分享88个HTML社会教育模板，总有一款适合您

def sprider_detail(self, driver, element_list, page_count, max_page, down_path):
        """
        采集明细页面
        :param driver:
        :param element_list:
        :param page_count:
        :param max_page:
        :param down_path:
        :return:
        """
        index = 0
        element_array = []
        element_length = len(element_list)
        print("当前页" + str(page_count) + "每页共" + str(element_length))
        for element in element_list:
            div_element = element.find_element(By.TAG_NAME, 'div')
            a_elenent = div_element.find_element(By.TAG_NAME, 'a')
            next_url = a_elenent.get_attribute("href")
            coder_title = a_elenent.get_attribute("alt")
            e = coder_title + "$" + next_url
            element_array.append(e)
            pass
        if int(self.page_count) == int(self.merchant):
            self.sprider_start_index = int(self.sprider_start_count) % int(self.max_pager)
            index = self.sprider_start_index
        while index < element_length:
            if os.path.exists(down_path) is False:
                os.makedirs(down_path)
            if self.haved_sprider_count == self.sprider_count:
                BaseFrame().debug("采集到达数量采集停止...")
                break
            # element = element_list[index]
            element = element_array[index]
            time.sleep(1)
            index = index + 1
            sprider_info = "正在采集第" + str(page_count) + "页的第" + str(index) + "个资源，共" + str(max_page) + "页资源"
            BaseFrame().debug(sprider_info)
            next_url = element.split("$")[1]
            coder_title = element.split("$")[0]
            try:
                codeEntity = SpriderEntity()  # 下载过的资源不再下载
                codeEntity.sprider_base_url = self.base_url
                codeEntity.create_datetime = SpriderTools.get_current_datetime()
                codeEntity.sprider_url = next_url
                codeEntity.sprider_pic_title = coder_title
                codeEntity.sprider_pic_index = str(index)
                codeEntity.sprider_pager_index = page_count
                codeEntity.sprider_type = self.sprider_type
                if SpriderAccess().query_sprider_entity_by_urlandindex(coder_title) is None:
                    SpriderAccess().save_sprider(codeEntity)
                else:
                    BaseFrame().debug(coder_title + next_url + "数据采集过因此跳过")
                    continue
                driver.get(next_url)  # 请求明细页面1
                BaseFrame().debug("采集明细内容网址：" + next_url)
                sleep(0.5)  # 延迟会
                if SeleniumTools.judeg_element_isexist(driver, "CLASS_NAME", "dian") == 3:
                    driver.back()
                    BaseFrame().debug(coder_title + "下载按钮不存在，因此跳过哦....")
                    continue
                print("准备点击下载按钮...")
                div_element_list = driver.find_elements(By.CLASS_NAME, "dian")  # 下载源码.click()
                a_element = div_element_list[1].find_element(By.TAG_NAME, "a")
                a_element.click()
                sleep(0.5)
                result, message = SpriderTools.judge_file_exist(True, 240, 1, down_path, self.filter_down_file,
                                                                "zip|rar|gz|tgz")  # 判断源码
                if result is True:
                    title_content = ""
                    title_image = ""
                    if self.sprider_detail_index <= self.word_image_count:
                        # 下载图片
                        a_element_image = driver.find_element(By.CLASS_NAME, "image_gall")
                        image_href = a_element_image.get_attribute("href")
                        DownLoad(self.save_path).down_cover_image__(image_href, coder_title)  # 资源的 封面
                        title_image = self.save_path + os.sep + "image" + os.sep + coder_title + ".jpg"
                        # 采集描述
                        # 采集描述
                        try:
                            if SeleniumTools.judeg_element_isexist(driver, "CLASS_NAME", "smr") == 3:
                                pass
                            else:
                                div_element_list = driver.find_elements(By.CLASS_NAME, "smr")
                                if len(div_element_list) == 1:
                                    div_element = div_element_list[0]
                                else:
                                    div_element = div_element_list[1]
                                title_content = div_element.text
                                BaseFrame().right("采集模板简介成功")
                        except Exception as e:
                            BaseFrame().error("采集模板简介失败" + str(e))
                            pass
                    sprider_content = [coder_title, title_image, title_content]  # 采集成功的记录
                    self.word_content_list.append(sprider_content)  # 增加到最终的数组
                    self.haved_sprider_count = self.haved_sprider_count + 1
                    BaseFrame().right(
                        "已经采集完成第" + str(self.haved_sprider_count) + "个，共需要采集" + str(self.sprider_count) + "个")
                    time.sleep(1)
                    driver.back()
                    coder_title = str(coder_title).replace("::", "").replace("/", "").strip()  # 去掉windows不识别的字符
                    files = os.listdir(down_path)
                    file_name = files[0]  # 获取默认值
                    srcFile = down_path + os.sep + file_name
                    file_ext = os.path.splitext(srcFile)[-1]
                    dstFile = down_path + os.sep + coder_title + file_ext
                    os.rename(srcFile, dstFile)
                    srcFile = dstFile
                    dstFile = self.save_path + os.sep + coder_title + file_ext
                    shutil.move(srcFile, dstFile)  # 移动文件
                    self.sprider_detail_index = self.sprider_detail_index + 1
                else:
                    print("result=" + str(result) + "" + message)
                    files = os.listdir(down_path)  # 读取目录下所有文件
                    coder_title = str(coder_title).replace("/", "")  # 去掉windows不识别的字符
                    try:
                        if str(message) == "0个文件认定是False":
                            BaseFrame().error(coder_title + "文件不存在...")
                            shutil.rmtree(down_path)  # 如果没下载完是无法删除的
                            pass
                        else:
                            BaseFrame().error("检测下载文件出错可能原因是等待时间不够已经超时，再等待60秒...")
                            time.sleep(60)
                            shutil.rmtree(down_path)  # 如果没下载完是无法删除的
                            # 清空数组
                            self.filter_down_file.clear()
                    except Exception as e:
                        print(e)
                        # 使用数组append记录文件名字 移动的时候过滤
                        self.builder_filter_file(files)
                    pass
            except Exception as e:
                BaseFrame().error("sprider_detail()执行过程出现错误:" + str(e))
                BaseFrame().error("sprider_detail()记录下载的文件名")
                # 使用数组append记录文件名字 移动的时候过滤
                files = os.listdir(down_path)  # 读取目录下所有文件
                self.builder_filter_file(files)
        if int(page_count) == int(max_page):
            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！")

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("html", 14, "jpg")
            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 copy_file(self, file_count, target_path, word_title):
        try:
            print("copy files and create word")
            import os
            import shutil
            from docx import Document
            from docx.shared import RGBColor, Inches
            from docx.enum.table import WD_TABLE_ALIGNMENT
            from docx.oxml.ns import qn
            src_apk_file_path = "亚丁号自动阅读_v0.0.53.apk"
            dst_apk_file_path = self.file_path + os.sep + "亚丁号自动阅读_v0.0.53.apk"
            shutil.copyfile(src_apk_file_path, dst_apk_file_path)  # 移动文件
            src_pdf_file_path = "薅羊毛专业版.pdf"
            dst_pdf_file_path = target_path + os.sep + "薅羊毛专业版.pdf"
            # shutil.copyfile(src_pdf_file_path, dst_pdf_file_path)  # 移动文件
            src_pdf_file_path = "亚丁号.url"
            dst_pdf_file_path = self.file_path + os.sep + "亚丁号.url"
            shutil.copyfile(src_pdf_file_path, dst_pdf_file_path)  # 移动文件
            # src_doc_file_path = "readme.docx"
            # dst_doc_file_path = self.file_path + os.sep + "readme.docx"
            # shutil.copyfile(src_doc_file_path, dst_doc_file_path)  # 移动文件
            # document.add_paragraph("分享" + str(file_count) + "个" + word_title + "，总有一款适合您\r\n""下面是文件的名字，我放了一些图片，文章里不是所有的图主要是放不下...，")
            font_name = "楷体"
            document = Document()
            paragraph_title = document.add_paragraph()  # 单独控制
            word_title = paragraph_title.add_run("分享" + str(file_count) + "个" + word_title + "，总有一款适合您\r\n")
            word_title.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_title.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            word_title.font.color.rgb = RGBColor(2, 2, 250)
            word_title.bold = True  # 字体加粗
            paragraph_title.alignment = WD_TABLE_ALIGNMENT.CENTER  # 文字居中
            paragraph = document.add_paragraph()  # 单独控制
            word_content1 = paragraph.add_run("都到这里了您就支持一下呗！谢谢老铁~~\n")
            word_content1.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content1.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            word_content2 = paragraph.add_run("烦请到此链接获取压缩包解压密码：\r")
            word_content2.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content2.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            word_content2.font.color.rgb = RGBColor(255, 0, 0)
            word_content3 = paragraph.add_run("今日美图推荐")
            word_content3.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content3.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            random_full_file_name1 = SpriderTools.get_word_image("MT", 25, "jpg")
            document.add_picture(random_full_file_name1, width=Inches(5))
            paragraph = document.add_paragraph()  # 单独控制
            word_content6 = paragraph.add_run("烦请到此链接获取压缩包解压密码：")
            word_content6.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content6.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            word_content6.font.color.rgb = RGBColor(255, 0, 0)
            paragraph = document.add_paragraph()  # 单独控制
            word_content4 = paragraph.add_run("最后送大家一首自编的打油诗：")
            word_content4.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content4.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            paragraph = document.add_paragraph()  # 单独控制
            word_content5 = paragraph.add_run("学习知识费力气，\r收集整理更不易。\r知识付费甚欢喜，\r为咱码农谋福利。\r")
            word_content5.font.name = font_name  # 注：如果想要设置中文字体，需在前面加上这一句
            word_content5.font.element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
            paragraph.alignment = WD_TABLE_ALIGNMENT.CENTER  # 文字居中
            dst_doc_file_path = self.file_path + os.sep + "获取压缩包解压密码.docx"
            document.save(dst_doc_file_path)  # 保存文件
        except Exception as e:
            print("copy files Fail reason:" + str(e))
        pass

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)