分享100个PHP源码，总有一款适合您

page_count = 1  # 每个栏目开始业务content="text/html; charset=gb2312"
    base_url = "https://down.chinaz.com"  # 采集的网址  https://sc.chinaz.com/tag_ppt/zhongguofeng.html
    save_path = "D:\\Freedom\\Sprider\\ChinaZ\\"
    sprider_count = 109# 采集数量
    haved_sprider_count = 0  # 已经采集的数量正在采集第91页的第15个资源
    word_content_list = []
    folder_name = ""
    first_column_name = "PHP"
    sprider_start_count=1940 #已经采集完成第136个 debug
    max_pager=16 #每页的数量

def sprider(self, title_name="PHP"):
        """
        采集 https://down.chinaz.com/class/572_5_1.htm
        :return:
        """
        if title_name == "PHP":
            self.folder_name = "PHP源码"
            self.second_column_name = "572_5"
        elif title_name == "Go":
            self.folder_name = "Go源码"
            self.second_column_name = "606_572"
        merchant = int(self.sprider_start_count) // int(self.max_pager) + 1
        second_folder_name = str(self.sprider_count) + "个" + self.folder_name
        self.save_path = self.save_path+ os.sep + "Code" + os.sep +  second_folder_name
        print("开始采集ChinaZCode"+self.folder_name+"...")
        sprider_url = (self.base_url + "/class/{0}_1.htm".format(self.second_column_name))
        #print(sprider_url)
        #sprider_url = (self.base_url + "/" +  self.first_column_name + "/" + second_column_name + ".html")
        response = requests.get(sprider_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
        response.encoding = 'UTF-8'
        soup = BeautifulSoup(response.text, "html5lib")
        #print(soup)
        div_list =soup.find('div', attrs={"class": 'main'})
        div_list=div_list.find_all('div', attrs={"class": 'item'})
        #print(div_list)
        laster_pager_ul = soup.find('ul', attrs={"class": 'el-pager'})
        laster_pager_li = laster_pager_ul.find_all('li', attrs={"class": 'number'})
        laster_pager_url = laster_pager_li[len(laster_pager_li)-1]
        #<a href="zhongguofeng_89.html"><b>89</b></a>
        page_end_number = int(laster_pager_url.string)
        #print(page_end_number)
        self.page_count = merchant
        while self.page_count <= int(page_end_number):  # 翻完停止
            try:
                if self.page_count == 1:
                    self.sprider_detail(div_list,self.page_count,page_end_number)
                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.save_path, 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 + "/class/{0}_{1}.htm".format(self.second_column_name,self.page_count )
                    response = requests.get(next_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
                    response.encoding = 'UTF-8'
                    soup = BeautifulSoup(response.text, "html5lib")
                    div_list = soup.find('div', attrs={"class": 'main'})
                    div_list = div_list.find_all('div', attrs={"class": 'item'})
                    self.sprider_detail(div_list, self.page_count,page_end_number)
                    pass
            except Exception as e:
                print("sprider()执行过程出现错误" + str(e))
                pass
            self.page_count = self.page_count + 1  # 页码增加1

import os
# 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)