194 lines
8.6 KiB
Python
194 lines
8.6 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)
|
||
middle_page = total_pages // 2 # 计算中间页
|
||
|
||
# 确保中间页前后各一页（共3页），如果不足3页，则尽可能取足
|
||
start_page = max(0, middle_page - 1)
|
||
num_pages_to_read = 3
|
||
|
||
for i in range(start_page, min(start_page + num_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_twice(pdf_path, output_folder, output_suffix,common_header):
|
||
pdf_document = PdfReader(pdf_path)
|
||
begin_page=5
|
||
start_page = None
|
||
end_page = None
|
||
# 定义用于检测是否包含"文件的构成"的正则表达式
|
||
exclusion_pattern = re.compile(r'文件的构成|文件的组成')
|
||
if output_suffix == "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
|
||
)
|
||
for i in range(len(pdf_document.pages)):
|
||
page = pdf_document.pages[i]
|
||
text = page.extract_text() or ""
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
if re.search(begin_pattern, cleaned_text) and i > begin_page and not re.search(exclusion_pattern, cleaned_text):
|
||
start_page = i
|
||
if start_page is not None and re.search(end_pattern, cleaned_text) and i > start_page:
|
||
end_page = i
|
||
break
|
||
if start_page is None or end_page is None:
|
||
print(f"twice: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||
return ""
|
||
else:
|
||
return save_extracted_pages(pdf_document,start_page, end_page, pdf_path,output_folder, output_suffix)
|
||
|
||
|
||
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 = None
|
||
end_page = None
|
||
for i in range(len(pdf_document.pages)):
|
||
page = pdf_document.pages[i]
|
||
text = page.extract_text() or ""
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
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
|
||
if start_page is None or end_page is None:
|
||
if output_suffix == "procurement":
|
||
return extract_pages_twice(pdf_path, output_folder, output_suffix,common_header)
|
||
else:
|
||
print(f"未找到起始或结束页在文件 {pdf_path} 中！")
|
||
return None
|
||
|
||
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 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"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):
|
||
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.*',
|
||
# r'^[一二三四五六七八九十百千]+、\s*采购清单',
|
||
)
|
||
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]+'
|
||
)
|
||
output_suffix = "procurement"
|
||
|
||
else:
|
||
print("无效的选择")
|
||
return None
|
||
|
||
# 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, 2):
|
||
files = truncate_pdf_main(input_path, output_folder, selection)
|
||
truncate_files.extend(files)
|
||
return truncate_files
|
||
|
||
if __name__ == "__main__":
|
||
input_path = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\招标文件(107国道).pdf"
|
||
output_folder = "C:\\Users\\Administrator\\Desktop\\货物标\\output1"
|
||
truncate_pdf_multiple(input_path,output_folder)
|
||
# selection = 1 # 例如：1 - 投标人须知前附表, 2 - 评标办法, 3 - 投标人须知正文 4-招标公告-合同条款前
|
||
# generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||
# print("生成的文件:", generated_files)
|
||
|