Merge branch 'develop-1.17' into develop

This commit is contained in:
zy123 2025-01-21 17:21:54 +08:00
commit ccb6043189
3 changed files with 9 additions and 9 deletions

View File

@ -171,7 +171,7 @@ def merge_selected_pdfs(output_folder, truncate_files, output_path, base_file_na
required_suffixes = [ required_suffixes = [
f'{base_file_name}_before.pdf', f'{base_file_name}_before.pdf',
f'{base_file_name}_notice.pdf', f'{base_file_name}_notice.pdf',
f'{base_file_name}_tobidders_notice_table1.pdf' f'{base_file_name}_tobidders_notice_part1.pdf'
] ]
optional_suffixes = [] optional_suffixes = []
elif mode == 'goods': elif mode == 'goods':

View File

@ -88,7 +88,6 @@ def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selection
truncate_files.extend(handle_exception(selection)) truncate_files.extend(handle_exception(selection))
# 定义合并后的输出路径 # 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") 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 # 调用 merge_selected_pdfs 并获取返回值
merged_path = merge_selected_pdfs( merged_path = merge_selected_pdfs(
output_folder, output_folder,
@ -111,6 +110,7 @@ def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selection
logger.warning(f"合并失败,没有生成合并文件 for {pdf_path}") 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)) logger.info("已截取文件路径: " + str(truncate_files))
print(truncate_files)
return truncate_files return truncate_files
if __name__ == "__main__": if __name__ == "__main__":

View File

@ -23,7 +23,7 @@ def little_parse_goods(output_folder, pdf_path,logger):
dict: 包含 '基础信息' 的字典 dict: 包含 '基础信息' 的字典
""" """
# 截取特定的货物 PDF 文件 # 截取特定的货物 PDF 文件
selections = [1,4,6] # 仅处理 selection 1和4 #公告+投标人须知 selections = [1,4] # 仅处理 selection 1和4 #公告+投标人须知
files = truncate_pdf_multiple(pdf_path, output_folder,logger,'goods',selections) files = truncate_pdf_multiple(pdf_path, output_folder,logger,'goods',selections)
if not files: if not files:
raise ValueError("未找到截取后的文件。") raise ValueError("未找到截取后的文件。")
@ -34,8 +34,8 @@ def little_parse_goods(output_folder, pdf_path,logger):
# 上传文件并获取文件 ID # 上传文件并获取文件 ID
file_id = upload_file(baseinfo_file_path) file_id = upload_file(baseinfo_file_path)
# 注意:以下路径被硬编码,确保该路径存在并且正确 # 注意:以下路径被硬编码,确保该路径存在并且正确
baseinfo_prompt_file_path='flask_app/static/提示词/小解析基本信息货物标.txt' # baseinfo_prompt_file_path='flask_app/static/提示词/小解析基本信息货物标.txt'
# baseinfo_prompt_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\小解析基本信息货物标.txt' baseinfo_prompt_file_path = 'D:\\flask_project\\flask_app\\static\\提示词\\小解析基本信息货物标.txt'
# 从提示词文件中读取问题 # 从提示词文件中读取问题
questions = read_questions_from_file(baseinfo_prompt_file_path) questions = read_questions_from_file(baseinfo_prompt_file_path)
# 多线程处理问题使用指定的处理模式2 代表使用 qianwen-long # 多线程处理问题使用指定的处理模式2 代表使用 qianwen-long
@ -59,7 +59,7 @@ def little_parse_engineering(output_folder, pdf_path,logger):
dict: 包含 '基础信息' 的字典 dict: 包含 '基础信息' 的字典
""" """
# 截取特定的工程 PDF 文件 # 截取特定的工程 PDF 文件
selections = [ 1,4] #公告+投标人须知前附表 selections = [1,4] #公告+投标人须知前附表
files = truncate_pdf_multiple(pdf_path, output_folder,logger,'engineering',selections) files = truncate_pdf_multiple(pdf_path, output_folder,logger,'engineering',selections)
if not files: if not files:
raise ValueError("未找到截取后的文件。") raise ValueError("未找到截取后的文件。")
@ -139,10 +139,10 @@ if __name__ == "__main__":
# zb_type=2 #1:工程标 2货物标 # zb_type=2 #1:工程标 2货物标
# input_file = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\ztbfile.pdf" # input_file = "C:\\Users\\Administrator\\Desktop\\货物标\\zbfiles\\ztbfile.pdf"
output_folder=r"C:\Users\Administrator\Desktop\fsdownload\b18e9c17-e866-4116-8db3-aaab722d1463\tmp" output_folder=r"C:\Users\Administrator\Desktop\fsdownload\20c9e7fa-0245-4de0-b004-d5231d0be940\tmp"
zb_type=1 #1:工程 2货物 zb_type=2 #1:工程 2货物
# input_file=r"C:\Users\Administrator\Desktop\fsdownload\865a5d46-a5f8-467a-8374-c71c415d0af9\ztbfile.pdf" # input_file=r"C:\Users\Administrator\Desktop\fsdownload\865a5d46-a5f8-467a-8374-c71c415d0af9\ztbfile.pdf"
input_file=r"C:\Users\Administrator\Desktop\fsdownload\b18e9c17-e866-4116-8db3-aaab722d1463\ztbfile.pdf" input_file=r"C:\Users\Administrator\Desktop\fsdownload\20c9e7fa-0245-4de0-b004-d5231d0be940\ztbfile.pdf"
final_json_path=little_parse_main(output_folder, input_file, file_type, zb_type,"122334") final_json_path=little_parse_main(output_folder, input_file, file_type, zb_type,"122334")
with open(final_json_path, 'r', encoding='utf-8') as f: with open(final_json_path, 'r', encoding='utf-8') as f:
# logger.info('final_json_path:' + final_json_path) # logger.info('final_json_path:' + final_json_path)