class Adfly:
def __init__(self):
self.unshorten = UnshortenIt()
self.session = requests.session()
def unshorten_adfly_url(self, adfly_url: str):
spinner = Halo(text='Grabbing url...', spinner='dots')
spinner.start(text='Getting url...')
current_link = adfly_url
while True:
try:
url = self.unshorten.unshorten(uri=current_link)
current_link = url
if 'adfly' in url:
pass
else:
request = self.session.get(url=url)
soup = BeautifulSoup(request.text, 'html.parser')
if 'redirecting' in request.url:
current_link = soup.find_all('p')[2].text.replace('You will be visiting: ', '')
spinner.succeed(text='Successfully retrieved url!')
return current_link
except (InvalidURL, MissingSchema, ConnectionError, NotFound, UnshortenFailed) as exception:
spinner.fail(text=f'Error: {exception}')
return
def button(update,context):
query=update.callback_query
query.answer()
a=query.data
if a=="unshort":
unshortener=UnshortenIt()
uri=unshortener.unshorten(link)
query.edit_message_text(text="Unshorted url 👇🏼 : \n"+str(uri))
if a=="short":
response=s.bitly.short(link)
query.edit_message_text("Shorted url 👇🏼:\n"+str(response))
def inlinequery(update,context):
query = update.inline_query.query
###for short links#######
shortlink=s.bitly.short(query)
#####for unshort link####$#$
unshortener=UnshortenIt()
unshortlink=unshortener.unshorten(query)
results=[InlineQueryResultArticle(id=uuid4(),title="short",input_message_content=InputTextMessageContent(shortlink), description="Click to shorten the link"),
InlineQueryResultArticle(id=uuid4(),title="unshort",input_message_content=InputTextMessageContent(unshortlink), description="Click to unshort the link")]
update.inline_query.answer(results)
def url_unshortener(short_link):
"""
Расшифровка коротких ссылок
:param shor_link: короткая ссылка, которую нужно расшифровать.
:return: возвращает оригинульную ссылку.
Умеет расшифровывать 300+ сервисов-укорачивателей
"""
unshortener = UnshortenIt()
original_url = unshortener.unshorten(short_link)
return original_url
def deal_with_error():
new_ids = []
unshortener = UnshortenIt(default_timeout=20)
for line in tqdm(open("data/ira-urls-plus-1.json")):
d = json.loads(line.strip())
if "error" in d and d["error"] and d["hostname"] not in ["blackmattersus.com", "blacktolive.org"]:
try:
url = unshortener.unshorten(d["url"])
d["final_url"] = url
d['hostname'] = get_hostname_from_url(url)
del d["error"]
except Exception as e:
print(d["url"])
new_ids.append(d)
write2json(new_ids)
def home(request):
global data
data = ''
global title
title = ""
global uri
uri = ''
global meta
meta = ''
global get_domain
get_domain = ''
if request.method == 'POST':
form = UrlForm(request.POST)
if form.is_valid():
data = form.cleaned_data.get('url')
form.save()
form = UrlForm()
unshortener = UnshortenIt()
uri = unshortener.unshorten(data)
article = Goose().extract(uri)
title = article.title
meta = article.meta_description
domain = tldextract.extract(uri)
get_domain = domain.domain + '.' + domain.suffix
else:
form = UrlForm()
return render(
request, 'unmask/home.html', {
'form': form,
'ori_link': uri,
'title': title,
'meta': meta,
'domain': get_domain,
'data': data
})
def get_tweets(username):
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)
#set count to however many tweets you want
number_of_tweets = 500
#get tweets
for tweet in tweepy.Cursor(api.user_timeline,
screen_name=username).items(number_of_tweets):
#create array of tweet information: username, tweet id, date/time, text
if ("https://t.co/" in tweet.text):
index = (tweet.text).index('https://t.co')
t_url = (tweet.text)[index:(index + 24)]
unshortener = UnshortenIt()
url = unshortener.unshorten(t_url)
if ("open.spotify" in url):
print(url)
def task(_ids):
print("{} task starts ... ".format(os.getpid()), len(_ids))
unshortener = UnshortenIt(default_timeout=20)
new_ids = []
for d in tqdm(_ids):
# if "error" in d and d["error"]:
# print(d)
try:
d["error"] = False
if d["short"]:
# print(d)
url = unshortener.unshorten(d["url"])
d["final_url"] = url
d['hostname'] = get_hostname_from_url(url)
except Exception as e:
# print(e); traceback.print_exc(sys.stdout)
d['error'] = True
new_ids.append(d)
write2json(new_ids)
return new_ids
import csv
import re
from unshortenit import UnshortenIt
unshortener = UnshortenIt()
final = open('locations_coordinates.csv', mode='w')
csv_writer = csv.writer(final, dialect='excel')
with open('locations_link.csv') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
for row in csv_reader:
url = row[1]
if len(url) == 31 or len(url) == 32:
url = unshortener.unshorten(row[1])
if re.search('@(\-?[0-9]+\.[0-9]+),(\-?[0-9]+\.[0-9]+)', url,
re.DOTALL):
location = re.search('@(\-?[0-9]+\.[0-9]+),(\-?[0-9]+\.[0-9]+)',
url, re.DOTALL)
latitude = location.groups()[0]
longitude = location.groups()[1]
csv_writer.writerow([row[0], latitude, longitude])
print(
f'Location {row[0]}: latitude={latitude} and longitude = {longitude}'
)
elif re.search('q=(\-?[0-9]+\.[0-9]+),(\-?[0-9]+\.[0-9]+)', url,
re.DOTALL):
location = re.search('q=(\-?[0-9]+\.[0-9]+),(\-?[0-9]+\.[0-9]+)',
url, re.DOTALL)
latitude = location.groups()[0]
longitude = location.groups()[1]
csv_writer.writerow([row[0], latitude, longitude])
print(
"""Code snippets vol-59
292-Unshorten a URL
Download all snippets so far:
https://wp.me/Pa5TU8-1yg
Blog: stevepython.wordpress.com
Requirements:
pip3 install unshortenit
https://stackoverflow.com/questions/4201062/how-can-i-unshorten-a-url
"""
from unshortenit import UnshortenIt
unsh = UnshortenIt()
uri = unsh.unshorten('https://wp.me/Pa5TU8-2yD')
print(uri)
def cli(module, url, follow_nested):
unshortener = UnshortenIt()
print(unshortener.unshorten(url, module, unshorten_nested=follow_nested))
def carga(page):
global configuracion
global terminamos
browser = webdriver.Chrome()
browser2 = webdriver.Chrome()
web = 'https://3d-load.net/page/' + str(page) + '/'
print(' \n Accediendo a: ' + web + '\n' '')
browser.get(web)
assert '3DLOAD' in browser.title
# sleeper(5)
for a in browser.find_elements_by_class_name('link'):
links = a.get_attribute('href')
print(links)
browser2.get(links)
# browser2.minimize_window()
# browser.minimize_window()
if configuracion['Sitio.De.Descarga']['mega'] == 'si':
for b in browser2.find_elements_by_class_name(
'shortcode.button.red.large'):
alinks = b.get_attribute('href')
# print(alinks + '\n')
unshortener = UnshortenIt()
uri = unshortener.unshorten(alinks)
print(uri + '\n')
igual = uri.find("=")
total = len(uri)
file_id = uri[igual + 1:total]
# print("Descargando: ", file_id +'\n\n')
o = urlparse(links)
# print(o)
# print (o.path)
oPath = o.path
# print("len")
# print(len(oPath))
oPath = oPath[:len(oPath) - 1]
# print(oPath)
a = 0
while a != -1:
a = oPath.find("/")
oPath = oPath[a + 1:len(oPath)]
ocat = o.path[1:len(o.path)]
# print(ocat)
a = ocat.find("/")
# print(a)
file_name = ocat[a + 1:len(ocat) - 1]
ocat = ocat[0:a]
# print(ocat)
# print(file_name)
# print(file_id)
listado = open('listado.ini', 'r')
lista = listado.readlines()
listado.close()
# print(lista)
# print(file_name)
if file_name + '\n' not in lista:
print(" \n Descargando fichero: " + file_name + '\n')
os.system('mega-get --ignore-quota-warn ' + file_id +
' ./download/' + file_name)
print('\nDescomprimiendo en el directorio \'extract\'')
# title2 = oPath.replace('-',' ')
# title2 = title2.title()
# print(title2)
if os.path.isfile(file_name):
listado = open("listado.ini",
mode="a",
encoding="utf-8")
listado.write(file_name + '\n')
listado.close()
os.system('unrar x -u "./download/"' + file_name +
' ./extract/')
print('\nBorrando el archivo \'.rar\'')
# borra = './download/' + title2 + '.rar'
# os.remove (borra)
try:
os.remove('./download/' + file_name)
except OSError as e:
print(e)
else:
print("File is deleted successfully")
with open('3d-load.cfg', 'w') as archivoconfig:
configuracion.write(archivoconfig)
else:
print('si está')
ultconf = configuracion['Ult.Descargado']['ult.descargado']
if ultconf == file_name:
terminamos = 1
break
browser.close()
browser2.close()
def cli(module, url, follow_nested):
unshortener = UnshortenIt()
print(unshortener.unshorten(url, module, unshorten_nested=follow_nested))