需求：一些常用的对word的操作和提取word的表格，并保存在excel中
pip install python-docx
from docx import Documentfrom openpyxl import Workbookfrom docx.shared import Cm #Cm模块，用于设定图片尺寸大小#word中文档成为Document，每段内容称为Paragraph，每个段中不同部分称为Run（颜色、字体、粗细、斜体等不同就是不同的文字块）doc = Document(r"Test.docx")#提取文字和文字块儿print(doc.paragraphs)for paragraph in doc.paragraphs:print(paragraph.text)paragraph = doc.paragraphs[0]runs = paragraph.runsprint(runs)for run in paragraph.runs:print(run.text)paragraph = doc.paragraphs[3]runs = paragraph.runsprint(runs)for run in paragraph.runs:print(run.text)list1 = [["name","sex","Provin"],["violet1","女","日本省"],["violet2","女","日本省"],["violet3","女","日本省"],["violet4","女","日本省"]]list2 = [["name","sex","Provin"],["violet5","女","日本省"],["violet6","女","日本省"],["violet7","女","日本省"]]#向Word文档写入内容paragraph1 = doc.add_paragraph("新加段落1")paragraph2 = doc.add_paragraph("新加段落2")paragraph3 = doc.add_paragraph()paragraph3.add_run("加粗文字块").bold = Trueparagraph3.add_run("，普通文字块， ")paragraph3.add_run("斜体文字块").italic = Truedoc.add_page_break() #添加分页#doc.add_picture(r"E:\PycharmProjects\SpiderTest\violet.png",width=Cm(5),height=Cm(5))table1 = doc.add_table(rows=5,cols=3)for row in range(5):cells = table1.rows[row].cellsfor col in range(3):cells[col].text = str(list1[row][col])doc.add_paragraph("-----------------------------------------------------------")table2 = doc.add_table(rows=4,cols=3)for row in range(4):cells = table2.rows[row].cellsfor col in range(3):cells[col].text = str(list2[row][col])doc.save(r"Test2.docx")#提取word中的表格，并保存在excelt0 = doc.tables[0]workbook = Workbook()sheet = workbook.activefor i in range(len(t0.rows)):list1 = []for j in range(len(t0.columns)):print("元素："+t0.cell(i,j).text)list1.append(t0.cell(i,j).text)print("表格每一行list：", list1)sheet.append(list1)workbook.save(filename = r"TestByWord.xlsx")
处理后的结果：
TestByWord.xlsx：
