45 lines
1002 B
Python
45 lines
1002 B
Python
|
import urllib2
|
||
|
|
import re
|
||
|
|
from texts.models import *
|
||
|
|
|
||
|
|
NEXT = "http://next.pad.ma/"
|
||
|
|
OLD = "http://pad.ma/"
|
||
|
|
IdMapping = {}
|
||
|
|
|
||
|
|
|
||
|
|
def getNewUrl(oldUrl):
|
||
|
|
new = oldUrl.replace(OLD, NEXT)
|
||
|
|
try:
|
||
|
|
return urllib2.urlopen(new).url
|
||
|
|
except:
|
||
|
|
print "ERROR: " + oldUrl
|
||
|
|
|
||
|
|
def getNewId(oldId):
|
||
|
|
oldId = oldId.group().replace(OLD, "")[:-1]
|
||
|
|
print oldId
|
||
|
|
if oldId in IdMapping:
|
||
|
|
return IdMapping[oldId]
|
||
|
|
url = NEXT + oldId
|
||
|
|
u = urllib2.urlopen(url)
|
||
|
|
newId = u.url.replace(NEXT, "")
|
||
|
|
IdMapping[oldId] = newId
|
||
|
|
return newId
|
||
|
|
|
||
|
|
def replaceUrls(text):
|
||
|
|
regex = re.compile(r'(http:\/\/pad.ma\/V.*?)[\s\"\<]')
|
||
|
|
for f in re.findall(regex, text):
|
||
|
|
newUrl = getNewUrl(f)
|
||
|
|
print newUrl
|
||
|
|
text = text.replace(f, newUrl)
|
||
|
|
return text
|
||
|
|
# for m in re.findall(regex, text):
|
||
|
|
# print getNewId(m)
|
||
|
|
|
||
|
|
def doAll():
|
||
|
|
for p in PadmaText.objects.all():
|
||
|
|
print p.title
|
||
|
|
newText = replaceUrls(p.html)
|
||
|
|
p.html = newText
|
||
|
|
p.save()
|
||
|
|
|