itpub改版了,新版备份博客代码如下,思路和上一版备份思路一样
# -*- coding: utf-8 -*-
import re
import urllib2
import requests,re
from bs4 import BeautifulSoup as bsp
for page in range(1,30): ###这儿就是输入你希望下载的页数,输入你的总页数吧
url='http://blog.itpub.net/29096438/list/%d/'% page ####循环不同的页
text = urllib2.urlopen(url).read()
pattern = r'<a target=_blank href="/29096438/viewspace-[0-9]*/" class="w750"><p class="title">.*</p></a>'
regex = re.compile(pattern)
urlList = re.findall(regex,text) ####通过正则表达式找到所有文章的href,此时的href是带上标题的
for t in urlList:
i= t.split('=')[2].replace('class','').replace('"','').strip(' ')
newi=re.sub('/29096438','http://blog.itpub.net/29096438',i).decode('utf-8')
fname2=t.split('=')[-1].split('>')[1].split('<')[0]+'.html'.replace(' ','')
# print newi,fname2
try:
r=requests.get(newi,headers={'User-Agent':'Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1'})
soup=bsp(r.content,"html.parser")
cont=soup.find('div',{'class':'preview-main'})
f=open(fname2,'w')
f.write(str(cont))
f.close()
print fname2,r,'备份成功'
except:
pass
###上面的user-agent随机从下面取一个,我懒的写随机choice了
agents = [
'Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1',
'Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5',
'Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1',
'Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7',
'Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)',
'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; tr; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8 ( .NET CLR 3.5.30729; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
'Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0a2) Gecko/20110622 Firefox/6.0a2',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre',
'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )',
'Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90)',
'Mozilla/5.0 (Windows; U; Windows XP) Gecko MultiZilla/1.6.1.0a',
'Mozilla/2.02E (Win95; U)',
'Mozilla/3.01Gold (Win95; I)',
'Mozilla/4.8 [en] (Windows NT 5.1; U)',
'Mozilla/5.0 (Windows; U; Win98; en-US; rv:1.4) Gecko Netscape/7.1 (ax)',
'Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.2; U; de-DE) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/234.40.1 Safari/534.6 TouchPad/1.0',
]
备份如下
亿速云「云服务器」,即开即用、新一代英特尔至强铂金CPU、三副本存储NVMe SSD云盘,价格低至29元/月。点击查看>>
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。
原文链接:http://blog.itpub.net/29096438/viewspace-2157850/