Python:Ifexistslog.py

#ifexistslog.py
# TO FETCH THE PAGE:
#   http://noc.wikimedia.org/~tstarling/ifexist.log
# STORE IT, AND THEN FIND ALL STRINGS like:
#   2007-12-03 06:27:16 zh_yuewiki: 131 http://zh-yue.wikipedia.org/wiki/%E6%B4%9B%E7%A3%AF%E5%B1%B1%E8%84%88
 
import re
import urllib
import codecs
 
# CUSTOMIZE THE FOLLOWING LINE TO YOUR LANGUAGE
urlX = re.compile(r'http\://zh-yue.+\b',flags=re.U) 
 
file = urllib.urlopen('http://noc.wikimedia.org/~tstarling/ifexist.log')
saveFile = codecs.open('ifexists.log','a+',encoding='utf-8')
sortFile = codecs.open('ifexists.sort','a+',encoding='utf-8')
 
x=file.read()
 
saveFile.write(x)
saveFile.close()
 
list = urlX.findall(x)
 
a = raw_input('\n#################Here! \n\n\n\n\n\a')
 
## WE SHOULD REPLACE THE FOLLOWING BY SOMETHING WHICH CAN REMOVE THE DUPLICATIONS
 
n=0
for i in list:
  print(i)
  n+=1
print n, 'parses found.'
 
a=''
for i in list:
  print(i)
  if a=='': a=raw_input('press return to continue; type something else to automate')
  sortFile.write(i)
 
sortFile.close()