157 lines
6.8 KiB
Python
157 lines
6.8 KiB
Python
import json
|
||
import docx
|
||
import fitz
|
||
import re
|
||
import os
|
||
|
||
def extract_text_from_docx(file_path):
|
||
doc = docx.Document(file_path)
|
||
return '\n'.join([para.text for para in doc.paragraphs])
|
||
|
||
def clean_page_numbers(text):
|
||
# 删除每页开头的页码，假设页码后跟至少一个空格
|
||
cleaned_text = re.sub(r'^\s*\d+\s+', '', text)
|
||
# 删除每页末尾的页码，假设页码前有至少一个空格
|
||
cleaned_text = re.sub(r'\s+\d+\s*$', '', cleaned_text)
|
||
# 删除形如 /123 或 123/ 的页码
|
||
cleaned_text = re.sub(r'\s*/\s*\d+\s*|\s*\d+\s*/\s*', '', cleaned_text)
|
||
return cleaned_text
|
||
|
||
def extract_text_from_pdf(file_path):
|
||
doc = fitz.open(file_path)
|
||
text = ""
|
||
for page in doc:
|
||
page_text = page.get_text()
|
||
page_text = clean_page_numbers(page_text)
|
||
text += page_text
|
||
return text
|
||
|
||
def extract_section(text, start_pattern, end_phrases):
|
||
start_match = re.search(start_pattern, text)
|
||
if not start_match:
|
||
return "" # 如果没有找到匹配的开始模式，返回空字符串
|
||
start_index = start_match.start()
|
||
end_index = len(text)
|
||
for phrase in end_phrases:
|
||
# Use multiline mode with `re.MULTILINE`
|
||
match = re.search(phrase, text[start_index:], re.MULTILINE) #Hello, world!\nWelcome to OpenAI. 在多行字符串多，要 re.MULTILINE以匹配每一行的开头，否则只会匹配字符串的开头。
|
||
if match:
|
||
end_index = start_index + match.start()
|
||
break
|
||
|
||
return text[start_index:end_index]
|
||
|
||
def compare_headings(current, new):
|
||
# 使用过滤来确保只处理非空且为数字的部分
|
||
current_nums = [int(num) for num in current.split('.') if num.isdigit()]
|
||
new_nums = [int(num) for num in new.split('.') if num.isdigit()]
|
||
|
||
# 比较数字序列以确定标题的层次关系
|
||
for c, n in zip(current_nums, new_nums):
|
||
if n > c:
|
||
return True
|
||
elif n < c:
|
||
return False
|
||
|
||
# 如果新标题有更多层次，认为是新的子章节
|
||
return len(new_nums) > len(current_nums)
|
||
|
||
|
||
def should_add_newline(content, keywords, max_length=20):
|
||
content_str = ''.join(content).strip()
|
||
return any(keyword in content_str for keyword in keywords) or len(content_str) <= max_length
|
||
|
||
def handle_content_append(current_content, line_content, append_newline, keywords):
|
||
if append_newline:
|
||
if should_add_newline(current_content, keywords):
|
||
current_content.append('\n') # 添加换行符
|
||
append_newline = False
|
||
current_content.append(line_content)
|
||
return append_newline
|
||
|
||
#对二级标题如x.x进行额外处理：如果当前处理内容包含keywords中的内容，则必须保留换行符/如果当前内容字数大于20，不保留换行。
|
||
def parse_text_by_heading(text):
|
||
keywords = ['包含', '以下']
|
||
data = {}
|
||
current_key = None
|
||
current_content = []
|
||
append_newline = False
|
||
|
||
lines = text.split('\n')
|
||
for i, line in enumerate(lines):
|
||
line_stripped = line.strip()
|
||
# 匹配形如 '1.1'、'2.2.3' 等至少包含一个点的标题，并确保其前后没有字母或括号
|
||
match = re.match(r'^(?<![a-zA-Z（(])(\d+(?:\.\d+)+)\s*(.*)', line_stripped)
|
||
if not match:
|
||
match = re.match(r'^(\d+\.)\s*(.+)$', line_stripped)
|
||
|
||
if match:
|
||
new_key, line_content = match.groups()
|
||
line_content = line_content.lstrip('.')
|
||
# 检查是否应该更新当前键和内容
|
||
if current_key is None or (compare_headings(current_key, new_key) and (
|
||
len(current_content) == 0 or current_content[-1][-1] != '第')):
|
||
if current_key is not None:
|
||
# 将之前的内容保存到data中，保留第一个换行符，后续的换行符转为空字符
|
||
content_string = ''.join(current_content).strip()
|
||
data[current_key] = content_string.replace(' ', '')
|
||
current_key = new_key
|
||
current_content = [line_content]
|
||
# 只有当标题级别为两级（如 1.1）时，才设置 append_newline 为 True
|
||
append_newline = len(new_key.split('.')) == 2
|
||
else:
|
||
append_newline = handle_content_append(current_content, line_content, append_newline, keywords)
|
||
else:
|
||
if line_stripped:
|
||
append_newline = handle_content_append(current_content, line_stripped, append_newline, keywords)
|
||
|
||
if current_key is not None:
|
||
# 保存最后一部分内容
|
||
content_string = ''.join(current_content).strip()
|
||
data[current_key] = content_string.replace(' ', '')
|
||
|
||
return data
|
||
|
||
def convert_to_json(file_path, start_word, end_phrases):
|
||
if file_path.endswith('.docx'):
|
||
text = extract_text_from_docx(file_path)
|
||
elif file_path.endswith('.pdf'):
|
||
text = extract_text_from_pdf(file_path)
|
||
else:
|
||
raise ValueError("Unsupported file format")
|
||
# 提取从 start_word 开始到 end_phrases 结束的内容
|
||
text = extract_section(text, start_word, end_phrases)
|
||
parsed_data = parse_text_by_heading(text)
|
||
return parsed_data
|
||
|
||
def convert_clause_to_json(input_path,output_folder,type=1):
|
||
if type==1:
|
||
start_word = "投标人须知正文"
|
||
end_phrases = [
|
||
r'^第[一二三四五六七八九十]+章\s+评标办法', r'^评标办法前附表', r'^附录：', r'^附录一：', r'^附件：', r'^附件一：',
|
||
r'^附表：', r'^附表一：', r'^附录:', r'^附录一:', r'^附件:', r'^附件一:', r'^附表:', r'^附表一:',
|
||
]
|
||
else:
|
||
start_word = r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|招标编号:|招标编号：'
|
||
end_phrases=[r'第[一二三四五六七八九十]+章\s*投标人须知',r'投标人须知前附表']
|
||
result = convert_to_json(input_path, start_word, end_phrases)
|
||
file_name = "clause1.json" if type == 1 else "clause2.json"
|
||
output_path = os.path.join(output_folder, file_name)
|
||
with open(output_path, 'w', encoding='utf-8') as f:
|
||
json.dump(result, f, indent=4, ensure_ascii=False)
|
||
return output_path
|
||
|
||
if __name__ == "__main__":
|
||
file_path = 'C:\\Users\\Administrator\\Desktop\\招标文件\\zbtest16_tobidders_notice.pdf'
|
||
start_word = "投标人须知正文"
|
||
end_phrases = [
|
||
r'^第[一二三四五六七八九十]+章\s+评标办法', r'^评标办法前附表', r'^附录：', r'^附录一：', r'^附件：', r'^附件一：',
|
||
r'^附表：', r'^附表一：', r'^附录:', r'^附录一:', r'^附件:', r'^附件一:', r'^附表:', r'^附表一:',
|
||
]
|
||
output_folder = 'C:\\Users\\Administrator\\Desktop\\招标文件'
|
||
try:
|
||
output_path = convert_clause_to_json(file_path,output_folder)
|
||
print(f"Final JSON result saved to: {output_path}")
|
||
except ValueError as e:
|
||
print("Error:", e)
|