mooc-parser/process_mooc.py at main · lxydiy/mooc-parser · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
import json
import sys
import csv
import os

def process_json_to_csv(json_str, output_file="exam_results.csv"):
    try:
        data = json.loads(json_str)
        result = data.get("result", {})

        # 1. 建立题目和选项的映射字典
        # { qid: { "title": "...", "type": "...", "options": {opt_id: content} } }
        question_map = {}
        type_desc = {1: "单选", 2: "多选", 4: "判断"}

        for q in result.get("objectiveQList", []):
            qid = q["id"]
            q_type = type_desc.get(q["type"], f"未知({q['type']})")
            title = q["plainTextTitle"].strip()

            opts = {}
            opt_id_to_letter = {}
            if q.get("optionDtos"):
                for idx, opt in enumerate(q["optionDtos"]):
                    opts[opt["id"]] = opt["content"].replace("<p>", "").replace("</p>", "").strip()
                    opt_id_to_letter[opt["id"]] = chr(ord('A') + idx)

            question_map[qid] = {
                "title": title,
                "type": q_type,
                "options": opts,
                "score": q.get("score", 0),
                "opt_id_to_letter": opt_id_to_letter
            }

        # 2. 解析我的答案并准备写入行
        rows = []
        my_total_score = result.get("objectiveScore", 0)
        potential_total_score = sum(q.get("score", 0) for q in result.get("objectiveQList", []))
        score_diff = potential_total_score - my_total_score

        for ans in result.get("answers", []):
            qid = ans["qid"]
            if qid not in question_map:
                continue

            q_info = question_map[qid]
            # 获取所有选项原文（最多4个）
            opt_contents = list(q_info["options"].values())
            # 补齐4列选项
            while len(opt_contents) < 4:
                opt_contents.append("")

            # 获取我的选项原文
            my_opts = [q_info["options"].get(oid, "未知ID") for oid in ans.get("optIds", [])]
            my_ans_str = "|".join(my_opts)

            # 获取我的选项字母
            my_letters = [q_info["opt_id_to_letter"].get(oid, "?") for oid in ans.get("optIds", [])]
            my_letters_str = "".join(my_letters)

            rows.append([
                q_info["title"],
                q_info["type"],
                opt_contents[0],
                opt_contents[1],
                opt_contents[2],
                opt_contents[3],
                my_ans_str,
                my_letters_str
            ])

        # 3. 写入 CSV (追加模式)
        file_exists = os.path.isfile(output_file)
        with open(output_file, 'a', newline='', encoding='utf-8-sig') as f:
            writer = csv.writer(f)
            # 如果是新文件，写入表头
            if not file_exists:
                writer.writerow(["题目", "类型", "选项1", "选项2", "选项3", "选项4", "我的选项", "选择"])

            writer.writerows(rows)
            # 最后追加一行分数差
            writer.writerow([f"测验分数差：{score_diff}", "", "", "", "", "", "", ""])

        print(f"成功转换并追加到 {output_file}")
    except Exception as e:
        print(f"解析错误: {e}")

def main():
    print("请输入JSON数据（连续两个空行结束输入）：")
    content = ""
    empty_line_count = 0

    while True:
        line = sys.stdin.readline()
        if not line:
            break
        if line.strip() == "":
            empty_line_count += 1
        else:
            empty_line_count = 0

        content += line
        if empty_line_count >= 1:
            break

    if content.strip():
        process_json_to_csv(content)

if __name__ == "__main__":
    while True:
        main()