当前位置：首页 > news >正文

基于tabula对pdf中多个excel进行识别并转换成word中的优化（五）

news 2025/4/30 6:00:23

优化地方：处理合并的单元格内容。

1、修改为stream="complex"

2、增加换行符f"{table_data[i - 1][j]}\n{table_data[i][j]}".strip()

一、pdf中excel样例

二、完整代码

import tabula
import numpy as np
from docx import Document
from docx.oxml.ns import qn
from docx.oxml import OxmlElement# print("multitab:", tables)# 创建一个新的Word文档
doc = Document()def get_table_data(df_list):multi_table_data = []# 遍历每个表格for table_index, table in enumerate(df_list):table_data = []# 获取行数和列数rows, cols = table.shapeheading_cells = []for col_num, column_name in enumerate(table.columns):heading_cells.append(column_name)table_data.append(heading_cells)for row_index, row in table.iterrows():table_data.append(row.tolist())multi_table_data.append(table_data)return multi_table_datadef handle_table(multitable_data):multi_table_data = []for table_data in multitable_data:for i in range(len(table_data) - 1, 0, -1):if table_data[i][0] in [None, np.nan, ""] or table_data[i][1] in [None,np.nan,"",]:for j in range(len(table_data[i])):if table_data[i][j] not in [None,np.nan,"",]:  # 只有当单元格不为空时才合并table_data[i - 1][j] = f"{table_data[i - 1][j]}\n{table_data[i][j]}".strip()# 删除当前行del table_data[i]multi_table_data.append(table_data)return multi_table_datadef set_cell_borders(cell, border_color="000000", row_height=None):"""设置单元格的边框颜色:param cell: 单元格对象:param border_color: 边框颜色，默认为黑色"""tc = cell._elementtcPr = tc.get_or_add_tcPr()tcBorders = OxmlElement("w:tcBorders")for border_name in ("top", "left", "bottom", "right"):border = OxmlElement(f"w:{border_name}")border.set(qn("w:val"), "single")border.set(qn("w:sz"), "4")  # 边框大小border.set(qn("w:space"), "0")border.set(qn("w:color"), border_color)tcBorders.append(border)tcPr.append(tcBorders)# 设置内容居中显示for paragraph in cell.paragraphs:for run in paragraph.runs:run.font.size = paragraph.style.font.size  # 保持字体大小一致paragraph.alignment = 1  # 1 表示居中对齐# 设置行高if row_height is not None:tr = cell._element.getparent()  # 获取行元素trPr = tr.get_or_add_trPr()trHeight = OxmlElement("w:trHeight")trHeight.set(qn("w:val"), str(row_height))trPr.append(trHeight)def create_table_and_fill_data(tables_data, output_file):"""在 Word 文档中插入表格并填充数据:param data: 表格数据:param output_file: 输出文件路径"""# 创建一个新的 Word 文档doc = Document()for row_index, data in enumerate(tables_data):# 添加一个标题sssdoc.add_heading("测试信息表" + str(row_index), level=1)# 创建表格table = doc.add_table(rows=len(data), cols=len(data[0]))# 填充表格数据for row_index, row_data in enumerate(data):for col_index, cell_text in enumerate(row_data):cell = table.cell(row_index, col_index)cell.text = str(cell_text)set_cell_borders(cell, border_color="FF0000", row_height=300)# 设置表格边框颜色# 保存 Word 文档doc.save(output_file)# pdf_file = "multitab.pdf"
pdf_file = "excelcell.pdf"
output_file = "order0429multitab.docx"  # 输出的 Word 文件路径
# 读取PDF文件中的所有表格
tables = tabula.read_pdf(pdf_file, pages="all", multiple_tables=True, stream="complex")
multi_table_data = get_table_data(tables)
print("table_data:", multi_table_data)new_multi_table_data = handle_table(multi_table_data)# 替换 nan 值为空字符串
_new_multi_table_data = [[["" if isinstance(item, float) and np.isnan(item) else item for item in row]for row in table]for table in new_multi_table_data
]print("new_multi_table_data:", _new_multi_table_data)
create_table_and_fill_data(_new_multi_table_data, output_file)