PdfProcessing/extract_table.py

import pandas as pd
import pdfplumber
import re
from datetime import datetime

import tabula

ALLOWED_EXTENSIONS = {'pdf'}


def allowed_file(filename):
    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS


def safe_filename(filename):
    """生成安全的文件名，同时保留中文"""
    # 保留中文、字母、数字、下划线和点
    keep_chars = (' ', '.', '_', '-')
    filename = "".join(c for c in filename if c.isalnum() or c in keep_chars).rstrip()
    return filename


def get_pdf_page_count(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        page_count = len(pdf.pages)
    return page_count


def extract_temp_time(pdf_path):
    """第一种处理方法：基于文本分割的提取"""
    cleaned_data = []
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text = page.extract_text()
            if text:
                text_list = text.split("\n")
                for txt in text_list:
                    if ("历史数据表" not in txt) and ("时间" not in txt):
                        foo = [p for p in re.split(r'\s{1,}', txt.strip()) if p]
                        if len(foo) < 5:
                            print(foo)
                            continue
                        date_time, name, ids, temp, humi = foo[0] + " " + foo[1], foo[2], foo[3], foo[4], foo[5]
                        if foo[5] == "--":
                            humi = ""
                        cleaned_data.append([date_time, name, ids, temp, humi])

    df = pd.DataFrame(
        cleaned_data,
        columns=['时间', '名称', '编号', '温度', '湿度']
    )
    df = df.sort_values('时间').reset_index(drop=True)
    return df


def extract_pdf_table_to_excel(pdf_path):
    """第二种处理方法：基于表格提取"""
    cleaned_data = []
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages[2:]:
            tables = page.extract_table()
            if tables:
                if len(tables) >= 2:
                    for table in tables[1:]:
                        for row in table:
                            for cell in row.split('\n'):
                                foo = str(cell).strip().split("   ")
                                if len(foo) == 4:
                                    date_time, temp, humi = foo[0].replace("/", "-") + " " + foo[1], foo[2], foo[3]
                                    # 拆分日期和时间
                                    cleaned_data.append([date_time, temp, humi])

    result_df = pd.DataFrame(
        cleaned_data,
        columns=['时间', '温度', '湿度']
    )
    result_df = result_df.sort_values('时间').reset_index(drop=True)
    return result_df


def extract_temp_by_datetime_pattern(pdf_path):
    """第三种处理方法：基于日期时间模式和温度符号的提取"""
    all_data = []
    datetime_pattern = re.compile(r'\d{4}-\d{2}-\d{2} \d{2}:\d{2}')

    with pdfplumber.open(pdf_path) as pdf:
        # 从第二页开始处理（索引1）
        for page in pdf.pages[1:]:
            text = page.extract_text()
            if not text:
                continue

            lines = text.split('\n')

            for line in lines:
                # 检查行是否包含日期时间格式和温度符号
                if datetime_pattern.search(line) and '℃' in line:
                    parts = line.split()
                    if len(parts) >= 3:
                        # 提取时间部分
                        time_str = ' '.join(parts[:2])
                        try:
                            # 转换为datetime对象
                            time = datetime.strptime(time_str, '%Y-%m-%d %H:%M')
                            # 提取温度值（去掉℃符号）
                            temp_str = parts[2].replace('℃', '')
                            try:
                                # 添加到数据列表
                                all_data.append({'时间': time, '温度': temp_str})
                            except ValueError:
                                continue
                        except ValueError:
                            continue

                    if len(parts) >= 6:
                        # 提取时间部分
                        time_str = ' '.join(parts[3:5])
                        try:
                            # 转换为datetime对象
                            time = datetime.strptime(time_str, '%Y-%m-%d %H:%M')
                            # 提取温度值（去掉℃符号）
                            temp_str = parts[5].replace('℃', '')
                            try:
                                # 添加到数据列表
                                all_data.append({'时间': time, '温度': temp_str})
                            except ValueError:
                                continue
                        except ValueError:
                            continue

    df = pd.DataFrame(all_data, columns=['时间', '温度'])
    df = df.sort_values('时间').reset_index(drop=True)
    return df