PyComicPackRouMan/utils/base/BaseComicEntity.py

import json,os,time,random,shutil
from utils.HtmlUtils import htmlUtils
from utils.FileUtils import imageUtils
from utils.comic.ComicInfo import comicInfo as ci
from utils.CBZUtils import CBZUtils
from utils.CBZUtils import verUtils 
from utils.downloader import download_images
from utils.downloader import download_comic_icon
from utils.Ntfy import ntfy
from entity.down.RouMan import comicCommon as RouManComicCommon
from entity.down.JM import comicCommon as JMComicCommon
from entity.down.BaoZi import comicCommon as BaoZiComicCommon
from utils.comic.PathStr import pathStr
from utils.FileUtils import fileUtils

class baseComic:
    count_chapter = 0
    @classmethod
    def comics(cls,book_name,comic_href,updated=None):
        #不判断是否为空，ComicInfo方法内会自动判断
        ci.setComicInfo(comicname=book_name,update_at=updated)
        #白名单跳过
        if ci.getIsComicNameSkips(book_name): return None
        if not os.path.exists(ci.getDirConfComic()): ntfy.sendMsg(f"{random.randint(5,20)}秒后开始下载 漫画：{book_name}")
        else: ntfy.sendMsg(f"已存在 漫画：{book_name}")
        if ci.isUpdateComic(): return comic_href
        else:
            ntfy.sendMsg(f"{book_name} 已是最新")
            chapters = htmlUtils.xpathData('//div[contains(@class,"bookid_chapterBox")]//div[contains(@class,"bookid_chapter")]/a/text()',url=comic_href,update=False)
            chapter_index = 1
            for chapter in chapters:
                ci.setChapterIndex(chapter_index)
                ci.setChapterName(chapter)
                cbz_path = ci.getNewCBZComicChapter("file")
                icon_path = ci.getNewIconComicChapter("file")
                CBZUtils.replaceZip(cbz_path)
                #判断漫画是否完成
                if ci.isProgress(ci.PROGRESS_DONE) and not os.path.exists(cbz_path): ci.isProgress(ci.PROGRESS_DONE,remove=True)
                if not os.path.exists(cbz_path):
                    ci.updateComicDate("0")
                    return comic_href
                chapter_index = chapter_index + 1
            return None
     
    @classmethod
    def oneComic(cls,url,title,author,icon,tags,dep,chapters,chapter_href,alias=None,genre=None,lang="zh",sleep=None):
        ci.setComicInfo(homepage=url,comicname=title,alias=ci.setComicNames(title+","+alias),
            author=author,icon=icon,tags=tags,dep=dep,genre=genre,lang=lang,chapters=chapters)
        cls.count_chapter = 0
        for href in chapter_href:
            ci.setChapterName(chapters[cls.count_chapter])
            ci.setChapterIndex(cls.count_chapter+1)
            if ci.isProgress(ci.PROGRESS_DONE) and not os.path.exists(ci.getNewCBZComicChapter("file")): ci.isProgress(ci.PROGRESS_DONE,remove=True)
            if not ci.isProgress(ci.PROGRESS_DONE): cls.comicChapter(href,scramble=True,sleep=random.randint(5,15))
            #存在就校验CBZ包是否完整
            #if ci.nextExistsGetPath("done_"):
            #    verUtils.verCBZ()
            cls.count_chapter += 1
        #一本漫画下载后等待
        #清空文件夹
        if os.path.exists(ci.getDirComic()): shutil.rmtree(ci.getDirComic())
        if sleep != None: time.sleep(sleep)
             
    '''
    
    读取某章节下所有图片
    ''' 
    @classmethod
    def comicChapter(cls,chapter_url,scramble=None,sleep=None):
        is_next = True
        try:
            is_next = cls.Onechapter(chapter_url,scramble)
        #进入下个阶段
        #章节图片全部下载后，调用下载封面
            if ci.isProgress(ci.PROGRESS_DOWN): download_comic_icon()
         #下个阶段
            if ci.isProgress(ci.PROGRESS_CBZ): is_next = CBZUtils.packAutoComicChapterCBZ()
        except Exception as e: is_next = ntfy.sendMsg(f"{ci.getComicName()} 下载出错了",error=e)
        ntfy.sendMsg(f"预计总章节大小：{cls.count_chapter + 1}  / "+ str(ci.getLenChapters()))
        ci.setChapterIndex(cls.count_chapter + 1)
        if sleep != None and is_next == True: ntfy.sendMsg(f"{sleep} 秒后开始下载下一个章节",sleep=sleep)

    
    @classmethod
    def Onechapter(cls,chapter_url,scramble=None):
        is_next = True
        if not str(chapter_url).startswith("http"): chapter_url = ci.getBaseUrl() + chapter_url
        try: 
            is_next = cls.comicChapterDownload(chapter_url)
        except:
            htmlUtils.remove_HtmlCache(chapter_url)
        ci.nextInfoToImgChapter()
        #下载完成后, 开始解密图片
        chapter_dir = ci.getDirComicChapter()
        if scramble and os.path.exists(chapter_dir): #获取章节图片路径
            dirs = os.listdir(chapter_dir)
            for img in dirs:
                if img.startswith("scramble="):
                    imageUtils.encode_scramble_image(os.path.join(chapter_dir,img))
        #进入下一阶段
        ci.nextImgToDownloadChapter()
        return is_next
    
    @classmethod
    def comicChapterDownload(cls,url,is_next=True):
        comic_main = pathStr.getComicMain()
        if comic_main == pathStr.comic_jm: JMComicCommon.comicChapterDownload(url)
        if comic_main == pathStr.comic_bz: BaoZiComicCommon.comicChapterDownload(url)
        if comic_main == pathStr.comic_rm: RouManComicCommon.comicChapterDownload(url)
        if comic_main == None: print("comic_main为空，退出中...") & exit()
        list_img = ci.getChapterListImg()
        files_name = ci.getChapterFilesName()
        chapter_name = ci.getChapter()
        book_name = ci.getComicName()
        ci.setChapterImgs(list_img)
        #保存信息
        ci.nextSaveInfoChapter(chapter_name, list_img)
        #验证数据是已存在且是否完整
        #cbz_path = ci.getDirCBZComicChapter()+".CBZ"
        cbz_path = ci.getNewCBZComicChapter()+".CBZ"
        #更新Icon
        ci.getNewIconComicChapter()
        if os.path.exists(cbz_path):
            if CBZUtils.PackCBZAndequZipLength:
                ntfy.sendMsg(f"{book_name} {chapter_name} 数据完整，已跳过")
                ci.nextDoneSave(list_img)
                is_next = False
            else:
                ntfy.sendMsg(f"{book_name} {chapter_name} 数据不完整，尝试删除配置CBZ文件后重试")
                try:
                    if os.path.getsize(cbz_path) < 300000: fileUtils.remove(cbz_path)
                    else: is_next = False
                except:
                    ntfy(f"删除失败 {cbz_path}")
        if is_next:
            if not os.path.exists(ci.getPathComicInfoXML()):
                #print("不存在ComicInfo.xml 生成中...")
                ci.setPages(files_name)
                ci.writeComicInfoXML(chapter_name)    
            ntfy.sendMsg(f"{book_name} {chapter_name} 下载中")
            is_next = verUtils.verNextCBZ(list_img)
            is_unzip = verUtils.existsUnzipCBZ(files_name)
            repeat = 1 
            while not is_next and repeat <= 2 and not is_unzip:
                download_images(list_img,ci.getDirComicChapter(), files_name=files_name,concurrency=10,timeout=60)
                is_next = len(",".join(os.listdir(ci.getDirComicChapter())).split(".jpg"))-1 == len(list_img)
                if not is_next:
                    sleep_time = 3+int(repeat)*2
                    time.sleep(sleep_time)
                    ntfy.sendMsg(f"下载数据(不完整，{sleep_time}秒钟后尝试第{repeat}次")
                repeat += 1
        return is_next