2024-09-19 18:00:24 +08:00
|
|
|
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
|
|
|
|
|
|
|
|
|
|
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 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
|
|
|
|
|
if __name__ == '__main__':
|
2024-09-30 16:23:39 +08:00
|
|
|
file_path = "C:\\Users\\Administrator\\Desktop\\货物标\\output4\\ztbfile_tobidders_notice_part2.pdf"
|
2024-09-19 18:00:24 +08:00
|
|
|
res=extract_text_by_page(file_path)
|
|
|
|
|
# print(res)
|
