88 lines
3.5 KiB
Python
88 lines
3.5 KiB
Python
|
from docx import Document
|
|||
|
|
import json
|
|||
|
|
|
|||
|
|
def read_tables_from_docx(file_path):
|
|||
|
|
"""读取DOCX文件中的表格数据，并以嵌套字典的形式返回."""
|
|||
|
|
doc = Document(file_path)
|
|||
|
|
table_list = {}
|
|||
|
|
cur_title = []
|
|||
|
|
|
|||
|
|
for table in doc.tables:
|
|||
|
|
for i, row in enumerate(table.rows):
|
|||
|
|
cur_level = table_list
|
|||
|
|
temp_title = []
|
|||
|
|
for j, cell in enumerate(row.cells):
|
|||
|
|
text_str = cell.text.strip().replace(' ', '').replace('\n', '') # 移除键中的换行符
|
|||
|
|
if j < len(row.cells) - 1:
|
|||
|
|
if text_str == "":
|
|||
|
|
text_str = cur_title[j] if j < len(cur_title) else "<未识别到上级标题>"
|
|||
|
|
if text_str not in cur_level:
|
|||
|
|
cur_level[text_str] = {}
|
|||
|
|
cur_level = cur_level[text_str]
|
|||
|
|
temp_title.append(text_str)
|
|||
|
|
else:
|
|||
|
|
cell_text = cell.text.strip().replace(' ', '')
|
|||
|
|
if len(temp_title) > 0:
|
|||
|
|
last_key = temp_title[-1]
|
|||
|
|
if last_key in cur_level:
|
|||
|
|
if isinstance(cur_level[last_key], dict):
|
|||
|
|
cur_level[last_key] = f"\n{cell_text}"
|
|||
|
|
else:
|
|||
|
|
cur_level[last_key] += f"\n{cell_text}" # 追加值到已有键
|
|||
|
|
else:
|
|||
|
|
cur_level[last_key] = cell_text # 初始化键的值
|
|||
|
|
else:
|
|||
|
|
last_key = f"第{i}行内容"
|
|||
|
|
if last_key in cur_level:
|
|||
|
|
if isinstance(cur_level[last_key], dict):
|
|||
|
|
cur_level[last_key] = f"\n{cell_text}"
|
|||
|
|
else:
|
|||
|
|
cur_level[last_key] += f"\n{cell_text}" # 追加值到'第i行内容'
|
|||
|
|
else:
|
|||
|
|
cur_level[last_key] = cell_text
|
|||
|
|
cur_title = temp_title[:]
|
|||
|
|
|
|||
|
|
return table_list
|
|||
|
|
|
|||
|
|
def flatten_nested_dicts(d):
|
|||
|
|
"""平坦化嵌套字典，以便更简洁地保存为JSON."""
|
|||
|
|
keys_to_remove = []
|
|||
|
|
items_to_add = {}
|
|||
|
|
|
|||
|
|
for key, value in list(d.items()):
|
|||
|
|
if isinstance(value, dict):
|
|||
|
|
value = flatten_nested_dicts(value)
|
|||
|
|
if len(value) == 1 and key in value:
|
|||
|
|
keys_to_remove.append(key)
|
|||
|
|
items_to_add[key] = value[key]
|
|||
|
|
elif len(value) == 1 and list(value.keys())[0] == list(value.values())[0]:
|
|||
|
|
items_to_add[key] = list(value.values())[0]
|
|||
|
|
|
|||
|
|
for key in keys_to_remove:
|
|||
|
|
del d[key]
|
|||
|
|
d.update(items_to_add)
|
|||
|
|
|
|||
|
|
return d
|
|||
|
|
|
|||
|
|
def save_data_to_json(data, filename):
|
|||
|
|
"""将数据保存到JSON文件中."""
|
|||
|
|
with open(filename, 'w', encoding='utf-8') as file:
|
|||
|
|
json.dump(data, file, ensure_ascii=False, indent=4)
|
|||
|
|
|
|||
|
|
def extract_tables_main(path, output_filename):
|
|||
|
|
# 读取文档表格数据
|
|||
|
|
table_data = read_tables_from_docx(path)
|
|||
|
|
|
|||
|
|
# 平坦化嵌套字典
|
|||
|
|
flattened_data = flatten_nested_dicts(table_data)
|
|||
|
|
|
|||
|
|
# 保存平坦化后的数据到JSON文件
|
|||
|
|
save_data_to_json(flattened_data, output_filename)
|
|||
|
|
|
|||
|
|
print(f"The data has been processed and saved to '{output_filename}'.")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\招标03_tobidders_notice_table.docx'
|
|||
|
|
output_filename = "C:\\Users\\Administrator\\Desktop\\招标文件\\truncate_output.json" # 前附表json文件
|
|||
|
|
extract_tables_main(path, output_filename)
|