pip install spire.pdf.free openpyxl

from spire.pdf.common import *
from spire.pdf import *

# 創(chuàng)建PdfDocument對(duì)象
doc = PdfDocument()

# 加載PDF文件
doc.LoadFromFile("C:\Users\Administrator\Desktop\input.pdf")

# 設(shè)置XLSX布局轉(zhuǎn)換選項(xiàng)
options = XlsxLineLayoutOptions(False, False, False, True, False)

# 應(yīng)用轉(zhuǎn)換選項(xiàng)到文檔
doc.ConvertOptions.SetPdfToXlsxOptions(options)

# 將文檔保存為XLSX文件
doc.SaveToFile("output/ToExcel.xlsx", FileFormat.XLSX)

# 關(guān)閉文檔
doc.Close()

from spire.pdf import *
from openpyxl import Workbook
from openpyxl.utils import get_column_letter

# 創(chuàng)建PdfDocument對(duì)象
doc = PdfDocument()

# 加載PDF文件
doc.LoadFromFile("C:/Users/Administrator/Desktop/AI.pdf")

# 為PDF文檔設(shè)置表格提取器
extractor = PdfTableExtractor(doc)

# 創(chuàng)建新的Excel工作簿并移除默認(rèn)工作表
workbook = Workbook()
workbook.remove(workbook.active)

# 逐頁(yè)從PDF中提取表格
for page_index in range(doc.Pages.Count):
    tables = extractor.ExtractTable(page_index)
    for t_index, table in enumerate(tables):
        # 為每個(gè)提取的表格創(chuàng)建新工作表
        sheet = workbook.create_sheet(title=f"第{page_index+1}頁(yè)_表{t_index+1}")

        # 初始化列表，記錄各列的最大長(zhǎng)度
        max_lengths = [0] * table.GetColumnCount()

        for row in range(table.GetRowCount()):
            for col in range(table.GetColumnCount()):
                # 獲取單元格文本，清理后寫入Excel工作表
                text = table.GetText(row, col).replace("\n", " ").strip()
                sheet.cell(row=row + 1, column=col + 1, value=text)

                # 更新列的最大長(zhǎng)度
                max_lengths[col] = max(max_lengths[col], len(text))

        # 根據(jù)最大長(zhǎng)度自動(dòng)調(diào)整列寬
        for col in range(table.GetColumnCount()):
            adjusted_width = (max_lengths[col] + 2)  # 添加適當(dāng)邊距
            sheet.column_dimensions[get_column_letter(col + 1)].width = adjusted_width

# 保存工作簿到Excel文件
workbook.save("output/TableData.xlsx")