feat: 实现获取验证码完成

Author: juwenzhang

DealVerificationCode/__pycache__/Paddelocr_learn.cpython-38.pyc

@@ -0,0 +1,66 @@
+#!/usr/bin/env python
+# coding:utf-8
+
+import requests
+from hashlib import md5
+
+class Chaojiying_Client(object):
+
+    def __init__(self, username, password, soft_id):
+        self.username = username
+        password =  password.encode('utf8')
+        self.password = md5(password).hexdigest()
+        self.soft_id = soft_id
+        self.base_params = {
+            'user': self.username,
+            'pass2': self.password,
+            'softid': self.soft_id,
+        }
+        self.headers = {
+            'Connection': 'Keep-Alive',
+            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
+        }
+
+    def PostPic(self, im, codetype):
+        """
+        im: 图片字节
+        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
+        """
+        params = {
+            'codetype': codetype,
+        }
+        params.update(self.base_params)
+        files = {'userfile': ('ccc.jpg', im)}
+        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
+        return r.json()
+
+    def PostPic_base64(self, base64_str, codetype):
+        """
+        im: 图片字节
+        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
+        """
+        params = {
+            'codetype': codetype,
+            'file_base64':base64_str
+        }
+        params.update(self.base_params)
+        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, headers=self.headers)
+        return r.json()
+
+    def ReportError(self, im_id):
+        """
+        im_id:报错题目的图片ID
+        """
+        params = {
+            'id': im_id,
+        }
+        params.update(self.base_params)
+        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
+        return r.json()
+
+
+if __name__ == '__main__':
+    chaojiying = Chaojiying_Client('', '', '')	#用户中心>>软件ID 生成一个替换 96001
+    im = open('a.jpg', 'rb').read()													#本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
+    print(chaojiying.PostPic(im, 1004)['pic_str'])										#1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
+    #print chaojiying.PostPic(base64_str, 1902)  #此处为传入 base64代码

DealVerificationCode/__pycache__/__init__.cpython-38.pyc

@@ -0,0 +1,71 @@
+# 开始实现我们的爬取一个 GuShiWen 网站的数据
+import os
+import requests
+from lxml import etree
+from chaojiying_Python.chaojiying import Chaojiying_Client
+
+
+class GetGuShiWenData(object):
+    def __init__(self):
+        self.index_url = "https://www.gushiwen.cn/user/login.aspx?from=http://www.gushiwen.cn/user/collect.aspx"
+        self.headers = {
+            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537."
+                          "36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36",
+        }
+
+    def __del__(self):
+        """
+        析构函数
+        :return:
+        """
+        print("此次爬虫任务完毕...")
+
+    def get_image_url(self):
+        """
+        用来实现获取我们的验证码请求链接网的处理函数
+        :return: f"https://so.gushiwen.cn{response_xml}"
+        """
+        response_html = requests.get(self.index_url, headers=self.headers).text
+        response_xml = etree.HTML(response_html).xpath('//img[@id="imgCode"]/@src')[0]
+        return f"https://so.gushiwen.cn{response_xml}"
+
+    def save_image_data(self, url):
+        """
+        实现的是保存我们爬取的图片连接
+        :param url:
+        :return: img_path
+        """
+        img_data = requests.get(url, headers=self.headers).content
+        img_path = "../get_image/parse_guzhiwen.jpg"
+        if os.path.exists(img_path):
+            with open(img_path, "r+b") as f:
+                f.write(img_data)
+        else:
+            with open(img_path, "w+b") as f:
+                f.write(img_data)
+        return img_path
+
+    def get_image_data(self, path):
+        """
+        实现获取验证码操作
+        :param path:
+        :return: ChaoJiYing.PostPic(img, 1004)['pic_str']
+        """
+        ChaoJiYing = Chaojiying_Client("juwenzhang", "451674jh", '958562')
+        img = open(path, "rb").read()
+        return ChaoJiYing.PostPic(img, 1004)['pic_str']
+
+    def parse_data(self):
+        pass
+
+    def save_dara(self):
+        pass
+
+    def run(self):
+        img_url = self.get_image_url()
+        img_path = self.save_image_data(img_url)
+        self.get_image_data(img_path)
+
+if __name__ == "__main__":
+    getGuShiWenData = GetGuShiWenData()
+    getGuShiWenData.run()