_url)
        img_b64 = image_to_base64(img_bytes)
        imagestring = ocr_image(img_b64)

        result_html = post_signin(session, imagehash, imagestring)

        if "验证码错误" not in result_html:
            print("[✓] 成功")
            return
        else:
            print("[!] 验证码错误，重试")

    print("[✗] 多次尝试失败")


if __name__ == "__main__":
    main()