分享88个Java框架源码，总有一款适合您

def sprider(self,title_name="JS"):
        """
       采集
       JavaScript https://down.chinaz.com/class/602_574_1.htm
       Java https://down.chinaz.com/class/574_517_1.htm
       :return:
       """
        if title_name == "PHP":
            self.folder_name = "PHP源码"
            self.second_column_name = "572_5"
        elif title_name == "JS":
            self.folder_name = "JavaScript框架源码"
            self.second_column_name = "602_574"
        elif title_name == "Java":
            self.folder_name = "Java框架源码"
            self.second_column_name = "574_517"
        BaseFrame().right("本次采集参数：日志路径：" + str(BaseFrame().LOG_PATH) + "")
        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 + "")
        first_column_name = title_name # 一级目录
        self.sprider_category = title_name  # 一级目录
        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
        self.file_path = self.save_path + os.sep + self.sprider_top_level + os.sep + first_column_name + os.sep + second_folder_name
        self.save_path = self.save_path+ os.sep +  self.sprider_top_level + os.sep+first_column_name+os.sep + second_folder_name+ os.sep + self.folder_name
        BaseFrame().debug("开始采集ChinaZCode"+self.folder_name+"...")
        sprider_url = (self.base_url + "/class/{0}_1.htm".format(self.second_column_name))
        down_path="D:\\Freedom\\Sprider\\ChinaZ\\"+ self.sprider_top_level+"\\"+first_column_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
        # print(content)
        div_elem = driver.find_element(By.CLASS_NAME, "main")  # 列表页面 核心内容
        element_list = div_elem.find_elements(By.CLASS_NAME, 'item')
        laster_pager_ul = driver.find_element(By.CLASS_NAME, "el-pager")
        laster_pager_li =laster_pager_ul.find_elements(By.CLASS_NAME, 'number')
        laster_pager_url = laster_pager_li[len(laster_pager_li) - 1]
        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/
                    next_url = self.base_url + "/class/{0}_{1}.htm".format(self.second_column_name, self.page_count)
                    driver.get(next_url)
                    div_elem = driver.find_element(By.CLASS_NAME, "main")  # 列表页面 核心内容
                    element_list = div_elem.find_elements(By.CLASS_NAME, 'item')
                    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
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.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 = "社会教育"
class ChinaZJsSelenium:
    base_url = "https://sc.chinaz.com/"  # 采集的网址
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count = 88 # 116+66+20
    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"

import os
import shutil
def void_folder(path):
    # 访问path路径下的文件或文件夹
    lst = os.listdir(path)
    # 打印每一层的文件或文件夹
    for name in lst:
        # 拼接名称，得到绝对路径，判断该文件是否符合是文件夹
        real_path = os.path.join(path, name)
        # 如果是文件夹，则打空格表示，并且递归访问下一层
        if os.path.isdir(real_path):
            # print(name)
            files = os.listdir(real_path)
            if len(files) == 0:
                print("void_folder()："+name)
                shutil.rmtree(real_path)
                endindex = len(real_path) - len(name)
                real_path = real_path[0:endindex]
                void_folder(real_path)
            else:
                void_folder(real_path)
        # 如果不是文件夹，直接打印，不再递归访问下一层
        else:
            #print(name)
            pass
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)