127 lines
5.1 KiB
Python
127 lines
5.1 KiB
Python
|
import concurrent.futures
|
|||
|
|
import os
|
|||
|
|
import time
|
|||
|
|
|
|||
|
|
from flask_app.general.merge_pdfs import merge_selected_pdfs
|
|||
|
|
from flask_app.general.截取pdf通用函数 import check_pdf_pages
|
|||
|
|
from flask_app.general.通用功能函数 import get_global_logger
|
|||
|
|
from flask_app.工程标.截取pdf工程标版 import truncate_pdf_main_engineering
|
|||
|
|
from flask_app.货物标.截取pdf货物标版 import truncate_pdf_main_goods
|
|||
|
|
|
|||
|
|
|
|||
|
|
def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selections=None):
|
|||
|
|
"""
|
|||
|
|
统一的 PDF 截取和合并函数，支持 'goods' 和 'engineering' 两种模式，
|
|||
|
|
以及默认的全选和指定选择。
|
|||
|
|
|
|||
|
|
参数：
|
|||
|
|
- pdf_path (str): 输入的 PDF 文件路径。
|
|||
|
|
- output_folder (str): 输出文件夹路径。
|
|||
|
|
- logger (Logger): 日志记录器。
|
|||
|
|
- mode (str, 可选): 模式类型，支持 'goods' 和 'engineering'。默认为 'engineering'。
|
|||
|
|
- selections (List[int], 可选): 选择的模式列表，默认为 [1, 2, 3, 4, 5]。
|
|||
|
|
|
|||
|
|
返回:
|
|||
|
|
- list: 截取和合并后的文件路径列表，如果截取或合并失败，则包含空字符串。
|
|||
|
|
"""
|
|||
|
|
if selections is None:
|
|||
|
|
selections = [1, 2, 3, 4, 5]
|
|||
|
|
|
|||
|
|
# 确认模式有效
|
|||
|
|
if mode not in ['goods', 'engineering']:
|
|||
|
|
raise ValueError("mode 参数必须是 'goods' 或 'engineering'")
|
|||
|
|
def handle_exception(selection):
|
|||
|
|
return ["", ""] if selection == 4 else [""]
|
|||
|
|
# 设置模式相关的参数和函数
|
|||
|
|
if mode == 'goods':
|
|||
|
|
truncate_function = truncate_pdf_main_goods
|
|||
|
|
merge_mode = 'goods'
|
|||
|
|
|
|||
|
|
# 根据 'goods' 模式定义异常处理的逻辑
|
|||
|
|
else: # mode == 'engineering'
|
|||
|
|
truncate_function = truncate_pdf_main_engineering
|
|||
|
|
merge_mode = 'engineering'
|
|||
|
|
|
|||
|
|
mode_flag = 1
|
|||
|
|
num_selections = len(selections)
|
|||
|
|
if num_selections < 5:
|
|||
|
|
mode_flag = 2
|
|||
|
|
|
|||
|
|
res = check_pdf_pages(pdf_path, mode_flag, logger)
|
|||
|
|
if res is not None:
|
|||
|
|
return res # 返回包含空字符串的列表
|
|||
|
|
|
|||
|
|
base_file_name = os.path.splitext(os.path.basename(pdf_path))[0] # 纯文件名
|
|||
|
|
truncate_files = []
|
|||
|
|
|
|||
|
|
# 使用 ThreadPoolExecutor 进行多线程处理
|
|||
|
|
with concurrent.futures.ThreadPoolExecutor(max_workers=num_selections) as executor:
|
|||
|
|
# 提交所有任务并保持 selection 顺序
|
|||
|
|
future_to_selection = {
|
|||
|
|
selection: executor.submit(
|
|||
|
|
truncate_function,
|
|||
|
|
pdf_path,
|
|||
|
|
output_folder,
|
|||
|
|
selection,
|
|||
|
|
logger
|
|||
|
|
# 如果 'goods' 模式需要额外参数，如 output_suffix，可以在这里处理
|
|||
|
|
)
|
|||
|
|
for selection in selections
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
# 按 selection 顺序收集结果
|
|||
|
|
for selection in selections:
|
|||
|
|
future = future_to_selection.get(selection)
|
|||
|
|
try:
|
|||
|
|
files = future.result()
|
|||
|
|
if files:
|
|||
|
|
truncate_files.extend(files)
|
|||
|
|
# 无需额外处理，因为 `truncate_function` 已处理空字符串的添加和日志记录
|
|||
|
|
except Exception as e:
|
|||
|
|
logger.error(f"Selection {selection} 生成了一个异常: {e}")
|
|||
|
|
# 根据模式和 selection 添加相应数量的空字符串
|
|||
|
|
truncate_files.extend(handle_exception(selection))
|
|||
|
|
|
|||
|
|
# 定义合并后的输出路径
|
|||
|
|
merged_output_path = os.path.join(output_folder, f"{base_file_name}_merged_baseinfo.pdf")
|
|||
|
|
|
|||
|
|
# 调用 merge_selected_pdfs 并获取返回值
|
|||
|
|
merged_path = merge_selected_pdfs(
|
|||
|
|
output_folder,
|
|||
|
|
truncate_files,
|
|||
|
|
merged_output_path,
|
|||
|
|
base_file_name,
|
|||
|
|
mode=merge_mode
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
if merged_path:
|
|||
|
|
# 合并成功，添加合并后的文件路径
|
|||
|
|
truncate_files.append(merged_path)
|
|||
|
|
logger.info(f"已成功合并 PDF 文件到 '{merged_output_path}'。")
|
|||
|
|
else:
|
|||
|
|
# 合并失败，添加空字符串
|
|||
|
|
truncate_files.append("")
|
|||
|
|
logger.warning(f"合并失败，没有生成合并文件 for {pdf_path}")
|
|||
|
|
|
|||
|
|
logger.info("已截取文件路径: " + str(truncate_files))
|
|||
|
|
return truncate_files
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
logger=get_global_logger("123")
|
|||
|
|
start_time = time.time()
|
|||
|
|
# input_path = r"C:\Users\Administrator\Desktop\new招标文件\工程标"
|
|||
|
|
pdf_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest5.pdf"
|
|||
|
|
|
|||
|
|
# pdf_path = r"C:\Users\Administrator\Desktop\招标文件\招标02.pdf"
|
|||
|
|
# input_path=r"C:\Users\Administrator\Desktop\招标文件\招标test文件夹\zbtest8.pdf"
|
|||
|
|
output_folder = r"C:\Users\Administrator\Desktop\fsdownload\91399aa4-1ee8-447d-a05b-03cd8d15ced5\tmp"
|
|||
|
|
# selections = [1, 4] # 仅处理 selection 4、1
|
|||
|
|
selections=[5]
|
|||
|
|
files=truncate_pdf_multiple(pdf_path,output_folder,logger,'engineering',selections)
|
|||
|
|
print(files)
|
|||
|
|
# selection = 1 # 例如：1 - 招标公告, 2 - 评标办法, 3 -资格审查条件 4-投标人须知前附表+正文 5-无效标
|
|||
|
|
# generated_files = truncate_pdf_main_engineering(pdf_path, output_folder, selection,logger)
|
|||
|
|
# print(generated_files)
|
|||
|
|
# print("生成的文件:", generated_files)
|
|||
|
|
end_time = time.time()
|
|||
|
|
print("耗时：" + str(end_time - start_time))
|