涌益周度版图

yongyi_pig/yongyi_pig_manual.py

@@ -1,152 +1,178 @@
-# coding:utf-8
-import os
-import shutil
-from time import sleep
-from bottle import route, run
-import datetime
-
-import hug
-import rarfile as rarfile
-from selenium import webdriver
-
-# 设置Chrome浏览器选项
-from selenium.common import exceptions
-from selenium.webdriver.chrome.service import Service
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.wait import WebDriverWait
-
-
-def rename_week_file(new_dir, current_time, rar_name):
-    files = os.listdir(rar_name)
-    for dir in files:
-        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())
-                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)
-                    # os.rename(old_name, new_name)
-                    shutil.copy(old_name, new_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")
-            return
-    return
-
-@hug.get('/yongyi/download')
-def yongyi_download(dayFlag, weekFlag):
-    print("dayFlag:"+dayFlag)
-    print("weekFlag:"+weekFlag)
-
-    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.get('https://data.yongyizixun888.com/')
-        sleep(3)
-
-        account = driver.find_element(By.XPATH, '//*[@id="dr_member_info"]/a[1]').text
-        print(account)
-
-        # 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
-        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")
-        current_time_full = datetime.datetime.now().strftime('%Y{y}%m{m}%d{d}').format(y='年', m='月', d='日')
-        print(current_time_full)
-
-        # 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 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='127.0.0.1', port=7010)
+# coding:utf-8
+import os
+import shutil
+import subprocess
+from time import sleep
+from bottle import route, run
+import datetime
+
+import hug
+import rarfile as rarfile
+from selenium import webdriver
+
+# 设置Chrome浏览器选项
+from selenium.common import exceptions
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.wait import WebDriverWait
+
+
+def rename_week_file(new_dir, rar_name):
+    files = os.listdir(rar_name)
+    for dir in files:
+        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())
+                if f.title().find("周度数据") != -1:
+                    file_name = f.title().split('/')[-1]
+                    new_name = f'{new_dir}/{file_name}'
+                    old_name = os.path.join(file_path, f)
+                    new_name = new_name.lower()
+                    # os.rename(old_name, new_name)
+                    shutil.copy(old_name, new_name)
+                    print(f'周度数据文件重命名成功, 旧文件名{old_name} 新文件名{new_name}')
+                elif f.title().find("周度图表版图") != -1:
+                    file_name = f.title().split('/')[-1]
+                    new_name = f'{new_dir}/{file_name}'
+                    old_name = os.path.join(file_path, f)
+                    new_name = new_name.lower()
+                    # os.rename(old_name, new_name)
+                    shutil.copy(old_name, new_name)
+                    print(f'周度图表版图文件重命名成功, 旧文件名{old_name} 新文件名{new_name}')
+        else:
+            print(dir.title() + "不是一个文件夹")
+            return
+    return
+
+
+def get_yongyi_driver():
+    # 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")
+
+    print("重新打开")
+    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.get('https://data.yongyizixun888.com/')
+
+    return driver
+
+@hug.get('/yongyi/download')
+def yongyi_download(dayFlag, weekFlag):
+    print("dayFlag:"+dayFlag)
+    print("weekFlag:"+weekFlag)
+    # 修改下载地址
+    # save_to_dir = '/Users/xiexiaoyuan/Downloads'
+    save_to_dir = r'D:/eta/yongyi_data/download'
+    # 获取当前时间，并将其格式化为指定的形式
+    # new_dir = '/Users/xiexiaoyuan/Downloads/yongyi/unread'
+    new_dir = r'D:\eta\yongyi_data\unread'
+    try:
+        try:
+            driver = get_yongyi_driver()
+        except Exception as e:
+            print("Exception:")
+            print(str(e))
+            if str(e).find("chrome not reachable") != -1:
+                print("浏览器未开启")
+                return False
+            else:
+                return False
+        sleep(3)
+        account = driver.find_element(By.XPATH, '//*[@id="dr_member_info"]/a[1]').text
+        print(account)
+
+        # 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
+        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)
+
+        # 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 = ""
+        i =0
+        for file in files:
+            if i > 3:
+                break
+            print(file.title())
+            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
+            i = i+1
+        if dayFlag == '1':
+            if day_file != "":
+                print(day_file.title())
+                # 获取文件名
+                file_name = day_file.title().split('/')[-1]
+                new_name = f'{new_dir}/{file_name}'
+                new_name = new_name.lower()
+                # 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, 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='127.0.0.1', port=7010)