|
|
|
|
@ -38,23 +38,29 @@ def get_docx_content_by_pandoc(docx_file):
|
|
|
|
|
img_idx = 0 # 图片索引
|
|
|
|
|
with open(temp_markdown, 'r', encoding='utf-8') as f:
|
|
|
|
|
for line in f:
|
|
|
|
|
if line.strip():
|
|
|
|
|
# 改进后的正则表达式，匹配更多格式的MathType公式
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
问题2 氢气与氧气燃烧的方程式
|
|
|
|
|
..
|
|
|
|
|
问题3 我是一个图片
|
|
|
|
|
{width="3.1251607611548557in" height="3.694634733158355in"}
|
|
|
|
|
"""
|
|
|
|
|
if line.index("![](media/image") >= 0 and line.index(".wmf") > 0:
|
|
|
|
|
content = content + formula_list[wmf_idx] + "\n"
|
|
|
|
|
wmf_idx = wmf_idx + 1
|
|
|
|
|
elif line.index("![](media/image") >= 0 and (
|
|
|
|
|
line.index(".png") > 0 or line.index(".jpg") > 0 or line.index(".jpeg") > 0):
|
|
|
|
|
content = content + "【图片" + str(img_idx) + "】\n"
|
|
|
|
|
else:
|
|
|
|
|
content = content + line.strip() + "\n"
|
|
|
|
|
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)
|
|
|
|
|
|
