1

main.py

@@ -14,4 +14,5 @@ if __name__=='__main__':
     # sse = Sse()
     # sse.crawl()
     cninfo =Cninfo()
-    cninfo.download()
+    cninfo.download()
+

poetry.lock

@@ -293,6 +293,17 @@ ssh = ["bcrypt (>=3.1.5)"]
 test = ["certifi", "pretend", "pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-xdist"]
 test-randomorder = ["pytest-randomly"]
 
+[[package]]
+name = "et-xmlfile"
+version = "1.1.0"
+description = "An implementation of lxml.xmlfile for the standard library"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "et_xmlfile-1.1.0-py3-none-any.whl", hash = "sha256:a2ba85d1d6a74ef63837eed693bcb89c3f752169b0e3e7ae5b16ca5e1b3deada"},
+    {file = "et_xmlfile-1.1.0.tar.gz", hash = "sha256:8eb9e2bc2f8c97e37a2dc85a09ecdcdec9d8a396530a6d5a33b30b9a92da0c5c"},
+]
+
 [[package]]
 name = "h11"
 version = "0.14.0"
@@ -490,6 +501,20 @@ files = [
     {file = "numpy-2.0.0.tar.gz", hash = "sha256:cf5d1c9e6837f8af9f92b6bd3e86d513cdc11f60fd62185cc49ec7d1aba34864"},
 ]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.5"
+description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2"},
+    {file = "openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050"},
+]
+
+[package.dependencies]
+et-xmlfile = "*"
+
 [[package]]
 name = "outcome"
 version = "1.3.0.post0"
@@ -1067,4 +1092,4 @@ h11 = ">=0.9.0,<1"
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.12,<3.13"
-content-hash = "bfd4a770ce9f91676a24d972b9d00a621e41789dc44d950646738e1471032f1f"
+content-hash = "74e0a6a257c473378c36b26b8132dd1a8a067ca411adca35781be23db31c1212"

pyproject.toml

@@ -15,6 +15,7 @@ selenium = "4.11.2"
 webdriver-manager = "4.0.1"
 pdfplumber = "^0.11.1"
 pandas = "^2.2.2"
+openpyxl = "^3.1.5"
 
 
 [tool.poetry.group.dev.dependencies]

requirements.txt

@@ -6,4 +6,4 @@ selenium==4.11.2
 webdriver_manager==4.0.1
 pdfplumber
 pandas
-
+openpyxl

scripts/start_sse.bat

@@ -0,0 +1,13 @@
+@echo off
+REM ***************************************************************************
+REM @Contact :   liuyuqi.gov@msn.cn
+REM @Time    :   2024/07/03 18:54:02
+REM @Version :   1.0
+REM @License :   (C)Copyright 2019 liuyuqi.
+REM @Desc    :   None
+REM %1 - ext_name
+REM %2 - characters replaced
+REM %3 - new characters
+REM ***************************************************************************
+crawl_sse nianbao --download
+REM ./crawl_sse nianbao --download