Created
March 20, 2012 00:22
-
-
Save DrSkippy/2128919 to your computer and use it in GitHub Desktop.
Lengthen Short URL with service longurl.org
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# | |
# Scott Hendrickson | |
# 2012-03-18 | |
# | |
import sys | |
import re | |
import urllib | |
import httplib2 | |
import json | |
# URLS | |
r1 = r"(\b(http|https)://([-A-Za-z0-9+&@#/%?=~_()|!:,.;]*[-A-Za-z0-9+&@#/%=~_()|]))" | |
urlRE = re.compile(r1) | |
######################### | |
# http://longurl.org/api | |
http = httplib2.Http() | |
header = { 'User-Agent' : 'Mozilla/5.0' } | |
urlsUnrolled = 'http://api.longurl.org/v2/services?format=json' | |
response, content = http.request(urlsUnrolled, 'GET', headers=header) | |
# list contains all valid domains - don't try to process invalid domains | |
domainList = json.loads(content) | |
def unroll(x): | |
# x e.g. "http://bit.ly/asdfg" | |
domain = x.split('/')[2] | |
if domain in domainList: | |
u = 'http://api.longurl.org/v2/expand?url='+urllib.quote(x) | |
response, content = http.request(u, 'GET', headers=header) | |
# response verification here some day? | |
tmp = urlRE.search(content) | |
if tmp is not None: | |
return tmp.group(0) | |
else: | |
return x | |
else: | |
return x | |
########################## | |
for r in sys.stdin: | |
# r is some text containing 1 or more urls | |
for x in urlRE.findall(r.strip()): | |
print unroll(x[0]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment