crawl path update

anhui/__init__.py

@@ -0,0 +1,11 @@
+import os
+from pathlib import Path
+
+script_dir = os.path.dirname(os.path.abspath(__file__))
+download_dir = os.path.join(script_dir, 'downloads')
+# 创建目录（如果不存在）
+os.makedirs(download_dir, exist_ok=True)
+# 切换当前工作目录到 download_dir
+os.chdir(download_dir)
+Path(download_dir).mkdir(parents=True, exist_ok=True)
+print("最终工作目录:", os.getcwd())

anhui/crawl_gov_anhui_full.py

@@ -1,7 +1,6 @@
 import os
 import random
 import re
-import sys
 import time
 from datetime import datetime, timedelta
 from pathlib import Path
@@ -13,15 +12,12 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import WebDriverWait
 
-import gov_commodity_anhui_city
-import gov_commodity_anhui_country
-import gov_commodity_anhui_import_export
+from anhui import gov_commodity_anhui_city, download_dir
+from anhui import gov_commodity_anhui_country
+from anhui import gov_commodity_anhui_import_export
 from utils import base_country_code, base_mysql
 from utils.log import log
 
-download_dir = base_country_code.download_dir
-Path(download_dir).mkdir(parents=True, exist_ok=True)
-
 def configure_stealth_options():
     """增强型反检测配置[1,4](@ref)"""
     opts = FirefoxOptions()
@@ -202,7 +198,8 @@ def crawl_with_selenium(url, mark):
         res = detect_latest_month(driver, url)
         if res is None:
             log.info("安徽省海关没有最新数据更新")
-            sys.exit(0)
+            # sys.exit(0)
+            return None
         year_month = res
         print(f"检测到最新有效数据：{year_month}")
 
@@ -251,6 +248,16 @@ def crawl_with_selenium(url, mark):
 
     finally:
         driver.quit()
+        print(f"安徽合肥海关全量数据下载任务完成")
+        # 等待5s后执行
+        time.sleep(5)
+        hierarchical_traversal(download_dir)
+        print("安徽合肥海关类章、国家、城市所有文件处理完成！")
+        time.sleep(5)
+        base_mysql.update_january_yoy('安徽省')
+        base_mysql.update_shandong_yoy('安徽省')
+        print("安徽合肥海关城市同比sql处理完成")
+
 
 def wait_for_download_complete(timeout=30, existing_files=None):
     """
@@ -311,16 +318,18 @@ def hierarchical_traversal(root_path):
                 gov_commodity_anhui_country.process_folder(md['path'])
                 gov_commodity_anhui_city.process_folder(md['path'])
 
-if __name__ == "__main__":
+def main():
     crawl_with_selenium('http://hefei.customs.gov.cn/hefei_customs/zfxxgkzl59/3169584/479584/479585/index.html', 'all')
     # crawl_with_selenium('http://hefei.customs.gov.cn/hefei_customs/zfxxgkzl59/3169584/479584/479585/index.html', 'increment')
-    print(f"安徽合肥海关全量数据下载任务完成")
-    # 等待5s后执行
-    time.sleep(5)
-    hierarchical_traversal(base_country_code.download_dir)
-    print("安徽合肥海关类章、国家、城市所有文件处理完成！")
-    time.sleep(5)
-    base_mysql.update_january_yoy('安徽省')
-    base_mysql.update_shandong_yoy('安徽省')
-    print("安徽合肥海关城市同比sql处理完成")
-
+    # print(f"安徽合肥海关全量数据下载任务完成")
+    # # 等待5s后执行
+    # time.sleep(5)
+    # hierarchical_traversal(base_country_code.download_dir)
+    # print("安徽合肥海关类章、国家、城市所有文件处理完成！")
+    # time.sleep(5)
+    # base_mysql.update_january_yoy('安徽省')
+    # base_mysql.update_shandong_yoy('安徽省')
+    # print("安徽合肥海关城市同比sql处理完成")
+
+if __name__ == '__main__':
+    main()

anhui/gov_commodity_anhui_city.py

@@ -1,8 +1,8 @@
-import time
 from pathlib import Path
 
 import pandas as pd
 
+from anhui import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -126,5 +126,5 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info(f"安徽合肥海关城市所有文件处理完成！")

anhui/gov_commodity_anhui_country.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from anhui import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -135,5 +136,5 @@ def hierarchical_traversal(root_path):
 
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info("安徽合肥海关国别所有文件处理完成！")

anhui/gov_commodity_anhui_import_export.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from anhui import download_dir
 from utils import base_country_code, base_mysql
 
 from utils.base_country_code import format_sql_value
@@ -175,7 +176,7 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
 
     # root = Path(base_country_code.download_dir)/'2025'/'04'
     # process_folder(root)

auto_incre_main.py

@@ -0,0 +1,19 @@
+from anhui import crawl_gov_anhui_full
+from hebei import crawl_gov_hebei_full
+from jiangsu import crawl_gov_jiangsu_full
+from zhejiang import crawl_gov_zhejiang_full
+from fujian import selenium_fujian_download
+from henan import selenium_henan_download
+from shandong import selenium_shandong_download
+from guangdong import selenium_guangdong_download
+
+# test
+if __name__ == '__main__':
+    crawl_gov_anhui_full.main()
+    crawl_gov_hebei_full.main()
+    crawl_gov_jiangsu_full.main()
+    crawl_gov_zhejiang_full.main()
+    selenium_fujian_download.main()
+    selenium_henan_download.main()
+    selenium_shandong_download.main()
+    selenium_guangdong_download.main()

hebei/__init__.py

@@ -0,0 +1,11 @@
+import os
+from pathlib import Path
+
+script_dir = os.path.dirname(os.path.abspath(__file__))
+download_dir = os.path.join(script_dir, 'downloads')
+# 创建目录（如果不存在）
+os.makedirs(download_dir, exist_ok=True)
+# 切换当前工作目录到 download_dir
+os.chdir(download_dir)
+Path(download_dir).mkdir(parents=True, exist_ok=True)
+print("最终工作目录:", os.getcwd())

hebei/crawl_gov_hebei_full.py

@@ -2,9 +2,8 @@ import os
 import random
 import re
 import time
-import sys
-from pathlib import Path
 from datetime import datetime, timedelta
+from pathlib import Path
 
 from faker import Faker
 from selenium import webdriver
@@ -13,15 +12,13 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import WebDriverWait
 
+from hebei import download_dir
+from hebei import gov_commodity_hebei_city
+from hebei import gov_commodity_hebei_country
+from hebei import gov_commodity_hebei_import_export
 from utils import base_country_code, base_mysql
-import gov_commodity_hebei_import_export
-import gov_commodity_hebei_country
-import gov_commodity_hebei_city
 from utils.log import log
 
-download_dir = base_country_code.download_dir
-Path(download_dir).mkdir(parents=True, exist_ok=True)
-
 
 def get_current_target_titles():
     return [
@@ -179,7 +176,8 @@ def crawl_with_selenium(url, mark):
         res = detect_latest_month(driver, url)
         if res is None:
             log.info("河北省海关没有最新数据更新")
-            sys.exit(0)
+            # sys.exit(0)
+            return
         year_month = res
         print(f"检测到最新有效数据：{year_month}")
 
@@ -227,6 +225,14 @@ def crawl_with_selenium(url, mark):
             log.info(f"开始爬取 {next_page_url} 页面数据")
     finally:
         driver.quit()
+        # 等待5s后执行
+        time.sleep(5)
+        hierarchical_traversal(download_dir)
+        log.info(f"河北石家庄海关全量数据下载任务完成")
+        time.sleep(5)
+        base_mysql.update_january_yoy('河北省')
+        base_mysql.update_shandong_yoy('河北省')
+        log.info("河北石家庄海关城市同比sql处理完成")
 
 def wait_for_download_complete(timeout=30, existing_files=None):
     """
@@ -289,14 +295,17 @@ def hierarchical_traversal(root_path):
                 gov_commodity_hebei_city.process_folder(md['path'])
 
 
-if __name__ == "__main__":
-    crawl_with_selenium('http://shijiazhuang.customs.gov.cn/shijiazhuang_customs/zfxxgk43/2988665/2988681/index.html', 'all')
-    # crawl_with_selenium('http://shijiazhuang.customs.gov.cn/shijiazhuang_customs/zfxxgk43/2988665/2988681/index.html', 'increment')
+def main():
+    # crawl_with_selenium('http://shijiazhuang.customs.gov.cn/shijiazhuang_customs/zfxxgk43/2988665/2988681/index.html', 'all')
+    crawl_with_selenium('http://shijiazhuang.customs.gov.cn/shijiazhuang_customs/zfxxgk43/2988665/2988681/index.html', 'increment')
     # 等待5s后执行
-    time.sleep(5)
-    hierarchical_traversal(base_country_code.download_dir)
-    log.info(f"河北石家庄海关全量数据下载任务完成")
-    time.sleep(5)
-    base_mysql.update_january_yoy('河北省')
-    base_mysql.update_shandong_yoy('河北省')
-    log.info("河北石家庄海关城市同比sql处理完成")
+    # time.sleep(5)
+    # hierarchical_traversal(base_country_code.download_dir)
+    # log.info(f"河北石家庄海关全量数据下载任务完成")
+    # time.sleep(5)
+    # base_mysql.update_january_yoy('河北省')
+    # base_mysql.update_shandong_yoy('河北省')
+    # log.info("河北石家庄海关城市同比sql处理完成")
+
+if __name__ == '__main__':
+    main()

hebei/gov_commodity_hebei_city.py

@@ -3,6 +3,7 @@ from pathlib import Path
 import pandas
 import pandas as pd
 
+from hebei import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -122,5 +123,5 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info(f"河北石家庄海关城市所有文件处理完成！")

hebei/gov_commodity_hebei_country.py

@@ -3,6 +3,7 @@ from pathlib import Path
 import pandas
 import pandas as pd
 
+from hebei import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -117,5 +118,5 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info(f"河北石家庄海关国家的所有文件处理完成！")

hebei/gov_commodity_hebei_import_export.py

@@ -4,6 +4,7 @@ import pandas as pd
 import re
 from utils.log import log
 
+from hebei import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 
@@ -178,8 +179,8 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
 
-    # root = Path(base_country_code.download_dir)/'2023'/'02'
+    # root = Path(download_dir)/'2023'/'02'
     # process_folder(root)
     log.info(f"河北石家庄海关出入口商品所有文件处理完成！")

jiangsu/__init__.py

@@ -0,0 +1,11 @@
+import os
+from pathlib import Path
+
+script_dir = os.path.dirname(os.path.abspath(__file__))
+download_dir = os.path.join(script_dir, 'downloads')
+# 创建目录（如果不存在）
+os.makedirs(download_dir, exist_ok=True)
+# 切换当前工作目录到 download_dir
+os.chdir(download_dir)
+Path(download_dir).mkdir(parents=True, exist_ok=True)
+print("最终工作目录:", os.getcwd())

jiangsu/crawl_gov_jiangsu_full.py

@@ -15,17 +15,17 @@ from selenium.webdriver import FirefoxOptions
 from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import WebDriverWait
-import gov_commodity_jiangsu_country
-import gov_commodity_jiangsu_city
-import gov_commodity_jiangsu_import_export
+
+from jiangsu import download_dir
+from jiangsu import gov_commodity_jiangsu_country
+from jiangsu import gov_commodity_jiangsu_city
+from jiangsu import gov_commodity_jiangsu_import_export
 
 from utils import base_country_code, base_mysql
 from utils.log import log
 
 # rarfile.UNRAR_EXECUTABLE = r"C:\Program Files\WinRAR\UnRAR.exe"
 rarfile.UNRAR_EXECUTABLE = "unrar"
-download_dir = base_country_code.download_dir
-Path(download_dir).mkdir(parents=True, exist_ok=True)
 
 def configure_stealth_options():
     """增强型反检测配置[1,4](@ref)"""
@@ -217,7 +217,8 @@ def crawl_with_selenium(url, mark):
         res = detect_latest_month(driver, url)
         if res is None:
             log.info("江苏省海关没有最新数据更新")
-            sys.exit(0)
+            # sys.exit(0)
+            return
         year_month = res
         print(f"检测到最新有效数据：{year_month}")
 
@@ -266,6 +267,16 @@ def crawl_with_selenium(url, mark):
 
     finally:
         driver.quit()
+        log.info(f"江苏南京海关全量数据下载任务完成")
+        # 等待5s后执行
+        time.sleep(5)
+        all_records = base_mysql.get_hs_all()
+        hierarchical_traversal(download_dir, all_records)
+        log.info("江苏南京海关类章、国家、城市所有文件处理完成！")
+        time.sleep(5)
+        base_mysql.update_january_yoy('江苏省')
+        base_mysql.update_shandong_yoy('江苏省')
+        log.info("江苏南京海关城市同比sql处理完成")
 
 
 def wait_for_download_complete(timeout=30, existing_files=None):
@@ -321,17 +332,19 @@ def hierarchical_traversal(root_path, all_records):
                 gov_commodity_jiangsu_country.process_folder(md['path'])
                 gov_commodity_jiangsu_city.process_folder(md['path'])
 
-if __name__ == "__main__":
+def main():
     crawl_with_selenium('http://nanjing.customs.gov.cn/nanjing_customs/zfxxgk58/fdzdgknr95/3010051/589289/7e2fcc72-1.html', 'all')
     # crawl_with_selenium('http://nanjing.customs.gov.cn/nanjing_customs/zfxxgk58/fdzdgknr95/3010051/589289/7e2fcc72-1.html', 'increment')
-    log.info(f"江苏南京海关全量数据下载任务完成")
-    # 等待5s后执行
-    time.sleep(5)
-    all_records = base_mysql.get_hs_all()
-    hierarchical_traversal(base_country_code.download_dir, all_records)
-    log.info("江苏南京海关类章、国家、城市所有文件处理完成！")
-    time.sleep(5)
-    base_mysql.update_january_yoy('江苏省')
-    base_mysql.update_shandong_yoy('江苏省')
-    log.info("江苏南京海关城市同比sql处理完成")
-
+    # log.info(f"江苏南京海关全量数据下载任务完成")
+    # # 等待5s后执行
+    # time.sleep(5)
+    # all_records = base_mysql.get_hs_all()
+    # hierarchical_traversal(base_country_code.download_dir, all_records)
+    # log.info("江苏南京海关类章、国家、城市所有文件处理完成！")
+    # time.sleep(5)
+    # base_mysql.update_january_yoy('江苏省')
+    # base_mysql.update_shandong_yoy('江苏省')
+    # log.info("江苏南京海关城市同比sql处理完成")
+
+if __name__ == '__main__':
+    main()

jiangsu/gov_commodity_jiangsu_city.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from jiangsu import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -127,7 +128,7 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info(f"江苏南京海关城市所有文件处理完成！")
     time.sleep(5)
     base_mysql.update_january_yoy('江苏省')

jiangsu/gov_commodity_jiangsu_country.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from jiangsu import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -129,5 +130,5 @@ def hierarchical_traversal(root_path):
 
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info("江苏南京海关国别所有文件处理完成！")

jiangsu/gov_commodity_jiangsu_import_export.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from jiangsu import download_dir
 from utils import base_country_code, base_mysql
 from utils.log import log
 
@@ -56,12 +57,12 @@ def process_folder(path, all_records):
                 file_path = Path(path) / file
                 df = pd.read_excel(file_path, header=None).iloc[6:]
 
-                temp_df = df[[1, 5]].rename(columns={1: 'commodity', 5: 'import'})
+                temp_df = df[[1, 6]].rename(columns={1: 'commodity', 6: 'import'})
                 temp_df['import'] = pd.to_numeric(temp_df['import'].replace('--', 0), errors='coerce')
                 temp_df['import'] = temp_df['import'] * 10
                 import_df = pd.concat([import_df, temp_df])
 
-                temp_df = df[[1, 3]].rename(columns={1: 'commodity', 3: 'export'})
+                temp_df = df[[1, 4]].rename(columns={1: 'commodity', 4: 'export'})
                 temp_df['export'] = pd.to_numeric(temp_df['export'].replace('--', 0), errors='coerce')
                 temp_df['export'] = temp_df['export'] * 10
                 export_df = pd.concat([export_df, temp_df])
@@ -162,8 +163,8 @@ def hierarchical_traversal(root_path, all_records):
 
 if __name__ == '__main__':
     all_records = base_mysql.get_hs_all()
-    hierarchical_traversal(base_country_code.download_dir, all_records)
+    hierarchical_traversal(download_dir, all_records)
 
-    # root = Path(base_country_code.download_dir)/'2024'/'11'
+    # root = Path(download_dir)/'2024'/'10'
     # process_folder(root, all_records)
     print("江苏南京海关类章所有文件处理完成！")

utils/base_country_code.py

@@ -328,11 +328,4 @@ def extract_year_month_from_path(path):
             raise ValueError(f"无效月份格式：{month_part}")
         return int(year_part), int(month_part)
     except IndexError:
-        raise ValueError("路径结构不符合要求，示例：.../shandong/2025/04")
-
-download_dir = os.path.abspath(os.path.join('downloads'))
-download_dir_find = os.path.abspath(os.path.join('downloads/demo'))
-
-if __name__ == '__main__':
-    year, month = extract_year_month_from_path(Path(download_dir)/'2025'/'02')
-    log.info(year, month)
+        raise ValueError("路径结构不符合要求，示例：.../shandong/2025/04")

utils/base_mysql.py

@@ -401,10 +401,13 @@ if __name__ == '__main__':
     # count = get_code_exist(f'{check_year}-{check_month:02d}', "340000")
     # print(count)
 
-    # update_january_yoy('浙江省')
-    # update_shandong_yoy('浙江省')
-
+    # 新表更新地级市同比
     for province in provinces:
-        update_january_yoy_origin(province)
-        update_shandong_yoy_origin(province)
+        update_january_yoy(province)
+        update_shandong_yoy(province)
+
+    # 旧表更新省份同比
+    # for province in provinces:
+    #     update_january_yoy_origin(province)
+    #     update_shandong_yoy_origin(province)
     log.info("同比sql处理完成")

zhejiang/__init__.py

@@ -0,0 +1,11 @@
+import os
+from pathlib import Path
+
+script_dir = os.path.dirname(os.path.abspath(__file__))
+download_dir = os.path.join(script_dir, 'downloads')
+# 创建目录（如果不存在）
+os.makedirs(download_dir, exist_ok=True)
+# 切换当前工作目录到 download_dir
+os.chdir(download_dir)
+Path(download_dir).mkdir(parents=True, exist_ok=True)
+print("最终工作目录:", os.getcwd())

zhejiang/crawl_gov_zhejiangi_full.py → zhejiang/crawl_gov_zhejiang_full.py

@@ -15,15 +15,13 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.ui import WebDriverWait
 
-import gov_commodity_zhejiang_city
-import gov_commodity_zhejiang_country
-import gov_commodity_zhejiang_import_export
+from zhejiang import download_dir
+from zhejiang import gov_commodity_zhejiang_city
+from zhejiang import gov_commodity_zhejiang_country
+from zhejiang import gov_commodity_zhejiang_import_export
 from utils import base_country_code, base_mysql
 from utils.log import log
 
-download_dir = base_country_code.download_dir
-Path(download_dir).mkdir(parents=True, exist_ok=True)
-
 def configure_stealth_options():
     """增强型反检测配置[1,4](@ref)"""
     opts = FirefoxOptions()
@@ -289,7 +287,8 @@ def crawl_with_selenium(url, mark):
         res = detect_latest_month(driver, url)
         if res is None:
             log.info("浙江省海关没有最新数据更新")
-            sys.exit(0)
+            # sys.exit(0)
+            return
         year_month = res
         print(f"检测到最新有效数据：{year_month}")
 
@@ -311,6 +310,15 @@ def crawl_with_selenium(url, mark):
 
     finally:
         driver.quit()
+        log.info(f"浙江杭州海关全量数据下载任务完成")
+        # 等待5s后执行
+        time.sleep(5)
+        hierarchical_traversal(download_dir)
+        log.info("浙江杭州海关类章、国家、城市所有文件处理完成！")
+        time.sleep(5)
+        base_mysql.update_january_yoy('浙江省')
+        base_mysql.update_shandong_yoy('浙江省')
+        log.info("浙江杭州海关城市同比sql处理完成")
 
 def wait_for_download_complete(timeout=30, existing_files=None):
     """
@@ -371,16 +379,18 @@ def hierarchical_traversal(root_path):
                 gov_commodity_zhejiang_country.process_folder(md['path'])
                 gov_commodity_zhejiang_city.process_folder(md['path'])
 
-if __name__ == "__main__":
+def main():
     # crawl_with_selenium('http://hangzhou.customs.gov.cn/hangzhou_customs/575609/zlbd/575612/575612/6430241/6430315/index.html', 'all')
     crawl_with_selenium('http://hangzhou.customs.gov.cn/hangzhou_customs/575609/zlbd/575612/575612/6430241/6430315/index.html', 'increment')
-    log.info(f"浙江杭州海关全量数据下载任务完成")
-    # 等待5s后执行
-    time.sleep(5)
-    hierarchical_traversal(base_country_code.download_dir)
-    log.info("浙江杭州海关类章、国家、城市所有文件处理完成！")
-    time.sleep(5)
-    base_mysql.update_january_yoy('浙江省')
-    base_mysql.update_shandong_yoy('浙江省')
-    log.info("浙江杭州海关城市同比sql处理完成")
-
+    # log.info(f"浙江杭州海关全量数据下载任务完成")
+    # # 等待5s后执行
+    # time.sleep(5)
+    # hierarchical_traversal(download_dir)
+    # log.info("浙江杭州海关类章、国家、城市所有文件处理完成！")
+    # time.sleep(5)
+    # base_mysql.update_january_yoy('浙江省')
+    # base_mysql.update_shandong_yoy('浙江省')
+    # log.info("浙江杭州海关城市同比sql处理完成")
+
+if __name__ == '__main__':
+    main()

zhejiang/gov_commodity_zhejiang_city.py

@@ -3,6 +3,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from zhejiang import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -155,11 +156,11 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
     log.info(f"浙江杭州海关城市所有文件处理完成！")
     time.sleep(5)
     base_mysql.update_january_yoy('浙江省')
     base_mysql.update_shandong_yoy('浙江省')
     log.info("同比sql处理完成")
-    # root = Path(base_country_code.download_dir)/'2024'/'07'
+    # root = Path(download_dir)/'2024'/'07'
     # process_folder(root)

zhejiang/gov_commodity_zhejiang_country.py

@@ -2,6 +2,7 @@ from pathlib import Path
 
 import pandas as pd
 
+from zhejiang import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -165,8 +166,8 @@ def hierarchical_traversal(root_path):
 
 
 if __name__ == '__main__':
-    # hierarchical_traversal(base_country_code.download_dir)
+    # hierarchical_traversal(download_dir)
 
-    root = Path(base_country_code.download_dir) / '2024' / '07'
+    root = Path(download_dir) / '2024' / '07'
     process_folder(root)
     log.info("浙江杭州海关国别所有文件处理完成！")

zhejiang/gov_commodity_zhejiang_import_export.py

@@ -3,6 +3,7 @@ from pathlib import Path
 import re
 import pandas as pd
 
+from zhejiang import download_dir
 from utils import base_country_code, base_mysql
 from utils.base_country_code import format_sql_value
 from utils.log import log
@@ -221,8 +222,8 @@ def hierarchical_traversal(root_path):
                 process_folder(md['path'])
 
 if __name__ == '__main__':
-    hierarchical_traversal(base_country_code.download_dir)
+    hierarchical_traversal(download_dir)
 
-    # root = Path(base_country_code.download_dir)/'2023'/'01'
+    # root = Path(download_dir)/'2023'/'01'
     # process_folder(root)
     log.info("浙江杭州海关类章所有文件处理完成！")