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]
-    print(f"Questions with <2 options: {len(bad)}")
-    
-    with open(output_json_path, 'w', encoding='utf-8') as f:
-        json.dump(questions, f, ensure_ascii=False, indent=2)
+    for out_path in output_json_paths:
+        os.makedirs(os.path.dirname(os.path.abspath(out_path)), exist_ok=True)
+        with open(out_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)
+