update

Editer.py

@@ -0,0 +1,394 @@
+#!/usr/bin/python
+# -*- coding:utf-8 -*-
+
+import requests  # 用来抓取网页的html源码
+from bs4 import BeautifulSoup  # 用于代替正则式 取源码中相应标签中的内容
+import time  # 时间相关操作
+import os
+from rich.progress import track as tqdm
+from utils import *
+import zipfile
+import shutil
+import re
+import pickle
+from PIL import Image
+import time
+import threading
+from concurrent.futures import ThreadPoolExecutor, wait
+import pickle
+from selenium import webdriver
+from selenium.webdriver.edge.options import Options
+
+lock = threading.RLock()
+
+class Editer(object):
+    def __init__(self, root_path, head='https://www.linovelib.com', book_no='0000', volume_no=1):
+
+        self.header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47', 'referer': head, 'cookie':'night=1'}
+
+        self.url_head = head
+        options = Options()
+        options.add_argument('--start-minimized')
+
+        self.driver = webdriver.Edge(options = options)
+        self.main_page = f'{self.url_head}/novel/{book_no}.html'
+        self.cata_page = f'{self.url_head}/novel/{book_no}/catalog'
+        self.read_tool_page = f'{self.url_head}/themes/zhmb/js/readtool.js'
+        self.color_chap_name = '插图'
+        self.color_page_name = '彩页'
+        self.html_buffer = dict()
+        
+        main_html = self.get_html(self.main_page)
+        bf = BeautifulSoup(main_html, 'html.parser')
+        self.title = bf.find('meta', {"property": "og:novel:book_name"})['content']
+        self.author = bf.find('meta', {"property": "og:novel:author"})['content']
+        try:
+            self.cover_url = re.search(r'src=\"(.*?)\"', str(bf.find('div', {"class": "book-img fl"}))).group(1)
+        except:
+            self.cover_url = 'cid'
+            
+        self.img_url_map = dict()
+        self.volume_no = volume_no
+
+        self.epub_path = root_path
+        self.temp_path = os.path.join(self.epub_path,  'temp_'+ check_chars(self.title) + '_' + str(self.volume_no))
+    
+        self.missing_last_chap_list = []
+        self.is_color_page = True
+        self.page_url_map = dict()
+        self.ignore_urls = []
+        self.url_buffer = []
+        self.max_thread_num = 8
+        self.pool = ThreadPoolExecutor(self.max_thread_num)
+        
+    # 获取html文档内容
+    def get_html(self, url, is_gbk=False):
+        while True:
+            time.sleep(0.5)
+            self.driver.get(url)
+            req = self.driver.page_source
+            while '<title>Access denied | www.linovelib.com used Cloudflare to restrict access</title>' in req:
+                time.sleep(5)
+                self.driver.get(url)
+                req = self.driver.page_source
+            if is_gbk:
+                req.encoding = 'GBK'       #这里是网页的编码转换，根据网页的实际需要进行修改，经测试这个编码没有问题
+            break
+        return req
+    
+    def get_html_img(self, url):
+        time.sleep(0.5)
+        req=requests.get(url, headers=self.header)
+        num_retry = 0
+        while 'Forbidden' in str(req.content[0:100]) and num_retry<10:
+            req=requests.get(url, headers=self.header)
+            time.sleep(0.5)
+            num_retry += 1
+        if 'Forbidden' in str(req.content[0:100]):
+            print('插图下载失败，链接：' + url) 
+        return req.content
+        
+    def make_folder(self):
+        os.makedirs(self.temp_path, exist_ok=True)
+
+        self.text_path = os.path.join(self.temp_path, 'OEBPS/Text')
+        os.makedirs(self.text_path, exist_ok=True)
+
+        self.img_path = os.path.join(self.temp_path,  'OEBPS/Images')
+        os.makedirs(self.img_path, exist_ok=True)
+    
+    def get_index_url(self):
+        self.volume = {}
+        self.volume['chap_urls'] = []
+        self.volume['chap_names'] = []
+        chap_html_list = self.get_chap_list(is_print=False)
+        if len(chap_html_list)<self.volume_no:
+            print('输入卷号超过实际卷数！')
+            return False
+        volume_array = self.volume_no - 1
+        chap_html = chap_html_list[volume_array]
+
+        self.volume['book_name'] = chap_html.find('h2', {'class': 'v-line'}).text
+        chap_list = chap_html.find_all('li', {'class', 'col-4'})
+        for chap_html in chap_list:
+            self.volume['chap_names'].append(chap_html.text)
+            self.volume['chap_urls'].append(self.url_head + chap_html.find('a').get('href'))
+        return True
+        
+    def get_chap_list(self, is_print=True):
+        cata_html = self.get_html(self.cata_page, is_gbk=False)
+        bf = BeautifulSoup(cata_html, 'html.parser')
+        chap_html_list = bf.find_all('div', {'class', 'volume clearfix'})
+        if is_print:
+            for chap_no, chap_html in enumerate(chap_html_list):
+                print(f'[{chap_no+1}]', chap_html.find('h2', {'class': 'v-line'}).text)
+            return
+        else:
+            return chap_html_list
+
+
+    def get_page_text(self, content_html):
+        bf = BeautifulSoup(content_html, 'html.parser')
+        text_with_head = bf.find('div', {'id': 'TextContent', 'class': 'read-content'}) 
+        text_html = str(text_with_head)
+        img_urlre_list = re.findall(r"<img .*?>", text_html)
+        for img_urlre in img_urlre_list:
+            img_url_full = re.search(r'.[a-zA-Z]{3}/(.*?).(jpg|png|jpeg)', img_urlre)
+            img_url_name = img_url_full.group(1)
+            img_url_tail = img_url_full.group(0).split('.')[-1]
+            img_url = f'https://img3.readpai.com/{img_url_name}.{img_url_tail}'
+
+            text_html = text_html.replace('<br/>\n' + img_urlre +'\n<br/>', img_urlre)
+            if not img_url in self.img_url_map:
+                self.img_url_map[img_url] = str(len(self.img_url_map)).zfill(2)
+            img_symbol = f'<p>[img:{self.img_url_map[img_url]}]</p>'
+            if '00' in img_symbol:
+                text_html = text_html.replace(img_urlre, '')  #默认第一张为封面图片 不写入彩页
+            else:
+                text_html = text_html.replace(img_urlre, img_symbol)
+                symbol_index = text_html.index(img_symbol)
+                if text_html[symbol_index-1] != '\n':
+                    text_html = text_html[:symbol_index] + '\n' + text_html[symbol_index:]
+        text = BeautifulSoup(text_html, 'html.parser').get_text()
+        return text
+    
+    def get_chap_text(self, url, chap_name, return_next_chapter=False):
+        text_chap = ''
+        page_no = 1 
+        url_ori = url
+        next_chap_url = None
+        while True:
+            if page_no == 1:
+                str_out = chap_name
+            else:
+                str_out = f'    正在下载第{page_no}页......'
+            print(str_out)
+            content_html = self.get_html(url, is_gbk=False)
+            text = self.get_page_text(content_html)
+            text_chap += text
+            url_new = url_ori.replace('.html', '_{}.html'.format(page_no+1))[len(self.url_head):]
+            if url_new in content_html:
+                page_no += 1
+                url = self.url_head + url_new
+            else:
+                if return_next_chapter:
+                    next_chap_url = self.url_head + re.search(r'书签</a><a href="(.*?)">下一章</a>', content_html).group(1)
+                break
+        return text_chap, next_chap_url
+    
+    def get_text(self):
+        self.make_folder()   
+        img_strs = []   #记录后文中出现的所有图片位置
+        text_no=0   #text_no正文章节编号(排除插图)   chap_no 是所有章节编号
+        for chap_no, (chap_name, chap_url) in enumerate(zip(self.volume['chap_names'], self.volume['chap_urls'])):
+            is_fix_next_chap_url = (chap_name in self.missing_last_chap_list)
+            text, next_chap_url = self.get_chap_text(chap_url, chap_name, return_next_chapter=is_fix_next_chap_url)
+            if is_fix_next_chap_url: 
+                self.volume['chap_urls'][chap_no+1] = next_chap_url #正向修复
+            if chap_name == self.color_chap_name:
+                text_html_color = text2htmls(self.color_page_name, text)
+            else:
+                text_html = text2htmls(chap_name, text)
+                textfile = self.text_path + f'/{str(text_no).zfill(2)}.xhtml'
+                with open(textfile, 'w+', encoding='utf-8') as f:
+                    f.writelines(text_html)
+                for text_line in text_html:
+                    img_str = re.search(r"<img(.*?)\/>", text_line)
+                    if img_str is not None:
+                        img_strs.append(img_str.group(0))
+                text_no += 1
+            
+        # 将彩页中后文已经出现的图片删除，避免重复
+        if self.is_color_page: #判断彩页是否存在
+            text_html_color_new = []
+            textfile = self.text_path + '/color.xhtml'
+            for text_line in text_html_color: 
+                is_save = True
+                for img_str in img_strs:
+                    if img_str in text_line:
+                        is_save = False
+                        break
+                if is_save:
+                   text_html_color_new.append(text_line) 
+        
+            with open(textfile, 'w+', encoding='utf-8') as f:
+                f.writelines(text_html_color_new)
+        
+
+    def get_image(self, is_gui=False, signal=None):
+        if is_gui:
+            len_iter = len(self.img_url_map.items())
+            signal.emit('start')
+            for i, (img_url, img_name) in enumerate(self.img_url_map.items()):
+                content = self.get_html_img(img_url)
+                with open(self.img_path+f'/{img_name}.jpg', 'wb') as f:
+                    f.write(content) #写入二进制内容 
+                signal.emit(int(100*(i+1)/len_iter))
+            signal.emit('end')
+        else:
+            for img_url, img_name in tqdm(self.img_url_map.items()):
+                content = self.get_html_img(img_url)
+                with open(self.img_path+f'/{img_name}.jpg', 'wb') as f:
+                    f.write(content) #写入二进制内容
+
+    def get_cover(self, is_gui=False, signal=None):
+        textfile = os.path.join(self.text_path, 'cover.xhtml')
+        img_w, img_h = 300, 300
+        try:
+            imgfile = os.path.join(self.img_path, '00.jpg')
+            img = Image.open(imgfile)
+            img_w, img_h = img.size
+            signal_msg = (imgfile, img_h, img_w)
+            if is_gui:
+                signal.emit(signal_msg)
+        except Exception as e:
+            print(e)
+            print('没有封面图片，请自行用第三方EPUB编辑器手动添加封面')
+        img_htmls = get_cover_html(img_w, img_h)
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(img_htmls)
+
+    def check_volume(self, is_gui=False, signal=None, editline=None):
+        chap_names = self.volume['chap_names']
+        chap_num = len(self.volume['chap_names'])
+        for chap_no, url in enumerate(self.volume['chap_urls']):
+            if self.check_url(url):
+                if not self.prev_fix_url(chap_no, chap_num): #先尝试反向递归修复
+                    if chap_no == 0:    #第一个章节都反向修复失败 说明后面章节全部缺失，只能手动输入第一个章节，保证第一个章节一定有效
+                        self.volume['chap_urls'][0] = self.hand_in_url(chap_names[chap_no], is_gui, signal, editline)
+                    else:   #其余章节反向修复失败 默认使用正向修复 
+                        self.missing_last_chap_list.append(chap_names[chap_no-1])
+        
+         #没有检测到插图页，手动输入插图页标题
+        if self.color_chap_name not in self.volume['chap_names']:
+            self.color_chap_name = self.hand_in_color_page_name(is_gui, signal, editline)
+        self.volume['color_chap_name'] = self.color_chap_name
+
+        #没有彩页 但主页封面存在，将主页封面设为书籍封面 
+        if self.color_chap_name=='' and (not self.check_url(self.cover_url)):  
+            self.is_color_page = False
+            self.img_url_map[self.cover_url] = str(len(self.img_url_map)).zfill(2)
+            print('**************')
+            print('提示：没有彩页，但主页封面存在，将使用主页的封面图片作为本卷图书封面')
+            print('**************')
+    
+    def check_url(self, url):#当检测有问题返回True
+        return ('javascript' in url or 'cid' in url)   
+    
+    def get_prev_url(self, chap_no): #获取前一个章节的链接
+        content_html = self.get_html(self.volume['chap_urls'][chap_no], is_gbk=False)
+        next_url = self.url_head + re.search(r'<div class="mlfy_page"><a href="(.*?)">上一章</a>', content_html).group(1)
+        return next_url
+    
+    def prev_fix_url(self, chap_no, chap_num):  #反向递归修复缺失链接（后修复前），若成功修复返回True，否则返回False 
+        if chap_no==chap_num-1: #最后一个章节直接选择不修复 返回False
+            return False
+        elif self.check_url(self.volume['chap_urls'][chap_no+1]):
+            if self.prev_fix_url(chap_no+1, chap_num):
+                self.volume['chap_urls'][chap_no] = self.get_prev_url(chap_no+1)
+                return True
+            else:
+                return False
+        else:
+            self.volume['chap_urls'][chap_no] = self.get_prev_url(chap_no+1)
+            return True
+        
+    def hand_in_msg(self, error_msg='', is_gui=False, signal=None, editline=None):
+        if is_gui:
+            print(error_msg)
+            signal.emit('hang')
+            time.sleep(1)
+            while not editline.isHidden():
+                time.sleep(1)
+            content = editline.text()
+            editline.clear()
+        else:
+            content = input(error_msg)
+        return content
+            
+    def hand_in_url(self, chap_name, is_gui=False, signal=None, editline=None):
+        error_msg = f'章节\"{chap_name}\"连接失效，请手动输入该章节链接(手机版“{self.url_head}”开头的链接):'
+        return self.hand_in_msg(error_msg, is_gui, signal, editline)
+    
+    def hand_in_color_page_name(self, is_gui=False, signal=None, editline=None):
+        if is_gui:
+            error_msg = f'插图页面不存在，需要下拉选择插图页标题，若不需要插图页则保持本栏为空直接点确定：'
+            editline.addItems(self.volume['chap_names'])
+            editline.setCurrentIndex(-1)
+        else:
+            error_msg = f'插图页面不存在，需要手动输入插图页标题，若不需要插图页则不输入直接回车：'
+        return self.hand_in_msg(error_msg, is_gui, signal, editline) 
+    
+    def get_toc(self):
+        if self.is_color_page:
+            ind = self.volume["chap_names"].index(self.color_chap_name)
+            self.volume["chap_names"].pop(ind)
+        toc_htmls = get_toc_html(self.title, self.volume["chap_names"])
+        textfile = self.temp_path + '/OEBPS/toc.ncx'
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(toc_htmls)
+
+    def get_content(self):
+        num_chap = len(self.volume["chap_names"])
+        num_img = len(os.listdir(self.img_path))
+        content_htmls = get_content_html(self.title + '-' + self.volume['book_name'], self.author, num_chap, num_img, self.is_color_page)
+        textfile = self.temp_path + '/OEBPS/content.opf'
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(content_htmls)
+
+    def get_epub_head(self):
+        mimetype = 'application/epub+zip'
+        mimetypefile = self.temp_path + '/mimetype'
+        with open(mimetypefile, 'w+', encoding='utf-8') as f:
+            f.write(mimetype)
+        metainf_folder = os.path.join(self.temp_path, 'META-INF')
+        os.makedirs(metainf_folder, exist_ok=True)
+        container = metainf_folder + '/container.xml'
+        container_htmls = get_container_html()
+        with open(container, 'w+', encoding='utf-8') as f:
+            f.writelines(container_htmls)
+
+    def get_epub(self):
+        os.remove(os.path.join(self.temp_path, 'buffer.pkl'))
+        epub_file = self.epub_path + '/' + check_chars(self.title + '-' + self.volume['book_name']) + '.epub'
+        with zipfile.ZipFile(epub_file, "w", zipfile.ZIP_DEFLATED) as zf:
+            for dirpath, _, filenames in os.walk(self.temp_path):
+                fpath = dirpath.replace(self.temp_path,'') #这一句很重要，不replace的话，就从根目录开始复制
+                fpath = fpath and fpath + os.sep or ''
+                for filename in filenames:
+                    zf.write(os.path.join(dirpath, filename), fpath+filename)
+        shutil.rmtree(self.temp_path)
+        return epub_file
+    
+    # # 恢复函数，根据secret_map进行恢复
+    # def restore_chars(self, text):
+    #     restored_text = ""
+    #     i = 0
+    #     while i < len(text):
+    #         char = text[i]
+    #         if char in self.secret_map:
+    #                 restored_text += self.secret_map[char]
+    #         else:
+    #                 restored_text += char
+    #         i += 1
+    #     return restored_text
+    
+    def buffer(self):
+        filename = 'buffer.pkl'
+        filepath = os.path.join(self.temp_path, filename)
+        if os.path.isfile(filepath):
+            with open(filepath, 'rb') as f:
+                self.volume, self.img_url_map = pickle.load(f)
+                self.text_path = os.path.join(self.temp_path, 'OEBPS/Text')
+                os.makedirs(self.text_path, exist_ok=True)
+                self.img_path = os.path.join(self.temp_path,  'OEBPS/Images')
+                os.makedirs(self.img_path, exist_ok=True)
+                self.color_chap_name = self.volume['color_chap_name']
+        else:
+            with open(filepath, 'wb') as f:
+                pickle.dump((self.volume ,self.img_url_map), f)
+    
+    def is_buffer(self):
+        filename = 'buffer.pkl'
+        filepath = os.path.join(self.temp_path, filename)
+        return os.path.isfile(filepath)

Editer2.py

@@ -0,0 +1,449 @@
+#!/usr/bin/python
+# -*- coding:utf-8 -*-
+
+import requests  # 用来抓取网页的html源码
+from bs4 import BeautifulSoup  # 用于代替正则式 取源码中相应标签中的内容
+import time  # 时间相关操作
+import os
+from rich.progress import track as tqdm
+from utils import *
+import zipfile
+import shutil
+import re
+import pickle
+from PIL import Image
+import time
+import threading
+from concurrent.futures import ThreadPoolExecutor, wait
+import pickle
+# from selenium import webdriver
+# from selenium.webdriver.edge.options import Option
+
+lock = threading.RLock()
+
+class Editer(object):
+    def __init__(self, root_path, book_no='0000', volume_no=1):
+
+
+        self.url_head = 'https://www.linovelib.com'
+        self.url_head_mobile = 'https://www.bilinovel.com'
+        
+        self.header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47', 'referer': self.url_head, 'Accept-Language': 'zh-CN,zh;q=0.9',}
+        self.header_mobile = {'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1', 'referer': self.url_head_mobile, 'Accept-Language': 'zh-CN,zh;q=0.9', 'cookie':'night=1'}
+
+        
+        # options = Options()
+        # self.driver = webdriver.Edge(options = options)
+        self.main_page = f'{self.url_head}/novel/{book_no}.html'
+        self.cata_page = f'{self.url_head}/novel/{book_no}/catalog'
+        self.read_tool_page = f'{self.url_head}/themes/zhmb/js/readtool.js'
+        self.color_chap_name = '插图'
+        self.color_page_name = '彩页'
+        self.html_buffer = dict()
+        self.get_secret_map()
+        
+        main_html = self.get_html(self.main_page)
+        bf = BeautifulSoup(main_html, 'html.parser')
+        self.title = bf.find('meta', {"property": "og:novel:book_name"})['content']
+        self.author = bf.find('meta', {"property": "og:novel:author"})['content']
+        try:
+            self.cover_url = re.search(r'src=\"(.*?)\"', str(bf.find('div', {"class": "book-img fl"}))).group(1)
+        except:
+            self.cover_url = 'cid'
+            
+        self.img_url_map = dict()
+        self.volume_no = volume_no
+
+        self.epub_path = root_path
+        self.temp_path = (os.path.join(self.epub_path,  'temp_'+ check_chars(self.title) + '_' + str(self.volume_no)))
+    
+        self.missing_last_chap_list = []
+        self.is_color_page = True
+        self.page_url_map = dict()
+        self.ignore_urls = []
+        self.url_buffer = []
+        self.max_thread_num = 8
+        self.pool = ThreadPoolExecutor(self.max_thread_num)
+        
+        
+    # 获取html文档内容
+    def get_html(self, url, is_gbk=False, use_mobile=False):
+        if use_mobile:
+            header = self.header_mobile
+        else:
+            header = self.header
+        while True:
+            time.sleep(0.5)
+            # self.driver.get(url)
+            # req = self.driver.page_source
+            req = requests.get(url, headers=header)
+            while 'used Cloudflare to restrict access</title>' in req.text:
+                time.sleep(5)
+                # self.driver.get(url)
+                # req = self.driver.page_source
+                req = requests.get(url, headers=header)
+            if is_gbk:
+                req.encoding = 'GBK'       #这里是网页的编码转换，根据网页的实际需要进行修改，经测试这个编码没有问题
+            break
+        return req.text
+    
+    def get_html_content(self, url, is_buffer=False, use_mobile=False):
+        if use_mobile:
+            header = self.header_mobile
+        else:
+            header = self.header
+        if is_buffer:
+            while not url in self.html_buffer.keys():
+                time.sleep(0.1) 
+        if url in self.html_buffer.keys():
+            return self.html_buffer[url]
+        while True:
+            try:
+                req=requests.get(url, headers=header)
+                break
+            except Exception as e:
+                pass
+        lock.acquire()
+        self.html_buffer[url] = req.content
+        lock.release()
+        return req.content
+    
+    def get_secret_map(self):
+        with open('secret_map.cfg', 'rb') as f:
+            self.secret_map = pickle.load(f)
+
+
+    def get_secret_map(self):
+        url = 'https://gitee.com/bosswangs/bili-novel-map/releases/tag/secret_map'
+        html = self.get_html(url, is_gbk=True)
+        # print(html)
+        url_download = 'https://gitee.com' + re.search(r'{\"download_url\":\"(.*?).cfg', html).group(1)+'.cfg'
+        version = re.search(r'_v(.*?).cfg', url_download).group(1)
+        path = 'secret_map.cfg'
+        if os.path.exists(path):
+            with open(path, 'rb') as f:
+                map = pickle.load(f)
+                version_exist = map[1]
+                if version == version_exist:
+                    self.secret_map = map[0]
+                    return
+
+        content = self.get_html_content(url_download)
+        if content is not None:
+            with open(path, 'wb') as f:
+                f.write(content) #写入二进制内容
+            with open(path, 'rb') as f:
+                map = pickle.load(f)
+                self.secret_map = map[0]
+        return
+        
+    def make_folder(self):
+        os.makedirs(self.temp_path, exist_ok=True)
+
+        self.text_path = os.path.join(self.temp_path, 'OEBPS/Text')
+        os.makedirs(self.text_path, exist_ok=True)
+
+        self.img_path = os.path.join(self.temp_path,  'OEBPS/Images')
+        os.makedirs(self.img_path, exist_ok=True)
+    
+    def get_index_url(self):
+        self.volume = {}
+        self.volume['chap_urls'] = []
+        self.volume['chap_names'] = []
+        chap_html_list = self.get_chap_list(is_print=False)
+        if len(chap_html_list)<self.volume_no:
+            print('输入卷号超过实际卷数！')
+            return False
+        volume_array = self.volume_no - 1
+        chap_html = chap_html_list[volume_array]
+
+        self.volume['book_name'] = chap_html.find('h2', {'class': 'v-line'}).text
+        chap_list = chap_html.find_all('li', {'class', 'col-4'})
+        for chap_html in chap_list:
+            self.volume['chap_names'].append(chap_html.text)
+            self.volume['chap_urls'].append(self.url_head_mobile + chap_html.find('a').get('href'))
+        return True
+        
+    def get_chap_list(self, is_print=True):
+        cata_html = self.get_html(self.cata_page, is_gbk=False)
+        bf = BeautifulSoup(cata_html, 'html.parser')
+        chap_html_list = bf.find_all('div', {'class', 'volume clearfix'})
+        if is_print:
+            for chap_no, chap_html in enumerate(chap_html_list):
+                print(f'[{chap_no+1}]', chap_html.find('h2', {'class': 'v-line'}).text)
+            return
+        else:
+            return chap_html_list
+
+
+    def get_page_text(self, content_html):
+        bf = BeautifulSoup(content_html, 'html.parser')
+        # text_with_head = bf.find('div', {'id': 'TextContent', 'class': 'read-content'}) 
+        text_with_head = bf.find('div', {'id': 'acontentz', 'class': 'bcontent'})
+        text_html = str(text_with_head)
+        img_urlre_list = re.findall(r"<img .*?>", text_html)
+        for img_urlre in img_urlre_list:
+            img_url_full = re.search(r'.[a-zA-Z]{3}/(.*?).(jpg|png|jpeg)', img_urlre)
+            img_url_name = img_url_full.group(1)
+            img_url_tail = img_url_full.group(0).split('.')[-1]
+            img_url = f'https://img3.readpai.com/{img_url_name}.{img_url_tail}'
+
+            text_html = text_html.replace('<br/>\n' + img_urlre +'\n<br/>', img_urlre)
+            if not img_url in self.img_url_map:
+                self.img_url_map[img_url] = str(len(self.img_url_map)).zfill(2)
+            img_symbol = f'<p>[img:{self.img_url_map[img_url]}]</p>'
+            if '00' in img_symbol:
+                text_html = text_html.replace(img_urlre, '')  #默认第一张为封面图片 不写入彩页
+            else:
+                text_html = text_html.replace(img_urlre, img_symbol)
+                symbol_index = text_html.index(img_symbol)
+                if text_html[symbol_index-1] != '\n':
+                    text_html = text_html[:symbol_index] + '\n' + text_html[symbol_index:]
+        text = BeautifulSoup(text_html, 'html.parser').get_text()
+        text = self.restore_chars(text)
+        return text
+    
+    def get_chap_text(self, url, chap_name, return_next_chapter=False):
+        text_chap = ''
+        page_no = 1 
+        url_ori = url
+        next_chap_url = None
+        while True:
+            if page_no == 1:
+                str_out = chap_name
+            else:
+                str_out = f'    正在下载第{page_no}页......'
+            print(str_out)
+            content_html = self.get_html(url, is_gbk=False, use_mobile=True)
+            text = self.get_page_text(content_html)
+            text_chap += text
+            url_new = url_ori.replace('.html', '_{}.html'.format(page_no+1))[len(self.url_head):]
+            if url_new in content_html:
+                page_no += 1
+                url = self.url_head_mobile + url_new
+            else:
+                if return_next_chapter:
+                    # next_chap_url = self.url_head_mobile + re.search(r'书签</a><a href="(.*?)">下一章</a>', content_html).group(1)
+                    bf = BeautifulSoup(content_html, 'html.parser')
+                    next_chap_url = bf.find('link', {'rel': 'prerender'}).get('href')
+                break
+        return text_chap, next_chap_url
+    
+    def get_text(self):
+        self.make_folder()   
+        img_strs = []   #记录后文中出现的所有图片位置
+        text_no=0   #text_no正文章节编号(排除插图)   chap_no 是所有章节编号
+        for chap_no, (chap_name, chap_url) in enumerate(zip(self.volume['chap_names'], self.volume['chap_urls'])):
+            is_fix_next_chap_url = (chap_name in self.missing_last_chap_list)
+            text, next_chap_url = self.get_chap_text(chap_url, chap_name, return_next_chapter=is_fix_next_chap_url)
+            if is_fix_next_chap_url: 
+                self.volume['chap_urls'][chap_no+1] = next_chap_url #正向修复
+            if chap_name == self.color_chap_name:
+                text_html_color = text2htmls(self.color_page_name, text)
+            else:
+                text_html = text2htmls(chap_name, text)
+                textfile = self.text_path + f'/{str(text_no).zfill(2)}.xhtml'
+                with open(textfile, 'w+', encoding='utf-8') as f:
+                    f.writelines(text_html)
+                for text_line in text_html:
+                    img_str = re.search(r"<img(.*?)\/>", text_line)
+                    if img_str is not None:
+                        img_strs.append(img_str.group(0))
+                text_no += 1
+            
+        # 将彩页中后文已经出现的图片删除，避免重复
+        if self.is_color_page: #判断彩页是否存在
+            text_html_color_new = []
+            textfile = self.text_path + '/color.xhtml'
+            for text_line in text_html_color: 
+                is_save = True
+                for img_str in img_strs:
+                    if img_str in text_line:
+                        is_save = False
+                        break
+                if is_save:
+                   text_html_color_new.append(text_line) 
+        
+            with open(textfile, 'w+', encoding='utf-8') as f:
+                f.writelines(text_html_color_new)
+        
+
+    def get_image(self, is_gui=False, signal=None):
+        for url in self.img_url_map.keys():
+            self.pool.submit(self.get_html_content, url)
+        img_path = self.img_path
+        if is_gui:
+            len_iter = len(self.img_url_map.items())
+            signal.emit('start')
+            for i, (img_url, img_name) in enumerate(self.img_url_map.items()):
+                content = self.get_html_content(img_url, is_buffer=True)
+                with open(img_path+f'/{img_name}.jpg', 'wb') as f:
+                    f.write(content) #写入二进制内容 
+                signal.emit(int(100*(i+1)/len_iter))
+            signal.emit('end')
+        else:
+            for img_url, img_name in tqdm(self.img_url_map.items()):
+                content = self.get_html_content(img_url)
+                with open(img_path+f'/{img_name}.jpg', 'wb') as f:
+                    f.write(content) #写入二进制内容
+
+    def get_cover(self, is_gui=False, signal=None):
+        textfile = os.path.join(self.text_path, 'cover.xhtml')
+        img_w, img_h = 300, 300
+        try:
+            imgfile = os.path.join(self.img_path, '00.jpg')
+            img = Image.open(imgfile)
+            img_w, img_h = img.size
+            signal_msg = (imgfile, img_h, img_w)
+            if is_gui:
+                signal.emit(signal_msg)
+        except Exception as e:
+            print(e)
+            print('没有封面图片，请自行用第三方EPUB编辑器手动添加封面')
+        img_htmls = get_cover_html(img_w, img_h)
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(img_htmls)
+
+    def check_volume(self, is_gui=False, signal=None, editline=None):
+        chap_names = self.volume['chap_names']
+        chap_num = len(self.volume['chap_names'])
+        for chap_no, url in enumerate(self.volume['chap_urls']):
+            if self.check_url(url):
+                if not self.prev_fix_url(chap_no, chap_num): #先尝试反向递归修复
+                    if chap_no == 0:    #第一个章节都反向修复失败 说明后面章节全部缺失，只能手动输入第一个章节，保证第一个章节一定有效
+                        self.volume['chap_urls'][0] = self.hand_in_url(chap_names[chap_no], is_gui, signal, editline)
+                    else:   #其余章节反向修复失败 默认使用正向修复 
+                        self.missing_last_chap_list.append(chap_names[chap_no-1])
+        
+         #没有检测到插图页，手动输入插图页标题
+        if self.color_chap_name not in self.volume['chap_names']:
+            self.color_chap_name = self.hand_in_color_page_name(is_gui, signal, editline)
+
+        #没有彩页 但主页封面存在，将主页封面设为书籍封面 
+        if self.color_chap_name=='' and (not self.check_url(self.cover_url)):  
+            self.is_color_page = False
+            self.img_url_map[self.cover_url] = str(len(self.img_url_map)).zfill(2)
+            print('**************')
+            print('提示：没有彩页，但主页封面存在，将使用主页的封面图片作为本卷图书封面')
+            print('**************')
+    
+    def check_url(self, url):#当检测有问题返回True
+        return ('javascript' in url or 'cid' in url)   
+    
+    def get_prev_url(self, chap_no): #获取前一个章节的链接
+        content_html = self.get_html(self.volume['chap_urls'][chap_no], is_gbk=False)
+        # next_url = self.url_head + re.search(r'<div class="mlfy_page"><a href="(.*?)">上一章</a>', content_html).group(1)
+        next_url = self.url_head_mobile + re.search('var prevpage=\"(.*?)\";var', content_html).group(1)
+        return next_url
+    
+    def prev_fix_url(self, chap_no, chap_num):  #反向递归修复缺失链接（后修复前），若成功修复返回True，否则返回False 
+        if chap_no==chap_num-1: #最后一个章节直接选择不修复 返回False
+            return False
+        elif self.check_url(self.volume['chap_urls'][chap_no+1]):
+            if self.prev_fix_url(chap_no+1, chap_num):
+                self.volume['chap_urls'][chap_no] = self.get_prev_url(chap_no+1)
+                return True
+            else:
+                return False
+        else:
+            self.volume['chap_urls'][chap_no] = self.get_prev_url(chap_no+1)
+            return True
+        
+    def hand_in_msg(self, error_msg='', is_gui=False, signal=None, editline=None):
+        if is_gui:
+            print(error_msg)
+            signal.emit('hang')
+            time.sleep(1)
+            while not editline.isHidden():
+                time.sleep(1)
+            content = editline.text()
+            editline.clear()
+        else:
+            content = input(error_msg)
+        return content
+            
+    def hand_in_url(self, chap_name, is_gui=False, signal=None, editline=None):
+        error_msg = f'章节\"{chap_name}\"连接失效，请手动输入该章节链接(手机版“{self.url_head}”开头的链接):'
+        return self.hand_in_msg(error_msg, is_gui, signal, editline)
+    
+    def hand_in_color_page_name(self, is_gui=False, signal=None, editline=None):
+        if is_gui:
+            error_msg = f'插图页面不存在，需要下拉选择插图页标题，若不需要插图页则保持本栏为空直接点确定：'
+            editline.addItems(self.volume['chap_names'])
+            editline.setCurrentIndex(-1)
+        else:
+            error_msg = f'插图页面不存在，需要手动输入插图页标题，若不需要插图页则不输入直接回车：'
+        return self.hand_in_msg(error_msg, is_gui, signal, editline) 
+    
+    def get_toc(self):
+        if self.is_color_page:
+            ind = self.volume["chap_names"].index(self.color_chap_name)
+            self.volume["chap_names"].pop(ind)
+        toc_htmls = get_toc_html(self.title, self.volume["chap_names"])
+        textfile = self.temp_path + '/OEBPS/toc.ncx'
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(toc_htmls)
+
+    def get_content(self):
+        num_chap = len(self.volume["chap_names"])
+        num_img = len(os.listdir(self.img_path))
+        content_htmls = get_content_html(self.title + '-' + self.volume['book_name'], self.author, num_chap, num_img, self.is_color_page)
+        textfile = self.temp_path + '/OEBPS/content.opf'
+        with open(textfile, 'w+', encoding='utf-8') as f:
+            f.writelines(content_htmls)
+
+    def get_epub_head(self):
+        mimetype = 'application/epub+zip'
+        mimetypefile = self.temp_path + '/mimetype'
+        with open(mimetypefile, 'w+', encoding='utf-8') as f:
+            f.write(mimetype)
+        metainf_folder = os.path.join(self.temp_path, 'META-INF')
+        os.makedirs(metainf_folder, exist_ok=True)
+        container = metainf_folder + '/container.xml'
+        container_htmls = get_container_html()
+        with open(container, 'w+', encoding='utf-8') as f:
+            f.writelines(container_htmls)
+
+    def get_epub(self):
+        os.remove(os.path.join(self.temp_path, 'buffer.pkl'))
+        epub_file = (self.epub_path + '/' + check_chars(self.title) + '-' + check_chars(self.volume['book_name']) + '.epub')
+        with zipfile.ZipFile(epub_file, "w", zipfile.ZIP_DEFLATED) as zf:
+            for dirpath, _, filenames in os.walk(self.temp_path):
+                fpath = dirpath.replace(self.temp_path,'') #这一句很重要，不replace的话，就从根目录开始复制
+                fpath = fpath and fpath + os.sep or ''
+                for filename in filenames:
+                    zf.write(os.path.join(dirpath, filename), fpath+filename)
+        shutil.rmtree(self.temp_path)
+        return epub_file
+    
+    # 恢复函数，根据secret_map进行恢复
+    def restore_chars(self, text):
+        restored_text = ""
+        i = 0
+        while i < len(text):
+            char = text[i]
+            if char in self.secret_map:
+                    restored_text += self.secret_map[char]
+            else:
+                    restored_text += char
+            i += 1
+        return restored_text
+    
+    def buffer(self):
+        filename = 'buffer.pkl'
+        filepath = os.path.join(self.temp_path, filename)
+        if os.path.isfile(filepath):
+            with open(filepath, 'rb') as f:
+                self.volume, self.img_url_map = pickle.load(f)
+                self.text_path = os.path.join(self.temp_path, 'OEBPS/Text')
+                os.makedirs(self.text_path, exist_ok=True)
+                self.img_path = os.path.join(self.temp_path,  'OEBPS/Images')
+                os.makedirs(self.img_path, exist_ok=True)
+        else:
+            with open(filepath, 'wb') as f:
+                pickle.dump((self.volume ,self.img_url_map), f)
+    
+    def is_buffer(self):
+        filename = 'buffer.pkl'
+        filepath = os.path.join(self.temp_path, filename)
+        return os.path.isfile(filepath)

README.md

@@ -0,0 +1,77 @@
+
+<div align="center">
+  <img src="resource/logo_big.png" width="300" style="margin-right: 3000px;"/> 
+</div>
+
+<h1 align="center">
+  &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;EPUB下载器
+</h1>
+
+
+
+
+
+[哔哩轻小说](https://www.linovelib.com)(linovelib)网站小说下载，EPUB打包。
+
+特性:
+
+* Fluent Design风格界面，下载进度与书籍封面显示，主题切换，下载目录自定义。
+* 前后端分离，同时支持命令行版本。
+* EPUB格式打包，支持多种阅读器。
+* 正文黑白插图和彩页插图智能排版。
+* 书籍批量下载。
+* 图片多线程下载。
+<!-- * <del>多线程预缓存策略，下载速度快。</del>(网站限制访问频率，默认单线程下载) -->
+* 缺失链接自动修复。
+* 自定义彩页。
+* ...................
+
+
+有建议或bug可以提issue，由于软件更新频繁，可以加QQ群获得更多信息：563072544
+
+图形界面使用[PyQt-Fluent-Widgets](https://pyqt-fluent-widgets.readthedocs.io/en/latest/index.html)界面编写。
+
+[release](https://github.com/ShqWW/bilinovel-download/releases/tag/exe)页面发布了已经打包好的exe可执行程序，包括图形化版本和命令行版本(系统最低要求Windows 10)。
+
+界面样例：
+<div align="center">
+  <img src="resource/example1.png" width="400"/>
+  <img src="resource/example2.png" width="400"/>
+</div>
+
+PS：暂不支持漫画的排版（本来也没几个漫画<
+## 使用前安装需要的包
+```
+pip install -r requirements.txt -i https://pypi.org/simple/
+```
+## 使用命令行模式运行(无需安装图形界面库，支持Linux):
+```
+python bilinovel.py
+```
+
+## 使用图形界面运行:
+```
+python bilinovel_gui.py
+```
+
+## 使用pyinstaller打包:
+```
+pip install pyinstaller
+```
+```
+pyinstaller -F -w -i .\resource\logo.png .\bilinovel_gui.py
+```
+
+## 相关项目：
+
+* [轻小说文库EPUB下载器](https://github.com/ShqWW/lightnovel-download)
+
+* [哔哩轻小说EPUB下载器](https://github.com/ShqWW/bilinovel-download)
+
+* [拷贝漫画EPUB下载器](https://github.com/ShqWW/copymanga-download)
+
+
+## EPUB书籍编辑和管理工具推荐：
+1. [Sigil](https://sigil-ebook.com/) 
+2. [Calibre](https://www.calibre-ebook.com/)
+

bilinovel.py

@@ -0,0 +1,145 @@
+import argparse
+from Editer2 import Editer
+import os
+import shutil
+from utils import *
+
+def parse_args():
+    """Parse input arguments."""
+    parser = argparse.ArgumentParser(description='config')
+    parser.add_argument('--book_no', default='0000', type=str)
+    parser.add_argument('--volume_no', default='1', type=int)
+    parser.add_argument('--no_input', default=False, type=bool)
+    args = parser.parse_args()
+    return args
+
+
+def query_chaps(book_no):
+    print('未输入卷号，将返回书籍目录信息......')
+    editer = Editer(root_path='./out', book_no=book_no)
+    print('*******************************')
+    print(editer.title, editer.author)
+    print('*******************************')
+    editer.get_chap_list()
+    print('*******************************')
+    print('请输入所需要的卷号进行下载（多卷可以用英文逗号分隔或直接使用连字符，详情见说明）')
+
+temp_path = ''
+
+def delete_tmp():
+    print(temp_path)
+    if os.path.exists(temp_path): 
+        shutil.rmtree(temp_path)
+
+def download_single_volume(root_path,
+                           book_no,
+                           volume_no,
+                           is_gui=False,
+                           hang_signal=None,
+                           progressring_signal=None,
+                           cover_signal=None,
+                           edit_line_hang=None):
+    
+    editer = Editer(root_path=root_path, book_no=book_no, volume_no=volume_no)
+    print('正在积极地获取书籍信息....')
+    success = editer.get_index_url()
+    if not success:
+        print('书籍信息获取失败')
+        return
+    print(editer.title + '-' + editer.volume['book_name'], editer.author)
+    print('****************************')
+    temp_path = editer.temp_path
+    if not editer.is_buffer():
+        editer.check_volume(is_gui=is_gui, signal=hang_signal, editline=edit_line_hang)
+        print('正在下载文本....')
+        print('*********************') 
+        editer.get_text()
+        print('*********************')
+        editer.buffer()
+    else:
+        print('检测到文本文件，直接下载插图')
+        editer.buffer()
+    
+
+    print('正在下载插图.....................................')
+    editer.get_image(is_gui=is_gui, signal=progressring_signal)
+    
+    print('正在编辑元数据....')
+    editer.get_cover(is_gui=is_gui, signal=cover_signal)
+    editer.get_toc()
+    editer.get_content()
+    editer.get_epub_head()
+
+    print('正在生成电子书....')
+    epub_file = editer.get_epub()
+    print('生成成功！', f'电子书路径【{epub_file}】')
+    
+
+def downloader_router(root_path,
+                      book_no,
+                      volume_no,
+                      is_gui=False, 
+                      hang_signal=None,
+                      progressring_signal=None,
+                      cover_signal=None,
+                      edit_line_hang=None):
+    is_multi_chap = False
+    if len(book_no)==0:
+        print('请检查输入是否完整正确！')
+        return
+    elif volume_no == '':
+        query_chaps(book_no)
+        return 
+    elif volume_no.isdigit():
+        volume_no = int(volume_no)
+        if volume_no<=0:
+            print('请检查输入是否完整正确！') 
+            return
+    elif "-" in volume_no:
+        start, end = map(str, volume_no.split("-"))
+        if start.isdigit() and end.isdigit() and int(start)>0 and int(start)<int(end):
+            volume_no_list = list(range(int(start), int(end) + 1))
+            is_multi_chap = True
+        else:
+            print('请检查输入是否完整正确！')
+            return
+    elif "," in volume_no:
+        volume_no_list = [num for num in volume_no.split(",")]
+        if all([num.isdigit() for num in volume_no_list]):
+            volume_no_list = [int(num) for num in volume_no_list] 
+            is_multi_chap = True
+        else:
+            print('请检查输入是否完整正确！')
+            return
+    else:
+            print('请检查输入是否完整正确！')
+            return
+    if is_multi_chap:
+        for volume_no in volume_no_list:
+            download_single_volume(root_path, book_no, volume_no, is_gui, hang_signal, progressring_signal, cover_signal, edit_line_hang)
+        print('所有下载任务都已经完成！')
+    else:
+        download_single_volume(root_path, book_no, volume_no, is_gui, hang_signal, progressring_signal, cover_signal, edit_line_hang)
+    
+if __name__=='__main__':
+    args = parse_args()
+    download_path = os.path.join(os.path.expanduser('~'), 'Downloads')
+
+    if args.no_input:
+        downloader_router(root_path='out', book_no=args.book_no, volume_no=args.volume_no)
+    else:
+        while True:
+            args.book_no = input('请输入书籍号：')
+            args.volume_no = input('请输入卷号(查看目录信息不输入直接按回车，下载多卷请使用逗号分隔或者连字符-)：')
+            downloader_router(root_path='out', book_no=args.book_no, volume_no=args.volume_no)
+            # args.book_no = '2931'
+            # args.volume_no = '7'
+            # downloader_router(root_path='out', book_no=args.book_no, volume_no=args.volume_no)
+            # exit(0)
+    
+        
+
+    
+
+    
+    

bilinovel_gui.py

@@ -0,0 +1,337 @@
+# coding:utf-8
+from PyQt5.QtCore import Qt, pyqtSignal, QObject, QThread, QRegExp
+from PyQt5.QtGui import QIcon, QFont, QTextCursor, QPixmap, QColor,QRegExpValidator
+from PyQt5.QtWidgets import QApplication, QFrame, QGridLayout, QFileDialog
+from qfluentwidgets import (setTheme, Theme, PushSettingCard, SettingCardGroup, ExpandLayout, TextEdit, ImageLabel, LineEdit, PushButton, Theme, ProgressRing, setTheme, Theme, OptionsSettingCard, OptionsConfigItem, OptionsValidator, FluentWindow, SubtitleLabel, NavigationItemPosition, setThemeColor, qconfig, EditableComboBox, BoolValidator)
+from qfluentwidgets import FluentIcon as FIF
+import sys
+import base64
+import shutil
+from resource.logo import logo_base64
+from resource.book import book_base64
+from bilinovel import *
+
+font_label = QFont('微软雅黑', 18)
+font_msg = QFont('微软雅黑', 11)
+
+class MainThread(QThread):
+    def __init__(self, parent):
+        super().__init__()
+        self.parent = parent
+        
+    def run(self):
+        self.parent.clear_signal.emit('')
+        try:
+            book_no = self.parent.editline_book.text()
+            volumn_no = self.parent.editline_volumn.text()
+            downloader_router(self.parent.parent.out_path, book_no, volumn_no, True, self.parent.hang_signal, self.parent.progressring_signal, self.parent.cover_signal, self.parent.editline_hang)
+            self.parent.end_signal.emit('')
+        except Exception as e:
+            self.parent.end_signal.emit('')
+            print('错误，请检查网络情况或确认输入是否正确')
+            print('错误信息：')
+            print(e)
+    def terminate(self) -> None:
+        result = super().terminate()
+        return result
+
+class EmittingStr(QObject):
+    textWritten = pyqtSignal(str)  # 定义一个发送str的信号
+    def write(self, text):
+        self.textWritten.emit(str(text))
+    def flush(self):
+        pass
+    def isatty(self):
+        pass
+
+class SettingWidget(QFrame):
+    def __init__(self, text: str, parent=None):
+        super().__init__(parent=parent)
+
+        self.parent = parent
+        self.expandLayout = ExpandLayout(self)
+        self.setObjectName(text.replace(' ', '-'))
+        self.setting_group = SettingCardGroup(self.tr("下载设置"), self)
+        
+        self.download_path_card = PushSettingCard(
+            self.tr('选择文件夹'),
+            FIF.DOWNLOAD,
+            self.tr("下载目录"),
+            self.parent.out_path,
+            self.setting_group
+        )
+        self.themeMode = OptionsConfigItem(
+        None, "ThemeMode", Theme.DARK, OptionsValidator(Theme), None)
+
+        self.threadMode = OptionsConfigItem(
+        None, "ThreadMode", True, BoolValidator())
+
+        self.theme_card = OptionsSettingCard(
+            self.themeMode,
+            FIF.BRUSH,
+            self.tr('应用主题'),
+            self.tr("更改外观"),
+            texts=[
+                self.tr('亮'), self.tr('暗'),
+                self.tr('跟随系统设置')
+            ],
+            parent=self.parent
+        )
+
+        self.setting_group.addSettingCard(self.download_path_card)
+        self.setting_group.addSettingCard(self.theme_card)
+        self.expandLayout.setSpacing(28)
+        self.expandLayout.setContentsMargins(20, 10, 20, 0)
+        self.expandLayout.addWidget(self.setting_group)
+
+        self.download_path_card.clicked.connect(self.download_path_changed)
+        self.theme_card.optionChanged.connect(self.theme_changed)
+
+    def download_path_changed(self):
+        """ download folder card clicked slot """
+        self.parent.out_path = QFileDialog.getExistingDirectory(
+            self, self.tr("Choose folder"), self.parent.out_path)
+        self.download_path_card.contentLabel.setText(self.parent.out_path)
+    
+    def theme_changed(self):
+        theme_name = self.theme_card.choiceLabel.text()
+        self.parent.set_theme(theme_name)
+        if os.path.exists('./config'):
+            shutil.rmtree('./config')
+
+
+            
+
+class HomeWidget(QFrame):
+
+    progressring_signal = pyqtSignal(object) 
+    end_signal = pyqtSignal(object) 
+    hang_signal = pyqtSignal(object)
+    clear_signal = pyqtSignal(object)
+    cover_signal = pyqtSignal(object)
+
+    def __init__(self, text: str, parent=None):
+        super().__init__(parent=parent)
+        self.setObjectName(text)
+        self.parent = parent
+        self.label_book = SubtitleLabel('书号：', self)
+        self.label_volumn = SubtitleLabel('卷号：', self)
+        self.editline_book = LineEdit(self) 
+        self.editline_volumn = LineEdit(self) 
+        validator = QRegExpValidator(QRegExp("\\d+"))  # 正则表达式匹配阿拉伯数字
+        self.editline_book.setValidator(validator)
+        # self.editline_volumn.setValidator(validator)
+
+        self.editline_book.setMaxLength(4)
+        # self.editline_volumn.setMaxLength(2)
+        
+        # self.editline_book.setText('2059')
+        # self.editline_volumn.setText('3')
+        self.book_icon = QPixmap()
+        self.book_icon.loadFromData(base64.b64decode(book_base64))
+        self.cover_w, self.cover_h = 152, 230
+
+        self.label_cover = ImageLabel(self.book_icon, self)
+        self.label_cover.setBorderRadius(8, 8, 8, 8)
+        self.label_cover.setFixedSize(self.cover_w, self.cover_h)
+
+        self.text_screen = TextEdit()
+        self.text_screen.setReadOnly(True)
+        self.text_screen.setFixedHeight(self.cover_h)
+
+        self.progressRing = ProgressRing(self)
+        self.progressRing.setValue(0)
+        self.progressRing.setTextVisible(True)
+        self.progressRing.setFixedSize(50, 50)
+        
+        self.btn_run = PushButton('确定', self)
+        self.btn_run.setShortcut(Qt.Key_Return)
+        self.btn_stop = PushButton('取消', self)
+        self.btn_hang = PushButton('确定', self)
+        
+        self.editline_hang = EditableComboBox(self)
+        self.gridLayout = QGridLayout(self)
+        self.screen_layout = QGridLayout()
+        self.btn_layout = QGridLayout()
+        self.hang_layout = QGridLayout()
+        
+        self.label_book.setFont(font_label)
+        self.label_volumn.setFont(font_label)
+        self.editline_book.setFont(font_label)
+        self.editline_volumn.setFont(font_label)
+        self.text_screen.setFont(font_msg)
+        self.editline_hang.setFont(font_msg)
+
+        self.gridLayout.addWidget(self.editline_book, 0, 1)
+        self.gridLayout.addWidget(self.editline_volumn, 1, 1)
+        self.gridLayout.addWidget(self.label_book, 0, 0)
+        self.gridLayout.addWidget(self.label_volumn, 1, 0)
+
+        self.gridLayout.addLayout(self.btn_layout, 2, 1, 1, 1)
+        self.btn_layout.addWidget(self.btn_run, 2, 1)
+        self.btn_layout.addWidget(self.btn_stop, 2, 2)
+
+        self.gridLayout.addLayout(self.screen_layout, 3, 0, 2, 2)
+
+        self.screen_layout.addWidget(self.progressRing, 0, 1, Qt.AlignLeft|Qt.AlignBottom)
+        self.screen_layout.addWidget(self.text_screen, 0, 0)
+        self.screen_layout.addWidget(self.label_cover, 0, 1)
+        
+        
+
+        self.gridLayout.addLayout(self.hang_layout, 5, 0, 1, 2)
+        self.hang_layout.addWidget(self.editline_hang, 0, 0)
+        self.hang_layout.addWidget(self.btn_hang, 0, 1)
+
+        self.screen_layout.setContentsMargins(0,0,0,0)
+        self.btn_layout.setContentsMargins(0,0,0,0)
+        self.gridLayout.setContentsMargins(20, 10, 20, 10)
+
+        self.btn_run.clicked.connect(self.process_start)
+        self.btn_stop.clicked.connect(self.process_stop)
+        self.btn_hang.clicked.connect(self.process_continue)
+
+        self.progressring_signal.connect(self.progressring_msg)
+        self.end_signal.connect(self.process_end)
+        self.hang_signal.connect(self.process_hang)
+        self.clear_signal.connect(self.clear_screen)
+        self.cover_signal.connect(self.display_cover)
+
+        self.progressRing.hide()
+        self.btn_hang.hide()
+        self.editline_hang.hide()
+        self.btn_stop.setEnabled(False)
+        
+        sys.stdout = EmittingStr(textWritten=self.outputWritten)
+        sys.stderr = EmittingStr(textWritten=self.outputWritten)
+        self.text_screen.setText(self.parent.welcome_text) 
+    
+    def process_start(self):
+        self.label_cover.setImage(self.book_icon)
+        self.label_cover.setFixedSize(self.cover_w, self.cover_h)
+        self.btn_run.setEnabled(False)
+        self.btn_run.setText('正在下载')
+        self.btn_stop.setEnabled(True)
+        self.main_thread = MainThread(self)
+        self.main_thread.start()
+        
+    def process_end(self, input=None):
+        self.btn_run.setEnabled(True)
+        self.btn_run.setText('开始下载')
+        self.btn_run.setShortcut(Qt.Key_Return)
+        self.btn_stop.setEnabled(False)
+        self.progressRing.hide()
+        self.btn_hang.hide()
+        self.editline_hang.clear()
+        self.editline_hang.hide()
+        if input=='refresh':
+            self.label_cover.setImage(self.book_icon)
+            self.label_cover.setFixedSize(self.cover_w, self.cover_h)
+            self.clear_signal.emit('')
+            self.text_screen.setText(self.parent.welcome_text) 
+        
+    def outputWritten(self, text):
+        cursor = self.text_screen.textCursor()
+        scrollbar=self.text_screen.verticalScrollBar()
+        is_bottom = (scrollbar.value()>=scrollbar.maximum() - 15)
+        cursor.movePosition(QTextCursor.End)
+        cursor.insertText(text)
+        if is_bottom:
+            self.text_screen.setTextCursor(cursor)
+        # self.text_screen.ensureCursorVisible()
+    
+    def clear_screen(self):
+        self.text_screen.clear()
+    
+    def display_cover(self, signal_msg):
+        filepath, img_h, img_w = signal_msg
+        self.label_cover.setImage(filepath)
+        self.label_cover.setFixedSize(int(img_w*self.cover_h/img_h), self.cover_h)
+        
+    def progressring_msg(self, input):
+        if input == 'start':
+            self.label_cover.setImage(self.book_icon)
+            self.label_cover.setFixedSize(self.cover_w, self.cover_h)
+            self.progressRing.show()
+        elif input == 'end':
+            self.progressRing.hide()
+            self.progressRing.setValue(0)
+        else:
+            self.progressRing.setValue(input)
+    
+    def process_hang(self, input=None):
+        self.btn_hang.setEnabled(True)
+        self.btn_hang.setShortcut(Qt.Key_Return)
+        self.btn_hang.show()
+        self.editline_hang.show()
+    
+    def process_continue(self, input=None):
+        self.btn_hang.hide()
+        self.btn_hang.setEnabled(False)
+        self.editline_hang.hide()
+        
+    
+    def process_stop(self):
+        self.main_thread.terminate()
+        self.end_signal.emit('refresh')
+        
+        
+    
+
+class Window(FluentWindow):
+    def __init__(self):
+        super().__init__()
+
+        self.out_path = os.path.join(os.path.expanduser('~'), 'Downloads')
+        self.head = 'https://www.linovelib.com'
+        split_str = '**************************************\n    '
+        self.welcome_text = f'使用说明（共4条，记得下拉）：\n{split_str}1.哔哩轻小说{self.head}，根据书籍网址输入书号以及下载的卷号，书号最多输入4位阿拉伯数字。\n{split_str}2.例如小说网址是{self.head}/novel/2704.html，则书号输入2704。\n{split_str}3.要查询书籍卷号卷名等信息，则可以只输入书号不输入卷号，点击确定会返回书籍卷名称和对应的卷号。\n{split_str}4.根据上一步返回的信息确定自己想下载的卷号，要下载编号[2]对应卷，则卷号输入2。想下载多卷比如[1]至[3]对应卷，则卷号输入1-3或1,2,3（英文逗号分隔，编号也可以不连续）并点击确定。'
+        self.homeInterface = HomeWidget('Home Interface', self)
+        self.settingInterface = SettingWidget('Setting Interface', self)
+        self.initNavigation()
+        self.initWindow()
+        
+    def initNavigation(self):
+        self.addSubInterface(self.homeInterface, FIF.HOME, '主界面')
+        self.addSubInterface(self.settingInterface, FIF.SETTING, '设置', NavigationItemPosition.BOTTOM)
+
+    def initWindow(self):
+        self.resize(700, 460)
+        pixmap = QPixmap()
+        pixmap.loadFromData(base64.b64decode(logo_base64))
+        self.setWindowIcon(QIcon(pixmap))
+        self.setWindowTitle('哔哩轻小说EPUB下载器')
+        self.setFont(font_label)
+
+        desktop = QApplication.desktop().availableGeometry()
+        w, h = desktop.width(), desktop.height()
+        self.move(w//2 - self.width()//2, h//2 - self.height()//2)
+    
+    def set_theme(self, mode=None):
+        if mode=='亮':
+            setTheme(Theme.LIGHT)
+        elif mode=='暗':
+            setTheme(Theme.DARK)
+        elif mode=='跟随系统设置':
+            setTheme(Theme.AUTO)
+        theme = qconfig.theme
+        if theme == Theme.DARK:
+            self.homeInterface.label_book.setTextColor(QColor(255,255,255))
+            self.homeInterface.label_volumn.setTextColor(QColor(255,255,255))
+        elif theme == Theme.LIGHT:
+            self.homeInterface.label_book.setTextColor(QColor(0,0,0))
+            self.homeInterface.label_volumn.setTextColor(QColor(0,0,0))
+
+
+    
+if __name__ == '__main__':
+    QApplication.setHighDpiScaleFactorRoundingPolicy(Qt.HighDpiScaleFactorRoundingPolicy.PassThrough)
+    QApplication.setAttribute(Qt.AA_EnableHighDpiScaling)
+    QApplication.setAttribute(Qt.AA_UseHighDpiPixmaps)
+
+    setTheme(Theme.DARK)
+    setThemeColor('#FF7233')
+    app = QApplication(sys.argv)
+    w = Window()
+    w.show()
+    app.exec_()

debug.py

@@ -0,0 +1,73 @@
+import requests  # 用来抓取网页的html源码
+head='https://www.linovel.com'
+# url = 'https://www.linovelib.com/novel/3207/163708.html'
+url1 = 'https://www.linovelib.com/novel/2662/catalog'
+url = 'https://www.linovelib.com/novel/2662/183423.html'
+# url = 'https://img3.readpai.com/2/2662/183423/210186.jpg'
+url0 = 'https://www.linovelib.com/'
+cookie = "night=1"
+header = {'User-Agent': "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1", 'referer': head, 'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6', 'cookie':cookie}
+header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47', 'referer': head, 'Accept-Language':'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6', 'cookie':cookie}
+# session = requests.Session()
+# req=session.get(url1, headers=header)
+req=requests.get(url, headers=header)
+print(req.text)
+
+
+
+
+# from selenium import webdriver
+# from selenium.webdriver.edge.options import Options
+# import time
+
+# options = Options()
+# options.add_argument('--start-minimized')
+
+# driver = webdriver.Edge(options = options)
+# driver2 = webdriver.Edge(options = options)
+# # exit(0)
+# driver.get(url0)
+# cookies = driver.get_cookies()
+# print(driver.page_source)
+# # driver.delete_all_cookies()
+# driver2.get('https://www.linovelib.com/')
+# # driver2.get(url)
+# time.sleep(5)
+# for cookie in cookies:
+#     driver2.add_cookie({'name': cookie['name'], 'value': cookie['value'], 'domain': cookie['domain']})
+# driver2.get(url)
+# print(driver2.page_source)
+
+
+
+# cookies_dict = dict()
+# for cookie in cookies:
+#     cookies_dict[cookie["name"]] = cookie["value"]
+
+# # 将 cookie 设置到 requests 的 CookieJar 中
+# requests_cookiejar = requests.utils.cookiejar_from_dict(cookies_dict)
+# req=requests.get(url, headers=header, cookies=requests_cookiejar)
+# print(req.text)
+
+
+# driver.get(url)
+# cookies = driver.get_cookies()
+
+
+
+# 打印 Cookie
+# for cookie in cookies:
+#     print(cookie["name"])
+#     print('*******************')
+#     print(cookie["value"])
+#     print('*******************')
+
+
+# print(driver2.page_source)
+# # driver.delete_all_cookies()
+# driver.get(url)
+# print(driver.page_source)
+# import pdb
+# pdb.set_trace()
+
+# print(driver.element)

requirements.txt

@@ -0,0 +1,7 @@
+# pip install -r requirements.txt -i https://pypi.org/simple/
+requests
+bs4
+rich
+pyqt5
+PyQt-Fluent-Widgets[full]
+selenium

resource/book.py

@@ -0,0 +1 @@
+book_base64 = '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'

resource/trans_base64.py

@@ -0,0 +1,23 @@
+from PIL import Image
+import base64
+from resource.logo import logo_base64
+import io
+
+# # 从Base64编码数据中获取图像数据
+# image_bytes = base64.b64decode(logo_base64)
+
+# # 将图像数据解码为Image对象
+# image = Image.open(io.BytesIO(image_bytes))
+
+# # 显示图像
+# image.show()
+
+
+def image_to_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        encoded_string = base64.b64encode(image_file.read())
+        return encoded_string.decode("utf-8")
+
+image_path = "resource/book.png "
+base64_string = image_to_base64(image_path)
+print(base64_string)

utils.py

@@ -0,0 +1,149 @@
+def get_cover_html(img_w, img_h):
+    img_htmls = []
+    img_msg = '      <image width=\"'+ str(img_w)+'\" height=\"'+ str(img_h)+'\" xlink:href="../Images/00.jpg"/>\n'
+    img_htmls.append('<?xml version="1.0" encoding="UTF-8" standalone="no" ?>\n')
+    img_htmls.append('<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n')
+    img_htmls.append('\"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n')
+    img_htmls.append('<html xmlns=\"http://www.w3.org/1999/xhtml\">\n')
+    img_htmls.append('<head>\n')
+    img_htmls.append('  <title>Cover</title>\n')
+    img_htmls.append('</head>\n')
+    img_htmls.append('<body>\n')
+    img_htmls.append('  <div style="text-align: center; padding: 0pt; margin: 0pt;">\n')
+    img_htmls.append('    <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"100%\" preserveAspectRatio=\"xMidYMid meet\" version=\"1.1\" viewBox=\"0 0 '+ str(img_w)+' '+ str(img_h)+'\" width=\"100%\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n')
+    img_htmls.append(img_msg)
+    img_htmls.append('    </svg>\n')
+    img_htmls.append('  </div>\n')
+    img_htmls.append('</body>\n')
+    img_htmls.append('</html>')
+    return img_htmls
+
+
+def text2htmls(chap_name, text):
+    text_lines = text.split('\n')
+    text_body = []
+    text_body.append('<body>\n')
+    text_body.append('<h1>' + chap_name + '</h1>\n')
+    for text_line in text_lines:
+        if text_line.startswith('[img:'):
+            img_no = text_line[5:7]
+            text_line_html = f'  <img alt=\"{img_no}\" src=\"../Images/{img_no}.jpg\"/>\n'
+        else:
+            text_line_html = '<p>' + text_line + '</p>\n'
+        text_body.append(text_line_html)
+    text_body.append('</body>\n')
+    text_head = []
+    text_head.append('<?xml version="1.0" encoding="UTF-8" standalone="no" ?>\n')
+    text_head.append('<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.1//EN\"\n')
+    text_head.append('\"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\n')
+    text_head.append('<html xmlns=\"http://www.w3.org/1999/xhtml\">\n')
+    text_head.append('<head>\n')
+    text_head.append('<title>'+ chap_name+'</title>\n')
+    text_head.append('<style>p{text-indent:2em;}</style>\n')
+    text_head.append('</head>\n')
+    text_htmls = text_head + text_body + ['</html>']
+    return text_htmls
+
+def get_toc_html(title, chap_names):
+    toc_htmls = []
+    toc_htmls.append('<?xml version=\"1.0\" encoding=\"utf-8\"?>\n')
+    toc_htmls.append('<!DOCTYPE ncx PUBLIC \"-//NISO//DTD ncx 2005-1//EN\"\n')
+    toc_htmls.append('   \"http://www.daisy.org/z3986/2005/ncx-2005-1.dtd\">\n\n')
+    toc_htmls.append('<ncx xmlns=\"http://www.daisy.org/z3986/2005/ncx/\" version=\"2005-1\">\n')
+    toc_htmls.append('  <head>\n')
+    toc_htmls.append('    <meta name=\"dtb:uid\" content=\"urn:uuid:a18aac05-497d-476d-b66f-0211f609743d\" />\n')
+    toc_htmls.append('    <meta name=\"dtb:depth\" content=\"0\" />\n')
+    toc_htmls.append('    <meta name=\"dtb:totalPageCount\" content=\"0\" />\n')
+    toc_htmls.append('    <meta name=\"dtb:maxPageNumber\" content=\"0\" />\n')
+    toc_htmls.append('  </head>\n')
+    toc_htmls.append('<docTitle>\n')
+    toc_htmls.append('  <text>'+ title +'</text>\n')
+    toc_htmls.append('</docTitle>\n')
+    toc_htmls.append('<navMap>\n')
+    for chap_no, chap_name in enumerate(chap_names):
+        toc_htmls.append('    <navPoint id=\"navPoint-'+str(chap_no+1)+'\" playOrder=\"'+str(chap_no+1)+'\">\n')
+        toc_htmls.append('      <navLabel>\n')
+        toc_htmls.append('        <text>'+ chap_name +'</text>\n')
+        toc_htmls.append('      </navLabel>\n')
+        toc_htmls.append('      <content src="Text/'+str(chap_no).zfill(2)+'.xhtml"/>\n')
+        toc_htmls.append('    </navPoint>\n')
+    toc_htmls.append('</navMap>\n')
+    toc_htmls.append('</ncx>')
+    return toc_htmls
+
+
+def get_content_html(title, author, num_chap, num_img, img_exist=False):
+    content_htmls = []
+    content_htmls.append('<?xml version=\"1.0\" encoding=\"utf-8\"?>\n')
+    content_htmls.append('<package version=\"2.0\" unique-identifier=\"BookId\" xmlns=\"http://www.idpf.org/2007/opf\">\n')
+    content_htmls.append('  <metadata xmlns:dc=\"http://purl.org/dc/elements/1.1/\" xmlns:opf=\"http://www.idpf.org/2007/opf\">\n')
+    content_htmls.append('    <dc:identifier id=\"BookId\" opf:scheme=\"UUID\">urn:uuid:942b8224-476b-463b-9078-cdfab0ee2686</dc:identifier>\n')
+    content_htmls.append('    <dc:language>zh</dc:language>\n')
+    content_htmls.append('    <dc:title>'+ title +'</dc:title>\n')
+    content_htmls.append('    <dc:creator opf:role="aut" opf:file-as="未知">'+ author +'</dc:creator>\n')
+    content_htmls.append('    <meta name=\"cover\" content=\"x00.jpg\"/>\n')
+    content_htmls.append('  </metadata>\n')
+    content_htmls.append('  <manifest>\n')
+    content_htmls.append('    <item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml"/>\n')
+    content_htmls.append('    <item id="cover.xhtml" href="Text/cover.xhtml" media-type="application/xhtml+xml"/>\n')
+    if img_exist:
+        content_htmls.append('    <item id="xcolor" href="Text/color.xhtml" media-type="application/xhtml+xml"/>\n')
+    for chap_no in range(num_chap):
+        content_htmls.append('    <item id=\"x'+str(chap_no).zfill(2)+'.xhtml\" href=\"Text/'+ str(chap_no).zfill(2)+'.xhtml\" media-type=\"application/xhtml+xml\"/>\n')
+
+
+    for img_no in range(num_img):
+        content_htmls.append('    <item id=\"x'+str(img_no).zfill(2)+'.jpg\" href=\"Images/'+ str(img_no).zfill(2)+'.jpg\" media-type=\"image/jpeg\"/>\n')
+
+    content_htmls.append('  </manifest>\n')
+    content_htmls.append('  <spine toc="ncx">\n')
+
+
+    content_htmls.append('    <itemref idref="cover.xhtml"/>\n')
+    content_htmls.append('    <itemref idref="xcolor"/>\n')
+    for chap_no in range(num_chap):
+        content_htmls.append('    <itemref idref=\"x'+str(chap_no).zfill(2)+'.xhtml\"/>\n')
+
+    content_htmls.append('  </spine>\n')
+    content_htmls.append('  <guide>\n')
+    content_htmls.append('    <reference type="cover" title="封面" href="Text/cover.xhtml"/>\n')
+    content_htmls.append('  </guide>\n')
+    content_htmls.append('</package>\n')
+    return content_htmls
+
+
+def get_container_html():
+    container_htmls = []
+    container_htmls.append('<?xml version="1.0" encoding="UTF-8"?>\n')
+    container_htmls.append('<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">\n')
+    container_htmls.append('    <rootfiles>\n')
+    container_htmls.append('        <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>\n')
+    container_htmls.append('   </rootfiles>\n')
+    container_htmls.append('</container>\n')
+    return container_htmls
+
+
+def get_color_html(colorimg_num):
+    color_htmls = []
+    color_htmls.append('<?xml version=\"1.0\" encoding=\"utf-8\"?>\n')
+    color_htmls.append('<html>\n')
+    color_htmls.append('<head>\n')
+
+    color_htmls.append('  <title>彩插</title>\n')
+    color_htmls.append('</head>\n')
+    color_htmls.append('<body>\n')
+    for i in range(1, colorimg_num):
+        color_htmls.append('  <img alt=\"'+str(i).zfill(2)+'\" src=\"../Images/'+str(i).zfill(2)+'.jpg\"/>\n')
+    color_htmls.append('</body>\n')
+    color_htmls.append('</html>')
+    return color_htmls
+
+def check_chars(win_chars):
+    win_illegal_chars = '?*"<>|:/'
+    new_chars = ''
+    for char in win_chars:
+        if char in win_illegal_chars:
+            new_chars += '\u25A0'
+        else:
+            new_chars += char
+    return new_chars