You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
64 lines
2.6 KiB
64 lines
2.6 KiB
import os
|
|
import subprocess
|
|
import uuid
|
|
|
|
|
|
def get_docx_content_by_pandoc(docx_file, output_file=None, parent_dir=None):
|
|
# 最后拼接的内容
|
|
content = ""
|
|
# output_file 设置为临时目录下的uuid.md
|
|
file_name = uuid.uuid4().hex
|
|
# 将docx_file去掉扩展名
|
|
prefix = docx_file.split(".")[0].split("/")[-1]
|
|
temp_markdown = os.path.join('./static/markdown/', prefix + '.md')
|
|
if parent_dir:
|
|
temp_markdown = os.path.join('../static/markdown/', prefix + '.md')
|
|
# 调用pandoc将docx文件转换成markdown
|
|
if parent_dir is None:
|
|
os.mkdir("./static/Images/" + file_name)
|
|
extract_media = "./static/Images/"
|
|
else:
|
|
os.mkdir("../static/Images/" + file_name)
|
|
extract_media = "../static/Images/"
|
|
|
|
subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
|
|
'--extract-media=' + extract_media + file_name])
|
|
# 读取然后修改内容，输出到新的文件
|
|
img_idx = 0 # 图片索引
|
|
with open(temp_markdown, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = line.strip()
|
|
if not line:
|
|
continue
|
|
# 跳过图片高度描述行
|
|
if line.startswith('height=') and line.endswith('in"}'):
|
|
continue
|
|
# 使用find()方法安全地检查图片模式
|
|
is_img = line.find("![](") >= 0 and (
|
|
line.find(".png") > 0 or
|
|
line.find(".jpg") > 0 or
|
|
line.find(".jpeg") > 0
|
|
)
|
|
if is_img:
|
|
# {width="3.1251607611548557in"
|
|
# height="3.694634733158355in"}
|
|
# {width="3.1251607611548557in"
|
|
pos = line.find(")")
|
|
q = line[:pos + 1]
|
|
q = q.replace("./static", ".")
|
|
# q = q[4:-1]
|
|
# q='<img src="'+q+'" alt="我是图片">'
|
|
img_idx += 1
|
|
content += q + "\n"
|
|
else:
|
|
content += line.strip().replace("**", "") + "\n"
|
|
content = content.replace("\phantom", "")
|
|
# 将content回写到markdown文件
|
|
if output_file is not None:
|
|
with open(output_file, 'w', encoding='utf-8') as f:
|
|
f.write(content)
|
|
print("Conversion completed successfully!")
|
|
# 删除临时文件
|
|
os.remove(temp_markdown)
|
|
return content.replace("\n\n", "\n").replace("\\", "")
|