58 lines
2.4 KiB
Python
58 lines
2.4 KiB
Python
import os
|
|
|
|
from PyPDF2 import PdfReader, PdfWriter
|
|
#合并PDF
|
|
def merge_pdfs(paths, output_path):
|
|
pdf_writer = PdfWriter()
|
|
last_page_text = None # 用于存储上一个PDF的最后一页的文本
|
|
|
|
for path in paths:
|
|
pdf_reader = PdfReader(path)
|
|
pages = pdf_reader.pages
|
|
start_index = 0 # 从第一页开始添加
|
|
|
|
# 如果这不是第一个文件，并且有上一个文件的最后一页文本
|
|
if last_page_text is not None and len(pages) > 0:
|
|
current_first_page_text = pages[0].extract_text() if pages[0].extract_text() else ""
|
|
# 比较当前文件的第一页和上一个文件的最后一页的文本
|
|
if current_first_page_text == last_page_text:
|
|
start_index = 1 # 如果相同，跳过当前文件的第一页
|
|
|
|
# 添加当前PDF的页面到写入器
|
|
for page in range(start_index, len(pages)):
|
|
pdf_writer.add_page(pages[page])
|
|
|
|
# 更新last_page_text为当前PDF的最后一页的文本
|
|
if len(pages) > 0:
|
|
last_page_text = pages[-1].extract_text() if pages[-1].extract_text() else ""
|
|
|
|
# 写入合并后的PDF到文件
|
|
with open(output_path, 'wb') as out:
|
|
pdf_writer.write(out)
|
|
|
|
def judge_file_exist(original_path, new_suffix):
|
|
# 提取目录路径和原始文件名
|
|
directory = os.path.dirname(original_path)
|
|
original_filename = os.path.basename(original_path)
|
|
|
|
# 替换文件名中的旧后缀为新后缀
|
|
# 假设原始文件名格式为 '2-招标文件_qualification.pdf'
|
|
# 需要替换 '_qualification' 部分为 '_qualification2'
|
|
new_filename = original_filename.replace("_qualification1", f"_{new_suffix}")
|
|
new_filename = new_filename.replace("_qualification2", f"_{new_suffix}")
|
|
# 生成新的文件路径
|
|
new_file_path = os.path.join(directory, new_filename)
|
|
|
|
# 检查新文件是否存在
|
|
if os.path.isfile(new_file_path):
|
|
return new_file_path
|
|
else:
|
|
return None
|
|
|
|
def merge_and_cleanup(output_pdf_path, suffix_to_merge):
|
|
another_file_path = judge_file_exist(output_pdf_path, suffix_to_merge)
|
|
if another_file_path:
|
|
paths = [output_pdf_path, another_file_path] # 需要合并的 PDF 文件路径
|
|
merge_pdfs(paths, output_pdf_path)
|
|
os.remove(another_file_path)
|
|
print(f"文件 {another_file_path} 已删除。") |