python读取json数据还原表格批量转换成html

目录

• 一、实操
• 1.首先创建一个新的文档
• 2.添加文本
• 二、word转成html
• 1.使用pydocx转换
• 2.使用win32模块

pip install python_docx

from docx import Document
document = Document()

table = document.add_table(rows=37,cols=13,)

table.cell(0,0).merge(table.cell(2,2))

document = Document()
table = document.add_table(rows=37,cols=13,)

document.save("table-1.docx")

document1 = Document("table-1.docx")
table = document1.tables[0]
for row,obj_row in enumerate(table.rows):
   for col,cell in enumerate(obj_row.cells):
       cell.text = cell.text + "%d,%d " % (row,col)

document1.save("table-2.docx")

hdr_cells0 = table.rows[0].cells

hdr_cells0[0].add_paragraph("数据文字")

pip install pydocx

from pydocx import PyDocX
html = PyDocX.to_html("test.docx")
f = open("test.html", "w", encoding="utf-8")
f.write(html)
f.close()

pip3 install pypiwin32

from win32com import client as wc
import os

word = wc.Dispatch("Word.Application")


def wordsToHtml(dir):
    for path, subdirs, files in os.walk(dir):
        for wordFile in files:
            wordFullName = os.path.join(path, wordFile)
            doc = word.Documents.Open(wordFullName)

            wordFile2 = wordFile
            dotIndex = wordFile2.rfind(".")
            if (dotIndex == -1):
                print(wordFullName + "********************ERROR: 未取得后缀名！")

            fileSuffix = wordFile2[(dotIndex + 1):]
            if (fileSuffix == "doc" or fileSuffix == "docx"):
                fileName = wordFile2[: dotIndex]
                htmlName = fileName + ".html"
                htmlFullName = os.path.join(path, htmlName)
                print("generate html:" + htmlFullName)
                doc.SaveAs(htmlFullName, 10)
                doc.Close()

    word.Quit()
    print("")
    print("Finished!")


if __name__ == "__main__":
    import sys

    if len(sys.argv) != 2:
        print("Usage: python funcName.py rootdir")
        sys.exit(100)
    wordsToHtml(sys.argv[1])