zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

2.15 排查截取pdf

Browse Source
This commit is contained in:
zy123 2025-02-15 14:47:26 +08:00
parent add2bad285
commit 110d1767f4
1 changed files with 19 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
flask_app/routes/货物标解析main.py
View File

@ -55,22 +55,25 @@ def preprocess_files(output_folder, file_path, file_type,logger):
invalid_path = truncate_files[6] if truncate_files[6] != "" else pdf_path #无效标（投标文件格式\合同条款之前的内容）
truncate_endtime = time.time()
logger.info(f"文件切分CPU耗时：{truncate_endtime - start_time:.2f} 秒")
if not is_pure_image_flag:
invalid_added_pdf = insert_mark(invalid_path)
invalid_added_docx = pdf2docx(invalid_added_pdf) # 有标记的invalid_path，用于废标项提取，使用正则。
try:
# 尝试加载 .docx 文件
doc = Document(invalid_added_docx)
# print("yes")
except Exception as e:
# 捕获异常并打印错误信息
invalid_added_docx=pdf2docx(invalid_path)
invalid_deleted_docx = delete_mark(invalid_added_docx) # 无标记的invalid_path
if not invalid_deleted_docx:
invalid_deleted_docx=pdf2docx(invalid_path)
else: #主要是节约了pdf2docx的一块钱
invalid_deleted_docx=file_path
invalid_added_docx='' #由于传入的docx是纯图片型，正则是提取不到的，需要调用大模型。
# if not is_pure_image_flag:
# invalid_added_pdf = insert_mark(invalid_path)
# change_start=time.time()
# invalid_added_docx = pdf2docx(invalid_added_pdf) # 有标记的invalid_path，用于废标项提取，使用正则。
# change_end=time.time()
# logger.info(f"文档转换p2d耗时：{change_end - change_start:.2f} 秒")
# try:
# # 尝试加载 .docx 文件
# doc = Document(invalid_added_docx)
# # print("yes")
# except Exception as e:
# # 捕获异常并打印错误信息
# invalid_added_docx=pdf2docx(invalid_path)
# invalid_deleted_docx = delete_mark(invalid_added_docx) # 无标记的invalid_path
# if not invalid_deleted_docx:
# invalid_deleted_docx=pdf2docx(invalid_path)
# else: #主要是节约了pdf2docx的一块钱
invalid_deleted_docx=file_path
invalid_added_docx='' #由于传入的docx是纯图片型，正则是提取不到的，需要调用大模型。
end_time = time.time()
logger.info(f"文件预处理总耗时：{end_time - start_time:.2f} 秒")