1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44

import sys, urllib,string
import re,os
import threading
 
url=raw_input('input url:')
s=url.find("index.html")
str=url[0:s]
content = urllib.urlopen(url).read()

#获取链接与章节目录
re_result=re.compile(r'(?<=<a href=")\d+.html(?=")')
lianjie=re.findall(re_result,content)
 
#获取小说名称
re_title=re.compile(r'(?<=<div id="title">).+(?=</)')
re_title_result=re.findall(re_title,content)
 
# 章节重新排序
lianjie.sort()
 
#获取文章链接
i=0
wzsj=[]
for j in lianjie:
    wzsj.append(str+lianjie[i])
    i=i+1
 
# 获取文章内容
fb=open("d:\\"+ re_title_result[0]+".txt","w")
for b in wzsj:
    nr=urllib.urlopen(b).read()
    #获取文章标题
    title_re=re.compile(r'(?<=<div id="title">).+(?=</)')
    title=re.findall(title_re,nr)
    #获取正文内容
    b2=re.compile(r'(?<=<div id="content"><div id="adright"></div>)[\s|\S]*(?=</div>)')
    nr2=re.findall(b2,nr)
    #空白符与换行符处理
    t=nr2[0].replace(r'<br />','\n')
    t2=t.replace(r'&nbsp;','') 
   
    print("Now DownLoad&#65306;"+title[0])
    fb.write("\n\n\n"+title[0]+"\n\n"+t2)
    fb.close()