eta_python/yongyi_pig/yongyi_pig_manual.py

# coding:utf-8
import os
from time import sleep
import datetime
import openpyxl
import rarfile as rarfile
import requests
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

from imgcode_ak import image_code

def rename_week_file(new_dir, current_time, rar_name):
    files = os.listdir(rar_name)
    for dir in files:
        print(dir.title())
        if os.path.isdir(dir.title()):
            dir_list = os.listdir(rar_name + "/" + dir.title())
            for f in dir_list:
                print(f.title())
                if f.title().find("周度数据") != -1:
                    new_name = f'{new_dir}/{current_time}_week.xlsx'
                    os.rename(rar_name + "/" + dir.title() + "/" + f.title(), new_name)
                    return
    return

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:\download\excel'
    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')
    driver = webdriver.Chrome(service=s, options=options)
    # driver.maximize_window()
    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
                            Object.defineProperty(navigator, 'webdriver', {
                              get: () => undefined
                            })
                          """
    })
    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
    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)

    # 获取当前时间，并将其格式化为指定的形式
    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 = files[-1]
    # new_dir = '/Users/xiexiaoyuan/Downloads/yongyi'
    new_dir = r'D:\data\yongyi'
    if day_file.title().find("日度") == -1:
        day_file = files[-2]

    if day_file.title().find("日度") != -1:
        new_name = f'{new_dir}/{current_time}_day.xlsx'
        os.rename(day_file.title(), new_name)
    else:
        print("未找到日度下载文件")

    week_file = files[-2]
    if week_file.title().find("周度") == -1:
        week_file = files[-1]
    print(week_file.title())
    if week_file.title().find("周度") != -1:
        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")