83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
|
import re
|
|||
|
|
|
|||
|
|
|
|||
|
|
def extract_common_header(pdf_path):
|
|||
|
|
from PyPDF2 import PdfReader
|
|||
|
|
|
|||
|
|
def get_headers(pdf_document, start_page, pages_to_read):
|
|||
|
|
headers = []
|
|||
|
|
for i in range(start_page, min(start_page + pages_to_read, len(pdf_document.pages))):
|
|||
|
|
page = pdf_document.pages[i]
|
|||
|
|
text = page.extract_text() or ""
|
|||
|
|
if text:
|
|||
|
|
# 只取每页的前三行，去除前后的空白字符
|
|||
|
|
first_lines = [line.strip() for line in text.strip().split('\n')[:3]]
|
|||
|
|
headers.append(first_lines)
|
|||
|
|
return headers
|
|||
|
|
|
|||
|
|
def find_common_headers(headers):
|
|||
|
|
if not headers:
|
|||
|
|
return []
|
|||
|
|
|
|||
|
|
# 使用 zip 对齐所有页的对应行
|
|||
|
|
common_headers = []
|
|||
|
|
for lines in zip(*headers):
|
|||
|
|
# 检查所有行是否完全相同
|
|||
|
|
if all(line == lines[0] for line in lines[1:]):
|
|||
|
|
common_headers.append(lines[0])
|
|||
|
|
return common_headers
|
|||
|
|
|
|||
|
|
pdf_document = PdfReader(pdf_path)
|
|||
|
|
total_pages = len(pdf_document.pages)
|
|||
|
|
|
|||
|
|
# 定义两个提取策略
|
|||
|
|
strategies = []
|
|||
|
|
if total_pages >= 3:
|
|||
|
|
# 策略1：中间的3页
|
|||
|
|
middle_page = total_pages // 2
|
|||
|
|
start_page = max(0, middle_page - 1)
|
|||
|
|
strategies.append((start_page, 3))
|
|||
|
|
elif total_pages == 2:
|
|||
|
|
# 策略1：2页
|
|||
|
|
strategies.append((0, 2))
|
|||
|
|
else:
|
|||
|
|
# 策略1：1页
|
|||
|
|
strategies.append((0, 1))
|
|||
|
|
|
|||
|
|
# 策略2：前三页
|
|||
|
|
if total_pages >= 3:
|
|||
|
|
strategies.append((0, 3))
|
|||
|
|
elif total_pages == 2:
|
|||
|
|
strategies.append((0, 2))
|
|||
|
|
elif total_pages == 1:
|
|||
|
|
strategies.append((0, 1))
|
|||
|
|
|
|||
|
|
common_headers = []
|
|||
|
|
|
|||
|
|
for idx, (start, count) in enumerate(strategies):
|
|||
|
|
headers = get_headers(pdf_document, start, count)
|
|||
|
|
if len(headers) < 2:
|
|||
|
|
continue # 需要至少2页来比较
|
|||
|
|
|
|||
|
|
current_common = find_common_headers(headers)
|
|||
|
|
if current_common:
|
|||
|
|
common_headers = current_common
|
|||
|
|
break # 找到共同部分后退出
|
|||
|
|
# 如果没有找到，继续下一个策略
|
|||
|
|
|
|||
|
|
return '\n'.join(common_headers)
|
|||
|
|
|
|||
|
|
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
|