109 lines
4.4 KiB
Python
109 lines
4.4 KiB
Python
# from docx import Document
|
||
import docx2txt
|
||
import re
|
||
|
||
|
||
def insert_html_tag(paragraph: str, keyword_list: list) -> str:
|
||
"""
|
||
插入html标签高亮敏感词
|
||
:param paragraph: 待处理的段落
|
||
:param keyword_list: 列表形式的敏感词
|
||
:return: 标记后的段落
|
||
"""
|
||
marked_paragraph = paragraph
|
||
for keyword in keyword_list:
|
||
marked_paragraph = marked_paragraph.replace(keyword,
|
||
'<span style="background-color:yellow">' + keyword + '</span>')
|
||
return marked_paragraph
|
||
|
||
|
||
def docx_find(file_path: str, keyword_list: list) -> dict:
|
||
"""
|
||
:param file_path: 文件路径
|
||
:param keyword_list: 列表形式的敏感词
|
||
:return: 返回一个字典，包含文件名和敏感词所在的段落 {'file_name': 'xxx.docx', 'find_list': ['段落1', '段落2', ...]}
|
||
"""
|
||
# doc_file = Document(file_path)
|
||
doc_text = docx2txt.process(file_path) # 使用docx2txt模块读取docx文件
|
||
find_dict = {'file_name': file_path, 'find_list': []}
|
||
find_list = []
|
||
paragraph_keyword = []
|
||
|
||
# 使用 python-docx 模块的检索 已废弃
|
||
# # 检索所有段落
|
||
# for para in doc_file.paragraphs:
|
||
# this_para_keyword = []
|
||
# for keyword in keyword_list: # 可能存在性能问题
|
||
# if keyword in para.text and not this_para_keyword: # 如果keyword在para.text中，且该段落没有被标记过
|
||
# find_list.append(para.text)
|
||
# this_para_keyword.append(keyword)
|
||
# elif keyword in para.text and this_para_keyword: # 如果keyword在para.text中，且该段落已经被标记过
|
||
# this_para_keyword.append(keyword)
|
||
# else:
|
||
# continue
|
||
#
|
||
# if this_para_keyword:
|
||
# # 若该段落被标记过，则将该段落的所有keyword加入到paragraph_keyword中
|
||
# paragraph_keyword.append(this_para_keyword)
|
||
# # 检索所有页眉
|
||
# for section in doc_file.sections:
|
||
# header = section.header
|
||
# if header is not None:
|
||
# for para in header.paragraphs:
|
||
# this_para_keyword = []
|
||
# for keyword in keyword_list:
|
||
# if keyword in para.text and not this_para_keyword:
|
||
# find_list.append(para.text)
|
||
# this_para_keyword.append(keyword)
|
||
# elif keyword in para.text and this_para_keyword:
|
||
# this_para_keyword.append(keyword)
|
||
# else:
|
||
# continue
|
||
|
||
for para in doc_text.split('\n'):
|
||
this_para_keyword = []
|
||
for keyword in keyword_list:
|
||
if keyword in para and not this_para_keyword:
|
||
# 如果敏感词在para中，且该段落没有被标记过
|
||
find_list.append(para)
|
||
this_para_keyword.append(keyword)
|
||
elif keyword in para and this_para_keyword:
|
||
# 如果敏感词在para中，且该段落已经被标记过
|
||
this_para_keyword.append(keyword)
|
||
else:
|
||
continue
|
||
|
||
if this_para_keyword:
|
||
# 若该段落中有敏感词，则将该段落的所有keyword加入到paragraph_keyword中
|
||
paragraph_keyword.append(this_para_keyword)
|
||
|
||
print(len(find_list))
|
||
find_dict['find_list'] = find_list
|
||
find_dict['paragraph_keyword'] = paragraph_keyword
|
||
return find_dict
|
||
|
||
|
||
# print(docx_find('浅水海底电缆打捞大作业.docx', ['机密', '铲出']))
|
||
def util_keyword_find(file_path: str, keyword_list: list) -> dict:
|
||
"""
|
||
对指定单一文件进行敏感词查找
|
||
:param file_path: 文件路径
|
||
:param keyword_list: 列表形式的敏感词
|
||
:return: 返回一个字典，包含文件名和敏感词所在的段落 {'file_name': 'xxx.docx', 'find_list': ['段落1', '段落2', ...]}
|
||
"""
|
||
# check file type
|
||
if file_path.endswith('.docx'):
|
||
find_dict = docx_find(file_path, keyword_list) # 调用docx_find函数
|
||
for para in find_dict['find_list']:
|
||
marked_para = insert_html_tag(para, keyword_list)
|
||
find_dict['find_list'][find_dict['find_list'].index(para)] = marked_para
|
||
# print(find_dict)
|
||
return find_dict
|
||
|
||
else:
|
||
return {'file_name': file_path, 'find_list': []}
|
||
|
||
|
||
if __name__ == '__main__':
|
||
print(util_keyword_find('浅水海底电缆打捞大作业.docx', ['打捞', '浅水']))
|