def test_adfly(self):
self.assertEqual(unshortenit.unshorten_only('http://adf.ly/WzXu2'),
('http://www39.zippyshare.com/v/69303767/file.html', 200))
self.assertEqual(unshortenit.unshorten_only('http://adf.ly/1icWR'),
('http://adf.ly/1icWR', 'No ysmm variable found'))
self.assertEqual(unshortenit.unshorten_only('http://links.devitrianto.com/yy', type='adfly'),
('http://www.sendspace.com/file/a2z6ji', 200))
# File has been DMCA removed, so if we allow the 301 HEAD request to resolve, it returns a different URL.
# Also - sidenote: Pirated files in your unit tests? Really?
self.assertEqual(unshortenit.unshorten_only('http://adf.ly/bJ8mm'),
('http://www.mediafire.com/download/cixal2y0auya19m/com.ratrodstudio.skateparty2.zip', 200))
def test_adfly(self):
self.assertEqual(
unshortenit.unshorten_only('http://adf.ly/WzXu2'),
('http://www39.zippyshare.com/v/69303767/file.html', 200))
self.assertEqual(unshortenit.unshorten_only('http://adf.ly/1icWR'),
('http://adf.ly/1icWR', 'No ysmm variable found'))
self.assertEqual(
unshortenit.unshorten_only('http://links.devitrianto.com/yy',
type='adfly'),
('http://www.sendspace.com/file/a2z6ji', 200))
# File has been DMCA removed, so if we allow the 301 HEAD request to resolve, it returns a different URL.
# Also - sidenote: Pirated files in your unit tests? Really?
self.assertEqual(unshortenit.unshorten_only('http://adf.ly/bJ8mm'), (
'http://www.mediafire.com/download/cixal2y0auya19m/com.ratrodstudio.skateparty2.zip',
200))
def cleanUrl(url):
# F*****g tumblr redirects.
if url.startswith("https://www.tumblr.com/login"):
return None
url, status = unshortenit.unshorten_only(url)
#assert (status == 200)
return url
def cleanUrl(url):
# F*****g tumblr redirects.
if url.startswith("https://www.tumblr.com/login"):
return None
url, status = unshortenit.unshorten_only(url)
#assert (status == 200)
return url
#!/bin/python
# -*- coding: utf-8 -*-
import requests
import json
import sys
from bs4 import BeautifulSoup
import unshortenit
# Carregando JSON
with open("links.json") as infile:
data = json.load(infile)
for post in data:
soup = BeautifulSoup(requests.get(post['url']).text, "lxml")
for post_body in soup.find_all("div", class_="post-body"):
# Pegando link de download e desencurtando (se necessário)
for anchor in post_body.find_all('a', href=True):
if ("adf.ly" in anchor['href']):
post["download_link"] = unshortenit.unshorten_only(anchor['href'])[0]
break
elif (("cloud.mail.ru" in anchor['href']) or ("mega.nz" in anchor['href'])):
post["download_link"] = anchor['href']
break
# Printando estado atual das coisas
print(json.dumps(post, sort_keys=True, indent=4))
with open('downloads.json', 'w') as fp:
json.dump(data, fp)