分享98个JS表单脚本，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.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 = "表单脚本"
class ChinaZJsSelenium:
    base_url =  "https://sc.chinaz.com/" # 采集的网址
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count = 100 # 采集数量
    sprider_start_count=0
    word_content_list = []
    folder_name = ""
    page_end_number=0
    max_pager=20 #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=[]
    def __init__(self):
        pass
    def sprider(self,title_name):
        """
       采集
       图片切换 https://sc.chinaz.com/tag_jiaoben/tupianqiehuan.html
       返回顶部 https://sc.chinaz.com/tag_jiaoben/fanhuidingbu.html
       动画效果 https://sc.chinaz.com/tag_jiaoben/donghuaxiaoguo.html
       倒计时 https://sc.chinaz.com/tag_jiaoben/daojishi.html
       弹出层 https://sc.chinaz.com/tag_jiaoben/danchuceng.html
       在线客服 https://sc.chinaz.com/jiaoben/kefu.html
       手风琴 https://sc.chinaz.com/tag_jiaoben/shoufengqin.html
       表单脚本 https://sc.chinaz.com/tag_jiaoben/biaodan.html
       :return:
       """
        if title_name == "图片切换":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "图片切换JS特效"
            self.second_column_name = "tupianqiehuan"
        elif title_name == "表单脚本":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "JS表单脚本"
            self.second_column_name = "biaodan"
        elif title_name == "返回顶部":
            self.folder_name = "JS返回顶部特效"
            self.second_column_name = "fanhuidingbu"
        elif title_name == "动画效果":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "JS特效动画效果"
            self.second_column_name = "donghuaxiaoguo"
        elif title_name == "倒计时":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "JS特效倒计时"
            self.second_column_name = "daojishi"
        elif title_name == "弹出层":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "JS特效弹出层"
            self.second_column_name = "danchuceng"
        elif title_name == "在线客服":
            self.first_column_name = "jiaoben"  # 一级目录
            self.folder_name = "JS特效在线客服"
            self.second_column_name = "kefu"
        elif title_name == "手风琴":
            self.first_column_name = "tag_jiaoben"
            self.folder_name = "JS特效手风琴"
            self.second_column_name = "shoufengqin"
        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.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 + "JS" + os.sep + self.folder_name  + os.sep + second_folder_name
        self.save_path = self.save_path+ os.sep + "JS" + os.sep+self.folder_name +os.sep + second_folder_name+ os.sep + self.folder_name
        BaseFrame().debug("开始采集ChinaZJS"+self.folder_name+"源码...")
        sprider_url = (self.base_url + "/{1}/{0}.html".format(self.second_column_name,self.first_column_name))
        down_path="D:\\Freedom\\Sprider\\ChinaZ\\JS\\"+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
        # driver.get方法将定位在给定的URL的网页，get接受url可以是任何网址，此处以百度为例
        driver.get(sprider_url)
        # content = driver.page_source
        element_list = driver.find_elements(By.CLASS_NAME, "picblock")  # 列表页面 核心内容
        #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/tag_jiaoben/tupianqiehuan_2.html
                    next_url = self.base_url + "/tag_jiaoben/{0}_{1}.html".format(self.second_column_name, self.page_count)
                    driver.get(next_url)
                    element_list = driver.find_elements(By.CLASS_NAME, "picblock")  # 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 "zipt" == 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)