网络爬虫：魔道祖师小说

好奇总被人提及的网络爬虫到底是什么技术，于是也想用，我的需求是可以下载小说、文献摘要、还有各种生信数据库的网站抓取等，先拿我喜欢的魔道祖师小说来练手。

如果懂点HTML/CSS/JS的话，基于网页的标签去读取识别，很简单了，直接上代码：

class downloader(object):

    def __init__(self):
        self.server = 'http://www.bequgew.com'
        self.target = 'http://www.bequgew.com/33489/'
        self.names = []            #存放章节名
        self.urls = []            #存放章节链接
        self.nums = 0            #章节数

    def get_download_url(self):
        req = requests.get(url = self.target)
        req.encoding = req.apparent_encoding
        html = req.text
        div_bf = BeautifulSoup(html)
        div = div_bf.find_all('div', class_ = 'article_texttitleb')
        a_bf = BeautifulSoup(str(div[0]))
        a = a_bf.find_all('a')
        #self.nums = len(a[15:])                                #剔除不必要的章节，并统计章节数
        self.nums = len(a) #我全要
        for each in a:
            self.names.append(each.string)
            self.urls.append(self.server + each.get('href'))

    def get_contents(self, target):
        req = requests.get(url = target)
        req.encoding = req.apparent_encoding
        html = req.text
        bf = BeautifulSoup(html)
        texts = bf.find_all('div', id = 'book_text')
        texts = texts[0].text.replace('\xa0'*4,'\n')
        return texts

    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')

if __name__ == "__main__":
    dl = downloader()
    dl.get_download_url()
    print('《魔道祖师》开始下载：')
    for i in range(dl.nums):
        print(dl.names[i])
        print(dl.urls[i])
        dl.writer(dl.names[i], '魔道祖师.txt', dl.get_contents(dl.urls[i]))
        sys.stdout.write("  已下载:%.3f%%" %  float(i/dl.nums) + '\r')
        sys.stdout.flush()
    print('《魔道祖师》下载完成')

版权说明：参考大神Jack-Cui的示例