def isresource(url, *args, **kwargs):
url = format.url(url)
kwargs.setdefault('allow_redirects', True)
kwargs.setdefault('verify', False)
r = requests.head(url, *args, **kwargs)
if 'content-disposition' in r.headers:
return True
mime = ""
content = r.headers.get('content-type')
if content:
mime, delemiter, charset = content.rpartition("charset=")
else:
from . import parse
name = parse.name(url)
root, ext = os.path.splitext(name)
if ext:
mime = parse.mime(name)
if 'html' not in mime:
return True
return False
def url_to_name(url, strict=False):
url = format.url(url)
url_p = urllib.parse.urlparse(url)
name = url_p.path.split('/')[-1]
if not name:
name = url_p.query.split('=', 1)[::-1][0].split('&', 1)[0]
if not name:
name = url_p.netloc.split('.', 1)[0]
return name.strip() if strict else format.name(name)
def name(url):
url = format.url(url)
up = urllib.parse.urlparse(url)
name = up.path.split('/')[-1]
if not name:
name = up.query.split('=', 1)[::-1][0].split('&', 1)[0]
if not name:
name = up.netloc.split('.', 1)[0]
return name.strip()
def isonline(url, *args, **kwargs):
online = True
url = format.url(url)
kwargs.setdefault('allow_redirects', True)
kwargs.setdefault('verify', False)
try:
requests.head(url, *args, **kwargs).raise_for_status()
except requests.TooManyRedirects:
online = True
except (requests.ConnectionError, requests.ConnectTimeout):
online = None
except requests.RequestException:
online = False
return online
def domain(url):
return tld.get_tld(format.url(url), fail_silently=True)
def isurl(url):
url = format.url(url)
try:
return validators.url(url)
except validators.ValidationFailure:
return False