update

.gitignore

@@ -1,3 +1,4 @@
 .scrapy/*
 images/*
+json/*
 /**/__pycache__

Comics/exporters.py

@@ -8,6 +8,8 @@ from Comics.items import ComicItem
 from Comics.settings import COMIC_INFO_XML_STORE
 from Comics.utils.Constant import ComicPath
 from scrapy.utils.python import is_listlike, to_bytes, to_unicode
+from itemadapter import ItemAdapter
+
 
 class ItemExporter(PythonItemExporter):
     def convert(self, data):
@@ -46,7 +48,12 @@ class ComicInfoXmlItemExporter(XmlItemExporter):
 
     def comic_to_info_item(self, comic_item):
         comic_info = {}
-        comic_info_dict = getattr(ComicItem, "data", 0)
+        info_item = ItemAdapter(ComicInfoItem())
+        comic_info_dict = {}
+        for field in info_item.field_names():
+            meta_info = info_item.get_field_meta(field).get('info')
+            if meta_info is not None:
+                comic_info_dict[meta_info] = field
         for key, value in ComicItem(comic_item).items():
             new_key = comic_info_dict.get(key)
             if new_key is not None:
@@ -63,7 +70,7 @@ class ComicInfoXmlItemExporter(XmlItemExporter):
                value = str(value).split(',')
             if value is not None or value != "":
                 self._export_xml_field(name, value, depth=2, child_element=child_element)
-        self._beautify_indent(depth=1)
+        #self._beautify_indent(depth=1)
         return comic_info
 
     def _export_xml_field(self, name, serialized_value, depth, child_element="value"):
@@ -71,8 +78,8 @@ class ComicInfoXmlItemExporter(XmlItemExporter):
         self.xg.startElement(name, {})
         if hasattr(serialized_value, "items"):
             self._beautify_newline()
-            for subname, value in serialized_value.items():
+            for sub_name, value in serialized_value.items():
-                self._export_xml_field(subname, value, depth=depth + 1)
+                self._export_xml_field(sub_name, value, depth=depth + 1)
             self._beautify_indent(depth=depth)
         elif is_listlike(serialized_value):
             self._beautify_newline()

Comics/items.py

@@ -4,18 +4,8 @@
 # https://docs.org/en/latest/topics/items.html
 from scrapy.item import Item, Field
 from Comics.utils.Constant import ComicPath
-from dataclasses import dataclass
 from scrapy.loader.processors import TakeFirst, MapCompose, Join
 
-
-data = {}
-def setinfo(**kwds):
-    def decorate(f):
-        for k in kwds: data[k] = kwds[k]
-        setattr(f, "data", data)
-        return f
-    return decorate
-
 def serialize_to_chinese(value):
     return ComicPath.chinese_convert(value)
 
@@ -27,34 +17,29 @@ class ComicOItem(Item):
     name = Field()
     chapterItem = Field()
 
-@setinfo(name="Series", chapter="Title",
-         author="Writer", tags="Tags",
-         dep="Summary", genre="Genre",
-         index="Number", images_name="Pages",
-         age_rating="AgeRating")
 class ComicItem(Item):
     # 编号
-    index = Field()
+    index = Field(output_processor=TakeFirst())
     # 漫画名
     name = Field(serializer=serialize_to_fix_file, output_processor=TakeFirst())
     # 章节名
-    chapter = Field(serializer=serialize_to_fix_file)
+    chapter = Field(serializer=serialize_to_fix_file, output_processor=TakeFirst())
     # 图片链接
     list_img = Field()
     # 作者
     author = Field(serialize_to_chinese=serialize_to_chinese, output_processor=TakeFirst())
     # 封面链接
-    icon = Field()
+    icon = Field(output_processor=TakeFirst())
     # 标签
-    tags = Field(serializer=serialize_to_chinese)
+    tags = Field(serializer=serialize_to_chinese, output_processor=TakeFirst())
     # 概述
-    dep = Field(serializer=serialize_to_chinese)
+    dep = Field(serializer=serialize_to_chinese, output_processor=TakeFirst())
     # 时间
-    date = Field()
+    date = Field(output_processor=TakeFirst())
     # 流派
-    genre = Field()
+    genre = Field(output_processor=TakeFirst())
     # 年龄分级
-    age_rating = Field()
+    age_rating = Field(output_processor=TakeFirst())
 
     images = Field()
     images_name = Field()
@@ -72,22 +57,22 @@ def serializer_info_writer(value):
     return ",".join(list_value)
 
 class ComicInfoItem(Item):
-    Title = Field()#"章节名",True]
+    Title = Field(info='chapter')#"章节名",True]
-    Series = Field()# ","漫画名",True]
+    Series = Field(info='name')# ","漫画名",True]
-    Number = Field()# ","编号",True]
+    Number = Field(info='index')# ","编号",True]
     SeriesGroup = Field()# ","别名",False]
-    Summary = Field()# ","概述",True]
+    Summary = Field(info='dep')# ","概述",True]
     Year = Field()# ","年",False]
     Month = Field()# ","月",False]
     Day = Field()# ","日",False]
-    Writer = Field(serializer=serializer_info_writer)# "作者",True]
+    Writer = Field(info='author',serializer=serializer_info_writer)# "作者",True]
     Publisher = Field()# ","出版社",False]
-    Genre = Field()# ","流派",True]
+    Genre = Field(info='genre')# ","流派",True]
-    Tags = Field()# ","标签",True]
+    Tags = Field(info='tags')# ","标签",True]
     Web = Field()# ","主页",False]
     PageCount = Field()# ","总页数",True]
     LanguageISO = Field()#","语言",True]
-    AgeRating = Field()#","年龄分级",False]
+    AgeRating = Field(info='age_rating')#","年龄分级",False]
-    Pages = Field()#","页码",True]
+    Pages = Field(info='images_name')#","页码",True]
-    Page = Field()
     # ComicInfo.xml and ComicChapter.json end
+

Comics/loader.py

@@ -0,0 +1,44 @@
+import json
+from scrapy.loader import ItemLoader
+class ComicLoader(ItemLoader):
+    def parseExec(cls,data,exec):
+        if data !=None and exec != None:
+            dots = str(exec).split(".")
+            if not isinstance(data,dict): data = json.loads(data)
+            for dot in dots:
+                data = data.get(dot)
+        return data
+
+    def add_xpath(self, field_name, xpath, *processors, index=None, exec=None, re=None, **kw):
+        """
+        Similar to :meth:`ItemLoader.add_value` but receives an XPath instead of a
+        value, which is used to extract a list of strings from the
+        selector associated with this :class:`ItemLoader`.
+
+        See :meth:`get_xpath` for ``kwargs``.
+
+        :param xpath: the XPath to extract data from
+        :type xpath: str
+
+        Examples::
+
+            # HTML snippet: <p class="product-name">Color TV</p>
+            loader.add_xpath('name', '//p[@class="product-name"]')
+            # HTML snippet: <p id="price">the price is $1200</p>
+            loader.add_xpath('price', '//p[@id="price"]', re='the price is (.*)')
+
+        """
+        values = self._get_xpathvalues(xpath, **kw)
+        if exec is not None:
+            values = self.parseExec(values, exec)
+        if index is not None:
+            values = values[index]
+        self.add_value(field_name, values, *processors, re=re, **kw)
+
+    def add_exec(self, field_name, value, str_exec=None, *processors, re=None, **kw):
+        if str_exec is not None:
+            value = self.parseExec(value, str_exec)
+        self.add_value(field_name, value, *processors, re=re, **kw)
+
+    def get_exec(self, value, str_exec):
+        return self.parseExec(value, str_exec)

Comics/middlewares.py

@@ -4,13 +4,16 @@
 # https://docs.scrapy.org/en/latest/topics/spider-middleware.html
 
 from scrapy import signals
-import random
+import random,logging
+from pathlib import Path
 from Comics.settings import PROXY_LIST
 # useful for handling different item types with a single interface
-from itemadapter import is_item, ItemAdapter
+
+logger = logging.getLogger(__name__)
 
 class ProxyMiddleware(object):
     def process_request(self, request, spider):
+        if len(PROXY_LIST) != 0:
             request.meta["proxy"] = random.choice(PROXY_LIST)
 
 class ComicsSpiderMiddleware:

Comics/pipelines.py

@@ -5,7 +5,7 @@
 
 
 # useful for handling different item types with a single interface
-import os,requests,re,scrapy,logging
+import os, scrapy
 from Comics import settings
 from Comics.utils.FileUtils import imageUtils
 from Comics.utils.FileUtils import fileUtils
@@ -15,7 +15,7 @@ from Comics.items import ImageItem
 from scrapy.pipelines.images import ImagesPipeline
 from Comics.exporters import ComicInfoXmlItemExporter
 from Comics.exporters import ItemExporter
-from Comics.utils.CBZUtils import CBZUtils
+from Comics.utils.FileUtils import CBZUtils
 
 class ComicsPipeline:
     def open_spider(self, spider):

Comics/settings.py

@@ -34,7 +34,7 @@ DOWNLOAD_DELAY = 20
 RETRY_ENABLED = True
 RETRY_TIMES = 10 # 想重试几次就写几
 # 下面这行可要可不要
-#RETRY_HTTP_CODES = [500, 502, 503, 504, 408]
+RETRY_HTTP_CODES = [500, 502, 503, 504, 408, 401]
 # The download delay setting will honor only one of:
 #CONCURRENT_REQUESTS_PER_DOMAIN = 16
 #CONCURRENT_REQUESTS_PER_IP = 16
@@ -102,7 +102,8 @@ AUTOTHROTTLE_DEBUG = False
 HTTPCACHE_ENABLED = True
 HTTPCACHE_EXPIRATION_SECS = 0
 HTTPCACHE_DIR = 'httpcache'
-HTTPCACHE_IGNORE_HTTP_CODES = [500, 502, 404, 403]
+HTTPCACHE_IGNORE_HTTP_CODES = [500, 502, 404, 403, 401]
+#HTTPCACHE_STORAGE = 'Comics.middlewares.MyFilesystemCacheStorage'
 HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
 
 CBZ_EXPORT_PATH = "CBZ"

Comics/spiders/rm_comic.py

@@ -1,9 +1,8 @@
-import urllib.parse
+import scrapy
-
-import scrapy,json,requests
 from Comics.items import ComicItem
-from Comics.utils.FileUtils import CommonUtils
+from Comics.loader import ComicLoader
-from scrapy.loader import ItemLoader
+from itemadapter import ItemAdapter
+from Comics.items import ComicInfoItem
 
 class RmComicSpider(scrapy.Spider):
     name = 'rm_comic'
@@ -15,48 +14,49 @@ class RmComicSpider(scrapy.Spider):
         yield scrapy.Request('https://rm01.xyz'
                              '/books/306ec1e2-f701-4fda-bb78-041ad6ec4020', callback=self.parse_comic)
 
+    # 获取某个漫画的相关数据
+    # 获取到多个章节链接后进入下个流程
     def parse_comic(self, response):
-        comic = ComicItem()
+        comic_item = ComicLoader(item=ComicItem(), response=response)
-#        comic_item = ItemLoader(item=ComicItem(), response=response)
+        comic_item.add_xpath('name', '//div[@class="col"]/h5/text()')
-        comic['name'] = response.xpath('//div[@class="col"]/h5/text()').extract_first()
+        comic_item.add_xpath('icon', '//img[@class="img-thumbnail"]/@src')
-        comic['icon'] = response.xpath('//img[@class="img-thumbnail"]/@src').extract_first()
+        comic_item.add_xpath('author', '//div[contains(@class,"bookid_bookInfo")]/p[1]/text()', index=1)
-        comic['author'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[1]/text()').extract()[1]
+        comic_item.add_xpath('tags', '//div[contains(@class,"bookid_bookInfo")]/p[3]/b/text()')
-        comic['tags'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[3]/b/text()').extract_first()
+        comic_item.add_xpath('dep', '//div[contains(@class,"bookid_bookInfo")]/p[4]/text()', index=1)
-        comic['dep'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[4]/text()').extract()[1]
+        comic_item.add_xpath('date', '//div[contains(@class,"bookid_bookInfo")]/p[5]/small/text()', index=1)
-        comic['date'] = response.xpath('//div[contains(@class,"bookid_bookInfo")]/p[5]/small/text()').extract()[1]
+        comic_item.add_value('genre', "韩漫")
-        comic['genre'] = "韩漫"
+        comic_item.add_value('age_rating', "R18+")
-        comic['age_rating'] = "R18+"
+        chapter_href = comic_item.get_xpath('//div[contains(@class,"bookid_chapterBox")]'
-        chapters = response.xpath('//div[contains(@class,"bookid_chapterBox")]'
+                                               '//div[contains(@class,"bookid_chapter")]/a/@href')
-                                           '//div[contains(@class,"bookid_chapter")]/a/text()').extract()
+        #chapters = response.xpath('//div[contains(@class,"bookid_chapterBox")]'
-        chapter_href = response.xpath('//div[contains(@class,"bookid_chapterBox")]'
+        #                                   '//div[contains(@class,"bookid_chapter")]/a/text()').extract()
-                                               '//div[contains(@class,"bookid_chapter")]/a/@href').extract()
         #for chapter, link in zip(chapters, chapter_href):
         for i, link in enumerate(chapter_href, start=1):
-                yield scrapy.Request(self.main_url+link, meta={'item' : comic, 'number': i}, callback=self.parse_chapter)
+            yield scrapy.Request(self.main_url+link, meta={'item': comic_item.load_item(), 'num': i}, callback=self.parse_chapter)
 
+    # 读取某章节下的所有图片
     def parse_chapter(self, response):
-        item = response.meta['item']
+        comic_item = ComicLoader(item=response.meta['item'], response=response)
-        number = response.meta['number']
+        data = comic_item.get_xpath('//script[@id="__NEXT_DATA__"]/text()')[0]
-        data = response.xpath('//script[@id="__NEXT_DATA__"]/text()').extract_first()
         str_exec = "props.pageProps."
-        comic_name = CommonUtils.parseExec(data, str_exec+"bookName")
+        #comic_item.add_exec('name', data, str_exec=str_exec+"bookName")
-        chapterName = CommonUtils.parseExec(data, str_exec+"chapterName")
+        #comic_item.add_exec('dep', data, str_exec=str_exec+"description")
-        description = CommonUtils.parseExec(data, str_exec+"description")
+        comic_item.add_value('index', response.meta['num'])
-        images = CommonUtils.parseExec(data, str_exec+"images")
+        comic_item.add_exec('chapter', data, str_exec=str_exec + "chapterName")
-        chapter_api_url = CommonUtils.parseExec(data, str_exec+"chapterAPIPath")
+        comic_item.add_exec('list_img', data, str_exec+"images")
-        item['chapter'] = chapterName
+        comic = comic_item.load_item()
-        item['list_img'] = images
+        chapter_api_url = comic_item.get_exec(data, str_exec+"chapterAPIPath")
-        item['index'] = number
+        if chapter_api_url is not None:
-        if chapter_api_url != None:
+            yield scrapy.Request(self.main_url + chapter_api_url, meta={'item': comic}, callback=self.parse_chapter_api)
-            yield scrapy.Request(self.main_url+ chapter_api_url,meta={'item' : item}, callback= self.parse_chapter_api)
         else:
-            yield item
+            yield comic
 
+    # 加密数据API处理
     def parse_chapter_api(self, response):
-        item = response.meta['item']
+        comic_item = ComicLoader(item=response.meta['item'], response=response)
-        item['chapter'] = CommonUtils.parseExec(response.text, "chapter.name")
+        comic_item.add_exec('chapter', response.text, str_exec='chapter.name')
-        item['list_img'] = CommonUtils.parseExec(response.text, "chapter.images")
+        comic_item.add_exec('list_img', response.text, str_exec='chapter.images')
-        yield item
+        yield comic_item.load_item()
 
     def parse(self, response):
         raise NotImplementedError

Comics/utils/CBZUtils.py

@@ -1,105 +0,0 @@
-import os, shutil, time, logging
-from datetime import datetime
-from pathlib import Path
-from zipfile import ZipFile
-from Comics.settings import COMIC_INFO_XML_FILE,CBZ_EXPORT_PATH,IMAGES_STORE
-
-class CBZUtils:
-
-    @classmethod
-    def readDirsOrFiles(cls,dir,type):
-        data = []
-        files = os.listdir(dir)
-        for file in files:
-            path = os.path.join(dir,file)
-            if type == "files" and os.path.isfile(path):
-                data.append(path)
-            if type == "dirs" and os.path.isdir(path):
-                data.append(path)
-        return data
-    
-    @classmethod
-    def zip_compression(cls, source_dir=None, target_file=None, remove=True):
-        target_dir = os.path.dirname(target_file)
-        if not os.path.exists(target_dir):
-            os.makedirs(target_dir)
-        if not os.path.exists(target_file) and source_dir != None:
-            with ZipFile(target_file, mode='w') as zf:
-                for path, dir_names, filenames in os.walk(source_dir):
-                    path = Path(path)
-                    arc_dir = path.relative_to(source_dir)
-                    y = 0
-                    for filename in filenames:
-                        y = y + 1
-                        print("打包中：" + str(y) + "/" + str(len(filenames)), os.path.join(source_dir, filename))
-                        zf.write(path.joinpath(filename), arc_dir.joinpath(filename))
-                zf.close()
-                logging.info(f"打包完成：{target_file}")
-
-    @classmethod
-    def packComicChapterCBZ(cls, comic, chapter, remove=True):
-        images_chapter_path = os.path.join(IMAGES_STORE, comic, chapter)
-        cbz_chapter_path = os.path.join(CBZ_EXPORT_PATH, comic, chapter)+".CBZ"
-        if os.path.exists(images_chapter_path):
-            dirs = os.listdir(images_chapter_path)
-            for file in dirs:
-                if file.startswith("scramble="):
-                    try: 
-                        os.remove(file)
-                    except:
-                        print(f"删除 {file} 发生错误，已跳过")
-                        return False
-        cls.zip_compression(images_chapter_path, cbz_chapter_path)
-        time.sleep(0.1)
-        if remove: shutil.rmtree(images_chapter_path)
-        return True
-
-    @classmethod
-    def replaceZip(cls,filepath,unpack_dir=None):
-        if not cls.compareFileDate(filepath): return None
-        if unpack_dir == None:
-            unpack_dir = str(filepath).split(".")[0]
-        fz = ZipFile(filepath, 'r')
-        for file in fz.namelist():
-            if file.endswith(".jpg"):
-                data = fz.read(file)
-                if len(data) < 500 and os.path.exists(filepath):
-                    os.remove(filepath)
-                    print(f"数据不完整,已删除:{filepath}")
-                if cls.compareFileDate(filepath):
-                    os.utime(filepath)
-                    print(f"已更新文件时间 {filepath}")
-        if os.path.exists(unpack_dir):
-            shutil.rmtree(unpack_dir)
-        # 删除删除main.ftl文件
-        #delete_filename = ''
-        #if os.path.exists(delete_filename):
-        #    os.remove(delete_filename)
-        # time.sleep(60)
-        # shutil.copy(文件的路径，另一个目录);拷贝main.ftl到准备压缩的目录下
-        #cls.zip_compression()
-        #小于则运行
-    @classmethod
-    def compareFileDate(cls,filepath):
-        if os.path.exists(filepath):
-            ctime = os.path.getmtime(filepath)
-            str_ctime = datetime.fromtimestamp(int(ctime))
-            file_ctime = str(str_ctime.year)+"{:0>2d}".format(str_ctime.month)+"{:0>2d}".format(str_ctime.day)+"{:0>2d}".format(str_ctime.hour)
-            c_ctime = 2023011603
-        else:
-            return False
-        if int(file_ctime) < c_ctime:
-            return True
-        return False
-
-    @classmethod
-    def zip_info(cls, path, filter=True):
-        result = None
-        try:
-            with ZipFile(path, "r") as zip_file:
-                result = zip_file.namelist()
-            if filter:
-                result.remove(COMIC_INFO_XML_FILE)
-        except Exception as e:
-            print(e)
-        return result

Comics/utils/ComicInfo.py

@@ -1,99 +0,0 @@
-import json,os
-import logging
-from xml.dom.minidom import Document
-from Comics.utils.Constant import ComicPath
-from itemadapter import is_item, ItemAdapter
-
-class ComicInfo:
-    IS_NEW_ICON = False 
-    document = Document()
-    path_comic_info = None
-    
-    @classmethod
-    def setNodeAndValue(cls,node,value):
-       if value != None:
-            if isinstance(value,str):
-                c_node =  cls.document.createElement(node)
-                child_node =  cls.document.createTextNode(value)
-                c_node.appendChild(child_node)
-                return c_node
-            else: return value 
-       return None
-    
-    #页数
-    @classmethod
-    def setPages(cls,values=None):
-       #if values == None: values = Comic.getChapterFilesName()
-       if values != None and isinstance(values,list):
-            suffix = "."+str(values[0]).split(".")[-1]
-            join_list=",".join(values).replace(suffix,"")
-            values = join_list.split(",")
-            #Comic.setPageCount(len(values)+1 if cls.IS_NEW_ICON else len(values))
-            root_node = cls.document.createElement("Pages")
-            if cls.IS_NEW_ICON:
-                #添加封面
-                icon_node = cls.document.createElement("Page")
-                icon_node.setAttribute("Image",ComicPath.COMIC_ICON_NAME)
-                icon_node.setAttribute("Type","FrontCover")
-                root_node.appendChild(icon_node)
-            for page in values:
-                c_node =  cls.document.createElement("Page")
-                page = page.split("_")[-1]
-                c_node.setAttribute("Image",page)
-                root_node.appendChild(c_node)
-            #Comic.dict_pages = Comic.setField(Comic.dict_pages,root_node,convert=False)
-
-    @classmethod
-    def getBaseUrl(cls,url=None):
-        #if url == None:
-        #    url = Comic.getHomePage()
-        (num,index) = [3,0]
-        for x in range(0, num):
-            index = str(url).find("/",index)+1
-        return url[0:index-1]
-    
-    #XML根文档
-    @classmethod
-    def root_node(cls,root_value): return cls.document.createElement(root_value)
-    
-    @classmethod
-    def add_nodes(cls,root,item):
-        item = ItemAdapter(item)
-        keys = item.keys()
-        files = item.field_names()
-        values = item.values()
-        print("test")
-        #if len(list_value) == 0: return list_value
-        #for value in list_value:
-        #    #Comic.chapter
-        #    if value[0] == None and value[4]:
-        #        #数据为空 value[0]， 但不允许为空value[4] = False
-        #        msg = f"#数据为空 key={value[3]} value[0]={value[0]}， 但不允许为空value[4]={value[4]}"
-        #        logging.error(msg)
-        #        exit()
-        #    if value[0] != None: root.appendChild(cls.setNodeAndValue(value[2],value[0]))
-            
-    @classmethod
-    def initComicInfoXML(cls):
-        cls.setPages()
-    
-    @classmethod
-    def writeComicInfoXML(cls,item,overlay=False):
-        #save_path = ComicPath.getPathComicInfoXML()
-        save_path = "ComicInfo.xml" 
-        if os.path.exists(save_path):
-            if overlay: 
-                os.remove(save_path)
-                logging.info(f"已存在文件，已删除... {save_path}") 
-            else:
-                logging.info(f"已存在文件，跳过中... {save_path}") 
-                return True
-        cls.initComicInfoXML()
-        root = cls.root_node("ComicInfo")
-        new_document = Document()
-        new_document.appendChild(root)
-        cls.add_nodes(root, item)
-        with open(save_path, "w", encoding="utf-8") as fo:
-            new_document.writexml(fo, indent='', addindent='\t', newl='\n', encoding="utf-8")
-            fo.close()
-            logging.info(f"已生成文件... {save_path}")

Comics/utils/Constant.py

@@ -1,14 +1,15 @@
 import os.path
 import re
 from opencc import OpenCC
-from Comics.settings import IMAGES_STORE
 class ComicPath:
+    PREFIX_SCRAMBLE = "scramble="
+
     @classmethod
     def getDirComicChapter(cls):
         return None
     
     @classmethod
-    def getFileScrambleImageName(cls,count,block,suffix=".jpg"): return "scramble="+str(block)+"_"+str(count)+suffix
+    def getFileScrambleImageName(cls,count,block,suffix=".jpg"): return cls.PREFIX_SCRAMBLE+str(block)+"_"+str(count)+suffix
     
     @classmethod
     def getFileScrambleImageSave(cls,file): return str(file).split("_")[-1]

Comics/utils/FileUtils.py

@@ -1,8 +1,10 @@
 import base64,hashlib,os,shutil
 import math,time,json,datetime,logging
 from PIL import Image
-from tinydb import TinyDB, Query
 from Comics.utils.Constant import ComicPath
+from pathlib import Path
+from zipfile import ZipFile
+from Comics.settings import COMIC_INFO_XML_FILE,CBZ_EXPORT_PATH,IMAGES_STORE
 
 class fileUtils:
     @classmethod
@@ -32,15 +34,15 @@ class imageUtils:
         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="):
+                if img.startswith(ComicPath.PREFIX_SCRAMBLE):
                     imageUtils.encode_scramble_image(os.path.join(chapter_dir,img))
                     scramble_count += 1
-                    logging.debug(f"scramble= {scramble_count}")
+                    logging.debug(f"{ComicPath.PREFIX_SCRAMBLE} {scramble_count}")
         return scramble_count
     
     @classmethod
     def deScrambleImagesByPath(cls, img_path, img_save=None):
-        if os.path.basename(img_path).startswith("scramble="):
+        if os.path.basename(img_path).startswith(ComicPath.PREFIX_SCRAMBLE):
            img_path =  imageUtils.encode_scramble_image(img_path, img_save)
         return img_path
 
@@ -233,3 +235,106 @@ class imageUtils:
                 os.remove(imgpath)
                 print("remove=",imgpath)
             return save_path
+
+
+class CBZUtils:
+
+    @classmethod
+    def readDirsOrFiles(cls, dir, type):
+        data = []
+        files = os.listdir(dir)
+        for file in files:
+            path = os.path.join(dir, file)
+            if type == "files" and os.path.isfile(path):
+                data.append(path)
+            if type == "dirs" and os.path.isdir(path):
+                data.append(path)
+        return data
+
+    @classmethod
+    def zip_compression(cls, source_dir=None, target_file=None, remove=True):
+        target_dir = os.path.dirname(target_file)
+        if not os.path.exists(target_dir):
+            os.makedirs(target_dir)
+        if not os.path.exists(target_file) and source_dir is not None:
+            with ZipFile(target_file, mode='w') as zf:
+                for path, dir_names, filenames in os.walk(source_dir):
+                    path = Path(path)
+                    arc_dir = path.relative_to(source_dir)
+                    y = 0
+                    for filename in filenames:
+                        y = y + 1
+                        print("打包中：" + str(y) + "/" + str(len(filenames)), os.path.join(source_dir, filename))
+                        zf.write(path.joinpath(filename), arc_dir.joinpath(filename))
+                zf.close()
+                logging.info(f"打包完成：{target_file}")
+
+    @classmethod
+    def packComicChapterCBZ(cls, comic, chapter, remove=True):
+        images_chapter_path = os.path.join(IMAGES_STORE, comic, chapter)
+        cbz_chapter_path = os.path.join(CBZ_EXPORT_PATH, comic, chapter) + ".CBZ"
+        if os.path.exists(images_chapter_path):
+            dirs = os.listdir(images_chapter_path)
+            for file in dirs:
+                if file.startswith(ComicPath.PREFIX_SCRAMBLE):
+                    try:
+                        os.remove(file)
+                    except Exception as e:
+                        print(f"删除 {file} 发生错误 {e}，已跳过")
+                        return False
+        cls.zip_compression(images_chapter_path, cbz_chapter_path)
+        time.sleep(0.1)
+        if remove: shutil.rmtree(images_chapter_path)
+        return True
+
+    @classmethod
+    def replaceZip(cls, filepath, unpack_dir=None):
+        if not cls.compareFileDate(filepath): return None
+        if unpack_dir == None:
+            unpack_dir = str(filepath).split(".")[0]
+        fz = ZipFile(filepath, 'r')
+        for file in fz.namelist():
+            if file.endswith(".jpg"):
+                data = fz.read(file)
+                if len(data) < 500 and os.path.exists(filepath):
+                    os.remove(filepath)
+                    print(f"数据不完整,已删除:{filepath}")
+                if cls.compareFileDate(filepath):
+                    os.utime(filepath)
+                    print(f"已更新文件时间 {filepath}")
+        if os.path.exists(unpack_dir):
+            shutil.rmtree(unpack_dir)
+        # 删除删除main.ftl文件
+        # delete_filename = ''
+        # if os.path.exists(delete_filename):
+        #    os.remove(delete_filename)
+        # time.sleep(60)
+        # shutil.copy(文件的路径，另一个目录);拷贝main.ftl到准备压缩的目录下
+        # cls.zip_compression()
+        # 小于则运行
+
+    @classmethod
+    def compareFileDate(cls, filepath):
+        if os.path.exists(filepath):
+            ctime = os.path.getmtime(filepath)
+            str_ctime = datetime.fromtimestamp(int(ctime))
+            file_ctime = str(str_ctime.year) + "{:0>2d}".format(str_ctime.month) + "{:0>2d}".format(
+                str_ctime.day) + "{:0>2d}".format(str_ctime.hour)
+            c_ctime = 2023011603
+        else:
+            return False
+        if int(file_ctime) < c_ctime:
+            return True
+        return False
+
+    @classmethod
+    def zip_info(cls, path, filter=True):
+        result = None
+        try:
+            with ZipFile(path, "r") as zip_file:
+                result = zip_file.namelist()
+            if filter:
+                result.remove(COMIC_INFO_XML_FILE)
+        except Exception as e:
+            print(e)
+        return result