update

entity/BaoZi.py

@@ -0,0 +1,53 @@
+import json
+from utils.HtmlUtils import htmlUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.downloader import download_images
+from utils.base.BaseComicEntity import baseComic
+
+class comicEntity:
+    @classmethod
+    def baseComicData(cls,url,update=False):
+        data = htmlUtils.xpathData('//script[@id="__NEXT_DATA__"]/text()',url=url,update=update)
+        data = json.loads(data[0])
+        data = data.get("props")
+        x = data.get("pageProps")
+        return x
+        
+    @classmethod
+    def downladsComcis(cls,url):
+            #漫画名
+        x = cls.baseComicData(url)
+        books = x.get("books")
+        len_books = len(books)
+        base_url = comicInfo.getBaseUrl(url)
+        for x in range(0, len_books):
+            book = books[x]
+            book_id = book.get("id")
+            book_name = book.get("name")
+            updated = book.get("updatedAt")
+            comic_href = base_url+"/books/"+book_id            
+            href = baseComic.downladsComcis(book_name=book_name,comic_href=comic_href,updated=updated)
+            cls.oneComic(href)
+            comicInfo.updateComicDate()
+
+    @classmethod
+    def oneComic(cls,c_url,sleep=None):
+        #漫画名
+        title = htmlUtils.xpathData('//div[@class="gb-inside-container"]/h1[contains(@class,"gb-headline-text")]/text()',url=c_url,update=True,num=0)
+        #别名
+        #alias = htmlUtils.xpathData('//span[contains(@class,"bookid_alias")]/text()',num=1)
+        #icon = htmlUtils.xpathData('//div[contains(@class,"gb-container")]/div[@class="gb-inside-container"]/img[contains(@class,"dynamic-featured-image")]/@src')
+        icon = htmlUtils.xpathData('//noscript/img[contains(@class,"dynamic-featured-image")]/@src',num=0)
+        author = htmlUtils.xpathData('//div[@class="gb-inside-container"]/div[@class="author-content"]/a/text()', num=0)
+        tags = htmlUtils.xpathData('//div[@class="gb-inside-container"]/div[@class="genres-content"]/a/text()')
+        dep = htmlUtils.xpathData('//div[@class="gb-inside-container"]/div/p/text()')
+        dep = "".join(dep)
+        #update_date = htmlUtils.xpathData('//div[@class="chapter-content-listing"]//a[@class="wp-manga-chapterlist"]//span[@class="chapter-release-date"]/i/text()')
+        chapters_url = htmlUtils.xpathData('//div[@class="chapter-content-listing"]//a[@class="c-chapter-readmore"]/@href',url=c_url,num=0)
+        chapters = htmlUtils.xpathData('//div[@class="chapter-content-listing"]//a[@class="wp-manga-chapterlist"]/text()',not_eq=' ',url=chapters_url)
+        chapter_href = htmlUtils.xpathData('//div[@class="chapter-content-listing"]//a[@class="wp-manga-chapterlist"]/@href',url=chapters_url)
+        #chapter_href = htmlUtils.xpathData('//div[@class="chapter-content-listing"]//a[@class="wp-manga-chapter"]/@href',url=c_url,next_xpath='//div[@class="chapter-content-listing"]//a[@class="c-chapter-readmore"]/@href')
+        
+        baseComic.oneComic(url=c_url,title=title,author=author,
+            icon=icon,tags=tags,dep=dep,chapters=chapters,chapter_href=chapter_href,
+            alias=None)

entity/JM.py

@@ -0,0 +1,74 @@
+import json
+import re
+from utils.HtmlUtils import htmlUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.downloader import download_images
+from utils.base.BaseComicEntity import baseComic
+
+class comicEntity:
+    @classmethod
+    def baseComicData(cls,url,update=False):
+        data = htmlUtils.xpathData('//script[@id="__NEXT_DATA__"]/text()',url=url,update=update)
+        data = json.loads(data[0])
+        data = data.get("props")
+        x = data.get("pageProps")
+        return x
+        
+    @classmethod
+    def downladsComcis(cls,url):
+            #漫画名
+        x = cls.baseComicData(url)
+        books = x.get("books")
+        len_books = len(books)
+        base_url = comicInfo.getBaseUrl(url)
+        for x in range(0, len_books):
+            book = books[x]
+            book_id = book.get("id")
+            book_name = book.get("name")
+            updated = book.get("updatedAt")
+            comic_href = base_url+"/books/"+book_id            
+            href = baseComic.downladsComcis(book_name=book_name,comic_href=comic_href,updated=updated)
+            cls.oneComic(href)
+            comicInfo.updateComicDate()
+
+    @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()",num=0)
+        title = 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)
+
+        referer = re.search(r'(https://\w+\.\w+)/', c_url).group(1)
+        if nums:
+            list_chapter_name = []
+            list_chapter_href = []
+            list_chapter_update = []
+            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.setValue1(cls.aid)
+                list_chapter_name.append(photo_name)
+                list_chapter_href.append(referer+i.attrib['href'])
+                list_chapter_update.append(photo_date[0])
+ 
+            baseComic.oneComic(url=c_url,title=title,author=author,
+                icon=icon,tags=tags,dep=dep,chapters=list_chapter_name,chapter_href=list_chapter_href,
+                alias=None)

entity/RouMan.py

@@ -0,0 +1,54 @@
+import json
+from utils.HtmlUtils import htmlUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.downloader import download_images
+from utils.base.BaseComicEntity import baseComic
+
+class comicEntity:
+    @classmethod
+    def baseComicData(cls,url,update=False):
+        data = htmlUtils.xpathData('//script[@id="__NEXT_DATA__"]/text()',url=url,update=update)
+        data = json.loads(data[0])
+        data = data.get("props")
+        x = data.get("pageProps")
+        return x
+        
+    @classmethod
+    def downladsComcis(cls,url):
+            #漫画名
+        x = cls.baseComicData(url,True)
+        books = x.get("books")
+        len_books = len(books)
+        base_url = comicInfo.getBaseUrl(url)
+        for x in range(0, len_books):
+            book = books[x]
+            book_id = book.get("id")
+            book_name = book.get("name")
+            updated = book.get("updatedAt")
+            comic_href = base_url+"/books/"+book_id
+            comicInfo.setUpdateAt(updated)
+            comicInfo.setComicName(book_name)
+            href = baseComic.downladsComcis(book_name=book_name,comic_href=comic_href,updated=updated)
+            if href != None:
+                cls.oneComic(href)
+                comicInfo.updateComicDate()
+
+    @classmethod
+    def oneComic(cls,c_url,sleep=None):
+            #漫画名
+        title = htmlUtils.xpathData('//div[@class="col"]/h5/text()',url=c_url,num=0,update=True)
+        #别名
+        alias = htmlUtils.xpathData('//span[contains(@class,"bookid_alias")]/text()',num=1)
+        icon = htmlUtils.xpathData('//img[@class="img-thumbnail"]/@src',num=0)
+        
+        author = htmlUtils.xpathData('//div[contains(@class,"bookid_bookInfo")]/p[1]/text()',num=1)
+        tags = htmlUtils.xpathData('//div[contains(@class,"bookid_bookInfo")]/p[3]/b/text()',num=0)
+        action = htmlUtils.xpathData('//div[contains(@class,"bookid_bookInfo")]/p[2]/text()',num=1)
+        dep = htmlUtils.xpathData('//div[contains(@class,"bookid_bookInfo")]/p[4]/text()',num=1)
+        update_date = htmlUtils.xpathData('//div[contains(@class,"bookid_bookInfo")]/p[5]/small/text()',num=1)
+        chapters = htmlUtils.xpathData('//div[contains(@class,"bookid_chapterBox")]//div[contains(@class,"bookid_chapter")]/a/text()')
+        chapter_href = htmlUtils.xpathData('//div[contains(@class,"bookid_chapterBox")]//div[contains(@class,"bookid_chapter")]/a/@href')
+        
+        baseComic.oneComic(url=c_url,title=title,author=author,
+            icon=icon,tags=tags,dep=dep,chapters=chapters,chapter_href=chapter_href,
+            alias=alias)

entity/down/BaoZi.py

@@ -0,0 +1,26 @@
+import hashlib
+import json
+import os
+from utils.HtmlUtils import htmlUtils
+from utils.FileUtils import imageUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.Ntfy import ntfy
+
+class comicCommon:
+    @classmethod
+    def comicChapterDownload(cls,chapter_url):
+        imgs_url =htmlUtils.xpathData("//div[@class='gb-inside-container']/img/@data-src",url=chapter_url,update=True)
+#        pages_imgs =htmlUtils.xpathData("//div[@class='center scramble-page']/@id",url=chapter_url)
+        #print("img_list:",len(img_list))
+        list_img = []
+        list_file_name = []
+        count = 1
+        for i in imgs_url:
+            img_su = str(i).split('.')[-1]
+            count_image = "{:0>3d}".format(count)
+            list_file_name.append(count_image+"."+img_su)
+            list_img.append(count_image)
+            count += 1
+        comicInfo.setPages(list_img)
+        comicInfo.writeComicInfoXML(comicInfo.str_chapter)
+        comicInfo.comicChapterDownload(imgs_url,list_file_name)

entity/down/JM.py

@@ -0,0 +1,108 @@
+import hashlib
+import json
+import os
+from utils.HtmlUtils import htmlUtils
+from utils.FileUtils import imageUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.Ntfy import ntfy
+
+class comicCommon:
+    @classmethod
+    def comicChapterDownload(cls,chapter_url):
+        chapter_url = chapter_url+"?shunt=2"
+        img_list =htmlUtils.xpathData("//div[@class='panel-body']/div/div[contains(@class,'center scramble-page')]/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]
+            aid = int(comicInfo.getValue1())
+            if aid > 220980:
+            #if is_scramble:
+                img_name = "scramble="+str(cls.get_scramble_num(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.comicChapterDownload(list_img,list_file_name)
+
+    @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)

entity/down/RouMan.py

@@ -0,0 +1,63 @@
+import json
+from utils.HtmlUtils import htmlUtils
+from utils.FileUtils import imageUtils
+from utils.comic.ComicInfo import comicInfo
+from utils.Ntfy import ntfy
+
+class comicCommon:
+    @classmethod
+    def baseComicData(cls,url,update=False):
+        data = htmlUtils.xpathData('//script[@id="__NEXT_DATA__"]/text()',url=url,update=update)
+        data = json.loads(data[0])
+        data = data.get("props")
+        x = data.get("pageProps")
+        return x
+
+    @classmethod
+    def comicChapterDownload(cls,chapter_url):
+        x = cls.baseComicData(chapter_url,update=True)
+        book_name = x.get("bookName")
+        chapter_name = x.get("chapterName")
+        #fileUtils.saveConfComicChapterInfo(chapterName,x,bookName)
+        #if comicInfo.nextExistsGetPath("info_"):
+        #    print(f"{bookName} {chapterName} info文件已存在跳过")
+        alias = x.get("alias")
+        description = x.get("description")
+        images = x.get("images")
+        chapter_api_path = x.get("chapterAPIPath")
+        comicInfo.setComicName(book_name)
+        comicInfo.setChapterName(chapter_name)
+        comicInfo.setDep(description)
+        
+        if chapter_api_path != None:
+            chapter_api_path = str(chapter_api_path).encode('utf-8').decode('unicode_escape')
+            base_url = comicInfo.getBaseUrl(chapter_url)
+            chapter_api_url = base_url+chapter_api_path
+            ntfy.sendMsg(f"chapterApiUrl= {chapter_api_url}",alert=False)
+            data = htmlUtils.getJSON(chapter_api_url,update=True)
+            if data != None:
+                data = data.get("chapter")
+                chapter_name = data.get("name")
+                images  = data.get("images")
+        if images == None:
+            ntfy.sendMsg(f"未获取到章节图像 comic_name={book_name} chapter={chapter_name}")
+
+        count = 1
+        list_img = []
+        list_file_name = []
+        for image in images:
+            image_src = image.get("src")
+            scramble = image.get("scramble")
+            count_image = "{:0>3d}".format(count)
+            list_img.append(image_src)
+            image_src_prefix = "."+str(image_src).split(".")[-1]
+            if scramble:
+                su = "."+str(image_src).split(".")[-1]
+                de_str = str(image_src).split("/")[-1].replace(su,"==")
+                blocks = imageUtils.encodeImage(de_str)
+                count_image = "scramble="+str(blocks)+"_"+count_image
+            list_file_name.append(count_image+image_src_prefix)
+            count+=1
+        #print("count_all_img=", count)
+        #netUtils.downloadComicChapterImages(list_img,scrambles=list_scramble)
+        comicInfo.comicChapterDownload(list_img,list_file_name)