SickGear/lib/feedparser/urls.py

131 lines
4.5 KiB
Python

from __future__ import absolute_import, unicode_literals
import re
try:
import urllib.parse as urlparse
except ImportError:
import urlparse as urlparse
from .html import _BaseHTMLProcessor
# If you want feedparser to allow all URL schemes, set this to ()
# List culled from Python's urlparse documentation at:
# http://docs.python.org/library/urlparse.html
# as well as from "URI scheme" at Wikipedia:
# https://secure.wikimedia.org/wikipedia/en/wiki/URI_scheme
# Many more will likely need to be added!
ACCEPTABLE_URI_SCHEMES = (
'file', 'ftp', 'gopher', 'h323', 'hdl', 'http', 'https', 'imap', 'magnet',
'mailto', 'mms', 'news', 'nntp', 'prospero', 'rsync', 'rtsp', 'rtspu',
'sftp', 'shttp', 'sip', 'sips', 'snews', 'svn', 'svn+ssh', 'telnet',
'wais',
# Additional common-but-unofficial schemes
'aim', 'callto', 'cvs', 'facetime', 'feed', 'git', 'gtalk', 'irc', 'ircs',
'irc6', 'itms', 'mms', 'msnim', 'skype', 'ssh', 'smb', 'svn', 'ymsg',
)
#ACCEPTABLE_URI_SCHEMES = ()
_urifixer = re.compile('^([A-Za-z][A-Za-z0-9+-.]*://)(/*)(.*?)')
def _urljoin(base, uri):
uri = _urifixer.sub(r'\1\3', uri)
try:
uri = urlparse.urljoin(base, uri)
except ValueError:
uri = ''
return uri
def _convert_to_idn(url):
"""Convert a URL to IDN notation"""
# this function should only be called with a unicode string
# strategy: if the host cannot be encoded in ascii, then
# it'll be necessary to encode it in idn form
parts = list(urlparse.urlsplit(url))
try:
parts[1].encode('ascii')
except UnicodeEncodeError:
# the url needs to be converted to idn notation
host = parts[1].rsplit(':', 1)
newhost = []
port = ''
if len(host) == 2:
port = host.pop()
for h in host[0].split('.'):
newhost.append(h.encode('idna').decode('utf-8'))
parts[1] = '.'.join(newhost)
if port:
parts[1] += ':' + port
return urlparse.urlunsplit(parts)
else:
return url
def _makeSafeAbsoluteURI(base, rel=None):
# bail if ACCEPTABLE_URI_SCHEMES is empty
if not ACCEPTABLE_URI_SCHEMES:
return _urljoin(base, rel or '')
if not base:
return rel or ''
if not rel:
try:
scheme = urlparse.urlparse(base)[0]
except ValueError:
return ''
if not scheme or scheme in ACCEPTABLE_URI_SCHEMES:
return base
return ''
uri = _urljoin(base, rel)
if uri.strip().split(':', 1)[0] not in ACCEPTABLE_URI_SCHEMES:
return ''
return uri
class _RelativeURIResolver(_BaseHTMLProcessor):
relative_uris = set([('a', 'href'),
('applet', 'codebase'),
('area', 'href'),
('audio', 'src'),
('blockquote', 'cite'),
('body', 'background'),
('del', 'cite'),
('form', 'action'),
('frame', 'longdesc'),
('frame', 'src'),
('iframe', 'longdesc'),
('iframe', 'src'),
('head', 'profile'),
('img', 'longdesc'),
('img', 'src'),
('img', 'usemap'),
('input', 'src'),
('input', 'usemap'),
('ins', 'cite'),
('link', 'href'),
('object', 'classid'),
('object', 'codebase'),
('object', 'data'),
('object', 'usemap'),
('q', 'cite'),
('script', 'src'),
('source', 'src'),
('video', 'poster'),
('video', 'src')])
def __init__(self, baseuri, encoding, _type):
_BaseHTMLProcessor.__init__(self, encoding, _type)
self.baseuri = baseuri
def resolveURI(self, uri):
return _makeSafeAbsoluteURI(self.baseuri, uri.strip())
def unknown_starttag(self, tag, attrs):
attrs = self.normalize_attrs(attrs)
attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs]
_BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
def _resolveRelativeURIs(htmlSource, baseURI, encoding, _type):
# if not _SGML_AVAILABLE:
# return htmlSource
p = _RelativeURIResolver(baseURI, encoding, _type)
p.feed(htmlSource)
return p.output()