eta_python/yongyi_pig/yongyi_pig_manual.py

# 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)