优化注释和 README

Author: lc6464

README.md

@@ -1,6 +1,21 @@
-# Python 验证码识别
+# 图形验证码识别系统
+- 由 Python 编写
+- 超级简单
+- 不怎么靠谱
+- 不建议用于生产环境
 
-> 由 Python 编写的超级简单的不怎么靠谱的验证码识别系统
+## 原理
+- 使用 `PIL` 处理验证码图片
+- 使用 ORC 方式识别验证码
+  - `pytesseract`
 
-- 使用 PIL 处理验证码图片
-- 使用 ORC 方式识别验证码
+
+## 文件
+- `program.py`：程序文件
+  - `class GetCode`
+  - `dict headers`
+  - 75行在生产环境下请删除或注释掉
+- `test.py`：测试文件
+  - 针对 [http://chaxun.heyuanedu.cn:88/](http://chaxun.heyuanedu.cn:88/ "http://chaxun.heyuanedu.cn:88/") 系统的测试
+  - 靠运气和大量尝试来尝试验证码
+  - 图片储存至 image/

program.py

@@ -10,50 +10,50 @@
 
 class GetCode:
 	def __init__(self, path, url=None, headers=headers, origin='chaxun.heyuanedu.cn:88', threshold=185): # 初始化对象实例
-		self.path = path
+		self.path = path # 赋值变量
 		self.url = url
 		self.headers = headers
 		self.origin = origin
 		self.threshold = threshold
 
 	def getReq(self, url=None, headers=None, origin='chaxun.heyuanedu.cn:88'): # 获取 Request 对象
-		self.url = url if url != None else self.url
+		self.url = url if url != None else self.url # 赋值变量
 		self.headers = headers if headers != None else self.headers
 		self.origin = origin if origin != None else self.origin
-		return Request(self.url, None, self.headers, self.origin)
+		return Request(self.url, None, self.headers, self.origin) # 返回 Request 对象
 
 	def setting(self, path=None, url=None, headers=None, origin=None, threshold=None): # 设置实例的各类变量
-		self.path = path if path != None else self.path
+		self.path = path if path != None else self.path # 赋值变量
 		self.url = url if url != None else self.url
 		self.headers = headers if headers != None else self.headers
 		self.origin = origin if origin != None else self.origin
 		self.threshold = threshold if threshold != None else self.threshold
 
 	def getSession(self, url=None, headers=None, origin=None): # 获取对应系统的 Session ，注意：请勿重复调用！否则将可能导致不可预知的问题！
-		self.url = url if url != None else self.url
+		self.url = url if url != None else self.url # 赋值变量
 		self.headers = headers if headers != None else self.headers
 		self.origin = origin if origin != None else self.origin
-		self.headers['Cookie'] = urlopen(self.getReq()).info()['Set-Cookie'].split(';')[0]
-		return self.headers
+		self.headers['Cookie'] = urlopen(self.getReq()).info()['Set-Cookie'].split(';')[0] # 写入 Cookie（无法处理多个 Cookies 的情况！如果重复调用也可能导致出现问题）（其实就是因为我懒）
+		return self.headers # 返回 headers
 
 	def download(self, url=None, path=None, headers=None, origin=None): # 下载验证码图片
-		self.url = url if url != None else self.url
+		self.url = url if url != None else self.url # 赋值变量
 		self.path = path if path != None else self.path
 		self.headers = headers if headers != None else self.headers
 		self.origin = origin if origin != None else self.origin
 		if not os.path.exists(self.path[:self.path.rfind(os.sep)]): # 防止目录不存在出错
-			os.mkdir(self.path[:self.path.rfind(os.sep)])
-		with open(self.path, 'wb') as f:
-			size = f.write(urlopen(self.getReq()).read())
-		return size
+			os.mkdir(self.path[:self.path.rfind(os.sep)]) # 创建目录
+		with open(self.path, 'wb') as f: # 开文件
+			size = f.write(urlopen(self.getReq()).read()) # 写文件（图片）
+		return size # 返回文件大小
 
 	def identify(self, path=None, threshold=None): # 识别验证码
-		self.path = path if path != None else self.path
+		self.path = path if path != None else self.path # 赋值变量
 		self.threshold = threshold if threshold != None else self.threshold
-		image = Image.open(self.path)
-		pixdata = image.load()
-		w, h = image.size
-		for y in range(h): # 处理多余色彩
+		image = Image.open(self.path) # PIL 打开图片
+		pixdata = image.load() # 载入图片到变量
+		w, h = image.size # 获取宽高
+		for y in range(h): # 处理色彩
 			for x in range(w):
 				if pixdata[x, y][0] < self.threshold and pixdata[x, y][1] < self.threshold and pixdata[x, y][2] < self.threshold:
 					pixdata[x, y] = (0, 0, 0)

test.py

@@ -7,32 +7,29 @@
 import re, os
 
 ele0 = ''
-p = re.compile(r'(\d)[^0-9]*(\d)[^0-9]*(\d)[^0-9]*(\d)') # 此系统验证码正则
+p = re.compile(r'(\d)[^0-9]*(\d)[^0-9]*(\d)[^0-9]*(\d)') # 验证码正则
 
 getCode = GetCode('image%scode.png'%os.sep, 'http://chaxun.heyuanedu.cn:88/validatecode.php?act=getimg') # 实例化对象
 getCode.getSession() # 获取 Session
 
 userName = input('姓名：')
 identity = input('准考证号：')
 
-while ele0 == '': # 识别通过正则但错误循环
+while ele0 == '': # 通过正则但错误
 	result2 = None
-	while result2 == None: # 识别无法通过正则循环
-		#time.sleep(0.2)
+	while result2 == None: # 无法通过正则  #time.sleep(0.2)
 		print('Downloading...')
-		getCode.download()
+		getCode.download() # 下载验证码
 		print('Identifying...')
-		result = getCode.identify()
-		result2 = ('%s%s%s%s'%p.search(result).groups() if p.search(result) != None else None)
-		result0 = (result2 if result2 != None else result) if result != '' else 'failure!'
+		result = getCode.identify() # 识别
+		result2 = ('%s%s%s%s'%p.search(result).groups() if p.search(result) != None else None) # 正则判断
+		result0 = (result2 if result2 != None else result) if result != '' else 'failure!' # 识别结果
 		print('Result: ' + result0)
 
 	req = Request('http://chaxun.heyuanedu.cn:88/search.php', urlencode({ 'userName': userName, 'identity': identity, 'code': result0 }).encode(), headers, 'chaxun.heyuanedu.cn:88')
 	res = urlopen(req) # 获取结果
-	html = res.read().decode()
-	#print(res.headers)
-	#print(html)
+	html = res.read().decode() # 获取结果  #print(res.headers) #print(html)
 	soup = BeautifulSoup(html,'lxml') # 解析 html
-	ele = soup.select('#printGrade')
-	ele0 = str(ele)[1:-1]
+	ele = soup.select('#printGrade') # 获取相应元素
+	ele0 = str(ele)[1:-1] # 获取结果(str)
 	print(ele0 if ele0 != '' else 'Error!')