Python+BeautifulSoup实现网络教学平台学生测试题导出

又到期末考试了，需要做问卷星来复习了。
但是网络教学平台上的题太多了，没办法写了个脚本来提取。
通过此脚本生成的excel，可以直接导入问卷星生成问卷。

1. 使用步骤

1. 登录网络教学平台
2. F12 打开开发者工具->Application->cookie

4. 找到 JSESSIONID 这个字段，把他的值复制下来。然后把代码中的JSEESIONID替换成你的

s = requests.get(url, headers={
	'cookie': 'JSESSIONID=2820553AF02867CBE9DB35273D032158'# 这里=后面的替换成你的sessionid
})

4. 安装 pandas, requests, BeautifulSoup依赖

pip install beautifulsoup4 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pandas -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install requests -i https://pypi.tuna.tsinghua.edu.cn/simple

5. 复制你要爬取的测试结果页面（注意是结果页面！！就是已经答完，可以查看答案的那种结果页面）的URL网址，把测试名也带上去

fetch_all([
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=84246354', '第二章测试题'),
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=85256551', '第三章测试题'),
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91007573', '第五章测试'),
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91008411', '第六章测试'),
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91251387', '第七章测试'),
('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91318025', '8237和DAC0832测试'),
])

2. 完整代码

import time

import pandas as pd
import requests
from bs4 import BeautifulSoup


def right_answer_convert(option_list: list):
    index_list = [i for i, item in enumerate(option_list) if '答案' in item]
    answer_tag_text = option_list[index_list[0]]
    for _ in index_list:
        option_list.remove(answer_tag_text)
    ret_answer = []
    for i, item in enumerate(index_list):
        ret_answer.append(chr(ord('A') + item - i - 1))
    return ''.join(ret_answer)


def fetch_one(url, save_file=''):
    s = requests.get(url, headers={
        'cookie': 'JSESSIONID=D916E34E743A99701B33AC73CDE3F6ED',
        'User-Agent':'Mozilla/5.0(iPhone;U;CPUiPhoneOS4_3_3likeMacOSX;en-us)AppleWebKit/533.17.9(KHTML,likeGecko)Version/5.0.2Mobile/8J2Safari/6533.18.5'
    })
    soup = BeautifulSoup(s.text, 'html.parser')
    question_raw_list = soup.find_all('div', class_='test_checkq_question_editorWrapper')
    ret_list = []
    for question_raw in question_raw_list:
        each_question = dict()
        each_question['type'] = '单选'
        each_question['title'] = question_raw.find('div', class_='title').text.strip()
        question_option = question_raw.find('div', class_='item')
        # print(question_option)
        if question_option is None:

            each_question['answer'] = question_raw.find('div', class_='rightAnswer_body').text.strip()
            print(each_question['answer'])
            if each_question['answer'] in ['T', 'F']:
                each_question['type'] = '判断题'
                each_question['answer'] = each_question['answer'].replace('T', '对').replace('F', '错')
                each_question['option'] = ['对', '错']
            else:
                each_question['type'] = '简答题'

        else:
            question_option = question_raw.find('div', class_='item').find_all('span')
            each_question['option'] = list(map(lambda x: x.get_text(), question_option))
            each_question['answer'] = right_answer_convert(each_question['option'])
            each_question['option'] = list(filter(lambda x: '答案' not in x, each_question['option']))
            each_question['type'] = '单选题' if len(each_question['answer']) == 1 else '多选题'
        ret_list.append(each_question)

    col_name_list = ['题型', '题目', '选项1', '选项2', '选项3', '选项4', '选项5', '正确答案', '答案解析', '分值']
    df = pd.DataFrame(columns=col_name_list)
    for i in ret_list:
        template = {
            '题型': i['type'],
            '题目': i['title'],
            '正确答案': i['answer'],
            '答案解析': '',
            '分值': '1'
        }
        if i['type'] not in ['判断题', '简答题']:
            for j, item in enumerate(i['option']):
                template['选项' + str(j + 1)] = item


        # df = df.append(template, ignore_index=True)
        df = pd.concat([df, pd.DataFrame(template, index=[0])], ignore_index=True)

    timestamp = str(int(time.mktime(time.localtime(time.time()))))
    df.to_excel('{}_{}.xlsx'.format(save_file, timestamp), index=False)
    # print(df)


def fetch_all(url_list):
    for i in url_list:
        fetch_one(i[0], i[1])

if __name__ == '__main__':
    fetch_all([
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=84246354', '第二章测试题'),
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=85256551', '第三章测试题'),
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91007573', '第五章测试'),
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91008411', '第六章测试'),
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91251387', '第七章测试'),
        ('https://eplat.imau.edu.cn/meol/test/stuQtestResult.do?testId=91318025', '8237和DAC0832测试'),
    ])