add：新增第2种提取表格的方式

app.py

@@ -9,7 +9,7 @@ from flask import Flask, request, jsonify, send_file
 from add_signature import find_signature_positions, add_signature_to_pdf
 from add_watermark import add_watermark_to_pdf
 from extract_table import extract_temp_time, extract_pdf_table_to_excel, extract_temp_by_datetime_pattern, allowed_file, \
-    safe_filename
+    safe_filename, extract_temperature_data_from_pdf
 from lib import Qiniu
 from werkzeug.utils import secure_filename
 from flask_cors import CORS
@@ -130,6 +130,8 @@ def extract_table():
                     df = extract_temp_time(filepath)
                 if "设备汇总报告" in text:
                     df = extract_temp_by_datetime_pattern(filepath)
+                if "详细数据" in text:
+                    df = extract_temperature_data_from_pdf(filepath)
 
         if df is None:
             os.remove(filepath)

extract_table.py

@@ -131,3 +131,30 @@ def extract_temp_by_datetime_pattern(pdf_path):
     df = pd.DataFrame(all_data, columns=['时间', '温度'])
     df = df.sort_values('时间').reset_index(drop=True)
     return df
+
+def extract_temperature_data_from_pdf(pdf_path):
+    """
+    从PDF文件中提取时间和温度数据
+    """
+    all_data = []
+
+    with pdfplumber.open(pdf_path) as pdf:
+        for page in pdf.pages:
+            text = page.extract_text()
+
+            # 使用正则表达式匹配数据行
+            # 匹配模式: 序号 | 日期时间 | 温度 | 状态
+            for value in text.split("\n"):
+                pattern = r'(\d+)\s+(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})\s+(-?\d+\.\d+|-?\d+)\s+([^\s]+)'
+                matches = re.findall(pattern, value)
+                for match in matches:
+                    index, datetime_str, temperature, status = match
+                    all_data.append({
+                        '时间': datetime_str,
+                        '温度': temperature,
+                    })
+    # 转换为DataFrame
+    df = pd.DataFrame(all_data, columns=['时间', '温度'])
+    # 按时间排序
+    df = df.sort_values('时间').reset_index(drop=True)
+    return df