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

Merge branch 'develop-1.17' into develop

Browse Source
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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
flask_app/general/merge_pdfs.py
View File

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

2
flask_app/general/截取pdf_main.py
View File

@ -88,7 +88,6 @@ def truncate_pdf_multiple(pdf_path, output_folder, logger,mode='goods',selection
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,
@ -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.info("已截取文件路径: " + str(truncate_files))
print(truncate_files)
return truncate_files
if __name__ == "__main__":

14
flask_app/routes/小解析main.py
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。
"""
# 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)
if not files:
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
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
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='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
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）
@ -59,7 +59,7 @@ def little_parse_engineering(output_folder, pdf_path,logger):
dict: 包含 '基础信息' 的字典。
"""
# 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)
if not files:
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
# 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"
zb_type=1 #1:工程 2：货物
output_folder=r"C:\Users\Administrator\Desktop\fsdownload\20c9e7fa-0245-4de0-b004-d5231d0be940\tmp"
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\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")
with open(final_json_path, 'r', encoding='utf-8') as f:
# logger.info('final_json_path:' + final_json_path)