274 lines
13 KiB
Python
274 lines
13 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
|
||
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
|
||
|
||
#PYPDF2库
|
||
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 save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page):
|
||
"""从原始PDF截取指定范围的页面并保存到新的PDF文件中"""
|
||
# 获取文件基本名称
|
||
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0]
|
||
# 构建输出文件路径
|
||
output_pdf_path = os.path.join(output_folder, f"{base_file_name}_{output_suffix}.pdf")
|
||
|
||
# 读取PDF文件
|
||
pdf_document = PdfReader(pdf_path)
|
||
output_doc = PdfWriter()
|
||
|
||
# 检查起始和结束页码是否有效
|
||
if start_page is not None and end_page is not None and start_page <= end_page:
|
||
# 添加指定范围的页面到新的PDF文档中
|
||
for page_num in range(start_page, end_page + 1):
|
||
output_doc.add_page(pdf_document.pages[page_num])
|
||
|
||
# 保存新的PDF文件
|
||
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 + 1} 到 {end_page + 1} 为 {output_pdf_path}")
|
||
else:
|
||
print("提供的页码范围无效。")
|
||
return output_pdf_path
|
||
|
||
|
||
def extract_pages_twice(pdf_path, output_folder, output_suffix):
|
||
common_header = extract_common_header(pdf_path)
|
||
last_begin_index = 0
|
||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|投标邀请书')
|
||
pdf_document = PdfReader(pdf_path)
|
||
for i, page in enumerate(pdf_document.pages):
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
# 检查“第一章”开始的位置
|
||
if begin_pattern.search(cleaned_text):
|
||
last_begin_index = i # 更新最后匹配的索引，页码从0开始
|
||
if output_suffix == "qualification":
|
||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||
# end_pattern = r'^(第[一二三四五六七八九十]+章\s*投标人须知|评标办法|评标办法前附表)'
|
||
end_pattern = re.compile(
|
||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 排除资质、能力、信誉的描述
|
||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表|投标人须知)', # 新增的匹配项
|
||
re.MULTILINE
|
||
)
|
||
start_page = None
|
||
end_page = None
|
||
|
||
# 从章节开始后的位置进行检查
|
||
for i, page in enumerate(pdf_document.pages[last_begin_index:], start=last_begin_index):
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
# 确定起始页，需在last_begin_index之后
|
||
if ("资格审查" in cleaned_text or "资质条件" in cleaned_text):
|
||
if re.search(common_pattern, cleaned_text, re.MULTILINE):
|
||
if start_page is None:
|
||
start_page = i # 确保起始页不小于章节的开始页码
|
||
# 确定结束页
|
||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||
if i > start_page:
|
||
end_page = i
|
||
break # 找到结束页后退出循环
|
||
|
||
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_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page)
|
||
elif output_suffix == "invalid":
|
||
pdf_document = PdfReader(pdf_path)
|
||
total_pages = len(pdf_document.pages)
|
||
# 计算总页数的三分之二
|
||
total = int(total_pages * 2 / 3)
|
||
start_page = last_begin_index
|
||
end_page = min(90, total)
|
||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page)
|
||
|
||
|
||
def extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||
common_header=extract_common_header(pdf_path)
|
||
# 打开PDF文件
|
||
pdf_document = PdfReader(pdf_path)
|
||
start_page = None
|
||
end_page = None
|
||
# 遍历文档的每一页，查找开始和结束短语的位置
|
||
for i in range(len(pdf_document.pages)):
|
||
page = pdf_document.pages[i]
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
# print(cleaned_text)
|
||
if re.search(begin_pattern, cleaned_text) and i > begin_page:
|
||
if output_suffix == "invalid" and start_page: # 仅当提取Invalid的时候，判断初始页码是第一个匹配到的页码，因为招标编号可能存在多个，后面的覆盖前面
|
||
continue
|
||
else:
|
||
start_page = i
|
||
if start_page is not None and re.search(end_pattern, cleaned_text):
|
||
# 如果output_suffix是"qualification"，调整条件检查
|
||
if output_suffix == "qualification":
|
||
condition = i > start_page
|
||
else:
|
||
condition = i > (start_page + 1)
|
||
if condition:
|
||
is_invalid_condition = output_suffix == "invalid" and i > 30 # 这边默认无效投标至少有30页
|
||
if is_invalid_condition or output_suffix != "invalid":
|
||
end_page = i
|
||
break
|
||
|
||
# 确保找到了起始和结束页面
|
||
if start_page is None or end_page is None:
|
||
if output_suffix == "qualification" or output_suffix =="invalid":
|
||
return extract_pages_twice(pdf_path, output_folder, output_suffix)
|
||
else:
|
||
print(f"first: 未找到起始或结束页在文件 {pdf_path} 中！")
|
||
return ""
|
||
else:
|
||
return save_pages_to_new_pdf(pdf_path, output_folder, output_suffix, start_page, end_page)
|
||
|
||
|
||
def process_input(input_path, output_folder, begin_pattern, begin_page, end_pattern, output_suffix):
|
||
# 确保输出文件夹存在
|
||
if not os.path.exists(output_folder):
|
||
os.makedirs(output_folder)
|
||
if os.path.isdir(input_path):
|
||
generated_files = []
|
||
# 遍历文件夹内的所有PDF文件
|
||
for file in os.listdir(input_path):
|
||
if file.endswith(".pdf"):
|
||
pdf_path = os.path.join(input_path, file)
|
||
output_pdf_path = extract_pages(pdf_path, output_folder, begin_pattern, begin_page, end_pattern,
|
||
output_suffix)
|
||
if output_pdf_path and os.path.isfile(output_pdf_path):
|
||
generated_files.append(output_pdf_path)
|
||
return generated_files
|
||
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 and os.path.isfile(output_pdf_path):
|
||
return [output_pdf_path] # 以列表形式返回，以保持一致性
|
||
else:
|
||
print("提供的路径既不是文件夹也不是PDF文件。")
|
||
return []
|
||
|
||
|
||
def truncate_pdf_main(input_path, output_folder, selection):
|
||
if selection == 1:
|
||
# Configure patterns and phrases for "投标人须知前附表"
|
||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知')
|
||
begin_page = 3
|
||
end_pattern = re.compile(r'投标人须知正文')
|
||
output_suffix = "tobidders_notice_table"
|
||
elif selection == 2:
|
||
# Configure patterns and phrases for "评标办法"
|
||
begin_pattern = re.compile(
|
||
r'第[一二三四五六七八九十]+章\s*评标办法') # 考虑到这种情况 '第三章 第三章 第三章 第三章 评标办法 评标办法 评标办法 评标办法'
|
||
begin_page = 10
|
||
end_pattern = re.compile(r'评标办法正文|评标办法')
|
||
output_suffix = "evaluation_method"
|
||
elif selection == 3:
|
||
# Configure patterns and phrases for "投标人须知正文"
|
||
begin_pattern = re.compile(r'投标人须知正文')
|
||
begin_page = 5
|
||
end_pattern = re.compile(
|
||
r'^第[一二三四五六七八九十]+章\s*评标办法|^评标办法前附表|^附录(?:一)?[：:]|^附件(?:一)?[：:]|^附表(?:一)?[：:]',
|
||
re.MULTILINE)
|
||
output_suffix = "tobidders_notice"
|
||
elif selection == 4:
|
||
# 配置用于 "资格审查条件" 的正则表达式模式和短语
|
||
common_pattern = r'^(?:附录(?:一)?[：:]|附件(?:一)?[：:]|附表(?:一)?[：:])'
|
||
begin_pattern = re.compile(common_pattern + r'.*(?:资质|能力|信誉).*$', re.MULTILINE)
|
||
begin_page = 5
|
||
end_pattern = re.compile(
|
||
common_pattern + r'(?!.*(?:资质|能力|信誉)).*$|' # 原有的模式
|
||
r'^(第[一二三四五六七八九十]+章\s*评标办法|评标办法前附表)', # 新增的匹配项
|
||
re.MULTILINE
|
||
)
|
||
output_suffix = "qualification"
|
||
elif selection == 5:
|
||
# 配置用于 "招标公告" 的正则表达式模式和短语
|
||
begin_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*招标公告|第一卷|投标邀请书')
|
||
begin_page = 0
|
||
end_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*投标人须知', re.MULTILINE)
|
||
output_suffix = "notice"
|
||
elif selection == 6:
|
||
# 配置用于 "无效标" 的正则表达式模式和短语
|
||
begin_pattern = re.compile(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：')
|
||
begin_page = 0
|
||
end_pattern = re.compile(r'第[一二三四五六七八九十]+章\s*合同|[：:]清标报告|第二卷', re.MULTILINE)
|
||
output_suffix = "invalid"
|
||
else:
|
||
print("无效的选择:请选择1-6")
|
||
return None
|
||
|
||
# Process the selected input
|
||
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, 5):
|
||
files = truncate_pdf_main(input_path, output_folder, selection)
|
||
truncate_files.extend(files)
|
||
return truncate_files
|
||
|
||
|
||
# TODO:需要完善二次请求。目前invalid一定能返回 前附表 须知正文如果为空的话要额外处理一下，比如说就不进行跳转（见xx表） 开评定标这里也要考虑 如果评分表为空，也要处理。
|
||
if __name__ == "__main__":
|
||
# input_path = "C:\\Users\\Administrator\\Desktop\\fsdownload\\4bda9fde-89fc-4e5e-94a4-ce6c43010f74\\ztbfile.pdf"
|
||
# output_folder = "C:\\Users\\Administrator\\Desktop\\fsdownload\\4bda9fde-89fc-4e5e-94a4-ce6c43010f74"
|
||
input_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest17.pdf"
|
||
output_folder="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\tmp"
|
||
truncate_pdf_multiple(input_path,output_folder)
|
||
# selection = 3 # 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-资格审查条件 5-招标公告 6-无效标
|
||
# generated_files = truncate_pdf_main(input_path, output_folder, selection)
|
||
# # print("生成的文件:", generated_files)
|