分享62个节日PPT，总有一款适合您

import os
import shutil
import time
from time import sleep
from docx import Document
from docx.shared import Inches
from framework.base.BaseFrame import BaseFrame
from sprider.business.DownLoad import DownLoad
from sprider.business.SeleniumTools import SeleniumTools
from sprider.business.SpiderTools import SpiderTools
from selenium import webdriver
from selenium.webdriver.common.by import By
from sprider.model.SpriderEntity import SpriderEntity
from sprider.access.SpriderAccess import SpriderAccess
title_name = "图片JS特效"
class PHP100Selenium:
    #region 经常修改的变量
    #https://www.php.cn/xiazai/js/banner https://www.php.cn/xiazai/js/banner?p=1
    base_url = "https://www.php.cn/xiazai"  # 采集的网址ASP.NET电子商务源码
    save_path = "D:\\Spider\\JS"
    spider_count =126 #采集数量
    spider_start_count =212#多次采集使用的 提升效率
    #endregion
    word_content_list = []
    folder_name = "图片JS特效"
    page_end_number = 0 # 最后一页
    max_pager = 20  # 每页的数量 影响再次采集的起始位置
    haved_spider_count = 0  # 已经采集的数量
    page_count = 1  # 每个栏目开始业务content="text/html; charset=gb2312"
    filter_down_file = []
    word_image_count = 1  # word插入图片数量 同时也是明细采集图片和描述的数量
    sprider_detail_index = 0  # 明细方法采集的数量 累加
    tempFileList = []
    def sprider(self, title_name):
        """
        采集
        焦点幻灯 https://www.php.cn/xiazai/js/banner
        菜单导航 https://www.php.cn/xiazai/js/nav
        选项卡TAB https://www.php.cn/xiazai/js/TAB
        在线客服 https://www.php.cn/xiazai/js/kefu
        图片特效 https://www.php.cn/xiazai/js/tupian
        :return:
        """
        if title_name == "焦点幻灯JS特效":
            self.first_column_name="js"
            self.second_column_name = "banner"
        elif title_name == "菜单导航JS特效":
            self.first_column_name = "js"
            self.second_column_name = "nav"
        elif title_name == "在线客服JS特效":
            self.first_column_name = "js"
            self.second_column_name = "kefu"
        elif title_name == "图片JS特效":
            self.first_column_name = "js"
            self.second_column_name = "tupian"
        BaseFrame().debug("开始采集" + self.folder_name + "...")
        self.merchant = int(self.spider_start_count) // int(self.max_pager) + 1  # 起始页码用于效率采集
        BaseFrame().right("本次采集参数：日志路径=" + str(BaseFrame().LOG_PATH) + "")
        BaseFrame().right("本次采集参数：spider_count=" + str(self.spider_count) + "")
        BaseFrame().right("本次采集参数：title_name=" + title_name + "")
        self.sprider_category = title_name  # 一级目录self.folder_name
        #多少个 某某某
        second_folder_name = str(self.spider_count) + "个" + title_name  # 二级目录
        self.sprider_type = second_folder_name #多少个某某某东东
        #浏览器的下载路径
        #self.down_path = self.save_path + os.sep +"\\" + self.folder_name + "\\" + second_folder_name + "\\Temp\\"
        self.down_path = self.save_path + os.sep + self.folder_name + os.sep + second_folder_name + "\\Temp"
        BaseFrame().right("本次采集参数：down_path=" +  self.down_path + "")
        # 原始路径+一级目录+二级目录
        # First/PPT/88个动态PPT模板
        self.file_path = self.save_path + os.sep + self.folder_name + os.sep + second_folder_name
        BaseFrame().right("本次采集参数：file_path=" + self.file_path + "")
        # First/PPT/88个动态PPT模板/动态PPT模板
        self.save_path = self.save_path + os.sep + self.folder_name + os.sep + second_folder_name + os.sep + title_name
        BaseFrame().right("本次采集参数：save_path=" + self.save_path + "")
        #根据栏目构建URL
        spider_url = self.base_url + "/{0}/{1}?p=1".format(self.first_column_name,self.second_column_name)
        if os.path.exists(self.down_path) is True:
            shutil.rmtree(self.down_path)
        if os.path.exists(self.down_path) is False:
            os.makedirs(self.down_path)
        if os.path.exists(self.save_path) is True:
            shutil.rmtree(self.save_path)
        if os.path.exists(self.save_path) is False:
            os.makedirs(self.save_path)
        chrome_options = webdriver.ChromeOptions()
        diy_prefs = {'profile.default_content_settings.popups': 0,
                     'download.default_directory': '{0}'.format(self.down_path)}
        # 添加路径到selenium配置中
        chrome_options.add_experimental_option('prefs', diy_prefs)
        #chrome_options.add_argument('--headless')  # 隐藏浏览器
        # 实例化chrome浏览器时，关联忽略证书错误
        driver = webdriver.Chrome(options=chrome_options)
        # 窗口最大化
        driver.maximize_window()
        driver.set_window_size(1920, 1080)  # 分辨率 1280*800
        self.wx_login(driver)
        BaseFrame().debug("开始采集:" + spider_url)
        driver.get(spider_url)
        # content = driver.page_source
        #masonry-brick
        element_list = driver.find_elements(By.CLASS_NAME, "listImg")
        page_end_number = 1000
        if SeleniumTools.judeg_element_isexist(driver, "LINK_TEXT", "末页") == 3:
            page_end_number = 18
        self.page_count = self.merchant
        while self.page_count <= int(page_end_number):  # 翻完停止
            try:
                if self.page_count == 1:
                    self.spider_detail(driver, element_list, self.page_count, page_end_number, self.down_path)
                    pass
                else:
                    if self.haved_spider_count == self.spider_count:
                        BaseFrame().debug("采集到达数量采集停止...")
                        BaseFrame().debug("开始写文章...")
                        self.builder_word(self.folder_name, self.word_content_list)
                        BaseFrame().debug("文件编写完毕，请到对应的磁盘查看word文件和下载文件！")
                        break
                    next_url = self.base_url + "/{0}/{1}?p={2}".format(self.first_column_name,
                                                                       self.second_column_name,
                                                                       self.page_count)
                    driver.get(next_url)
                    element_list = driver.find_elements(By.CLASS_NAME, "listImg")
                    self.spider_detail(driver, element_list, self.page_count, page_end_number, self.down_path)
                    pass
                # print(self.page_count)
                self.page_count = self.page_count + 1  # 页码增加1
            except Exception as e:
                print("sprider()执行过程出现错误:" + str(e))
                sleep(1)