改成从go的定时任务控制

yongyi_pig/yongyi_pig_manual.py

@@ -2,10 +2,11 @@
 import os
 import shutil
 from time import sleep
+from bottle import route, run
 import datetime
-import openpyxl
+
+import hug
 import rarfile as rarfile
-import requests
 from selenium import webdriver
 
 # 设置Chrome浏览器选项
@@ -15,8 +16,6 @@ from selenium.webdriver.common.by import By
 from selenium.webdriver.support import expected_conditions as EC
 from selenium.webdriver.support.wait import WebDriverWait
 
-from imgcode_ak import image_code
-
 
 def rename_week_file(new_dir, current_time, rar_name):
     files = os.listdir(rar_name)
@@ -24,7 +23,7 @@ def rename_week_file(new_dir, current_time, rar_name):
         file_path = os.path.join(rar_name, dir)
         if os.path.isdir(file_path):
             for f in os.listdir(file_path):
-                print("f.title()"+f.title())
+                print("f.title()" + f.title())
                 if f.title().find("周度数据") != -1:
                     new_name = f'{new_dir}/{current_time}_week.xlsx'
                     old_name = os.path.join(file_path, f)
@@ -33,100 +32,121 @@ def rename_week_file(new_dir, current_time, rar_name):
                     print(f'周度文件重命名成功, 旧文件名{old_name} 新文件名{new_name}')
                     return
         else:
-            print(dir.title()+"不是一个文件夹")
+            print(dir.title() + "不是一个文件夹")
             return
     return
 
+@hug.get('/yongyi/download')
+def yongyi_download(dayFlag, weekFlag):
+    print("dayFlag:"+dayFlag)
+    print("weekFlag:"+weekFlag)
 
-if __name__ == "__main__":
-    # python+selunium定位已打开的浏览器
-    # 创建一个 Chrome WebDriver 实例
-    options = webdriver.ChromeOptions()
-    # options.add_argument("headless")
-    # options.add_argument('--headless')
-    options.add_argument('--disable-gpu')
-    options.add_argument('--no-sandbox')
-    # 谷歌浏览器运行的默认调试端口：先用以下命令启动浏览器
-    # 找到谷歌浏览器的程序地址，开启一个新的端口，并设置一个文件夹来保存浏览器的数据
-    # /Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222  --user-data-dir=/Users/xiexiaoyuan/data/selenium/automationProfile
-    # --remote-debugging-port值，可以指定任何打开的端口
-    # --user-data-dir标记，指定创建新Chrome配置文件的目录。它是为了确保在单独的配置文件中启动chrome，不会污染你的默认配置文件。
-    #
-    # 此时会打开一个浏览器页面，我们输入目标网址，输入账号密码，登录成功。
-    # 登录之后，以后都不需要登录，它会把你这次登录的信息记入到 --user-data-dir指定的目录下
-    # 后面你只需要python + selenium + webdriver定位到这个已经登录的浏览器进行操作就可以啦
-    options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
-    # 修改下载地址
-    # save_to_dir = '/Users/xiexiaoyuan/Downloads'
-    save_to_dir = r'D:/eta/yongyi_data/download'
-    options.add_argument("--download.default_directory=" + save_to_dir)
-    options.add_argument('--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, '
-                         'like Gecko) Chrome/118.0.5993.70 Safari/537.36')
-    options.add_argument(" window-size=1920,1080")
+    try:
+        # python+selunium定位已打开的浏览器
+        # 创建一个 Chrome WebDriver 实例
+        options = webdriver.ChromeOptions()
+        # options.add_argument("headless")
+        # options.add_argument('--headless')
+        options.add_argument('--disable-gpu')
+        options.add_argument('--no-sandbox')
+        # 谷歌浏览器运行的默认调试端口：先用以下命令启动浏览器
+        # 找到谷歌浏览器的程序地址，开启一个新的端口，并设置一个文件夹来保存浏览器的数据
+        # /Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222  --user-data-dir=/Users/xiexiaoyuan/data/selenium/automationProfile
+        # --remote-debugging-port值，可以指定任何打开的端口
+        # --user-data-dir标记，指定创建新Chrome配置文件的目录。它是为了确保在单独的配置文件中启动chrome，不会污染你的默认配置文件。
+        #
+        # 此时会打开一个浏览器页面，我们输入目标网址，输入账号密码，登录成功。
+        # 登录之后，以后都不需要登录，它会把你这次登录的信息记入到 --user-data-dir指定的目录下
+        # 后面你只需要python + selenium + webdriver定位到这个已经登录的浏览器进行操作就可以啦
+        options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
+        # 修改下载地址
+        # save_to_dir = '/Users/xiexiaoyuan/Downloads'
+        save_to_dir = r'D:/eta/yongyi_data/download'
+        options.add_argument("--download.default_directory=" + save_to_dir)
+        options.add_argument('--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, '
+                             'like Gecko) Chrome/118.0.5993.70 Safari/537.36')
+        options.add_argument(" window-size=1920,1080")
 
-    # s = Service(executable_path='/Users/xiexiaoyuan/chromedriver_mac64_114/chromedriver')
-    # s = Service(executable_path='D:/download/chromedriver119-win64/chromedriver.exe')
-    s = Service(executable_path='D:/eta/chromedriver-win64/chromedriver.exe')
-    driver = webdriver.Chrome(service=s, options=options)
-    # driver.maximize_window()
-    driver.get('https://data.yongyizixun888.com/')
-    sleep(3)
+        # s = Service(executable_path='/Users/xiexiaoyuan/chromedriver_mac64_114/chromedriver')
+        # s = Service(executable_path='D:/download/chromedriver119-win64/chromedriver.exe')
+        s = Service(executable_path='D:/eta/chromedriver-win64/chromedriver.exe')
+        driver = webdriver.Chrome(service=s, options=options)
+        # driver.maximize_window()
+        driver.get('https://data.yongyizixun888.com/')
+        sleep(3)
 
-    account = driver.find_element(By.XPATH, '//*[@id="dr_member_info"]/a[1]').text
-    print(account)
+        account = driver.find_element(By.XPATH, '//*[@id="dr_member_info"]/a[1]').text
+        print(account)
 
-    # 下载涌溢日度数据库
-    sleep(1)
-    a = driver.find_element(By.XPATH, '/html/body/div[4]/div[1]/div[2]/div[2]/a')
-    print(a.get_attribute("href"))
-    a.click()
+        # 下载涌溢日度数据库
+        if dayFlag == '1':
+            sleep(1)
+            a = driver.find_element(By.XPATH, '/html/body/div[4]/div[1]/div[2]/div[2]/a')
+            print(a.get_attribute("href"))
+            a.click()
+            sleep(30)
 
-    # 下载涌溢完整数据库
-    sleep(2)
-    b = driver.find_element(By.XPATH, '/html/body/div[4]/div[1]/div[2]/div[3]/a')
-    print(b.get_attribute("href"))
-    b.click()
-    sleep(30)
+        # 下载涌溢完整数据库
+        if weekFlag == '1':
+            sleep(2)
+            b = driver.find_element(By.XPATH, '/html/body/div[4]/div[1]/div[2]/div[3]/a')
+            print(b.get_attribute("href"))
+            b.click()
+            sleep(30)
 
-    # 获取当前时间，并将其格式化为指定的形式
-    # new_dir = '/Users/xiexiaoyuan/Downloads/yongyi'
-    new_dir = r'D:\eta\yongyi_data\yongyi'
-    current_time = datetime.datetime.now().strftime("%Y-%m-%d")
-    # 查找文件并重命名
-    os.chdir(save_to_dir)
-    files = filter(os.path.isfile, os.listdir(save_to_dir))
-    files = [os.path.join(save_to_dir, f) for f in files]  # add path to each file
-    files.sort(key=lambda x: os.path.getmtime(x))
-    day_file = ""
-    week_file = ""
-    for file in files:
-        if file.title().find("涌益咨询日度数据") != -1:
-            if day_file == "":
-                day_file = file
-        if file.title().find("涌益咨询周度数据") != -1:
-            if week_file == "":
-                week_file = file
-        if day_file != "" and week_file != "":
-            break
+        # 获取当前时间，并将其格式化为指定的形式
+        # new_dir = '/Users/xiexiaoyuan/Downloads/yongyi'
+        new_dir = r'D:\eta\yongyi_data\yongyi'
+        current_time = datetime.datetime.now().strftime("%Y-%m-%d")
+        current_time_full = datetime.datetime.now().strftime("%Y年%m月%d日")
 
-    if day_file != "":
-        print(day_file.title())
-        new_name = f'{new_dir}/{current_time}_day.xlsx'
-        # os.rename(day_file.title(), new_name)
-        shutil.copy(day_file.title(), new_name)
-        print(f'日度文件重命名成功, 旧文件名{day_file.title()} 新文件名{new_name}')
-    else:
-        print("未找到日度下载文件")
+        # 查找文件并重命名
+        os.chdir(save_to_dir)
+        files = filter(os.path.isfile, os.listdir(save_to_dir))
+        files = [os.path.join(save_to_dir, f) for f in files]  # add path to each file
+        files.sort(key=lambda x: os.path.getmtime(x), reverse=True)
+        day_file = ""
+        week_file = ""
+        for file in files:
+            day_name = f'{current_time_full}涌益咨询日度数据'
+            if file.title().find(day_name) != -1:
+                if day_file == "":
+                    day_file = file
+            if file.title().find("涌益咨询周度数据") != -1:
+                if week_file == "":
+                    week_file = file
+            if day_file != "" and week_file != "":
+                break
 
-    if week_file != "":
-        print(week_file.title())
-        filename = week_file.title()
-        index = filename.find(".Rar")
-        rar_name = filename[:index]
-        # 解压缩
-        rar_file = rarfile.RarFile(filename, 'r')
-        rar_file.extractall(rar_name)
-        rar_file.close()
-        rename_week_file(new_dir, current_time, rar_name)
-    else:
-        print("未找到周度下载文件")
+        if dayFlag == '1':
+            if day_file != "":
+                print(day_file.title())
+                new_name = f'{new_dir}/{current_time}_day.xlsx'
+                # os.rename(day_file.title(), new_name)
+                shutil.copy(day_file.title(), new_name)
+                print(f'日度文件重命名成功, 旧文件名{day_file.title()} 新文件名{new_name}')
+            else:
+                print("未找到日度下载文件")
+
+        if weekFlag == '1':
+            if week_file != "":
+                print(week_file.title())
+                filename = week_file.title()
+                index = filename.find(".Rar")
+                rar_name = filename[:index]
+                # 解压缩
+                rar_file = rarfile.RarFile(filename, 'r')
+                rar_file.extractall(rar_name)
+                rar_file.close()
+                rename_week_file(new_dir, current_time, rar_name)
+            else:
+                print("未找到周度下载文件")
+        return True
+    except Exception as e:
+        print("Exception:")
+        print(str(e))
+        return False
+
+if __name__ == "__main__":
+    app = __hug__.http.server()
+    run(app=app, reloader=True, host='0.0.0.0', port=7010)