|
|
|
|
|
import re
|
|
|
|
|
|
import subprocess
|
|
|
|
|
|
import os
|
|
|
|
|
|
import uuid
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 获取MathType对应的Latex公式
|
|
|
|
|
|
def get_latex_list(docx_file):
|
|
|
|
|
|
# 获取当前目录的父级目录
|
|
|
|
|
|
current_dir = os.path.dirname(os.path.abspath(__file__))
|
|
|
|
|
|
current_dir = os.path.dirname(current_dir)
|
|
|
|
|
|
mtef = os.path.join(current_dir, 'mtef-go-3', 'mtef-go.exe')
|
|
|
|
|
|
res = []
|
|
|
|
|
|
output = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.txt')
|
|
|
|
|
|
command = mtef + r" -w " + docx_file + " -o " + output
|
|
|
|
|
|
os.system(command)
|
|
|
|
|
|
# 如果output没有正确生成
|
|
|
|
|
|
if not os.path.exists(output):
|
|
|
|
|
|
return res
|
|
|
|
|
|
with open(output, 'r', encoding='utf-8') as file:
|
|
|
|
|
|
for i, line in enumerate(file):
|
|
|
|
|
|
res.append(line.strip())
|
|
|
|
|
|
return res
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 结合Pandoc和mtef-go的结果，合并成最终的输出文本
|
|
|
|
|
|
def get_docx_content_by_pandoc(docx_file):
|
|
|
|
|
|
# 一、获取Latex公式列表
|
|
|
|
|
|
formula_list = get_latex_list(docx_file)
|
|
|
|
|
|
# 最后拼接的内容
|
|
|
|
|
|
content = ""
|
|
|
|
|
|
# output_file 设置为临时目录下的uuid.md
|
|
|
|
|
|
temp_markdown = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.md')
|
|
|
|
|
|
# 调用pandoc将docx文件转换成markdown
|
|
|
|
|
|
subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown])
|
|
|
|
|
|
# 打印 temp_markdown 文件
|
|
|
|
|
|
# with open(temp_markdown, 'r', encoding='utf-8') as f:
|
|
|
|
|
|
# print(f.read())
|
|
|
|
|
|
# 读取然后修改内容，输出到新的文件
|
|
|
|
|
|
wmf_idx = 0 # wmf索引
|
|
|
|
|
|
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_wmf = line.find("![](media/image") >= 0 and line.find(".wmf") > 0
|
|
|
|
|
|
is_img = line.find("![](media/image") >= 0 and (
|
|
|
|
|
|
line.find(".png") > 0 or
|
|
|
|
|
|
line.find(".jpg") > 0 or
|
|
|
|
|
|
line.find(".jpeg") > 0
|
|
|
|
|
|
)
|
|
|
|
|
|
if is_wmf:
|
|
|
|
|
|
content += formula_list[wmf_idx] + "\n"
|
|
|
|
|
|
wmf_idx += 1
|
|
|
|
|
|
elif is_img:
|
|
|
|
|
|
#{width="3.1251607611548557in"
|
|
|
|
|
|
# height="3.694634733158355in"}
|
|
|
|
|
|
img_idx += 1
|
|
|
|
|
|
content += "【图片" + str(img_idx) + "】\n"
|
|
|
|
|
|
else:
|
|
|
|
|
|
content += line.strip() + "\n"
|
|
|
|
|
|
|
|
|
|
|
|
# 删除临时文件 output_file
|
|
|
|
|
|
os.remove(temp_markdown)
|
|
|
|
|
|
return content
|
