带断点续传的小说爬虫

先上代码：

# -*- coding:UTF-8 -*-
from bs4 import BeautifulSoup
import requests, sys,os,json,re

"""
类说明:下载《唐三书》网小说《斗罗大陆》
Parameters:
    无
Returns:
    无
Modify:
    2018-09-23
"""
class downloader(object):

    def __init__(self,server,target,bookname):
        self.server = server
        self.target = target
        self.names = []            #存放章节名
        self.urls = []            #存放章节链接
        self.nums = 0            #章节数
        self.bookname = bookname
        self.book_storge_path = bookname + '.txt'
        self.book_config_path = bookname + '.json'
        self.bookconfig = []



    """
    函数说明:获取下载链接
    Parameters:
        无
    Returns:
        无
    Modify:
        2018-09-23
    """
    def get_download_url(self):
        req = requests.get(url = self.target)
        req.encoding = 'gbk'
        html = req.text
        div_bf = BeautifulSoup(html,features = "html.parser")
        
        div = div_bf.find_all('table')
        
        a_bf = BeautifulSoup(str(div[0]),features = "html.parser")
        a = a_bf.find_all('a')
        
        self.nums = 0
        for each in a:
            if not each.string is None:
                self.names.append(each.string)
                self.urls.append(self.server + each.get('href'))
                self.nums +=1


    """
    函数说明:获取章节内容
    Parameters:
        target - 下载连接(string)
    Returns:
        texts - 章节内容(string)
    Modify:
        2018-09-23
    """
    def get_contents(self, target):
       
        req = requests.get(url = target)
        req.encoding = 'gbk'
        html = req.text
        bf = BeautifulSoup(html,features="html.parser")
        #print(bf)
        texts = bf.find_all('div', class_ = 'blockcontent')

        texts = texts[0].text.replace('\xa0'*8,'\n\n')
        return texts

    """
    函数说明:将爬取的文章内容写入文件
    Parameters:
        name - 章节名称(string)
        path - 当前路径下,小说保存名称(string)
        text - 章节内容(string)
    Returns:
        无
    Modify:
        2018-09-23
    """
    def writer(self, name, path, text):
        #write_flag = True
        with open(path, 'a', encoding='utf-8') as f:
            f.write(name + '\n')
            f.writelines(text)
            f.write('\n\n')
    """
    函数说明:自动开始下载
    Parameters:
        无
    Returns:
        无
    Modify:
        2018-09-23
    """

    def auto_download(self):
        self.get_download_url()
        print('《' + self.bookname + '》开始下载：')

        if os.path.isfile(self.book_config_path):
            with open(self.book_config_path,'r',encoding = 'utf-8') as file:
                config_str = file.read()
                config_str = json.loads(config_str)
                for each in config_str:
                    self.bookconfig.append({'name':each['name'],'url':each['url'],'isDownloaded':each['isDownloaded']})
            
        else:
            print('进度文件不存在，从头开始下载')
            for i in range(self.nums):
                self.bookconfig.append({'name':self.names[i],'url':self.urls[i],'isDownloaded':'no'})
        
        for i in range(self.nums):
            if self.bookconfig[i]['isDownloaded'] == 'yes':
                print(self.names[i] + '    已下载，跳过')
                continue    
            self.writer(self.names[i], self.bookname + '.txt', self.get_contents(self.urls[i]))
            sys.stdout.write(self.names[i] +'  下载完成，完成度：%.2f%%'%float((i+1)/self.nums*100)  + '\r')
            sys.stdout.flush()
            self.bookconfig[i]['isDownloaded'] = 'yes'
            with open(self.book_config_path,'w',encoding = 'utf-8') as file:
                file.write(json.dumps(self.bookconfig,indent = 2,ensure_ascii = False))
        print('《' + self.bookname + '》下载完成')
        
if __name__ == "__main__":
    dl = []
    nums = 0
    urls = []
    names = []
    server = 'http://www.tangsanshu.com'
    req = requests.get(url = server)
    req.encoding = 'gbk'
    html = req.text
    div_bf = BeautifulSoup(html,features = "html.parser")
    div = div_bf.find_all('div',id = 'navmenu')
        
    a_bf = BeautifulSoup(str(div[0]),features = "html.parser")
    a = a_bf.find_all('a')
        
    for each in a:
        if not each.string is None:
            names.append(each.string)
            urls.append(server + each.get('href'))
            dl.append(downloader(server + each.get('href'),server + each.get('href'),each.string))
            dl[nums].auto_download()
            nums +=1