1.代碼：

# -*- coding:UTF-8 -*- from bs4 import BeautifulSoup import requests, sys""" 類說明:下載文字 Parameters:無 Returns:無 Modify:2017-09-13 """ class downloader(object):def __init__(self):self.server = 'http://www.biqukan.com/'self.target = 'http://www.biqukan.com/1_1094/'self.names = [] # 存放章節(jié)名self.urls = [] # 存放章節(jié)鏈接self.nums = 0 # 章節(jié)數""" 函數說明:獲取下載鏈接Parameters:無Returns:無Modify:2017-09-13""" def get_download_url(self):req = requests.get(url=self.target)html = req.textdiv_bf = BeautifulSoup(html)div = div_bf.find_all('div', class_='listmain')a_bf = BeautifulSoup(str(div[0]))a = a_bf.find_all('a')self.nums = len(a[15:]) # 剔除不必要的章節(jié)，并統(tǒng)計章節(jié)數for each in a[15:]:self.names.append(each.string)self.urls.append(self.server + each.get('href'))""" 函數說明:獲取章節(jié)內容Parameters:target - 下載連接(string)Returns:texts - 章節(jié)內容(string)Modify:2017-09-13""" def get_contents(self, target):req = requests.get(url=target)html = req.textbf = BeautifulSoup(html)texts = bf.find_all('div', class_='showtxt')texts = texts[0].text.replace('\xa0' * 8, '\n\n')return texts""" 函數說明:將爬取的文章內容寫入文件Parameters:name - 章節(jié)名稱(string)path - 當前路徑下,小說保存名稱(string)text - 章節(jié)內容(string)Returns:無Modify:2017-09-13""" def writer(self, name, path, text):write_flag = Truewith 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('《一年永恒》開始下載：')for i in range(dl.nums):dl.writer(dl.names[i], '一念永恒.txt', dl.get_contents(dl.urls[i]))sys.stdout.write(" 已下載:%.3f%%" % float(i / dl.nums) + '\r')sys.stdout.flush()print('《一年永恒》下載完成')

?

轉載于:https://www.cnblogs.com/wangshicheng/p/10184372.html

總結

以上是生活随笔為你收集整理的爬取小说 spider的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。