160 lines
5.9 KiB
Python
160 lines
5.9 KiB
Python
import PyPDF2
|
||
import re # 导入正则表达式库
|
||
|
||
from PyPDF2 import PdfReader
|
||
|
||
|
||
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
|
||
text = re.sub(r'\s*[—-]\s*\d+\s*[—-]\s*', '', text) # 删除形如 '—2—' 或 '-2-' 的页码
|
||
return text
|
||
def extract_common_header(pdf_path):
|
||
from PyPDF2 import PdfReader
|
||
|
||
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，按顺序保留
|
||
common_headers = []
|
||
for lines in zip(*headers):
|
||
# 提取第一行的词汇顺序
|
||
first_words = lines[0].split()
|
||
# 筛选所有页面都包含的词汇，保持顺序
|
||
common_line = [word for word in first_words if all(word in line.split() for line in lines[1:])]
|
||
if common_line:
|
||
common_headers.append(' '.join(common_line))
|
||
|
||
return '\n'.join(common_headers)
|
||
|
||
|
||
def extract_text_by_page(file_path):
|
||
common_header = extract_common_header(file_path)
|
||
result = ""
|
||
with open(file_path, 'rb') as file:
|
||
reader = PyPDF2.PdfReader(file)
|
||
num_pages = len(reader.pages)
|
||
# print(f"Total pages: {num_pages}")
|
||
for page_num in range(num_pages):
|
||
page = reader.pages[page_num]
|
||
text = page.extract_text()
|
||
if text:
|
||
cleaned_text = clean_page_content(text,common_header)
|
||
print(cleaned_text)
|
||
result += cleaned_text
|
||
# print(f"Page {page_num + 1} Content:\n{cleaned_text}")
|
||
else:
|
||
print(f"Page {page_num + 1} is empty or text could not be extracted.")
|
||
return result
|
||
|
||
# import fitz # PyMuPDF
|
||
# import re
|
||
#
|
||
#
|
||
# def clean_page_content(text, common_header):
|
||
# if common_header:
|
||
# for header_line in common_header.split('\n'):
|
||
# if header_line.strip():
|
||
# text = re.sub(r'^' + re.escape(header_line.strip()) + r'\n?', '', text, count=1)
|
||
#
|
||
# text = re.sub(r'^\s*\d+\s*(?=\D)', '', text)
|
||
# text = re.sub(r'\s+\d+\s*$', '', text)
|
||
# text = re.sub(r'\s*\/\s*\d+\s*', '', text)
|
||
#
|
||
# return text
|
||
#
|
||
#
|
||
# def extract_common_header(pdf_path):
|
||
# doc = fitz.open(pdf_path)
|
||
# headers = []
|
||
# total_pages = len(doc)
|
||
#
|
||
# 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 = doc[i]
|
||
# text = page.get_text()
|
||
# if text:
|
||
# first_lines = text.strip().split('\n')[:3]
|
||
# headers.append(first_lines)
|
||
#
|
||
# doc.close()
|
||
#
|
||
# if len(headers) < 2:
|
||
# return ""
|
||
#
|
||
# common_headers = []
|
||
# for lines in zip(*headers):
|
||
# 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 extract_text_by_page(file_path):
|
||
# common_header = extract_common_header(file_path)
|
||
# result = ""
|
||
# doc = fitz.open(file_path)
|
||
# num_pages = len(doc)
|
||
#
|
||
# for page_num in range(num_pages):
|
||
# page = doc[page_num]
|
||
# text = page.get_text()
|
||
# if text:
|
||
# cleaned_text = clean_page_content(text, common_header)
|
||
# print(cleaned_text)
|
||
# result += cleaned_text
|
||
# else:
|
||
# print(f"Page {page_num + 1} is empty or text could not be extracted.")
|
||
#
|
||
# doc.close()
|
||
# return result
|
||
|
||
|
||
if __name__ == '__main__':
|
||
# file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\output4\\广水农商行门禁控制主机及基础验证设备采购项目——磋商文件（定稿）（三次）_tobidders_notice_part2.pdf'
|
||
# file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\output4\\2-招标文件（2020年广水市中小学教师办公电脑系统及多媒体“班班通”设备采购安装项目）_tobidders_notice_part2.pdf'
|
||
# file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\output4\\磋商文件_tobidders_notice_part2.pdf'
|
||
# file_path = 'C:\\Users\\Administrator\\Desktop\\货物标\\截取test\\交警支队机动车查验监管系统项目采购_tobidders_notice_part1.pdf'
|
||
file_path="C:\\Users\\Administrator\\Desktop\\招标文件\\招标test文件夹\\zbtest18.pdf"
|
||
# ress = extract_common_header(file_path)
|
||
# print(ress)
|
||
res=extract_text_by_page(file_path)
|
||
# print(res)磋商文件_tobidders_notice_part2.pdf |