add jm

get_jm_url.py

@@ -0,0 +1,2 @@
+def app():
+    return ["jmcomic2.onl","jmcomic1.onl","jmcomic.onl","jmcomic.me","jmcomic1.me","18comic.org"]

jmdowning.py

@@ -0,0 +1,285 @@
+import io
+
+import requests
+import time
+import os,re
+from multiprocessing import Queue
+import threading
+from threading import Lock
+from lxml import etree
+import math
+import execjs
+from PIL import Image
+from myran import Myran
+import get_jm_url
+from utils.ComicInfo import comicInfo
+from utils.PathStr import pathStr
+from utils.CBZUtils import CBZUtils
+from utils.HtmlUtils import htmlUtils
+
+os.environ['EXECJS_RUNTIME'] = "JScript"
+
+class Data:
+
+    @classmethod
+    def oneChapter(cls,*args):
+        book_name = comicInfo.getComicName()
+        chapter_name = comicInfo.getChapter()
+        chapter_href = comicInfo.getWeb()
+        try:
+            #print(data[2])
+            #response = requests.get(url=chapter_href, headers=headers, proxies=proxy)
+            path_album = os.path.join(pathStr.base_comic_img,book_name)
+            path_photo = os.path.join(path_album, chapter_name)
+                 # path_img = "path_photo\\%s.jpg" %img_name
+            with lock:  # 判断文件夹是否存在要加锁
+                if not os.path.exists(path_album): os.makedirs(path_album)
+                if not os.path.exists(path_photo): os.makedirs(path_photo)
+#                    comicInfo.writeComicInfoXML(data[0],path=path_photo)
+            cls.parse(chapter_href,path_photo,args[0])
+        # except requests.exceptions.ConnectionError:
+        #     print("重新抛入queue：",data)
+        #     data_queue.put(data)
+        except Exception as e:
+            print(e.__traceback__.tb_lineno,e)
+            print("重新抛入data_queue：")
+            cls.oneChapter(args)
+    
+    @classmethod
+    def parse(cls,rsp,path_photo,photoid):
+        img_list =htmlUtils.xpathData("//div[@class='panel-body']/div/div[contains(@class,'center')]/img",url=rsp)
+
+        pages_imgs =htmlUtils.xpathData("//div[@class='center scramble-page']/@id",url=rsp)
+        comicInfo.setPages(pages_imgs)
+        comicInfo.writeComicInfoXML(comicInfo.str_chapter,path=path_photo)
+        #print("img_list:",len(img_list))
+        for i in img_list:
+            img_url= i.attrib['data-original']
+            img_name = os.path.basename(img_url).split('.')[0]
+            path_img = "%s\\%s.jpg" % (path_photo, img_name)
+            #print([img_url,photoid,path_img])
+            down_queue.put([img_url,photoid,path_img])
+            
+class Download(threading.Thread):
+    def __init__(self,thread_name):
+        super().__init__()
+        self.thread_name = thread_name
+    def run(self):
+        print("%s开始了！"%self.thread_name)
+        while not down_empty:
+            try:
+                print("还剩余%s张图片"%down_queue.qsize())
+                if not down_queue.empty():
+                    down = down_queue.get(False)
+                else:
+                    time.sleep(3)
+                    down = down_queue.get(False)
+                try:
+                    print("down",down)
+                    if not os.path.exists(down[2]):
+                        #scramble_id=220980 网页固定值
+                        if int(down[1])>220980:#albumid>aid就使用拼接函数 否则直接下载
+                            print("拼接图片")
+                            self.pjdown(down[0],down[1],down[2])
+                        else:
+                            print("直接下载图片")
+                            self.dowm_img(down[0],down[2])
+
+                except  Exception as e:
+                    print(e.__traceback__.tb_lineno,e)
+                    print("重新抛入queue：",down)
+                    down_queue.put(down)
+            except:
+                pass
+    def dowm_img(self,url,path_img):
+        # s=random.choice(list(range(3)))+1+random.random()
+        # time.sleep(s)
+        #print("time.sleep=%d"%s)
+        headers["User_Agent"]=myran.agents()
+        response = requests.get(url,headers=headers,proxies=proxy)
+        if response.status_code == 200:
+            with open(path_img,"wb") as f:
+                f.write(response.content)
+        else:print("图片request失败")
+    def pjdown(self,*args):
+        imgurl = args[0]
+        #print(imgurl)
+        imgpath=args[-1]
+        # httpproxy_handler = urllib.request.ProxyHandler(proxies=proxy)
+        # opener = urllib.request.build_opener(httpproxy_handler)
+        # urlz = urllib.request.Request(imgurl, headers={"User-Agent": myran.agents()})
+        # im2 = Image.open(opener.open(urlz))
+
+        headers["User_Agent"]=myran.agents()
+        response=requests.get(imgurl, headers=headers,proxies=proxy)
+        if response.status_code == 200:
+            im2 = Image.open(io.BytesIO(response.content))
+            #im2.show()
+            #print(imgurl, args[1],imgpath, im2)
+            self.splitimage(imgurl, args[1],imgpath, im2)
+    def get_md5(self,num):
+        with open('js/md5.js', 'r') as file:
+            result = file.read()
+        context1 = execjs.compile(result)
+        result1 = context1.call('md5', num)
+        return result1
+    def get_num(self,e, t):
+        #print(type(e),e, type(t),t)
+        a = 10
+        try:
+            num_dict = {}
+            for i in range(10):
+                num_dict[i] = i * 2 + 2
+            if (int(e) >= 268850):
+                n = str(e) + t;
+                # switch(n=(n = (n = md5(n)).substr(-1)), n %= 10) {
+                #print("n=",n)
+                tmp = ord(self.get_md5(n)[-1])
+                result = num_dict[tmp % 10]
+                a = result
+            return a
+        except Exception as e:
+            print(e.__traceback__.tb_lineno,e)
+            return False
+    def splitimage(self,src, aid,imgpath,imageob=''):
+        if imageob == '':
+            image = Image.open(src)
+        else:
+            image = imageob
+        w, h = image.size
+        #image.show()
+        img_name = os.path.basename(src).split('.')[0]
+        # print(type(aid),type(img_name))
+        if self.get_num(aid, img_name):
+            s = self.get_num(aid, img_name)  # 随机值
+            # print(s)
+            l = h % s  # 切割最后多余的值
+            box_list = []
+            hz = 0
+            for i in range(s):
+                c = math.floor(h / s)
+                g = i * c
+                hz += c
+                h2 = h - c * (i + 1) - l
+                if i == 0:
+                    c += l;hz += l
+                else:
+                    g += l
+                box_list.append((0, h2, w, h - g))
+
+            # print(box_list,len(box_list))
+            item_width = w
+            # box_list.reverse() #还原切图可以倒序列表
+            # print(box_list, len(box_list))
+            newh = 0
+            image_list = [image.crop(box) for box in box_list]
+            # print(box_list)
+            newimage = Image.new("RGB", (w, h))
+            for image in image_list:
+                # image.show()
+                b_w, b_h = image.size
+                newimage.paste(image, (0, newh))
+
+                newh += b_h
+            newimage.save(imgpath)
+
+down_queue=Queue()
+data_empty = False
+down_empty = False
+lock = Lock()
+myran = Myran()
+headers = {
+    #'cookie':'ipcountry=US; AVS=4eb0s4o5ho9hfmp704ge7jtium; ipm5=bb7f6ac39cebfa37e89bd07544c549fd; cover=1; guide=1; __atuvc=12|39,31|40,5|41,0|42,4|43; __atuvs=635cabf67eff0d49003; yuo1={"objName":"hT3l8Pyn15Uf","request_id":0,"zones":[{"idzone":"2967008","here":{}},{"idzone":"2967010","here":{}},{"idzone":"2967010","here":{}},{"idzone":"3597795","sub":"70","here":{}}]}',
+    #'referer': 'https://18comic.org/',
+    "User_Agent": myran.agents()
+}
+proxy = {
+#    "http":"127.0.0.1:7890",
+#    "https":"127.0.0.1:7890"
+}
+def app(url):
+    try:
+        global data_empty,down_empty
+
+        newurl_list=get_jm_url.app()
+        response=''
+        if newurl_list:
+            if re.findall(r'https://(.*?)/\w+/\d+/',url)[0] not in newurl_list:
+                for newurl in newurl_list:
+                    url = re.sub(re.findall(r'https://(.*?)/\w+/\d+/', url)[0], newurl, url)
+                    response = requests.get(url=url, headers=headers, proxies=proxy)
+                    break
+            else:
+                response = requests.get(url=url, headers=headers, proxies=proxy)
+        else:
+            response = requests.get(url=url, headers=headers, proxies=proxy)
+        if response:
+            albumid = re.search(r'/album/(\d+)', url).group(1)
+            referer = re.search(r'(https://\w+\.\w+)/', url).group(1)
+            print("albumid", albumid, referer, url)
+            print(response.url)
+            if response.status_code == 200:
+                print(response.status_code)
+                eth = etree.HTML(response.text)
+                #拿到所有话数
+                nums = eth.xpath("//div[@class='row']/div[6]/div[1]/div[1]/ul[contains(@class,'btn-toolbar')]/a")
+                book_name = eth.xpath("//div[@itemprop='name']/h1[@id='book-name']/text()")[0]
+                book_name = re.sub(r'[\\\/\|\(\)\~\?\.\:\：\-\*\<\>]', '', book_name)
+                tags = eth.xpath("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='tag-block']/span[@data-type='tags']/a[@class='btn btn-sm btn-primary']/text()")
+                author = eth.xpath("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='tag-block']/span[@data-type='author']/a[@class='btn btn-sm btn-primary']/text()")
+                book_msg = eth.xpath("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='p-t-5 p-b-5']/text()")
+                jmid = book_msg[0]
+                dep = str(book_msg[1]).replace("叙述：","")
+
+                comicInfo.setComicName(book_name)
+                comicInfo.setAuthor(author)
+                comicInfo.setDep(dep)
+                comicInfo.setTags(tags)
+                comicInfo.setTag(tags)
+                comicInfo.setCBS("韩漫")
+                comicInfo.setLang("zh")
+
+                if nums:
+                    for i in nums:
+                        photo_name_list = i.xpath("li/text()")[0].split()
+                        photo_date = i.xpath("li/span/text()")[0].split()
+                        #print(re.findall(r'[\u4E00-\u9FA5]+.*?', i.xpath("li/text()")[0]))
+                        try:
+                            if re.findall(r'[\u4E00-\u9FA5]', photo_name_list[2]):
+                                photo_name=re.sub(r'\s','',photo_name_list[0])+' '+photo_name_list[2]
+                            else:photo_name=re.sub(r'\s','',photo_name_list[0])
+                        except Exception as e:
+                            photo_name = re.sub(r'\s', '', photo_name_list[0])
+                        photo_name = re.sub(r'[\\\/\|\(\)\~\?\.\:\：\-\*\<\>\-]', '',photo_name)
+                        #print(photo_name)
+                        photoid=i.attrib['data-album']
+                        comicInfo.setChapterName(photo_name)
+                        comicInfo.setDate(photo_date[0],split='-')
+                        comicInfo.setWeb(referer+i.attrib['href'])
+                        Data.oneChapter(photoid)
+    except Exception as e:
+        print(e.__traceback__.tb_lineno,e)
+        startime=time.perf_counter()
+        while True:
+            if down_queue.qsize()>100 or time.perf_counter()-startime>10:
+                break
+        print('down_queue.qsize():%s'%down_queue.qsize())
+        down_list=['down下载线程%s号'%s for s in list(range(1,40 if down_queue.qsize()>40 else down_queue.qsize()))]
+        down_thread_list=[]
+        for i in down_list:
+            down=Download(i)
+            down.start()
+            time.sleep(0.7)
+            down_thread_list.append(down)
+        while not down_queue.empty():
+            pass
+        down_empty=True
+        for down_thread in down_thread_list:
+            down_thread.join()
+            print("%s结束了！"%down_thread.thread_name)
+        
+
+if __name__ == '__main__':
+#    os.environ["http_proxy"] = "http://127.0.0.1:7890"
+#    os.environ["https_proxy"] = "http://127.0.0.1:7890"
+    app("https://18comic.vip/album/407792/")

js/md5.js

@@ -0,0 +1,408 @@
+/*
+ * JavaScript MD5
+ * https://github.com/blueimp/JavaScript-MD5
+ *
+ * Copyright 2011, Sebastian Tschan
+ * https://blueimp.net
+ *
+ * Licensed under the MIT license:
+ * https://opensource.org/licenses/MIT
+ *
+ * Based on
+ * A JavaScript implementation of the RSA Data Security, Inc. MD5 Message
+ * Digest Algorithm, as defined in RFC 1321.
+ * Version 2.2 Copyright (C) Paul Johnston 1999 - 2009
+ * Other contributors: Greg Holt, Andrew Kepert, Ydnar, Lostinet
+ * Distributed under the BSD License
+ * See http://pajhome.org.uk/crypt/md5 for more info.
+ */
+
+/* global define */
+
+/* eslint-disable strict */
+;(function ($) {
+    'use strict'
+
+    /**
+     * Add integers, wrapping at 2^32.
+     * This uses 16-bit operations internally to work around bugs in interpreters.
+     *
+     * @param {number} x First integer
+     * @param {number} y Second integer
+     * @returns {number} Sum
+     */
+    function safeAdd(x, y) {
+        var lsw = (x & 0xffff) + (y & 0xffff)
+        var msw = (x >> 16) + (y >> 16) + (lsw >> 16)
+        return (msw << 16) | (lsw & 0xffff)
+    }
+
+    /**
+     * Bitwise rotate a 32-bit number to the left.
+     *
+     * @param {number} num 32-bit number
+     * @param {number} cnt Rotation count
+     * @returns {number} Rotated number
+     */
+    function bitRotateLeft(num, cnt) {
+        return (num << cnt) | (num >>> (32 - cnt))
+    }
+
+    /**
+     * Basic operation the algorithm uses.
+     *
+     * @param {number} q q
+     * @param {number} a a
+     * @param {number} b b
+     * @param {number} x x
+     * @param {number} s s
+     * @param {number} t t
+     * @returns {number} Result
+     */
+    function md5cmn(q, a, b, x, s, t) {
+        return safeAdd(bitRotateLeft(safeAdd(safeAdd(a, q), safeAdd(x, t)), s), b)
+    }
+
+    /**
+     * Basic operation the algorithm uses.
+     *
+     * @param {number} a a
+     * @param {number} b b
+     * @param {number} c c
+     * @param {number} d d
+     * @param {number} x x
+     * @param {number} s s
+     * @param {number} t t
+     * @returns {number} Result
+     */
+    function md5ff(a, b, c, d, x, s, t) {
+        return md5cmn((b & c) | (~b & d), a, b, x, s, t)
+    }
+
+    /**
+     * Basic operation the algorithm uses.
+     *
+     * @param {number} a a
+     * @param {number} b b
+     * @param {number} c c
+     * @param {number} d d
+     * @param {number} x x
+     * @param {number} s s
+     * @param {number} t t
+     * @returns {number} Result
+     */
+    function md5gg(a, b, c, d, x, s, t) {
+        return md5cmn((b & d) | (c & ~d), a, b, x, s, t)
+    }
+
+    /**
+     * Basic operation the algorithm uses.
+     *
+     * @param {number} a a
+     * @param {number} b b
+     * @param {number} c c
+     * @param {number} d d
+     * @param {number} x x
+     * @param {number} s s
+     * @param {number} t t
+     * @returns {number} Result
+     */
+    function md5hh(a, b, c, d, x, s, t) {
+        return md5cmn(b ^ c ^ d, a, b, x, s, t)
+    }
+
+    /**
+     * Basic operation the algorithm uses.
+     *
+     * @param {number} a a
+     * @param {number} b b
+     * @param {number} c c
+     * @param {number} d d
+     * @param {number} x x
+     * @param {number} s s
+     * @param {number} t t
+     * @returns {number} Result
+     */
+    function md5ii(a, b, c, d, x, s, t) {
+        return md5cmn(c ^ (b | ~d), a, b, x, s, t)
+    }
+
+    /**
+     * Calculate the MD5 of an array of little-endian words, and a bit length.
+     *
+     * @param {Array} x Array of little-endian words
+     * @param {number} len Bit length
+     * @returns {Array<number>} MD5 Array
+     */
+    function binlMD5(x, len) {
+        /* append padding */
+        x[len >> 5] |= 0x80 << len % 32
+        x[(((len + 64) >>> 9) << 4) + 14] = len
+
+        var i
+        var olda
+        var oldb
+        var oldc
+        var oldd
+        var a = 1732584193
+        var b = -271733879
+        var c = -1732584194
+        var d = 271733878
+
+        for (i = 0; i < x.length; i += 16) {
+            olda = a
+            oldb = b
+            oldc = c
+            oldd = d
+
+            a = md5ff(a, b, c, d, x[i], 7, -680876936)
+            d = md5ff(d, a, b, c, x[i + 1], 12, -389564586)
+            c = md5ff(c, d, a, b, x[i + 2], 17, 606105819)
+            b = md5ff(b, c, d, a, x[i + 3], 22, -1044525330)
+            a = md5ff(a, b, c, d, x[i + 4], 7, -176418897)
+            d = md5ff(d, a, b, c, x[i + 5], 12, 1200080426)
+            c = md5ff(c, d, a, b, x[i + 6], 17, -1473231341)
+            b = md5ff(b, c, d, a, x[i + 7], 22, -45705983)
+            a = md5ff(a, b, c, d, x[i + 8], 7, 1770035416)
+            d = md5ff(d, a, b, c, x[i + 9], 12, -1958414417)
+            c = md5ff(c, d, a, b, x[i + 10], 17, -42063)
+            b = md5ff(b, c, d, a, x[i + 11], 22, -1990404162)
+            a = md5ff(a, b, c, d, x[i + 12], 7, 1804603682)
+            d = md5ff(d, a, b, c, x[i + 13], 12, -40341101)
+            c = md5ff(c, d, a, b, x[i + 14], 17, -1502002290)
+            b = md5ff(b, c, d, a, x[i + 15], 22, 1236535329)
+
+            a = md5gg(a, b, c, d, x[i + 1], 5, -165796510)
+            d = md5gg(d, a, b, c, x[i + 6], 9, -1069501632)
+            c = md5gg(c, d, a, b, x[i + 11], 14, 643717713)
+            b = md5gg(b, c, d, a, x[i], 20, -373897302)
+            a = md5gg(a, b, c, d, x[i + 5], 5, -701558691)
+            d = md5gg(d, a, b, c, x[i + 10], 9, 38016083)
+            c = md5gg(c, d, a, b, x[i + 15], 14, -660478335)
+            b = md5gg(b, c, d, a, x[i + 4], 20, -405537848)
+            a = md5gg(a, b, c, d, x[i + 9], 5, 568446438)
+            d = md5gg(d, a, b, c, x[i + 14], 9, -1019803690)
+            c = md5gg(c, d, a, b, x[i + 3], 14, -187363961)
+            b = md5gg(b, c, d, a, x[i + 8], 20, 1163531501)
+            a = md5gg(a, b, c, d, x[i + 13], 5, -1444681467)
+            d = md5gg(d, a, b, c, x[i + 2], 9, -51403784)
+            c = md5gg(c, d, a, b, x[i + 7], 14, 1735328473)
+            b = md5gg(b, c, d, a, x[i + 12], 20, -1926607734)
+
+            a = md5hh(a, b, c, d, x[i + 5], 4, -378558)
+            d = md5hh(d, a, b, c, x[i + 8], 11, -2022574463)
+            c = md5hh(c, d, a, b, x[i + 11], 16, 1839030562)
+            b = md5hh(b, c, d, a, x[i + 14], 23, -35309556)
+            a = md5hh(a, b, c, d, x[i + 1], 4, -1530992060)
+            d = md5hh(d, a, b, c, x[i + 4], 11, 1272893353)
+            c = md5hh(c, d, a, b, x[i + 7], 16, -155497632)
+            b = md5hh(b, c, d, a, x[i + 10], 23, -1094730640)
+            a = md5hh(a, b, c, d, x[i + 13], 4, 681279174)
+            d = md5hh(d, a, b, c, x[i], 11, -358537222)
+            c = md5hh(c, d, a, b, x[i + 3], 16, -722521979)
+            b = md5hh(b, c, d, a, x[i + 6], 23, 76029189)
+            a = md5hh(a, b, c, d, x[i + 9], 4, -640364487)
+            d = md5hh(d, a, b, c, x[i + 12], 11, -421815835)
+            c = md5hh(c, d, a, b, x[i + 15], 16, 530742520)
+            b = md5hh(b, c, d, a, x[i + 2], 23, -995338651)
+
+            a = md5ii(a, b, c, d, x[i], 6, -198630844)
+            d = md5ii(d, a, b, c, x[i + 7], 10, 1126891415)
+            c = md5ii(c, d, a, b, x[i + 14], 15, -1416354905)
+            b = md5ii(b, c, d, a, x[i + 5], 21, -57434055)
+            a = md5ii(a, b, c, d, x[i + 12], 6, 1700485571)
+            d = md5ii(d, a, b, c, x[i + 3], 10, -1894986606)
+            c = md5ii(c, d, a, b, x[i + 10], 15, -1051523)
+            b = md5ii(b, c, d, a, x[i + 1], 21, -2054922799)
+            a = md5ii(a, b, c, d, x[i + 8], 6, 1873313359)
+            d = md5ii(d, a, b, c, x[i + 15], 10, -30611744)
+            c = md5ii(c, d, a, b, x[i + 6], 15, -1560198380)
+            b = md5ii(b, c, d, a, x[i + 13], 21, 1309151649)
+            a = md5ii(a, b, c, d, x[i + 4], 6, -145523070)
+            d = md5ii(d, a, b, c, x[i + 11], 10, -1120210379)
+            c = md5ii(c, d, a, b, x[i + 2], 15, 718787259)
+            b = md5ii(b, c, d, a, x[i + 9], 21, -343485551)
+
+            a = safeAdd(a, olda)
+            b = safeAdd(b, oldb)
+            c = safeAdd(c, oldc)
+            d = safeAdd(d, oldd)
+        }
+        return [a, b, c, d]
+    }
+
+    /**
+     * Convert an array of little-endian words to a string
+     *
+     * @param {Array<number>} input MD5 Array
+     * @returns {string} MD5 string
+     */
+    function binl2rstr(input) {
+        var i
+        var output = ''
+        var length32 = input.length * 32
+        for (i = 0; i < length32; i += 8) {
+            output += String.fromCharCode((input[i >> 5] >>> i % 32) & 0xff)
+        }
+        return output
+    }
+
+    /**
+     * Convert a raw string to an array of little-endian words
+     * Characters >255 have their high-byte silently ignored.
+     *
+     * @param {string} input Raw input string
+     * @returns {Array<number>} Array of little-endian words
+     */
+    function rstr2binl(input) {
+        var i
+        var output = []
+        output[(input.length >> 2) - 1] = undefined
+        for (i = 0; i < output.length; i += 1) {
+            output[i] = 0
+        }
+        var length8 = input.length * 8
+        for (i = 0; i < length8; i += 8) {
+            output[i >> 5] |= (input.charCodeAt(i / 8) & 0xff) << i % 32
+        }
+        return output
+    }
+
+    /**
+     * Calculate the MD5 of a raw string
+     *
+     * @param {string} s Input string
+     * @returns {string} Raw MD5 string
+     */
+    function rstrMD5(s) {
+        return binl2rstr(binlMD5(rstr2binl(s), s.length * 8))
+    }
+
+    /**
+     * Calculates the HMAC-MD5 of a key and some data (raw strings)
+     *
+     * @param {string} key HMAC key
+     * @param {string} data Raw input string
+     * @returns {string} Raw MD5 string
+     */
+    function rstrHMACMD5(key, data) {
+        var i
+        var bkey = rstr2binl(key)
+        var ipad = []
+        var opad = []
+        var hash
+        ipad[15] = opad[15] = undefined
+        if (bkey.length > 16) {
+            bkey = binlMD5(bkey, key.length * 8)
+        }
+        for (i = 0; i < 16; i += 1) {
+            ipad[i] = bkey[i] ^ 0x36363636
+            opad[i] = bkey[i] ^ 0x5c5c5c5c
+        }
+        hash = binlMD5(ipad.concat(rstr2binl(data)), 512 + data.length * 8)
+        return binl2rstr(binlMD5(opad.concat(hash), 512 + 128))
+    }
+
+    /**
+     * Convert a raw string to a hex string
+     *
+     * @param {string} input Raw input string
+     * @returns {string} Hex encoded string
+     */
+    function rstr2hex(input) {
+        var hexTab = '0123456789abcdef'
+        var output = ''
+        var x
+        var i
+        for (i = 0; i < input.length; i += 1) {
+            x = input.charCodeAt(i)
+            output += hexTab.charAt((x >>> 4) & 0x0f) + hexTab.charAt(x & 0x0f)
+        }
+        return output
+    }
+
+    /**
+     * Encode a string as UTF-8
+     *
+     * @param {string} input Input string
+     * @returns {string} UTF8 string
+     */
+    function str2rstrUTF8(input) {
+        return unescape(encodeURIComponent(input))
+    }
+
+    /**
+     * Encodes input string as raw MD5 string
+     *
+     * @param {string} s Input string
+     * @returns {string} Raw MD5 string
+     */
+    function rawMD5(s) {
+        return rstrMD5(str2rstrUTF8(s))
+    }
+
+    /**
+     * Encodes input string as Hex encoded string
+     *
+     * @param {string} s Input string
+     * @returns {string} Hex encoded string
+     */
+    function hexMD5(s) {
+        return rstr2hex(rawMD5(s))
+    }
+
+    /**
+     * Calculates the raw HMAC-MD5 for the given key and data
+     *
+     * @param {string} k HMAC key
+     * @param {string} d Input string
+     * @returns {string} Raw MD5 string
+     */
+    function rawHMACMD5(k, d) {
+        return rstrHMACMD5(str2rstrUTF8(k), str2rstrUTF8(d))
+    }
+
+    /**
+     * Calculates the Hex encoded HMAC-MD5 for the given key and data
+     *
+     * @param {string} k HMAC key
+     * @param {string} d Input string
+     * @returns {string} Raw MD5 string
+     */
+    function hexHMACMD5(k, d) {
+        return rstr2hex(rawHMACMD5(k, d))
+    }
+
+    /**
+     * Calculates MD5 value for a given string.
+     * If a key is provided, calculates the HMAC-MD5 value.
+     * Returns a Hex encoded string unless the raw argument is given.
+     *
+     * @param {string} string Input string
+     * @param {string} [key] HMAC key
+     * @param {boolean} [raw] Raw output switch
+     * @returns {string} MD5 output
+     */
+    function md5(string, key, raw) {
+        if (!key) {
+            if (!raw) {
+                return hexMD5(string)
+            }
+            return rawMD5(string)
+        }
+        if (!raw) {
+            return hexHMACMD5(key, string)
+        }
+        return rawHMACMD5(key, string)
+    }
+
+    if (typeof define === 'function' && define.amd) {
+        define(function () {
+            return md5
+        })
+    } else if (typeof module === 'object' && module.exports) {
+        module.exports = md5
+    } else {
+        $.md5 = md5
+    }
+})(this)

js/md5.min.js

@@ -0,0 +1,2 @@
+!function(n){"use strict";function d(n,t){var r=(65535&n)+(65535&t);return(n>>16)+(t>>16)+(r>>16)<<16|65535&r}function f(n,t,r,e,o,u){return d((u=d(d(t,n),d(e,u)))<<o|u>>>32-o,r)}function l(n,t,r,e,o,u,c){return f(t&r|~t&e,n,t,o,u,c)}function g(n,t,r,e,o,u,c){return f(t&e|r&~e,n,t,o,u,c)}function v(n,t,r,e,o,u,c){return f(t^r^e,n,t,o,u,c)}function m(n,t,r,e,o,u,c){return f(r^(t|~e),n,t,o,u,c)}function c(n,t){var r,e,o,u;n[t>>5]|=128<<t%32,n[14+(t+64>>>9<<4)]=t;for(var c=1732584193,f=-271733879,i=-1732584194,a=271733878,h=0;h<n.length;h+=16)c=l(r=c,e=f,o=i,u=a,n[h],7,-680876936),a=l(a,c,f,i,n[h+1],12,-389564586),i=l(i,a,c,f,n[h+2],17,606105819),f=l(f,i,a,c,n[h+3],22,-1044525330),c=l(c,f,i,a,n[h+4],7,-176418897),a=l(a,c,f,i,n[h+5],12,1200080426),i=l(i,a,c,f,n[h+6],17,-1473231341),f=l(f,i,a,c,n[h+7],22,-45705983),c=l(c,f,i,a,n[h+8],7,1770035416),a=l(a,c,f,i,n[h+9],12,-1958414417),i=l(i,a,c,f,n[h+10],17,-42063),f=l(f,i,a,c,n[h+11],22,-1990404162),c=l(c,f,i,a,n[h+12],7,1804603682),a=l(a,c,f,i,n[h+13],12,-40341101),i=l(i,a,c,f,n[h+14],17,-1502002290),c=g(c,f=l(f,i,a,c,n[h+15],22,1236535329),i,a,n[h+1],5,-165796510),a=g(a,c,f,i,n[h+6],9,-1069501632),i=g(i,a,c,f,n[h+11],14,643717713),f=g(f,i,a,c,n[h],20,-373897302),c=g(c,f,i,a,n[h+5],5,-701558691),a=g(a,c,f,i,n[h+10],9,38016083),i=g(i,a,c,f,n[h+15],14,-660478335),f=g(f,i,a,c,n[h+4],20,-405537848),c=g(c,f,i,a,n[h+9],5,568446438),a=g(a,c,f,i,n[h+14],9,-1019803690),i=g(i,a,c,f,n[h+3],14,-187363961),f=g(f,i,a,c,n[h+8],20,1163531501),c=g(c,f,i,a,n[h+13],5,-1444681467),a=g(a,c,f,i,n[h+2],9,-51403784),i=g(i,a,c,f,n[h+7],14,1735328473),c=v(c,f=g(f,i,a,c,n[h+12],20,-1926607734),i,a,n[h+5],4,-378558),a=v(a,c,f,i,n[h+8],11,-2022574463),i=v(i,a,c,f,n[h+11],16,1839030562),f=v(f,i,a,c,n[h+14],23,-35309556),c=v(c,f,i,a,n[h+1],4,-1530992060),a=v(a,c,f,i,n[h+4],11,1272893353),i=v(i,a,c,f,n[h+7],16,-155497632),f=v(f,i,a,c,n[h+10],23,-1094730640),c=v(c,f,i,a,n[h+13],4,681279174),a=v(a,c,f,i,n[h],11,-358537222),i=v(i,a,c,f,n[h+3],16,-722521979),f=v(f,i,a,c,n[h+6],23,76029189),c=v(c,f,i,a,n[h+9],4,-640364487),a=v(a,c,f,i,n[h+12],11,-421815835),i=v(i,a,c,f,n[h+15],16,530742520),c=m(c,f=v(f,i,a,c,n[h+2],23,-995338651),i,a,n[h],6,-198630844),a=m(a,c,f,i,n[h+7],10,1126891415),i=m(i,a,c,f,n[h+14],15,-1416354905),f=m(f,i,a,c,n[h+5],21,-57434055),c=m(c,f,i,a,n[h+12],6,1700485571),a=m(a,c,f,i,n[h+3],10,-1894986606),i=m(i,a,c,f,n[h+10],15,-1051523),f=m(f,i,a,c,n[h+1],21,-2054922799),c=m(c,f,i,a,n[h+8],6,1873313359),a=m(a,c,f,i,n[h+15],10,-30611744),i=m(i,a,c,f,n[h+6],15,-1560198380),f=m(f,i,a,c,n[h+13],21,1309151649),c=m(c,f,i,a,n[h+4],6,-145523070),a=m(a,c,f,i,n[h+11],10,-1120210379),i=m(i,a,c,f,n[h+2],15,718787259),f=m(f,i,a,c,n[h+9],21,-343485551),c=d(c,r),f=d(f,e),i=d(i,o),a=d(a,u);return[c,f,i,a]}function i(n){for(var t="",r=32*n.length,e=0;e<r;e+=8)t+=String.fromCharCode(n[e>>5]>>>e%32&255);return t}function a(n){var t=[];for(t[(n.length>>2)-1]=void 0,e=0;e<t.length;e+=1)t[e]=0;for(var r=8*n.length,e=0;e<r;e+=8)t[e>>5]|=(255&n.charCodeAt(e/8))<<e%32;return t}function e(n){for(var t,r="0123456789abcdef",e="",o=0;o<n.length;o+=1)t=n.charCodeAt(o),e+=r.charAt(t>>>4&15)+r.charAt(15&t);return e}function r(n){return unescape(encodeURIComponent(n))}function o(n){return i(c(a(n=r(n)),8*n.length))}function u(n,t){return function(n,t){var r,e=a(n),o=[],u=[];for(o[15]=u[15]=void 0,16<e.length&&(e=c(e,8*n.length)),r=0;r<16;r+=1)o[r]=909522486^e[r],u[r]=1549556828^e[r];return t=c(o.concat(a(t)),512+8*t.length),i(c(u.concat(t),640))}(r(n),r(t))}function t(n,t,r){return t?r?u(t,n):e(u(t,n)):r?o(n):e(o(n))}"function"==typeof define&&define.amd?define(function(){return t}):"object"==typeof module&&module.exports?module.exports=t:n.md5=t}(this);
+//# sourceMappingURL=md5.min.jsmd5.map

main.py

@@ -1,15 +1,16 @@
-from utils.entity.RouMan import comicEntity
+from utils.entity.JMTI import comicEntity
 from utils.comic.ComicInfo import comicInfo
 import os,shutil
 
 def comics():
-    for x in range(0,30):
-            comicEntity.downladsComcis("https://rm01.xyz/books?&page="+str(x))
+    for x in range(1,2):
+            comicEntity.downladsComcis("https://jmcomic.moe/albums/hanman?page="+str(x))
     
 if __name__ == '__main__':
-#    os.environ["http_proxy"] = "http://127.0.0.1:7890"
-#    os.environ["https_proxy"] = "http://127.0.0.1:7890"
+#     os.environ["http_proxy"] = "http://127.0.0.1:7890"
+#     os.environ["https_proxy"] = "http://127.0.0.1:7890"
 #    url = "https://rm01.xyz/books/3700b70b-c5a9-4328-9ae3-cffda6a77339/15"
 #    comicEntity.comicChapter(url,scramble=True)
 #    comicEntity.oneComic("https://rm01.xyz/books/c94f80c1-a673-4c74-bb5e-ad5ac7dd766b")
-    comics()
+#     comicEntity.oneComic("https://jmcomic2.onl/album/403327/")
+    comicEntity.downladsComcis("https://jmcomic2.onl/albums/hanman?shunt=2")

myran.py

@@ -0,0 +1,32 @@
+import random
+
+
+class Myran:
+
+    # 随机取出头文件
+    def agents(self):
+        browser_typelist = ['Windows NT 10.0; Win64; x64', 'Windows NT 10.0', 'Windows NT 6.3; Win64; x64',
+                            'Windows NT 6.3', 'Windows NT 6.2; Win64; x64', 'Windows NT 6.2',
+                            'Windows NT 6.1; Win64; x64', 'Windows NT 6.1']
+        os_versionlist = ['106.0.5249.36', '85.0.4183.34', '56.0.2924.26', '85.0.4183.84', '65.0.3325.65',
+                          '84.0.4147.136', '76.0.3809.102', '93.0.4577.69', '91.0.4472.66', '105.0.5195.112',
+                          '103.0.5060.132', '104.0.5112.110', '91.0.4472.81', '69.0.3497.35', '106.0.5239.0',
+                          '91.0.4456.0', '70.0.3532.8', '91.0.4472.167', '77.0.3865.105', '106.0.5249.12',
+                          '93.0.4577.10', '86.0.4240.199', '98.0.4758.107', '75.0.3770.102', '92.0.4515.162',
+                          '105.0.5195.24', '56.0.2924.110', '58.0.3029.89', '98.0.4758.79', '93.0.4577.95',
+                          '90.0.4430.51', '90.0.4430.218', '84.0.4147.21', '86.0.4240.15', '58.0.3029.140',
+                          '92.0.4515.157', '69.0.3497.120', '91.0.4472.10', '89.0.4389.116', '72.0.3626.49',
+                          '65.0.3325.167', '85.0.4183.134', '65.0.3325.209', '75.0.3770.144', '69.0.3497.95',
+                          '56.0.2924.87', '72.0.3626.97', '103.0.5060.53', '93.0.4577.36', '103.0.5060.15',
+                          '107.0.5283.0', '77.0.3865.35', '105.0.5195.134', '76.0.3809.136', '72.0.3626.122',
+                          '90.0.4430.73', '86.0.4240.77', '104.0.5112.83', '77.0.3865.120', '77.0.3865.93',
+                          '107.0.5304.10', '84.0.4147.94', '75.0.3770.19', '106.0.5249.49', '98.0.4758.0',
+                          '98.0.4758.14', '76.0.3809.38', '105.0.5195.42', '58.0.3029.31']
+        browser_type = random.choice(browser_typelist)
+        os_version = random.choice(os_versionlist)
+        ugt = "Mozilla/5.0 (%s) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/%s Safari/537.36" % (
+        browser_type, os_version)
+        return ugt
+
+
+myran = Myran()

utils/CBZUtils.py

@@ -60,6 +60,7 @@ class CBZUtils:
             size_imgs = len(comicInfo.getChapterImgs())
             if size_zip -1 == size_imgs:
                 ntfy.sendMsg(f"打包校验成功： {packCBZ_path}")
+                comicInfo.nextCBZToDoneChapter()
                 return True
             else:
                 ntfy.sendMsg(f"打包检验不完整：{packCBZ_path}")
@@ -68,7 +69,6 @@ class CBZUtils:
         except:
             print("")
             #ntfy.sendMsg("CBZ打包失败")
-        comicInfo.nextCBZToDoneChapter()
                     
     @classmethod           
     def zip_info(cls,zip_path=None):

utils/HtmlUtils.py

@@ -5,18 +5,29 @@ import traceback
 import time
 from urllib3.util.retry import Retry
 from requests.adapters import HTTPAdapter
+from myran import Myran
 from utils.Ntfy import ntfy
 import re
 from utils.comic.PathStr import pathStr
 
 class htmlUtils:
-    headers = {'User-Agent': UserAgent().random}
+
+    myran = Myran()
+    headers = {
+    #'cookie':'ipcountry=US; AVS=4eb0s4o5ho9hfmp704ge7jtium; ipm5=bb7f6ac39cebfa37e89bd07544c549fd; cover=1; guide=1; __atuvc=12|39,31|40,5|41,0|42,4|43; __atuvs=635cabf67eff0d49003; yuo1={"objName":"hT3l8Pyn15Uf","request_id":0,"zones":[{"idzone":"2967008","here":{}},{"idzone":"2967010","here":{}},{"idzone":"2967010","here":{}},{"idzone":"3597795","sub":"70","here":{}}]}',
+    #'referer': 'https://18comic.org/',
+    "User_Agent": myran.agents()
+}
+#    headers = {'User-Agent': UserAgent().random}
     url_data = {}
     
     @classmethod
     def getPathSaveHtml(cls,url,type=None):
         rstr = r"[\/\\\:\*\?\"\<\>\|\.]"  #  '/ \ : * ? " < > |'
-        file_url = re.sub(rstr, "", url)
+        try:
+            file_url = re.sub(rstr, "", url)
+        except:
+            file_url = "error_cache"
         file_path = os.path.join(pathStr.base_html_cache,file_url)
         if type == "new":
             return file_path
@@ -64,7 +75,7 @@ class htmlUtils:
             if count <= 3:
                 try:
                     print(f"请求地址：{curl}")
-                    res = s.get(curl,stream=True, headers=cls.headers, timeout=180)
+                    res = s.get(curl,stream=True, headers=cls.headers, timeout=1000)
                     if type == "bytes":
                         url_text = res
                     if type == "json":
@@ -74,6 +85,8 @@ class htmlUtils:
                     if type == None:
                         url_text = html.fromstring(res.text)
                         cls.saveHtml(curl,res.text)
+#                    if res.status_code != 200:
+#                        cls.remove_HtmlCache(curl)
                 except:
                     print(f'Retry! 第{count}次')
                     time.sleep(1)

utils/NetUtils.py

@@ -20,6 +20,7 @@ class netUtils:
                 return msg
            else:
                print("文件已损坏，已重试："+path)
+       path = os.path.join(os.path.dirname(path),str(os.path.basename(path)).split("?")[0])
        tmp_file = path+".downloads"
        if os.path.exists(tmp_file):
            os.remove(tmp_file)
@@ -81,6 +82,7 @@ class netUtils:
             return None
         save_name = "cover"
         icon_su = "."+str(icon_url).split(".")[-1]
+        icon_su = icon_su.split("?")[0]
         #判断漫画名路径是否已存在comicname/cover.jpg, 存在跳过
         pathComicIcon = os.path.join(comicInfo.getDirConfComic(),save_name+icon_su)
         if not os.path.exists(pathComicIcon):

utils/VerUtils.py

@@ -1,3 +1,4 @@
+from utils.HtmlUtils import htmlUtils
 from utils.Ntfy import ntfy
 from utils.CBZUtils import CBZUtils
 from utils.comic.ComicInfo import comicInfo
@@ -31,4 +32,29 @@ class  verUtils:
                 return False
         else:
             ntfy.sendMsg("info_data 为空")
-            return False
+            return False
+
+    @classmethod
+    def verNextCBZ(cls,list_img):
+                #验证数据是已存在且是否完整
+        cbz_path = comicInfo.getDirCBZComicChapter()+".CBZ"
+        is_next = False
+        if os.path.exists(cbz_path):
+            try:
+                cbz_size = len(CBZUtils.zip_info(cbz_path)) - 1
+            except:
+                cbz_size = 0
+            if len(list_img) == cbz_size:
+                ntfy.sendMsg(f"{comicInfo.getComicName()} {comicInfo.getChapter()} 数据完整，已跳过")
+                is_next = True
+            else:
+                ntfy.sendMsg(f"{comicInfo.getComicName()} {comicInfo.getChapter()} 数据不完整，尝试删除配置CBZ文件后重试")
+                try:
+                    if cbz_size < len(list_img) or os.path.getsize(cbz_path) < 300000:
+                        ntfy.sendMsg(f"删除 {cbz_path}")
+                        os.remove(cbz_path)
+                    else:
+                        is_next = True
+                except:
+                    ntfy(f"删除失败 {cbz_path}")
+        return is_next

utils/comic/ComicInfo.py

@@ -17,8 +17,14 @@ class comicInfo():
     cbs = "Publisher"
     lang = "LanguageISO"
     comic_names = "SeriesGroup"
-    tags = "Tag"
-    
+    tags = "Tags"
+    date_year = "Year"
+    date_month = "Month"
+    date_day = "Day"
+    page_count = "PageCount"
+    pages = "Pages"
+    web = "Web"
+
     str_comicName = None
     str_chapter = None
     str_icon = None
@@ -26,7 +32,12 @@ class comicInfo():
     str_listChapter = None
     str_chapter_imgs = None
     str_updateAt = None
-    
+    str_date_year = None
+    str_date_month = None
+    str_date_day = None
+    str_page_count = None
+    str_web = None
+
     chapter_node = None
     comicName_node = None
     dep_node = None
@@ -36,12 +47,18 @@ class comicInfo():
     lang_node = None
     comicNames_node = None
     tags_node = None
-     
+    date_year_node = None
+    date_month_node = None
+    date_day_node = None
+    page_count_node = None
+    pages_node = None
+    web_node = None
+
     @classmethod
     def setNodeAndValue(cls,node,value):
-       if not value == None:
+       if value != None:
             c_node =  cls.document.createElement(node)
-            node_text =  cls.document.createTextNode(value)
+            node_text =  cls.document.createTextNode(str(value).replace("\n",""))
             c_node.appendChild(node_text)
             return c_node
        return None
@@ -86,7 +103,7 @@ class comicInfo():
         
     @classmethod
     def setAuthor(cls,value):
-        cls.author_node =  cls.setNodeAndValue(cls.author,value)
+        cls.author_node =  cls.setNodeAndValue(cls.author,cls.getListToString(value))
         
     @classmethod
     def setLang(cls,value):
@@ -94,16 +111,55 @@ class comicInfo():
         
     @classmethod
     def setTag(cls,value):
-        cls.tag_node =  cls.setNodeAndValue(cls.tag, value)
+        cls.tag_node =  cls.setNodeAndValue(cls.tag, cls.getListToString(value))
         
     @classmethod
     def setTags(cls,value):
-        cls.tags_node = cls.setNodeAndValue(cls.tags,value)
+        cls.tags_node = cls.setNodeAndValue(cls.tags,cls.getListToString(value))
     
     @classmethod
     def setCBS(cls,value):
         cls.cbs_node =  cls.setNodeAndValue(cls.cbs,value)
     
+    @classmethod
+    def setWeb(cls,value):
+        cls.str_web = value
+        cls.web_node = cls.setNodeAndValue(cls.web,value)
+
+    @classmethod
+    def getWeb(cls):
+        return cls.str_web
+
+    @classmethod
+    def setPageCount(cls,value):
+        cls.str_page_count = value
+        cls.page_count_node = cls.setNodeAndValue(cls.page_count,value)
+
+    @classmethod
+    def setPages(cls,value):
+       if value != None:
+            su = "."+str(value[0]).split(".")[-1]
+            join_list=",".join(value).replace(su,"")
+            value = join_list.split(",")
+            cls.setPageCount(str(len(value)))
+            root_node = cls.document.createElement(cls.pages)
+            for page in value:
+                c_node =  cls.document.createElement("Page")
+                c_node.setAttribute("Image",page)
+                root_node.appendChild(c_node)
+            cls.pages_node = root_node
+
+    @classmethod
+    def setDate(cls,value,split):
+        values = str(value).split(split)
+        cls.str_date_year = values[0]
+        cls.str_date_month = values[1]
+        cls.str_date_day = values[2]
+        cls.date_year_node = cls.setNodeAndValue(cls.date_year,values[0])
+        cls.date_month_node = cls.setNodeAndValue(cls.date_month,values[1])
+        cls.date_day_node = cls.setNodeAndValue(cls.date_day,values[2])
+
+
     @classmethod
     def setIcon(cls,value):
         cls.str_icon = value
@@ -124,7 +180,14 @@ class comicInfo():
     @classmethod
     def getUpdateAt(cls):
         return cls.str_updateAt
-    
+
+    @classmethod
+    def getListToString(cls,to_list):
+        value = to_list
+        if isinstance(to_list,list):
+            value = ",".join(to_list)
+        return value
+
         '''
     获取网站主页
     '''
@@ -207,39 +270,40 @@ class comicInfo():
         return cls.pathComicInfo
        
     @classmethod
-    def writeComicInfoXML(cls,chapter):
+    def writeComicInfoXML(cls,chapter,path=None):
         if cls.chapter == cls.fixFileName(chapter):
             print(f"cls.chapter {cls.chapter} 与 chapter {chapter} 不相等，已自动跳过")
                 
         root = cls.Root()
         newDocument = Document()
         newDocument.appendChild(root)
-        if not cls.chapter_node == None:
-            root.appendChild(cls.chapter_node)
-        if not cls.comicName_node == None:
-            root.appendChild(cls.comicName_node)
-        if not cls.dep_node == None:
-            root.appendChild(cls.dep_node)
-        if not cls.author_node == None:
-            root.appendChild(cls.author_node)
-        if not cls.tag_node == None:
-            root.appendChild(cls.tag_node)
-        if not cls.cbs_node == None:
-            root.appendChild(cls.cbs_node)
-        if not cls.lang_node == None:
-            root.appendChild(cls.lang_node)
-        if not cls.comicNames_node == None:
-            root.appendChild(cls.comicNames_node)         
-        if not cls.tags_node == None:
-            root.appendChild(cls.tags_node)
+        if cls.chapter_node != None: root.appendChild(cls.chapter_node)
+        if cls.comicName_node != None: root.appendChild(cls.comicName_node)
+        if cls.dep_node != None: root.appendChild(cls.dep_node)
+        if cls.author_node != None: root.appendChild(cls.author_node)
+        if cls.tag_node != None: root.appendChild(cls.tag_node)
+        if cls.cbs_node != None: root.appendChild(cls.cbs_node)
+        if cls.lang_node != None: root.appendChild(cls.lang_node)
+        if cls.comicNames_node != None: root.appendChild(cls.comicNames_node)         
+        if cls.tags_node != None: root.appendChild(cls.tags_node)
+        if cls.date_year_node != None: root.appendChild(cls.date_year_node)
+        if cls.date_month_node != None: root.appendChild(cls.date_month_node)
+        if cls.date_day_node != None: root.appendChild(cls.date_day_node)
+        if cls.page_count_node != None: root.appendChild(cls.page_count_node)
+        if cls.pages_node != None: root.appendChild(cls.pages_node)
         cls.getPathComicInfoXML()
+        if path != None:
+            cls.pathComicInfo = os.path.join(path,"ComicInfo.xml")
         base_dir  = os.path.dirname(cls.pathComicInfo)
         if not os.path.exists(base_dir):
             os.makedirs(base_dir)
+        if os.path.exists(cls.pathComicInfo):
+            print("ComicInfo.xml 已存在")
+            return None
         with open(cls.pathComicInfo , "w", encoding="utf-8") as fo:
             newDocument.writexml(fo, indent='', addindent='\t', newl='\n', encoding="utf-8")
             fo.close()
-            #print("ComicInfo.xml 已生成 pathd=", cls.pathComicInfo)
+            print("ComicInfo.xml 已生成 pathd=", cls.pathComicInfo)
             
         #文件保存
     @classmethod

utils/comic/PathStr.py

@@ -2,7 +2,7 @@ import os,datetime
 from time import strftime
 class pathStr:
     #base_comic_out = "COMICOUT"
-    base_comic_out = os.path.join("/mnt", "bigTComics")
+    base_comic_out = os.path.join("/mnt", "bigTComics","JM")
     base_CBZ = os.path.join(base_comic_out,"CBZ")
     base_comic_img = os.path.join(base_comic_out,"outputComic")
     base_conf_path = os.path.join(base_comic_out,".conf")

utils/downloader.py

@@ -33,13 +33,16 @@ def download_image(image_url, dst_dir, file_name, timeout=20, proxy_type=None, p
 
     response = None
     file_path = os.path.join(dst_dir, file_name)
+    if os.path.exists(file_path):
+        print("文件已存在，已跳过=",file_path)
+        return None
     temp_path = os.path.join(dst_dir, file_name+".downloads")
     repair_count = 1
     try:
         response = requests.get(
             image_url, headers=headers, timeout=timeout, proxies=proxies)
         while response.status_code != 200 and repair_count <= 5:
-            time.sleep(3)
+            time.sleep(0.7)
             download_image(image_url,dst_dir,file_name)
             ntfy.sendMsg(f'重试：第{repair_count}次 {image_url}')
             repair_count += 1
@@ -83,4 +86,4 @@ def download_images(image_urls, dst_dir, file_prefix="img", concurrency=50, time
             future_list.append(executor.submit(
                 download_image, image_url, dst_dir, file_name, timeout, proxy_type, proxy))
             count += 1
-        concurrent.futures.wait(future_list, timeout=360)
+        concurrent.futures.wait(future_list, timeout)

utils/entity/JMTI.py

@@ -0,0 +1,277 @@
+import hashlib
+import json,os,time,random,shutil
+import re,math
+
+import execjs
+from utils.NetUtils import netUtils
+from utils.HtmlUtils import htmlUtils
+from utils.ImageUtils import imageUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.CBZUtils import CBZUtils
+from utils.downloader import download_images
+from utils.Ntfy import ntfy
+from utils.VerUtils import verUtils
+from PIL import Image
+
+class comicEntity:
+    count_chapter = 0
+    aid = None
+    repeat = 0
+
+
+    @classmethod
+    def downladsComcis(cls,url):
+            #漫画名
+        comic_href_list = htmlUtils.xpathData("//div[@class='thumb-overlay-albums']/a/@href",url,update=True)
+        comics_name = htmlUtils.xpathData("//span[@class='video-title title-truncate m-t-5']/text()")
+        len_books = len(comic_href_list)
+        base_url = comicInfo.getBaseUrl(url)
+        for x in range(0, len_books):
+            book_name = comics_name[x]
+            comicInfo.setComicName(book_name)
+            comic_href = base_url+comic_href_list[x]            
+            random_int = random.randint(5,20)
+            dir_conf_comic = comicInfo.getDirConfComic()
+            if not os.path.exists(dir_conf_comic):
+                ntfy.sendMsg(f"{random_int}秒后开始下载 漫画：{book_name}")
+                time.sleep(random_int)
+            else:
+                ntfy.sendMsg(f"已存在 漫画：{book_name}")
+            cls.oneComic(comic_href, random.uniform(0,10))
+            
+        #print(books)
+        #for comicHref in comicsHref:
+        #    cls.oneComic(comicHref,random.uniform(10,20))
+     
+    @classmethod
+    def oneComic(cls,c_url,sleep=None):
+        nums = htmlUtils.xpathData("//div[@class='row']/div[6]/div[1]/div[1]/ul[contains(@class,'btn-toolbar')]/a",url=c_url,update=True)
+        book_name = htmlUtils.xpathData("//div[@itemprop='name']/h1[@id='book-name']/text()")
+        book_name = re.sub(r'[\\\/\|\(\)\~\?\.\:\：\-\*\<\>]', '', book_name)
+        tags = htmlUtils.xpathData("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='tag-block']/span[@data-type='tags']/a[@class='btn btn-sm btn-primary']/text()")
+        author = htmlUtils.xpathData("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='tag-block']/span[@data-type='author']/a[@class='btn btn-sm btn-primary']/text()")
+        book_msg = htmlUtils.xpathData("//div[@class='row']/div[@class='col-lg-7']/div[1]/div[@class='p-t-5 p-b-5']/text()")
+        jmid = book_msg[0]
+        dep = str(book_msg[1]).replace("叙述：","")
+        icon = htmlUtils.xpathData("//div[@class='row']//div[@class='thumb-overlay']/img/@src",num=0)
+
+        comicInfo.setIcon(icon)
+        comicInfo.setHomePage(c_url)
+        comicInfo.setComicName(book_name)
+        comicInfo.setAuthor(author)
+        comicInfo.setDep(dep)
+        comicInfo.setTags(tags)
+        comicInfo.setTag(tags)
+        comicInfo.setCBS("韩漫")
+        comicInfo.setLang("zh")
+        albumid = re.search(r'/album/(\d+)', c_url).group(1)
+        referer = re.search(r'(https://\w+\.\w+)/', c_url).group(1)
+
+        if nums:
+            list_chapter_name = []
+            list_chapter_href = []
+            cls.count_chapter = 0
+
+            for i in nums:
+                photo_name_list = i.xpath("li/text()")[0].split()
+                photo_date = i.xpath("li/span/text()")[0].split()
+                #print(re.findall(r'[\u4E00-\u9FA5]+.*?', i.xpath("li/text()")[0]))
+                try:
+                    if re.findall(r'[\u4E00-\u9FA5]', photo_name_list[2]):
+                        photo_name=re.sub(r'\s','',photo_name_list[0])+' '+photo_name_list[2]
+                    else:photo_name=re.sub(r'\s','',photo_name_list[0])
+                except Exception as e:
+                    photo_name = re.sub(r'\s', '', photo_name_list[0])
+                photo_name = re.sub(r'[\\\/\|\(\)\~\?\.\:\：\-\*\<\>\-]', '',photo_name)
+                #print(photo_name)
+                photoid=i.attrib['data-album']
+                cls.aid = photoid
+                comicInfo.setChapterName(photo_name)
+                comicInfo.setDate(photo_date[0],split='-')
+                comicInfo.setWeb(referer+i.attrib['href'])
+                is_scramble = False
+                if int(photoid) > 220980:
+                    is_scramble = True
+                if not comicInfo.nextExistsGetPath("done_"):
+                    comicEntity.comicChapter(referer+i.attrib['href'],scramble=is_scramble,sleep=random.randint(5,15))
+                #存在就校验CBZ包是否完整
+                if comicInfo.nextExistsGetPath("done_"):
+                    verUtils.verCBZ()
+                cls.count_chapter += 1
+                #一本漫画下载后等待
+        #清空文件夹
+        path_dir_comic = comicInfo.getDirComic()
+        if os.path.exists(path_dir_comic):
+            shutil.rmtree(path_dir_comic)
+        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
+        if comicInfo.nextExistsGetPath("down_"):
+        #章节图片全部下载后，调用下载封面
+            netUtils.downloadComicIcon()
+         #下个阶段
+        if comicInfo.nextExistsGetPath("cbz_"):
+            time.sleep(0.1)
+            #下载后自动打包
+            is_next = CBZUtils.packAutoComicChapterCBZ()
+        #完成删除原文件
+            remove_path = comicInfo.getDirComicChapter()
+            shutil.rmtree(remove_path)
+            print(f"文件已删除: {remove_path}")
+#        except:
+#            ntfy.sendMsg(f"{comicInfo.getComicName()} 下载出错了")
+#            is_next = False
+        #ntfy.sendMsg(f"预计总章节大小：{cls.count_chapter + 1}  / "+ str(comicInfo.getLenChapters()))
+        if sleep != None and is_next == True:
+            ntfy.sendMsg(f"{sleep} 秒后开始下载下一个章节")
+            time.sleep(sleep)
+
+    
+    @classmethod
+    def Onechapter(cls,chapter_url,scramble=None):
+        if not str(chapter_url).startswith("http"):
+            chapter_url = comicInfo.getBaseUrl() + chapter_url
+        try:
+            is_next = cls.comicChapterDownload(chapter_url,scramble)
+        except:
+            htmlUtils.remove_HtmlCache(chapter_url)
+            cls.repeat = 0
+            is_next = cls.comicChapterDownload(chapter_url,scramble)
+        comicInfo.nextInfoToImgChapter()
+        #下载完成后, 开始解密图片
+        if scramble:
+            #获取章节图片路径
+            chapter_dir = comicInfo.getDirComicChapter()
+            dirs = os.listdir(chapter_dir)
+            for img in dirs:
+                is_scramble = str(img).startswith("scramble=")
+                if is_scramble:
+                    c_path = os.path.join(chapter_dir, img)
+                    #imageUtils.getScrambleImage(c_path)
+                    cls.encode_scramble_image(c_path)
+        #进入下一阶段
+        comicInfo.nextImgToDownloadChapter()
+        return is_next
+    
+    @classmethod
+    def comicChapterDownload(cls,chapter_url,c_scramble):
+        img_list =htmlUtils.xpathData("//div[@class='panel-body']/div/div[contains(@class,'center')]/img/@data-original",url=chapter_url,update=True)
+        pages_imgs =htmlUtils.xpathData("//div[@class='center scramble-page']/@id",url=chapter_url)
+        comicInfo.setPages(pages_imgs)
+        comicInfo.writeComicInfoXML(comicInfo.str_chapter)
+        #print("img_list:",len(img_list))
+        list_img = []
+        list_file_name = []
+        for i in img_list:
+            img_url= i
+            img_name = os.path.basename(img_url).split('.')[0]
+            if c_scramble:
+                img_name = "scramble="+str(cls.get_scramble_num(cls.aid,img_name))+"_"+img_name
+            #path_img = "%s\\%s.jpg" % (cls.aid, img_name)
+            path_img = "%s.jpg" % (img_name)
+            list_img.append(img_url)
+            list_file_name.append(path_img)
+        comicInfo.setChapterImgs(list_img)
+                #保存图像
+        comicInfo.nextSaveInfoChapter(comicInfo.str_chapter, list_img)
+        is_next = verUtils.verNextCBZ(list_img) 
+        list_shunt = ["?shunt=2","?shunt=1","?shunt=3",""]
+        while not is_next:
+            time.sleep(1)
+            download_images(list_img,comicInfo.getDirComicChapter(), filesName=list_file_name,timeout=1500)
+            file_imgs = os.listdir(comicInfo.getDirComicChapter())
+            count_jpg = ",".join(file_imgs).split(".jpg")
+            is_next = len(count_jpg)-1 == len(list_img)
+            cls.repeat += 1
+            if cls.repeat > 3:
+                url = list_shunt[cls.repeat % len(list_shunt)]
+                print("分流中=",url)
+                cls.comicChapterDownload(str(chapter_url).split("?")[0]+url,c_scramble)
+        return True
+         
+    @classmethod
+    def get_md5(cls,num):
+        result1 = hashlib.md5(num.encode()).hexdigest()
+        print('get_md5-', result1)
+        return result1
+        
+    @classmethod
+    def get_scramble_num(cls,e, t):
+        #print(type(e),e, type(t),t)
+        a = 10
+        try:
+            num_dict = {}
+            for i in range(10):
+                num_dict[i] = i * 2 + 2
+            if (int(e) >= 268850):
+                n = str(e) + t;
+                # switch(n=(n = (n = md5(n)).substr(-1)), n %= 10) {
+                #print("n=",n)
+                tmp = ord(cls.get_md5(n)[-1])
+                result = num_dict[tmp % 10]
+                a = result
+            return a
+        except Exception as e:
+            print(e.__traceback__.tb_lineno,e)
+            return False
+
+    @classmethod
+    def encode_scramble_image(cls,imgpath):
+        image = Image.open(imgpath)
+        w, h = image.size
+        #image.show()
+        file_str = str(imgpath).split("=")
+        #10_29.jpg
+        base_dir = file_str[0].replace("scramble","")
+        base_name = file_str[-1]
+        base_fn = base_name.split("_") 
+        save_name = base_fn[1]
+        save_name_delesu = save_name.split(".")[0]
+        blocks = int(base_fn[0])
+        img_type = os.path.basename(imgpath).split('.')[-1]
+        save_path = os.path.join(os.path.dirname(imgpath),save_name_delesu+"."+img_type)
+        # print(type(aid),type(img_name))
+        if blocks:
+            s = blocks  # 随机值
+            # print(s)
+            l = h % s  # 切割最后多余的值
+            box_list = []
+            hz = 0
+            for i in range(s):
+                c = math.floor(h / s)
+                g = i * c
+                hz += c
+                h2 = h - c * (i + 1) - l
+                if i == 0:
+                    c += l;hz += l
+                else:
+                    g += l
+                box_list.append((0, h2, w, h - g))
+
+            # print(box_list,len(box_list))
+            item_width = w
+            # box_list.reverse() #还原切图可以倒序列表
+            # print(box_list, len(box_list))
+            newh = 0
+            image_list = [image.crop(box) for box in box_list]
+            # print(box_list)
+            newimage = Image.new("RGB", (w, h))
+            for image in image_list:
+                # image.show()
+                b_w, b_h = image.size
+                newimage.paste(image, (0, newh))
+
+                newh += b_h
+            newimage.save(save_path)
+            if os.path.exists(imgpath):
+                os.remove(imgpath)

utils/entity/RouMan.py

@@ -101,7 +101,7 @@ class comicEntity:
             shutil.rmtree(path_dir_comic)
         if sleep != None:
             time.sleep(sleep)
-            
+             
     '''
     
     读取某章节下所有图片