爬小说

from bs4 import BeautifulSoup
import requests,sys

class downloader(object): #定义一个downloader类

    def __init__(self):   #当前类的实例
        self.server = 'http://www.biqukan.com/'
        self.target = 'http://www.biqukan.com/39_39591/'
        self.names = []     #章节名
        self.urls = []      #链接名
        self.nums = 0       #章节数

    def get_download_url(self):     #获取下载链接
        req = requests.get(url = self.target)
        html = req.text     #为什么有.text？？
        div_df = BeautifulSoup(html)
        div = div_df.find_all('div',class_ = 'listmain')
        a_bf = BeautifulSoup(str(div[0]))   #为什么要用str()？？
        a = a_bf.find_all('a')
        self.nums = len(a[12:])
        for each in a[12:]:
            self.names.append(each.string)
            self.urls.append(self.server + each.get('href'))

    def get_contents(self,target):      #获取章节内容
        req = requests.get(url = target)
        html = req.text
        bf = BeautifulSoup(html)
        texts = bf.find_all('div',class_ = 'showtxt')
        texts = texts[0].text.replace('\xa0' * 8, '\n\n')
        return texts

    def writer(self,name,path,text):  #将爬取的文章内容写入文件
        write_flag = True
        with open(path,'a',encoding = 'utf-8') as f:
            f.write(name + '\n')  #章节名
            f.writelines(text)    #章节内容
            f.write('\n\n')

if __name__ == '__main__':
    d1 = downloader()   #调用类
    d1.get_download_url()  #调用类中的方法
    print('《终鄢》开始下载:')
    for i in range(d1.nums):
        d1.writer(d1.names[i],'终鄢.txt',d1.get_contents(d1.urls[i]))
        sys.stdout.write(' 已下载：%.3f%%' % float(i/d1.nums) + '\r')
        sys.stdout.flush()
    print('《终鄢》下载完成')