首先要获取目录信息，主要是目录名称和网址。通过分析连载网站的网页源代码，编写Python代码如下：
# -*- coding:UTF-8 -*- import urllib.request, sys import re def openUrl(url): try: page = urllib.request.urlopen(url, data=None, timeout=5) except urllib.error.HTTPError as e: print(e.code) print(e.reason) return '' except urllib.error.URLError as e: print(e.reason) return '' else: html = page.read().decode('utf-8') return html def getList(html, tag): i = html.find(tag) if i == -1: print ('没有找到' + tag) return '' else: con = html[i+len(tag):] #print ("前30个字符：" + con[:30]) tag = 'ul' tag_pat = r'(?<=<'+ tag + '>).*?(?=</' + tag + '>)' tag_ex = re.compile(tag_pat, re.M|re.S) con = re.findall(tag_ex, con) #con = html.split('正文') #print (con[0]) return con[0] def printList(list, host): #获取text res = r'(.*?)' t = re.findall(res, list, re.S|re.M) #获取href res_url = r"(?<=href=\").+?(?=\")|(?<=href=\').+?(?=\')" h = re.findall(res_url, list, re.I|re.S|re.M) for i in range(len(t)): print (str(i+1) + '\t' + t[i] + '\t' + host + h[i]) def main(): url = 'http://www.mengxi.net/book/263745/index.html' i = url.index('/', 7) host = url[0 : i] print ('打开' + url) html = openUrl(url) if len(html) > 0: tag = '正文' list = getList(html, tag) printList(list, host) main()
程序运行结果如下：
