260 lines
11 KiB
Python
260 lines
11 KiB
Python
from PyPDF2 import PdfReader, PdfWriter
|
||
import re # 导入正则表达式库
|
||
import os # 用于文件和文件夹操作
|
||
from flask_app.main.format_change import docx2pdf
|
||
|
||
|
||
def clean_page_content(text, common_header):
|
||
# 首先删除抬头公共部分
|
||
if common_header: # 确保有公共抬头才进行替换
|
||
for header_line in common_header.split('\n'):
|
||
if header_line.strip(): # 只处理非空行
|
||
# 替换首次出现的完整行
|
||
text = re.sub(r'^' + re.escape(header_line.strip()) + r'\n?', '', text, count=1)
|
||
|
||
# 删除页码 eg:89/129 这个代码分三步走可以把89/129完全删除
|
||
text = re.sub(r'^\s*\d+\s*(?=\D)', '', text) # 删除开头的页码，仅当紧跟非数字字符时
|
||
text = re.sub(r'\s+\d+\s*$', '', text) # 删除结尾的页码
|
||
text = re.sub(r'\s*\/\s*\d+\s*', '', text) # 删除形如 /129 的页码
|
||
|
||
return text
|
||
|
||
|
||
def extract_common_header(pdf_path):
|
||
pdf_document = PdfReader(pdf_path)
|
||
headers = []
|
||
total_pages = len(pdf_document.pages)
|
||
|
||
# 确定要读取的页数和起始页
|
||
if total_pages == 2:
|
||
pages_to_read = 2
|
||
start_page = 0
|
||
else:
|
||
pages_to_read = 3
|
||
middle_page = total_pages // 2
|
||
start_page = max(0, middle_page - 1)
|
||
|
||
for i in range(start_page, min(start_page + pages_to_read, total_pages)):
|
||
page = pdf_document.pages[i]
|
||
text = page.extract_text() or ""
|
||
if text:
|
||
# 只取每页的前三行
|
||
first_lines = text.strip().split('\n')[:3]
|
||
headers.append(first_lines)
|
||
|
||
if len(headers) < 2:
|
||
return "" # 如果没有足够的页来比较，返回空字符串
|
||
|
||
# 寻找每一行中的公共部分
|
||
common_headers = []
|
||
for lines in zip(*headers):
|
||
# 在每一行中寻找公共单词
|
||
common_line = set(lines[0].split()).intersection(*[set(line.split()) for line in lines[1:]])
|
||
if common_line:
|
||
common_headers.append(' '.join(common_line))
|
||
|
||
return '\n'.join(common_headers)
|
||
|
||
|
||
def is_pdf_or_doc(filename):
|
||
# 判断文件是否为PDF或Word文档
|
||
return filename.lower().endswith(('.pdf', '.doc', '.docx'))
|
||
|
||
|
||
def convert_to_pdf(file_path):
|
||
# 假设 docx2pdf 函数已经被定义，这里仅根据文件扩展名来决定是否需要转换
|
||
if file_path.lower().endswith(('.doc', '.docx')):
|
||
return docx2pdf(file_path)
|
||
return file_path
|
||
|
||
|
||
def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||
if not os.path.exists(output_folder):
|
||
os.makedirs(output_folder)
|
||
generated_files = []
|
||
if os.path.isdir(input_path):
|
||
# 遍历文件夹内的所有PDF文件
|
||
for file in os.listdir(input_path):
|
||
file_path = os.path.join(input_path, file)
|
||
if is_pdf_or_doc(file):
|
||
pdf_path = convert_to_pdf(file_path)
|
||
output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||
output_suffix)
|
||
if output_pdf_path:
|
||
generated_files.append(output_pdf_path)
|
||
elif os.path.isfile(input_path) and input_path.endswith(".pdf"):
|
||
# 处理单个PDF文件
|
||
output_pdf_path = extract_pages(input_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||
output_suffix)
|
||
if output_pdf_path:
|
||
generated_files.append(output_pdf_path)
|
||
else:
|
||
print("提供的路径既不是文件夹也不是PDF文件。")
|
||
return generated_files
|
||
|
||
|
||
def extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page, common_header, exclusion_pattern=None):
|
||
start_page = None
|
||
end_page = None
|
||
for i, page in enumerate(pdf_document.pages):
|
||
text = page.extract_text() or ""
|
||
cleaned_text = clean_page_content(text, common_header)
|
||
if exclusion_pattern and re.search(exclusion_pattern, cleaned_text):
|
||
continue
|
||
if start_page is None and re.search(begin_pattern, cleaned_text) and i > begin_page:
|
||
start_page = i
|
||
if start_page is not None and re.search(end_pattern, cleaned_text) and i > start_page:
|
||
end_page = i
|
||
break
|
||
return start_page, end_page
|
||
|
||
|
||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||
try:
|
||
common_header = extract_common_header(pdf_path)
|
||
pdf_document = PdfReader(pdf_path)
|
||
start_page, end_page = extract_pages_generic(pdf_document, begin_pattern, end_pattern, begin_page,
|
||
common_header)
|
||
if start_page is None or end_page is None:
|
||
print(f"first: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！尝试备用提取策略。")
|
||
return extract_pages_twice(pdf_path, output_folder, output_suffix, common_header)
|
||
return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix)
|
||
except Exception as e:
|
||
print(f"Error processing {pdf_path}: {e}")
|
||
return None
|
||
|
||
|
||
def get_patterns_for_procurement():
|
||
begin_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务).*?要求|'
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:采购|技术标准).*|'
|
||
r'^[一二三四五六七八九十百千]+、\s*采购清单', re.MULTILINE)
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE)
|
||
return begin_pattern, end_pattern
|
||
|
||
|
||
def get_patterns_for_evaluation_method():
|
||
begin_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(磋商|谈判|评标|评定|评审)(方法|办法).*', re.MULTILINE)
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE)
|
||
return begin_pattern, end_pattern
|
||
|
||
|
||
def get_patterns_for_qualification():
|
||
# 原始匹配逻辑
|
||
begin_pattern_original = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格审查).*', re.MULTILINE)
|
||
end_pattern_original = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+', re.MULTILINE)
|
||
|
||
# 新匹配逻辑
|
||
begin_pattern_new = re.compile(
|
||
r'^资格性检查', re.MULTILINE)
|
||
end_pattern_new = re.compile(
|
||
r'^附件\s*\d+', re.MULTILINE)
|
||
|
||
return (begin_pattern_original, end_pattern_original), (begin_pattern_new, end_pattern_new)
|
||
|
||
|
||
def extract_pages_twice(pdf_path, output_folder, output_suffix, common_header):
|
||
exclusion_pattern = re.compile(r'文件的构成|文件的组成|须对应|需对应|须按照|需按照|须根据|需根据')
|
||
pdf_document = PdfReader(pdf_path)
|
||
patterns = None
|
||
|
||
if output_suffix == "procurement":
|
||
patterns = [get_patterns_for_procurement()]
|
||
elif output_suffix == "evaluation_method" or output_suffix=="qualification2":
|
||
patterns = [get_patterns_for_evaluation_method()]
|
||
elif output_suffix == "qualification":
|
||
patterns = get_patterns_for_qualification() # This now returns a tuple of pattern pairs
|
||
|
||
# Try each set of patterns until a valid range is found
|
||
for pattern_pair in patterns:
|
||
start_page, end_page = extract_pages_generic(pdf_document, pattern_pair[0], pattern_pair[1], 5, common_header,
|
||
exclusion_pattern)
|
||
if start_page is not None and end_page is not None:
|
||
break
|
||
if start_page is None or end_page is None:
|
||
if output_suffix == "qualification":
|
||
print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
|
||
print("third:尝试提取评分办法章节...")
|
||
return truncate_pdf_main(pdf_path,output_folder,2,"qualification2")
|
||
else:
|
||
print(f"second: {output_suffix} 未找到起始或结束页在文件 {pdf_path} 中！")
|
||
return ""
|
||
return save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix)
|
||
|
||
|
||
def save_extracted_pages(pdf_document, start_page, end_page, pdf_path, output_folder, output_suffix):
|
||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
|
||
output_doc = PdfWriter()
|
||
for page_num in range(start_page, end_page + 1):
|
||
output_doc.add_page(pdf_document.pages[page_num])
|
||
with open(output_pdf_path, 'wb') as f:
|
||
output_doc.write(f)
|
||
print(f"{output_suffix} 已截取并保存页面从 {start_page} 到 {end_page} 为 {output_pdf_path}")
|
||
return output_pdf_path
|
||
|
||
|
||
def truncate_pdf_main(input_path, output_folder, selection, output_suffix="default"):
|
||
if selection == 1:
|
||
# 更新的正则表达式以匹配"第x章"和"第x部分"，考虑到可能的空格和其他文字
|
||
begin_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(?:服务|项目|商务).*?要求|'
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?采购.*'
|
||
)
|
||
begin_page = 5
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
|
||
)
|
||
local_output_suffix = "procurement"
|
||
elif selection == 2:
|
||
begin_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(磋商|谈判|评标|评定|评审)(方法|办法).*'
|
||
)
|
||
begin_page = 5
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
|
||
)
|
||
local_output_suffix = "evaluation_method"
|
||
elif selection == 3:
|
||
begin_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分).*?(资格审查).*'
|
||
)
|
||
begin_page = 5
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十百千]+(?:章|部分)\s*[\u4e00-\u9fff]+'
|
||
)
|
||
local_output_suffix = "qualification"
|
||
else:
|
||
print("无效的选择")
|
||
return None
|
||
|
||
# 如果传入的 output_suffix 是 'default'，则使用本地生成的 output_suffix
|
||
if output_suffix == "default":
|
||
output_suffix = local_output_suffix
|
||
|
||
# 调用相应的处理函数
|
||
return process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix)
|
||
|
||
|
||
|
||
def truncate_pdf_multiple(input_path, output_folder):
|
||
truncate_files = []
|
||
for selection in range(1, 4):
|
||
files = truncate_pdf_main(input_path, output_folder, selection)
|
||
truncate_files.extend(files)
|
||
return truncate_files
|
||
|
||
|
||
# TODO:交通智能系统和招标(1)(1)文件有问题
|
||
if __name__ == "__main__":
|
||
input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\交通智能运行维护招标文件.pdf"
|
||
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\output3"
|
||
# truncate_pdf_multiple(input_path,output_folder)
|
||
selection = 3 # 例如：1 - 商务技术服务要求, 2 - 评标办法, 3 - 资格审查
|
||
generated_files = truncate_pdf_main(input_path, output_folder, selection)
|