python-docx读取doc,docx文档

API: http://python-docx.readthedocs.io/en/latest/#api-documentation

1.将doc转为docx
python3.8中win32com 要安装pypiwin32 pip install pypiwin32

from win32com import client as wc

word = wc.Dispatch("Word.Application")
doc = word.Documents.Open(路径+名称.doc)
doc.SaveAs(路径+名称.docx, 12)   12为docx
doc.Close()
word.Quit()

2.读取段落

import docx
docStr = Document(docName)   打开文档
for paragraph in docStr.paragraphs:
parStr = paragraph.text
--》paragraph.style.name == 'Heading 1'  一级标题   
--》paragraph.paragraph_format.alignment == 1  居中显示
--》paragraph.style.next_paragraph_style.paragraph_format.alignment == 1  下一段居中显示
--》paragraph.style.font.color

3.读取表格

numTables = docStr.tables
for table in numTables:
#行列个数
row_count = len(table.rows)
col_count = len(table.columns)
for i in range(row_count):
    row = table.rows[i].cells
	i行j列内容：row[j].text

或者：
row_count = len(table.rows)
col_count = len(table.columns)
for i in range(row_count):
    for j in range(col_count):
        print(table.cell(i,j).text)

4.按样式读取
读取标题

for p in doc.paragraphs:
    if p.style.name=='Heading 1':
        print(p.text)

import re
for p in doc.paragraphs:
    if re.match("^Heading d+$",p.style.name):
        print(p.text)

读取正文

for p in doc.paragraphs:
    if p.style.name=='Normal':
        print(p.text)

5.获取docx支持的样式

from docx.enum.style import WD_STYLE_TYPE
for i in s:
    if i.type==WD_STYLE_TYPE.PARAGRAPH:
        print(i.name)

6.设置首行缩进

from docx.shared import Inches,Pt
par2 = doc.add_paragraph('段落文本')
# 左缩进,0.5 英寸
par2.paragraph_format.left_indent = Inches(0.5)
# 右缩进,20 磅
par2.paragraph_format.right_indent = Pt(20)
# 首行缩进
par2.paragraph_format.first_line_indent = Inches(1)

查看首行缩进单位

from docx import Document
from docx.shared import Inches
from docx.oxml.ns import qn

from docx.shared import Cm, Pt
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT

from docx.shared import RGBColor

myDocument = Document('2020年建交集团3月分析报告.docx')

for paragraph in myDocument.paragraphs:
	print(paragraph.paragraph_format.first_line_indent)
	print(dir(paragraph))

https://blog.csdn.net/weixin_45903952/article/details/106200213
https://blog.csdn.net/zhouz92/article/details/107028727?utm_medium=distribute.pc_aggpage_search_result.none-task-blog-2_allfirst_rank_v2~rank_v25-18-107028727.nonecase&utm_term=python%20%E6%AE%B5%E8%90%BD%E8%AE%BE%E7%BD%AE&spm=1000.2123.3001.4430
https://blog.csdn.net/xtfge0915/article/details/83479922