Python爬取小说

#-*-coding:GBK-*-
#author:zwg
'''
爬取某小说网站的免费小说
'''
import urllib
import urllib2
import re
url='http://www.bxwx8.org/b/8/8987/2093383.html'
url1='http://www.bxwx8.org/b/8/8987/2093%d.html'
def gethtml(url):
    page=urllib.urlopen(url)
    html=page.read()
    return html
def get_name_content(html):
    re1=re.compile('<title>.+?</title>')
    re2=re.compile('<div id="content"><div id="adright">.+?</div>')
    s1=re1.findall(html)
    s2=re2.findall(html)
    if len(s1)>0 and len(s2)>0:
        name=s1[0].replace('<title>','')
        name=name.replace('TXT下载-笔下文学</title>','')
        content=s2[0].replace('''<div id="content"><div id="adright">''','')
        content=content.replace('</div>','')
        content=content.replace('<br /><br />    ','\n\t')
        content = content.replace('    ', '')
    else:
        name=' '
        content=' '
    return name,content
def write_novel(i,file1):
    file1.writelines('\n\r')
    s=383+i;
    html = gethtml(url1 % s)
    name,content = get_name_content(html)
    file1.writelines(name)
    file1.writelines('\n\t')
    file1.writelines(content)
    file1.writelines('\n\n\n')

file1=file('间客.txt','w+')
[write_novel(i,file1) for i in range(50)]
file1.close()