? ? ? ? 優化地方:處理合并的單元格內容。
? ? ? ? 1、修改為stream="complex"
? ? ? ? 2、增加換行符f"{table_data[i - 1][j]}\n{table_data[i][j]}".strip()
? ? ? ? 一、pdf中excel樣例
? ? ? 二、完整代碼
import tabula
import numpy as np
from docx import Document
from docx.oxml.ns import qn
from docx.oxml import OxmlElement# print("multitab:", tables)# 創建一個新的Word文檔
doc = Document()def get_table_data(df_list):multi_table_data = []# 遍歷每個表格for table_index, table in enumerate(df_list):table_data = []# 獲取行數和列數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,"",]: # 只有當單元格不為空時才合并table_data[i - 1][j] = f"{table_data[i - 1][j]}\n{table_data[i][j]}".strip()# 刪除當前行del table_data[i]multi_table_data.append(table_data)return multi_table_datadef set_cell_borders(cell, border_color="000000", row_height=None):"""設置單元格的邊框顏色:param cell: 單元格對象:param border_color: 邊框顏色,默認為黑色"""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") # 邊框大小border.set(qn("w:space"), "0")border.set(qn("w:color"), border_color)tcBorders.append(border)tcPr.append(tcBorders)# 設置內容居中顯示for paragraph in cell.paragraphs:for run in paragraph.runs:run.font.size = paragraph.style.font.size # 保持字體大小一致paragraph.alignment = 1 # 1 表示居中對齊# 設置行高if row_height is not None:tr = cell._element.getparent() # 獲取行元素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 文檔中插入表格并填充數據:param data: 表格數據:param output_file: 輸出文件路徑"""# 創建一個新的 Word 文檔doc = Document()for row_index, data in enumerate(tables_data):# 添加一個標題sssdoc.add_heading("測試信息表" + str(row_index), level=1)# 創建表格table = doc.add_table(rows=len(data), cols=len(data[0]))# 填充表格數據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)# 設置表格邊框顏色# 保存 Word 文檔doc.save(output_file)# pdf_file = "multitab.pdf"
pdf_file = "excelcell.pdf"
output_file = "order0429multitab.docx" # 輸出的 Word 文件路徑
# 讀取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)# 替換 nan 值為空字符串
_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)
三、效果展示
????????