feat: 过滤综合分析题主观题，重新生成客观题库共756题

extract_table.py

@@ -1,14 +1,21 @@
 import json
+import os
 import pdfplumber
 import re
 
-def extract_from_pdf(pdf_path, output_json_path):
+def extract_from_pdf(pdf_path, output_json_paths):
     questions = []
     current_q = None
     global_id = 1
     
     with pdfplumber.open(pdf_path) as pdf:
         for page_num, page in enumerate(pdf.pages):
+            text = page.extract_text() or ""
+            # 当遇到综合分析题或页码超过142页时停止抽取
+            if "大数据工程技术人员技能竞赛综合分析题" in text or page_num >= 142:
+                print(f"在第 {page_num + 1} 页检测到综合分析题或达到客观题边界，停止解析。")
+                break
+
             tables = page.extract_tables()
             for table in tables:
                 for row in table:
@@ -22,7 +29,6 @@ def extract_from_pdf(pdf_path, output_json_path):
                     is_new_q = False
                     if col0.isdigit():
                         is_new_q = True
-                        # q_id = int(col0)
                     
                     title = row[1] if row[1] else ""
                     options_raw = row[2] if row[2] else ""
@@ -30,7 +36,7 @@ def extract_from_pdf(pdf_path, output_json_path):
                     q_answer = row[4] if row[4] else ""
                     source_file = row[5] if len(row) > 5 and row[5] else ""
                     
-                    # Split options
+                    # 拆分选项
                     opts = re.split(r'(?=[A-H][\.、])', options_raw)
                     parsed_options = [opt.strip().replace('\n', '') for opt in opts if opt.strip()]
                     
@@ -44,7 +50,7 @@ def extract_from_pdf(pdf_path, output_json_path):
                             "options": parsed_options,
                             "type": q_type.replace('\n', '').strip(),
                             "answer": q_answer.replace('\n', '').strip(),
-                            "source_id": col0, # keeping original id for reference
+                            "source_id": col0,
                             "page_number": page_num + 1,
                             "source_file": source_file.replace('\n', '').strip()
                         }
@@ -64,13 +70,21 @@ def extract_from_pdf(pdf_path, output_json_path):
         current_q["id"] = global_id
         questions.append(current_q)
         
-    print(f"Extracted {len(questions)} questions via table parsing.")
+    print(f"共提取题目 {len(questions)} 道。")
+    single_count = sum(1 for q in questions if q['type'] == '单选')
+    multi_count = sum(1 for q in questions if q['type'] == '多选')
+    print(f"其中单选 {single_count} 道，多选 {multi_count} 道。")
     
-    bad = [x for x in questions if len(x['options']) < 2]
+    for out_path in output_json_paths:
-    print(f"Questions with <2 options: {len(bad)}")
+        os.makedirs(os.path.dirname(os.path.abspath(out_path)), exist_ok=True)
-    
+        with open(out_path, 'w', encoding='utf-8') as f:
-    with open(output_json_path, 'w', encoding='utf-8') as f:
             json.dump(questions, f, ensure_ascii=False, indent=2)
+        print(f"已保存题库至：{out_path}")
 
 if __name__ == "__main__":
-    extract_from_pdf("d:/code/bigdata/题库.pdf", "d:/code/bigdata/questions.json")
+    targets = [
+        "d:/code/bigdata/questions.json",
+        "d:/code/bigdata/quiz-app/src/questions.json"
+    ]
+    extract_from_pdf("d:/code/bigdata/题库.pdf", targets)
+

questions.json

@@ -11360,106 +11360,18 @@
     "id": 755
   },
   {
-    "title": "下列关于政务数据安全与开放的说法，正确的有____主要内容过车时间、车牌号、车型、车速、方向、卡口编号主要内容断面车流量、平均车速、时间占有率车辆经纬度、线路号、车速；乘客上下车刷卡路段平均速度、拥堵指数（第三方脱敏）天气、降雨量；事故、施工、大型活动plate_no（车牌）",
+    "title": "下列关于政务数据安全与开放的说法，正确的有____",
     "options": [
       "A.国家大力推进电子政务建设，提升运用数据服务经济社会发展的能力",
       "B.国家机关应当建立健全数据安全管理制度，保障政务数据安全",
       "C.国家机关应当按照规定及时、准确地公开所有政务数据",
-      "D.国家构建统一规范、互联互通、安全可控的政务数据开放平台",
+      "D.国家构建统一规范、互联互通、安全可控的政务数据开放平台"
-      "产生/上报方式",
-      "逐车产生“过车事件”",
-      "产生/上报方式",
-      "周期上报“断面指标”",
-      "持续上报/刷卡交易",
-      "第三方接口推送",
-      "接口/人工录入",
-      "vehicle_type（车型）"
     ],
-    "type": "多选上报频率逐 条 （ 高频）上报频率每 1 分钟10～30 秒分钟级不定时speed（车速km/h）",
+    "type": "多选",
-    "answer": "ABD时效要求秒级（实时）时效要求分钟级准实时分钟级准实时/离线pass_time（过车时间）",
+    "answer": "ABD",
     "source_id": "30",
     "page_number": 142,
-    "source_file": "中华人民共和国数据安全法gantry_id（卡口编号）",
+    "source_file": "中华人民共和国数据安全法",
     "id": 756
-  },
-  {
-    "title": "沪A·O12Z3",
-    "options": [
-      "小型客车"
-    ],
-    "type": "45",
-    "answer": "2026-05-3008:15:03",
-    "source_id": "1001",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 757
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "（空）"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1002",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 758
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "小型客车"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1003",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 759
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "小型客车"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1004",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 760
-  },
-  {
-    "title": "沪B·5566F",
-    "options": [
-      "大型货车"
-    ],
-    "type": "263",
-    "answer": "2026-05-3008:14:58",
-    "source_id": "1005",
-    "page_number": 152,
-    "source_file": "G0311",
-    "id": 761
-  },
-  {
-    "title": "（空）含义过车记录流水号车牌号含义车型瞬时车速（km/h）过车时间卡口编号",
-    "options": [
-      "小型客车",
-      "类型",
-      "BIGINT",
-      "STRING",
-      "类型",
-      "STRING",
-      "INT",
-      "TIMESTAMP",
-      "STRING"
-    ],
-    "type": "38是否可空否否是否可空是是否否",
-    "answer": "2026-05-3008:16:10备注主键个人信息，需脱敏管控备注小型客车 /大型货车等合理范围 0～200存在乱序关联卡口点位维表",
-    "source_id": "1006",
-    "page_number": 152,
-    "source_file": "G0311",
-    "id": 762
   }
 ]

quiz-app/src/questions.json

@@ -11360,106 +11360,18 @@
     "id": 755
   },
   {
-    "title": "下列关于政务数据安全与开放的说法，正确的有____主要内容过车时间、车牌号、车型、车速、方向、卡口编号主要内容断面车流量、平均车速、时间占有率车辆经纬度、线路号、车速；乘客上下车刷卡路段平均速度、拥堵指数（第三方脱敏）天气、降雨量；事故、施工、大型活动plate_no（车牌）",
+    "title": "下列关于政务数据安全与开放的说法，正确的有____",
     "options": [
       "A.国家大力推进电子政务建设，提升运用数据服务经济社会发展的能力",
       "B.国家机关应当建立健全数据安全管理制度，保障政务数据安全",
       "C.国家机关应当按照规定及时、准确地公开所有政务数据",
-      "D.国家构建统一规范、互联互通、安全可控的政务数据开放平台",
+      "D.国家构建统一规范、互联互通、安全可控的政务数据开放平台"
-      "产生/上报方式",
-      "逐车产生“过车事件”",
-      "产生/上报方式",
-      "周期上报“断面指标”",
-      "持续上报/刷卡交易",
-      "第三方接口推送",
-      "接口/人工录入",
-      "vehicle_type（车型）"
     ],
-    "type": "多选上报频率逐 条 （ 高频）上报频率每 1 分钟10～30 秒分钟级不定时speed（车速km/h）",
+    "type": "多选",
-    "answer": "ABD时效要求秒级（实时）时效要求分钟级准实时分钟级准实时/离线pass_time（过车时间）",
+    "answer": "ABD",
     "source_id": "30",
     "page_number": 142,
-    "source_file": "中华人民共和国数据安全法gantry_id（卡口编号）",
+    "source_file": "中华人民共和国数据安全法",
     "id": 756
-  },
-  {
-    "title": "沪A·O12Z3",
-    "options": [
-      "小型客车"
-    ],
-    "type": "45",
-    "answer": "2026-05-3008:15:03",
-    "source_id": "1001",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 757
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "（空）"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1002",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 758
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "小型客车"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1003",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 759
-  },
-  {
-    "title": "沪A·88K21",
-    "options": [
-      "小型客车"
-    ],
-    "type": "62",
-    "answer": "2026-05-3008:15:05",
-    "source_id": "1004",
-    "page_number": 152,
-    "source_file": "G0207",
-    "id": 760
-  },
-  {
-    "title": "沪B·5566F",
-    "options": [
-      "大型货车"
-    ],
-    "type": "263",
-    "answer": "2026-05-3008:14:58",
-    "source_id": "1005",
-    "page_number": 152,
-    "source_file": "G0311",
-    "id": 761
-  },
-  {
-    "title": "（空）含义过车记录流水号车牌号含义车型瞬时车速（km/h）过车时间卡口编号",
-    "options": [
-      "小型客车",
-      "类型",
-      "BIGINT",
-      "STRING",
-      "类型",
-      "STRING",
-      "INT",
-      "TIMESTAMP",
-      "STRING"
-    ],
-    "type": "38是否可空否否是否可空是是否否",
-    "answer": "2026-05-3008:16:10备注主键个人信息，需脱敏管控备注小型客车 /大型货车等合理范围 0～200存在乱序关联卡口点位维表",
-    "source_id": "1006",
-    "page_number": 152,
-    "source_file": "G0311",
-    "id": 762
   }
 ]