分享119个Android手机应用源代码总有一个是你想要的

def builder_word(self, word_title, list_files):
        """
        输出产物是word文件
        :param word_title: 文件的标题
        :param list_files: 文件集合（单个内容）
        :return:
        """
        try:
            file_count = len(list_files)
            font_name = "楷体"
            random_full_file_name = SpriderTools.get_word_image(self.sprider_category, 6, "png")
            document = Document()
            document.add_paragraph("分享" + str(file_count) + "个" + word_title + "，总有一款适合您\r\n")
            document.add_paragraph("" + str(file_count) + "个" + word_title + "下载")
            document.add_paragraph("Python采集代码下载链接：https://wwgn.lanzoul.com/iKGwb0kye3wj")
            # Python采集代码下载链接：采集代码.zipt - 蓝奏云
            if os.path.exists(random_full_file_name):
                document.add_picture(random_full_file_name, width=Inches(3))
            file_index = 0
            for files in list_files:
                try:
                    document.add_paragraph(files[0])
                    file_index = file_index + 1
                    if file_index >= self.word_image_count:
                        continue
                    document.add_picture(files[1], width=Inches(3))
                    document.add_paragraph(files[2] + "\r")
                except Exception as e:
                    pass
            random_full_file_name1 = SpriderTools.get_word_image("html", 14, "jpg")
            if os.path.exists(random_full_file_name1):
                document.add_picture(random_full_file_name1, width=Inches(3))
            document.add_paragraph("最后送大家一首诗:")
            paragraph = document.add_paragraph()  # 单独控制
            paragraph.add_run("山高路远坑深,\r")
            paragraph.add_run("大军纵横驰奔,\r")
            paragraph.add_run("谁敢横刀立马？\r")
            paragraph.add_run("惟有点赞加关注大军。\r")
            paragraph.bold = True  # 字体加粗
            file_full_path = self.file_path + os.sep + word_title + ".docx"
            document.save(file_full_path)
            print("Create Word：" + word_title)
            self.gen_passandtxt(file_count, word_title, list_files)
            self.copy_file(file_count, self.save_path, word_title)
        except Exception as e:
            print("Create Word Fail reason:" + str(e))

def sprider(self,title_name="JS"):
        """
       采集
       php https://down.chinaz.com/class/574_5_1.htm
       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框架源码"
            self.second_column_name = "574_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)