diff --git a/common/BaseComicEntity.py b/common/BaseComicEntity.py index 8b9304e..cf6d054 100644 --- a/common/BaseComicEntity.py +++ b/common/BaseComicEntity.py @@ -11,7 +11,6 @@ from common.ComicInfo import ComicInfo as ci from common.Comic import Comic from common.Comic import ListComic from common.Constant import ComicPath -from utils.FileUtils import fileUtils #中心框架 class baseComic: @@ -70,9 +69,6 @@ class baseComic: #if ciUtils.isProgressDone() and fu.notExists(ComicPath.getNewCBZComicChapter("file")): # ciUtils.setProgressFail() cbz_path = ComicPath.getPathCBZComicChapter() - #file_date = int(fileUtils.getModificationDate(cbz_path,"%Y%m%d%H",not_exists="2010010101")) - #if file_date > 2023040610 and file_date < 2023040710: - # os.remove(cbz_path) if not os.path.exists(cbz_path): print(f"CBZ不存在, {cbz_path}") ciUtils.setProgressFail() @@ -97,16 +93,7 @@ class baseComic: is_next = False #try: cls.Onechapter(chapter_url) - #进入下个阶段 - #章节图片全部下载后，调用下载封面 - comic_icon_path = ComicPath.getPathConfComicIcon() - chapter_icon_path = ComicPath.getPathCBZComicChapterIcon() - if ciUtils.isProgressDown and os.path.exists(comic_icon_path) and not os.path.exists(chapter_icon_path): - shutil.copy(comic_icon_path,chapter_icon_path) - ntfy.sendMsg(f"复制成功：{comic_icon_path} -> {chapter_icon_path}") - ciUtils.iconDB() - ciUtils.setProgressCBZ() - #下个阶段 + #下个阶段 if ciUtils.isProgressCBZ: 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(Comic.getLenChapters()),alert=True) @@ -115,31 +102,16 @@ class baseComic: #根据章节地址下载全部图片，并将文件名scramble开头的图片进行解密 @classmethod - def Onechapter(cls,chapter_url): - is_next = True - if not str(chapter_url).startswith("http"): chapter_url = ci.getBaseUrl() + chapter_url + def Onechapter(cls,url): #下载图片 - is_next = cls.comicChapterDownload(chapter_url) - #下载完成后, 开始解密图片 - chapter_dir = ComicPath.getDirComicChapter() - if 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 - ciUtils.setProgressDown() - return is_next - - @classmethod - def comicChapterDownload(cls,url): + url = ComicPath.getUrl(url) is_next = True #获取本次工程的HOME目录 try: domains.setdomain(url) except: htmlUtils.remove_HtmlCache(url) - cls.comicChapterDownload(url) + cls.Onechapter(url) #保存信息 ci.writeJson() #验证数据是已存在且是否完整 @@ -153,5 +125,20 @@ class baseComic: ci.writeComicInfoXML() ComicPath.TIME_SLEEP = random.randint(5,15) downloadUtils.putDownImageUrlDirFile(Comic.getIcon(),ComicPath.getDirConfComic(),ComicPath.COMIC_ICON_FILE_NAME) - downloadUtils.start_downloads(timeout=15) - return is_next \ No newline at end of file + downloadUtils.start_downloads(timeout=12.5,concurrency=10) + #下载完成后, 开始解密漫画章节下的加密图片 + imageUtils.deScrambleImagesByDir(ComicPath.getDirComicChapter()) + #进入下一阶段 + #章节图片全部下载后，调用下载封面 + cls.iconDownload() + ciUtils.setProgressCBZ() + + + @classmethod + def iconDownload(cls): + comic_icon_path = ComicPath.getPathConfComicIcon() + chapter_icon_path = ComicPath.getPathCBZComicChapterIcon() + if ciUtils.isProgressDown and os.path.exists(comic_icon_path) and not os.path.exists(chapter_icon_path): + shutil.copy(comic_icon_path,chapter_icon_path) + ntfy.sendMsg(f"复制成功：{comic_icon_path} -> {chapter_icon_path}") + ciUtils.iconDB() \ No newline at end of file diff --git a/common/Constant.py b/common/Constant.py index bf1435c..1df96ef 100644 --- a/common/Constant.py +++ b/common/Constant.py @@ -86,7 +86,13 @@ class ComicPath: COMIC_INFO_XML = "ComicInfo.xml" TIME_SLEEP = 0.5 IS_UPDATE_COMIC = False + COMIC_SCRABMLE_COUNT = 0 + @classmethod + def getUrl(cls,relative_url): + if not str(relative_url).startswith("http"): relative_url = pathStr.getBaseUrl(Comic.getHomePage())+relative_url + return relative_url + #顶级路径 @classmethod def setJoinPathDir(cls,path,dir="",suffix=None,mkdir=False): diff --git a/domain/down/RouMan.py b/domain/down/RouMan.py index e5d61c5..4c0b845 100644 --- a/domain/down/RouMan.py +++ b/domain/down/RouMan.py @@ -32,6 +32,7 @@ class DomainDown: ntfy.sendMsg(f"未获取到章节图像 comic_name={Comic.getComicName()} chapter={Comic.getChapterName()}") count = 1 + scramble_count = 0 (files_name,images_url) = [[],[]] for image in images: (image_src,scramble) = [image.get("src"),image.get("scramble")] @@ -42,9 +43,11 @@ class DomainDown: de_str = str(image_src).split("/")[-1].replace(image_src_suffix,"==") blocks_num = imageUtils.encodeImage(de_str) image_file_name = ComicPath.getFileScrambleImageName(count=count_image,block=blocks_num,suffix=image_src_suffix) + scramble_count += 1 files_name.append(image_file_name) images_url.append(image_src) downUtils.putDownImageUrlDirFile(image_src,ComicPath.getDirComicChapter(),image_file_name) count+=1 + ComicPath.COMIC_SCRABMLE_COUNT = scramble_count Comic.setChapterImgs(images_url) Comic.setChapterFilesName(files_name) \ No newline at end of file diff --git a/utils/FileUtils.py b/utils/FileUtils.py index 85deac4..de51120 100644 --- a/utils/FileUtils.py +++ b/utils/FileUtils.py @@ -6,7 +6,19 @@ from common.Constant import ComicPath from utils.Logger import logger class imageUtils: - + + @classmethod + def deScrambleImagesByDir(cls,chapter_dir): + scramble_count = 0 + if 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)) + scramble_count += 1 + logger.debug(f"scramble= {scramble_count}") + return scramble_count + @classmethod def encodeImage(cls,str_en): #print("en",str_en) @@ -195,7 +207,8 @@ class imageUtils: print("remove=",imgpath) class fileUtils: - + SCRAMBLE_COUNT = 0 + @classmethod def getModificationDate(cls,file_path,format="%Y%m%d",not_exists=None): if cls.notExists(file_path): return not_exists diff --git a/utils/NetUtils.py b/utils/NetUtils.py index 698a52d..0ec561f 100644 --- a/utils/NetUtils.py +++ b/utils/NetUtils.py @@ -183,7 +183,7 @@ class downloadUtils: def putDownImageUrlDirFile(cls,url,dir,file): cls.putDownUrlDirFileType(url,dir,file,cls.TYPE_IMG) @classmethod - def common_download(cls,file_url,dir,file,file_type,repair_max=15,timeout=10,proxy=None,proxy_type=None): + def common_download(cls,file_url,dir,file,file_type,repair_max=30,timeout=10,proxy=None,proxy_type=None): logger.debug(f"file_url={file_url}, dir={dir} , file={file}, file_type={file_type}") en_scrabmle_file = ComicPath.getFileScrambleImageSave(file) en_scrabmle_path = os.path.join(dir,en_scrabmle_file) @@ -214,7 +214,7 @@ class downloadUtils: raise NameError("下载异常") with open(temp_path, 'wb') as f: f.write(response.content) - time.sleep(0.7) + time.sleep(0.1) response.close() #验证是否是图像 if fu.ver_file(temp_path,type=file_type): @@ -225,10 +225,11 @@ class downloadUtils: raise NameError("## Fail: {} {}".format(file_url, "图像损坏")) except Exception as e: logger.warning(f'重试：第{repair_count}次 异常:{e} {file_url}') + time.sleep(1.5) repair_count += 1 @classmethod - def start_downloads(cls,repair_max=20,concurrency=None,timeout=20,proxy_type=None, proxy=None): + def start_downloads(cls,concurrency=None,timeout=20,proxy_type=None, proxy=None): """ Download image according to given urls and automatically rename them in order. :param timeout: