Python中docx2txt库的使用说明

pip install docx2txt

# extract text
docx2txt file.docx
# extract text and images
docx2txt -i /tmp/img_dir file.docx

# extract text
docx2txt file.docx
# extract text and images
docx2txt -i /tmp/img_dir file.docx

# 提取word目录
file = docx.Document(file_path)
children = file.element.body.iter()
child_iters = []
for child in children:
 # 通过类型判断目录
 if child.tag.endswith('main}sdt'):
  for ci in child.iter():
   if ci.text and ci.text.strip():
    child_iters.append(ci)
catalog = [ci.text for ci in child_iters]

# 提取word文本框中文本
file = docx.Document(file_path)
children = file.element.body.iter()
child_iters = []
for child in children:
 # 通过类型判断目录
 if child.tag.endswith('textbox'):
  for ci in child.iter():
   if ci.tag.endswith('main}r'):
    child_iters.append(ci)
textbox = [ci.text for ci in child_iters]

file = docx.Document(file_path)
children = file.element.body.iter()
child_iters = []
tags = []
for child in children:
 # 通过类型判断目录
 if child.tag.endswith(('AlternateContent','textbox')):
  for ci in child.iter():
   tags.append(ci.tag)
   if ci.tag.endswith(('main}r', 'main}pPr')):
    child_iters.append(ci)
text = ['']
for ci in child_iters :
 if ci.tag.endswith('main}pPr'):
  text.append('')
 else:
  text[-1] += ci.text
 ci.text = ''
trans_text = ['***'+t+'***' for t in text]
print(trans_text)
i， k = 0, 0
for ci in child_iters :
 if ci.tag.endswith('main}pPr'):
  i += 1
  k = 0
 elif k == 0:
  ci.text = trans_text[i]
  k = 1
file.save('E:/***/test.docx')