From f95df9b93857c03900defe911489d24f68ad24df Mon Sep 17 00:00:00 2001
From: JesterHey <144512889+JesterHey@users.noreply.github.com>
Date: Mon, 4 Dec 2023 13:05:34 +0800
Subject: [PATCH] =?UTF-8?q?=E7=88=AC=E8=99=AB=E7=9B=B8=E5=85=B3?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 get_params.py | 122 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 122 insertions(+)
 create mode 100644 get_params.py

diff --git a/get_params.py b/get_params.py
new file mode 100644
index 0000000..c6d47ce
--- /dev/null
+++ b/get_params.py
@@ -0,0 +1,122 @@
+'''
+本模块用于获取作业的参数，包括：
+1、关卡数
+2、每关的参数
+    a:任务描述
+    b:编程要求
+    c:编辑器中的所有代码
+3、课程id,实训id
+4、写入本地json文件中
+'''
+
+#导入所需模块
+import json
+from selenium.webdriver import Chrome
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+import re
+from lxml import etree
+import time
+import requests
+#配置参数
+opt = Options()
+opt.add_experimental_option('detach', True)
+chrome_driver = 'D:\ChromeDownload\chromedriver-win64\chromedriver-win64'
+#以下部分在发行版本需要优化UI
+# url = input('请输入作业中任意一关的网址：')
+# user_name = input('请输入用户名：')
+# password = input('请输入密码：')
+url = 'https://www.educoder.net/tasks/27V4D95N/1191515/vmxpzae734bj?coursesId=27V4D95N'
+user_name = 'hnu202311020126'
+password = 'hzy123456'
+safari = Chrome()
+safari.get(url)
+time.sleep(5) #等待页面加载
+#模拟登录
+safari.find_element(By.ID, 'login').send_keys(user_name)
+safari.find_element(By.ID, 'password').send_keys(password)
+safari.find_element(By.ID, 'password').send_keys(Keys.ENTER)
+time.sleep(4)
+#获取cookie，User-Agent
+Cookie = safari.get_cookies()
+User_Agent = safari.execute_script('return navigator.userAgent')
+cookie = f'autologin_trustie={Cookie[1]["value"]}; _educoder_session={Cookie[0]["value"]}'
+#获取关卡数
+#点击展开关卡页面
+safari.find_element(By.XPATH,'//*[@id="task-left-panel"]/div[1]/a[1]').click()
+time.sleep(2)
+#关卡数量由 class = "flex-container challenge-title space-between" 的元素数量决定
+htmltxt = safari.page_source
+html = etree.HTML(htmltxt)
+task_num = html.xpath('count(//*[@class="flex-container challenge-title space-between"])')
+task_num = int(task_num)
+#关闭关卡页面
+safari.find_element(By.XPATH,'//*[@id="task-left-panel"]/div[3]/div[1]').click()
+#对于每一关，获取参数
+#每一关的参数由以下元素组成：
+'''
+/html/body/div[1]/div/div/div/div[2]/section[1]/div[3]/div[3]/div/div/div/div/div[3]/div[1]/a
+/html/body/div[1]/div/div/div/div[2]/section[1]/div[3]/div[3]/div/div/div/div/div[4]/div[1]/a
+'''
+obj1 = re.compile(r'<h3 id="任务描述">任务描述</h3><p>(?P<describe>.*?)</p>',re.S)
+obj2 = re.compile(r'<h3 id="编程要求">编程要求</h3><p>(?P<require>.*?)</p>',re.S)
+#初始化一个总的json文件，名称为课程的id，这一部分等会实现
+total = {}
+#另外，目前好像只有实训作业有这些参数，其他的作业例如编程作业就没有，所以先判断一下是否为实训作业
+# def is_practice():
+#     try:
+#         safari.find_element(By.XPATH,'//*[@id="task-left-panel"]/div[1]/a[1]')
+#         return True
+#     except BaseException:
+#         return False
+i=1
+try:
+    while i <= task_num:
+        safari.find_element(By.XPATH, '//*[@id="task-left-panel"]/div[1]/a[1]').click()
+        time.sleep(2)
+        safari.find_element(By.XPATH,f'/html/body/div[1]/div/div/div/div[2]/section[1]/div[3]/div[3]/div/div/div/div/div[{i}]/div[1]/a').click()
+        time.sleep(4)
+        #获取课程id -> 根据url中?前面的，最后一个/后面的那部分参数构造请求，同时，似乎还需要用到cookie，User-Agent和Referer参数，这些统一用selenium在登陆后获取并组装成headers
+        #获取cookie，User-Agent和Referer
+        cur_url=Referer = safari.current_url
+        identity = cur_url.split('/')[-1].split('?')[0]
+        id_url = f'https://data.educoder.net/api/tasks/{identity}.json?'
+        #获取课程id
+        headers = {
+            'Cookie':cookie,
+            'User-Agent':User_Agent,
+            'Referer':Referer
+        }
+        try:
+            response = requests.get(url=id_url,headers=headers)
+            challenge_id = dict(response.json())['challenge']['id']
+            shixun_id = dict(response.json())['challenge']['shixun_id']
+        except BaseException:
+            print('获取课程id失败')
+        #获取任务描述(如果存在的话)
+        page_source = safari.page_source
+        describe = obj1.findall(page_source)
+        #获取编程要求(如果存在的话)
+        require = obj2.findall(page_source)
+        #获取编辑器中的代码,由于代码都是class = "view-line"的div,先找到所有class = "view-line"的div，获取其中的所有文本，再把不同行的代码用\n连接起来
+        code = safari.find_elements(By.CLASS_NAME,'view-line')
+        code = '\n'.join([i.text for i in code])
+
+        #把参数存入字典，再转换为json格式
+        task = {
+            'describe':describe[0] if len(describe) != 0 else '',
+            'require':require[0] if len(require) != 0 else '',
+            'code':code,
+            'verified': False #这个参数是用来标记答案是否被用户认证为正确答案的，初始值为False
+        }
+        #把每一关的参数存入总的字典中
+        total[challenge_id] = task
+        #去往下一关
+        i += 1
+except BaseException:
+    print('获取参数失败')
+#把参数写入本地json文件中，文件名字与实shixun_name相同键为course_id，值为一个列表，列表中每个元素为一个字典，字典中包含每一关的参数
+#这些数据都是将要上传到云端的，为防止每次运行程序都覆盖了，需要改写写入文件的逻辑
+with open(f'{shixun_id}.json','w',encoding='utf-8') as f:
+    json.dump(total,f,ensure_ascii=False,indent=4)