android游戏源码

import os
import requests
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Inches
from framework.base.BaseFrame import BaseFrame
from sprider.business.DownLoad import DownLoad
from sprider.business.SpriderTools import SpriderTools
from sprider.business.UserAgent import UserAgent
class JB51JSP:
    page_count = 1  # 每个栏目开始业务content="text/html; charset=gb2312"
    base_url = "https://www.365psd.com/"  # 采集的网址
    #https://www.365psd.com/free-psd/arts-design
    save_path = "D:\\Yadinghao\\Sprider\\365PSD\\"
    sprider_count = 128  # 采集数量
    haved_sprider_count = 0  # 已经采集的数量
    word_content_list = []
    folder_name = ""
    page_end_number=0
    def __init__(self):
        pass
    def sprider(self,url_para="arts-design"):
        """
        采集class/5_1.htm
        :return:
        """
        if url_para=="arts-design":
            self.folder_name="arts-design"
        elif url_para=="abstract":
            self.folder_name = "abstract"
        elif url_para == "animals-wildlife":
            self.folder_name = "animals-wildlife"
        elif url_para == "architecture":
            self.folder_name = "architecture"
        self.save_path = self.save_path + os.sep + self.folder_name
        BaseFrame().debug("开始采集365psd...")
        sprider_url=(self.base_url + "/free-psd/{0}".format(url_para))
        #print(sprider_url) #https://www.365psd.com/free-psd/arts-design
        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_all('div', attrs={"class": 'thumbnail'}) #列表页面 核心内容
        div_list=soup.find_all('h2', attrs={"itemprop": 'name'})
        #print(div_list)
        pager_url= soup.find('ul', attrs={"class": 'pagination my40'})
        li_array=pager_url.find_all("li")
        pager_count=len(li_array)
        li_element = li_array[pager_count - 2]
        if len(li_array)==0:
            self.sprider_detail(div_list, self.page_count, 1)
            return
        else:
            pass
        # url=str(a_array[len(a_array)-1].get("href"))
        page_end_number=li_element.find("a").text
        # #print(page_end_number)
        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)
                    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.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 + "/free-psd/{0}/{1}".format(url_para, 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_all('h2', attrs={"itemprop": 'name'})
                    self.sprider_detail(div_list, self.page_count,page_end_number)
                    pass
                #print(self.page_count)
                self.page_count = self.page_count + 1  # 页码增加1
            except Exception as e:
                print("执行过程出现错误" + str(e))
    def copy_file(self,target_path):
        print("copy files")
        import os
        import shutil
        src_apk_file_path="薅羊毛专业版.apk"
        dst_apk_file_path=target_path+os.sep+"薅羊毛专业版.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_doc_file_path = "readme.docx"
        dst_doc_file_path = target_path + os.sep + "readme.docx"
        shutil.copyfile(src_doc_file_path, dst_doc_file_path)  # 移动文件
        pass
    def sprider_detail(self, div_list,page_count,max_page):
        """
        采集明细页面
        :param div_list:
        :param page_count:
        :return:
        <h2 itemprop="name"><a href="/psd/abstract-rainbow-colors-photoshop-video-tutorial-hd-53322">Abstract rainbow colors Photoshop video tutorial (HD)</a></h2>
        """
        div_length=len(div_list)
        index=0
        while index < div_length:
            if self.haved_sprider_count == self.sprider_count:
                BaseFrame().debug("采集到达数量采集停止...")
                break
            h2 = div_list[index]
            index = index + 1
            sprider_info="正在采集第"+str(page_count)+"页的"+str(index)+"个资源"
            print(sprider_info)
            a=(h2.find("a"))
            next_url = self.base_url + a.get("href")
            coder_title =a.string
            response = requests.get(next_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
            response.encoding = 'utf-8'
            soup = BeautifulSoup(response.text, "html5lib")
            coder__file_url = soup.find('div', attrs={"class": 'detail-btns'})
            down_load_file_url= self.base_url +(coder__file_url.find('a').get("href"))
            image_src =""
            try:
                image_src = soup.find('ul', attrs={"class": 'bxslider-slider'}).find("li").find("img").get("src")
                #print(image_src)
            except Exception as e:
                print("源码不存在图片" + str(e))
            down_load_response = requests.get(down_load_file_url, timeout=10, headers=UserAgent().get_random_header(self.base_url))
            down_load_response.encoding = 'utf-8'
            down_load_soup = BeautifulSoup(response.text, "html5lib")
            coder_file_url = down_load_soup.find('a', attrs={"rel": 'nofollow'})
            coder_file_url=self.base_url +coder_file_url.get("href")
            #print(coder_file_url)
            if(DownLoad(self.save_path).down_load_file_by_url_no_ext(down_load_file_url, coder_title,self.folder_name)):
                DownLoad(self.save_path).down_cover_image__(image_src, coder_title)  # 资源的 封面
                sprider_content = [coder_title, self.save_path + os.sep +"image"+ os.sep + coder_title + ".jpg"]  # 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().debug("已经采集完成第" + str(self.haved_sprider_count) + "个")
        #最后才可以构建word文档
        # print("Max Number"+str(max_page))
        # print("Current NO."+str(page_count))
        if(int(page_count)==int(max_page)):
            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！")
    def builder_word(self, word_title, save_path, list_files):
        """
        输出产物是word文件
        :param word_title: 文件的标题
        :param save_path: 文件的保存路径
        :param list_files: 文件集合（单个内容）
        :return:
        """
        try:
            self.copy_file(self.save_path)
            print("Create Word"+word_title)
            file_count= len(list_files)
            self.gen_passandtxt(file_count,word_title)
            document = Document()
            document.add_heading(""+word_title+"PSD", level=2)
            document.add_paragraph("分享"+str(file_count)+"个"+word_title+"PSD文件，总有一款适合你\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...，大家下载后可以看到。")
            ppt_tieles = ""
            for files in list_files:
                ppt_tieles = ppt_tieles + str(files[0]) + "\r"
            document.add_paragraph(ppt_tieles)
            for files in list_files:
                try:
                    document.add_paragraph(files[0])
                    document.add_picture(files[1], width=Inches(3))
                except Exception as e:
                    pass
            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=save_path+os.sep+word_title+".docx"
            document.save(file_full_path)
        except Exception as e:
            print("Create Word Fail reason:" + str(e))
    def gen_passandtxt(self,file_count,word_title):
        print("Create PassWord and Pass.txt")
        message=SpriderTools.gen_password()
        password = "".join(message)
        content=""
        content = content + "\n分享"+str(file_count)+"个"+word_title+"JSP源码"
        content = content + "\n\r"
        content=content+"\n都到这里了您就支持一下呗！谢谢老铁~~"
        content=content+"\n\r"
        content=content+"\n文件我就不一一列举了,送老铁一首打油诗"
        content=content+"\n学习知识费力气，"
        content=content+"\n收集整理更不易。"
        content=content+"\n知识付费甚欢喜，"
        content=content+"\n为咱码农谋福利。"
        content=content+"\n\r"
        content=content+"\n\r"
        content=content+"\n感谢您的支持"
        content=content+"\n\r" 
        content=content+"\n-------------------------------------------华丽分割线-------------------------------------------------------"
        content=content+"\n友情提醒解压密码："+password+""
        full_path=self.save_path+os.sep+""+str(file_count)+"sell_pass.txt"
        with open(full_path, 'a', encoding='utf-8') as f:
            f.write(content)
if __name__ == "__main__":
    JB51JSP().sprider("architecture")