107 lines
3.9 KiB
Python
107 lines
3.9 KiB
Python
import PyPDF2
|
|
from flask_app.general.clean_pdf import extract_common_header, clean_page_content
|
|
|
|
def extract_text_by_page(file_path):
|
|
common_header = extract_common_header(file_path)
|
|
print(f"公共抬头：{common_header}")
|
|
print("--------------------正文开始-------------------")
|
|
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:
|
|
print("-------------------")
|
|
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='D:\\flask_project\\flask_app\\static\\output\\output1\\648e094b-e677-47ce-9073-09e0c82af210\\ztbfile_tobidders_notice_part2.pdf'
|
|
file_path =r"C:\Users\Administrator\Desktop\货物标\output4_2\招标文件111_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\\zbtest8.pdf"
|
|
# file_path="C:\\Users\\Administrator\\Desktop\\fsdownload\\45f650ce-e519-457b-9ad6-5840e2ede539\\ztbfile_procurement.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 |