- http://cafebabe.cc/nazo/basic/cache.html
- http://cafebabe.cc/nazo/medium/champion.html
- http://cafebabe.cc/nazo/basic/cherry.html
- http://cafebabe.cc/nazo/click.html
- http://cafebabe.cc/nazo/medium/delete.html
- http://cafebabe.cc/nazo/medium/dizzy.html
- http://cafebabe.cc/nazo/medium/for.html
- http://cafebabe.cc/nazo/medium/forty.html
- http://cafebabe.cc/nazo/basic/fractal.html
- http://cafebabe.cc/nazo/basic/index.html
- http://cafebabe.cc/nazo/index.html
- http://cafebabe.cc/nazo/basic/key.html
- http://cafebabe.cc/nazo/medium/kick.html
- http://cafebabe.cc/nazo/medium/level.html
- http://cafebabe.cc/nazo/medium/lie.html
- http://cafebabe.cc/nazo/basic/month.html
- http://cafebabe.cc/nazo/basic/office.html
- http://cafebabe.cc/nazo/medium/portal.html
- http://cafebabe.cc/nazo/basic/random.html
- http://cafebabe.cc/nazo/medium/reed.html
- http://cafebabe.cc/nazo/basic/shadow.html
- http://cafebabe.cc/nazo/medium/slumber.html
- http://cafebabe.cc/nazo/basic/solve.html
- http://cafebabe.cc/nazo/basic/sonic.html
- http://cafebabe.cc/nazo/medium/spring.html
- http://cafebabe.cc/nazo/medium/suffix.html
- http://cafebabe.cc/nazo/medium/template.html
- http://cafebabe.cc/nazo/medium/thumb.html
- http://cafebabe.cc/nazo/medium/tilt.html
- http://cafebabe.cc/nazo/medium/tyrant.html
- http://cafebabe.cc/nazo/java.html
代码:
#coding=utf8
import urllib2
word_file = open("words.txt","r")
url_file = open("nazo.html","a")
while True:
line = word_file.readline()
if not line:
break
line = line.strip()
url_list = ['http://cafebabe.cc/nazo/basic/','http://cafebabe.cc/nazo/medium/','http://cafebabe.cc/nazo/']
for url in url_list:
try:
url = url + line + '.html'
page = urllib2.urlopen(url)
print 'success -> ', url
url_file.write(url+"
")
except Exception,ex:
print '
failed -> ',line,
pass
word_file.close()
url_file.close()