[Python] 超星学习通作业批量下载

# -*- coding: utf8 -*-
#coder:nianboy
#time:2022-7-14
 
import os
import re
import requests
 
import pandas as pd
 
 
class ChaoXingWork:
    def __init__(self, user, password):
        self.password = password
        self.user = user
        self.work_data_list = []
        self.class_lists = []
        self.headers = {
            "User-agent": "Mozilla/4.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36",
        }
        self.session = requests.session()
 
    def session_token(self):
        login_api = "https://passport2.chaoxing.com/api/login"
        params = {
            "name": self.user,  # 学习通账号
            "pwd": self.password,  # 学习通密码
            "verify": "0",
            "schoolid": "",
        }
        self.session.get(login_api, params=params, headers=self.headers)
 
    def class_list(self):
        class_url = "http://mooc2-ans.chaoxing.com/visit/courses/list?v=1652629452722&rss=1&start=0&size=500&catalogId=0&searchname="
        class_data = self.session.get(url=class_url, headers=self.headers).text.replace(' ', "")
        obj = re.compile(
            r'"color1" href="(?P<src>.*?)".*?break-all;" title="(?P<name>.*?)">.*?<i class="icon-news"></i>', re.S)
        result = obj.finditer(class_data)
        for cx in result:
            dict = {}
            dict['src'] = cx.group("src")
            dict['name'] = cx.group("name")
            self.class_lists.append(dict)
 
    def class_data(self):
        pf = pd.DataFrame(self.class_lists)
        pf.index = pf.index + 1
        del pf['src']
        data_dicts = {
            "name": "课程名称",
        }
        pf.rename(columns=data_dicts, inplace=True)
        print(pf)
        type = int(input("请输入课程序号:"))
        if type == 0:
            for j in self.class_lists:
                src = j['src']
                self.name = j['name']
                self.work_datas(src)
 
        else:
            src = (self.class_lists[int(type) - 1]["src"])
            self.name = (self.class_lists[int(type) - 1]["name"])
            self.work_datas(src)
        try:
            pf = pd.DataFrame(self.work_data_list)
            pf.index = pf.index + 1
            data_dicts = {
                "type" : "文件类型",
                "file_name": "文件名称",
            }
            pf.rename(columns=data_dicts, inplace=True)
            del pf['enc']
            print(pf)
        except:
            print(self.name+"：该课程暂无作业可以下载！")
 
 
 
 
    def work_datas(self, src):
        if not os.path.exists(self.name):
            os.mkdir(self.name)
        class_res = self.session.get(url=src, headers=self.headers).text
        workurl = re.findall(r'title="作业" data-url="(.*?)">', class_res, re.S)[0]
        courseid = re.findall(r'name="courseid" value="(.*?)"/>', class_res, re.S)[0]
        classid = re.findall(r'name="clazzid" value="(.*?)"/>', class_res, re.S)[0]
        workenc = re.findall(r'name="workEnc" value="(.*?)">', class_res, re.S)[0]
        self.work_class_url = workurl + "?courseId=" + courseid + "&classId=" + classid + "&enc=" + workenc
        work_class_url_res = self.session.get(url=self.work_class_url, headers=self.headers).text
        if 'pageNum :' in work_class_url_res:
            pagenum = re.findall(r'pageNum : (.*?),',  work_class_url_res, re.S)[0]
            for i in range(1,int(pagenum)+1):
                self.work_class_urls = workurl + "?courseId=" + courseid + "&classId=" + classid + "&enc=" + workenc + "&pageNum=" + str(i)
                self.class_work_find()
        else:
            self.work_class_urls = workurl + "?courseId=" + courseid + "&classId=" + classid + "&enc=" + workenc + "&pageNum=1"
            self.class_work_find()
 
    def class_work_find(self):
        work_class_url_response = self.session.get(url=self.work_class_urls, headers=self.headers).text
        works_url = re.findall(r'<li(.*?)">', work_class_url_response, re.S)
        for j in works_url:
            page_text = self.session.get(url=j, headers=self.headers).text
            if "span data="" in page_text:
                obj = re.compile(
                    r'<h2 class="mark_title">(?P<name>.*?)</h2>.*?data="(?P<enc>.*?)" type="(?P<type>.*?)"',
                    re.S)
            else:
                obj = re.compile(
                    r'<h2 class="mark_title">(?P<name>.*?)</h2>.*?<p class="attachNew"><em style="font-style:normal; display:block;min-height:2px;"></em><span data="(?P<enc>.*?)" type="(?P<type>.*?)" name=".*?"',
                    re.S)
            class_result = obj.finditer(page_text)
 
            for j in class_result:
                if j.group("enc") == None:
                    print("该课程没有作业")
                else:
                    dict = {}
                    dict['enc'] = j.group("enc")
                    dict['type'] = j.group("type")
                    dict['file_name'] = (j.group("name") + "." + j.group("type")).replace(r"、", ".")
                    self.work_data_list.append(dict)
 
    def download_data(self):
        i = 0
        while i == 0:
            work_nums = int(input("输入0退出程序\n"
                                  "请输入你想下载文件的序号:"))
            if work_nums < 1:
                break
            else:
                work_enc = self.work_data_list[work_nums - 1]['enc']
                work_type = self.work_data_list[work_nums - 1]['type']
                work_name = self.work_data_list[work_nums - 1]['file_name']
                work_url = "https://mooc1.chaoxing.com/ueditorupload/read?objectId=" + work_enc
                headers = {
                    'Referer': self.work_class_url,
                    "User-agent": "Mozilla/4.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36",
                }
                if work_type == 'zip' or work_type == 'rar':
                    work_content = self.session.get(url=work_url, headers=headers, stream=True)
                else:
                    work_res = self.session.get(url=work_url, headers=self.headers).text
                    files_url = re.findall(r'<a class="btnDown" href="(.*?)"><span>', work_res)[0]
                    work_content = self.session.get(url=files_url, headers=headers, stream=True)
                work_path = "./" + self.name + "/" + work_name
                with open(work_path, 'wb') as f:
                    for chunk in work_content.iter_content(1024 * 1024 * 2):
                        f.write(chunk)
                print(work_name+"下载成功！")
 
 
if __name__ == "__main__":
    chaoxing = ChaoXingWork(user="学习通账号", password="学习通密码")
 
    chaoxing.session_token()
    chaoxing.class_list()
    chaoxing.class_data()
    chaoxing.download_data()