购买了一个英语题集,题目数量很多,是电子版docx格式,但是其中每一题下面都有译文和答案,希望删除
import docx
import os
from docx import Document
file=docx.Document("C://Users//苏江婉//Desktop//学习//学科//英语//ABC.docx")
def delWordContent(docx_file='',dest_file=''):
doc=Document(docx_file)
paragraphs=doc.paragraphs
def delete_paragraph(paragraph):
p = paragraph._element
p.getparent().remove(p)
paragraph._p = paragraph._element = None
if text.startswith("答案",0,3) is True:
delete.paragraph(p)
else:
doc.save(dest_file)
delWordContent(docx_file='C://Users//苏江婉//Desktop//学习//学科//英语//ABC.docx',dest_file='C://Users//苏江婉//Desktop//学习//学科//英语//ABC[已完成].docx')
import docx
from docx import Document
def del_answer_paragraph(docx_file, dest_file):
doc = Document(docx_file)
paragraphs = doc.paragraphs
for paragraph in paragraphs:
if "答案" in paragraph.text:
doc.paragraphs.remove(paragraph)
doc.save(dest_file)
del_answer_paragraph("C://Users//苏江婉//Desktop//学习//学科//英语//ABC.docx","C://Users//苏江婉//Desktop//学习//学科//英语//ABC[已完成].docx")