分享117个HTML婚纱模板，总有一款适合您

import os
import shutil
import time
from time import sleep
from docx import Document
from docx.opc.oxml import qn
from docx.shared import Inches, RGBColor
from framework.base.BaseFrame import BaseFrame
from sprider.business.DownLoad import DownLoad
from sprider.business.SeleniumTools import SeleniumTools
from sprider.business.SpriderTools import SpriderTools
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 = "婚纱模板"
class ChinaZJsSelenium:
    base_url =  "https://sc.chinaz.com/" # 采集的网址
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count =117 #正在采集第10页的第7个资源，共38页资源
    sprider_start_count=0
    word_content_list = []
    folder_name = ""
    page_end_number=0
    max_pager=24#每页的数量
    haved_sprider_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=5 #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
    sprider_top_level="HTML"

def sprider(self,title_name):
        """
       采集
       医疗保健 https://sc.chinaz.com/moban/YiLiaoBaoJian.html
       电子产品 https://sc.chinaz.com/moban/DianZiChanPin.html
       电子商务 https://sc.chinaz.com/moban/DianZiShangWu.html
       婚纱模板 https://sc.chinaz.com/moban/HunShaMoBan.html
       :return:
       """
        if title_name == "医疗保健":
            self.first_column_name = "moban"
            self.folder_name = "HTML医疗保健模板"
            self.second_column_name = "YiLiaoBaoJian"
        elif title_name == "婚纱模板":
            self.first_column_name = "moban"
            self.folder_name = "HTML婚纱模板"
            self.second_column_name = "HunShaMoBan"
        elif title_name == "电子产品":
            self.first_column_name = "moban"
            self.folder_name = "HTML电子产品模板"
            self.second_column_name = "DianZiChanPin"
        elif title_name == "电子商务":
            self.first_column_name = "moban"
            self.folder_name = "HTML电子商务模板"
            self.second_column_name = "DianZiShangWu"
        BaseFrame().right("本次采集参数：sprider_count=" + str(self.sprider_count) + "")
        BaseFrame().right("本次采集参数：title_name="+title_name+"")
        BaseFrame().right("本次采集参数：second_column_name=" + self.second_column_name + "")
        # self.folder_name = "JS表单验证"
        self.sprider_category = title_name  # 一级目录self.folder_name
        second_folder_name = str(self.sprider_count) + "个" + self.folder_name #二级目录
        self.sprider_type =second_folder_name
        self.merchant=int(self.sprider_start_count) //int(self.max_pager)+1 #起始页码用于效率采集
        #原始路径+一级目录+二级目录
        self.file_path = self.save_path + os.sep + self.sprider_top_level + os.sep + self.folder_name  + os.sep + second_folder_name
        self.save_path = self.save_path+ os.sep + self.sprider_top_level  + os.sep+self.folder_name +os.sep + second_folder_name+ os.sep + self.folder_name
        BaseFrame().debug("开始采集ChinaZJL"+self.folder_name+"...")
        sprider_url = (self.base_url + "/{1}/{0}.html".format(self.second_column_name,self.first_column_name))
        down_path="D:\\Freedom\\Sprider\\ChinaZ\\"+self.sprider_top_level +"\\"+self.folder_name +"\\"+second_folder_name+"\\Temp\\"
        if os.path.exists(down_path) is True:
            shutil.rmtree(down_path)
        if os.path.exists(down_path) is False:
            os.makedirs(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(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)
        driver.set_window_size(1280, 800)  # 分辨率 1280*800
        #
        BaseFrame().debug("开始采集"+sprider_url)
        driver.get(sprider_url)
        # content = driver.page_source
        element_list = driver.find_elements(By.CLASS_NAME, "masonry-brick")  # 列表页面 核心内容 box col3 ws_block masonry-brick
        #element_list = div_elem.find_elements(By.CLASS_NAME, 'item')
        #print(element_list.get_attribute('innerHTML'))
        laster_pager_div = driver.find_element(By.CLASS_NAME, "fenye")
        laster_pager_a = laster_pager_div.find_elements(By.TAG_NAME, 'a')
        laster_pager_url = laster_pager_a[len(laster_pager_a) - 2]
        page_end_number = int(laster_pager_url.text)
        self.page_count=self.merchant
        while self.page_count <= int(page_end_number):  # 翻完停止
            try:
                if self.page_count == 1:
                    self.sprider_detail(driver,element_list,self.page_count,page_end_number,down_path)
                    pass
                else:
                    if self.haved_sprider_count == self.sprider_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
                    #(self.base_url + "/sort/{0}/{1}/".format(url_index, self.page_count))
                    #http://soft.onlinedown.net/sort/177/2/
                    #https://sc.chinaz.com//jianli/xiaochengchu_2.html
                    next_url = self.base_url + "/{2}/{0}_{1}.html".format(self.second_column_name, self.page_count,self.first_column_name)
                    driver.get(next_url)
                    element_list = driver.find_elements(By.CLASS_NAME, "masonry-brick")  # 列表页面 核心内容
                    self.sprider_detail( driver, element_list, self.page_count, page_end_number, 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)

import os
def void_file(dirPath):
    dirs = os.listdir(dirPath)  # 查找该层文件夹下所有的文件及文件夹，返回列表
    for file in dirs:
        file_full_name = dirPath + '/' + file
        file_ext = os.path.splitext(file_full_name)[-1]
        if file_ext is None  or file_ext=="":
            continue
        if "rar" == str(file_ext.split(".")[1]):
            os.remove(file_full_name)
        if "zip" == str(file_ext.split(".")[1]):
            os.remove(file_full_name)
        if "gz" == str(file_ext.split(".")[1]):
            os.remove(file_full_name)
        if "tgz" == str(file_ext.split(".")[1]):
            os.remove(file_full_name)
# 查找指定文件夹下所有相同名称的文件
def search_file(dirPath, fileName):
    dirs = os.listdir(dirPath)  # 查找该层文件夹下所有的文件及文件夹，返回列表
    for currentFile in dirs:  # 遍历列表
        absPath = dirPath + '/' + currentFile
        if os.path.isdir(absPath):  # 如果是目录则递归，继续查找该目录下的文件
            search_file(absPath, fileName)
        elif currentFile == fileName:
            print(absPath)  # 文件存在，则打印该文件的绝对路径
            os.remove(absPath)