python 小说下载_通过python自动获取小说并下载

1 importurllib.request2 importos3

4 headers ={5 "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163"

6 "Safari/535.1",7 }8

9

10 #主程序，获取每个章节的名称及链接

11 defmain():12 print('开始下载')13 url_list =[]14 url = 'http://www.eywedu.com/honglou/01/index.htm'

15 res = urllib.request.Request(url, data=None, headers=headers)16 html = urllib.request.urlopen(res).read().decode('gb18030')17 lists = html.split('')34 get_content(net+cut[0], cut[1])35 print('第', page, '章已下完')36 page = page+1

37

38

39 #根据每章链接获得内容

40 defget_content(url, name):41 paragraphs =[]42 res = urllib.request.Request(url, data=None, headers=headers)43 html = urllib.request.urlopen(res).read().decode('gb18030')44 lists = html.split('
')45 t =046 while t

')[1]49 p = p.replace('\r\n', '')50 paragraphs.append(p)51 elif t == len(lists) - 1:52 p = lists[t].split(r'')[0]53 p = p.replace('\r\n', '')54 paragraphs.append(p)55 else:56 p = lists[t].replace('\r\n', '')57 paragraphs.append(p)58 t = t + 1

59 save_txt(paragraphs, name)60

61

62 #将得到的信息保存

63 defsave_txt(content, name):64 f = open('红楼梦\\'+name+'.txt', "a", encoding='utf-8')65 for i incontent:66 f.write(i)67 f.close()68

69

70 if __name__ == '__main__':71 main()