diff options
Diffstat (limited to 'Lib/urllib')
| -rw-r--r-- | Lib/urllib/parse.py | 161 | ||||
| -rw-r--r-- | Lib/urllib/request.py | 15 | ||||
| -rw-r--r-- | Lib/urllib/robotparser.py | 2 |
3 files changed, 90 insertions, 88 deletions
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index d368331..6012d35 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -34,7 +34,9 @@ import collections __all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag", "urlsplit", "urlunsplit", "urlencode", "parse_qs", "parse_qsl", "quote", "quote_plus", "quote_from_bytes", - "unquote", "unquote_plus", "unquote_to_bytes"] + "unquote", "unquote_plus", "unquote_to_bytes", + "DefragResult", "ParseResult", "SplitResult", + "DefragResultBytes", "ParseResultBytes", "SplitResultBytes"] # A classification of schemes ('' means apply by default) uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap', @@ -409,11 +411,13 @@ def urljoin(base, url, allow_fragments=True): return url if not url: return base + base, url, _coerce_result = _coerce_args(base, url) bscheme, bnetloc, bpath, bparams, bquery, bfragment = \ urlparse(base, '', allow_fragments) scheme, netloc, path, params, query, fragment = \ urlparse(url, bscheme, allow_fragments) + if scheme != bscheme or scheme not in uses_relative: return _coerce_result(url) if scheme in uses_netloc: @@ -421,9 +425,7 @@ def urljoin(base, url, allow_fragments=True): return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) netloc = bnetloc - if path[:1] == '/': - return _coerce_result(urlunparse((scheme, netloc, path, - params, query, fragment))) + if not path and not params: path = bpath params = bparams @@ -431,29 +433,46 @@ def urljoin(base, url, allow_fragments=True): query = bquery return _coerce_result(urlunparse((scheme, netloc, path, params, query, fragment))) - segments = bpath.split('/')[:-1] + path.split('/') - # XXX The stuff below is bogus in various ways... - if segments[-1] == '.': - segments[-1] = '' - while '.' in segments: - segments.remove('.') - while 1: - i = 1 - n = len(segments) - 1 - while i < n: - if (segments[i] == '..' - and segments[i-1] not in ('', '..')): - del segments[i-1:i+1] - break - i = i+1 + + base_parts = bpath.split('/') + if base_parts[-1] != '': + # the last item is not a directory, so will not be taken into account + # in resolving the relative path + del base_parts[-1] + + # for rfc3986, ignore all base path should the first character be root. + if path[:1] == '/': + segments = path.split('/') + else: + segments = base_parts + path.split('/') + # filter out elements that would cause redundant slashes on re-joining + # the resolved_path + segments = segments[0:1] + [ + s for s in segments[1:-1] if len(s) > 0] + segments[-1:] + + resolved_path = [] + + for seg in segments: + if seg == '..': + try: + resolved_path.pop() + except IndexError: + # ignore any .. segments that would otherwise cause an IndexError + # when popped from resolved_path if resolving for rfc3986 + pass + elif seg == '.': + continue else: - break - if segments == ['', '..']: - segments[-1] = '' - elif len(segments) >= 2 and segments[-1] == '..': - segments[-2:] = [''] - return _coerce_result(urlunparse((scheme, netloc, '/'.join(segments), - params, query, fragment))) + resolved_path.append(seg) + + if segments[-1] in ('.', '..'): + # do some post-processing here. if the last segment was a relative dir, + # then we need to append the trailing '/' + resolved_path.append('') + + return _coerce_result(urlunparse((scheme, netloc, '/'.join( + resolved_path) or '/', params, query, fragment))) + def urldefrag(url): """Removes any existing fragment from URL. @@ -641,7 +660,7 @@ class Quoter(collections.defaultdict): def __repr__(self): # Without this, will just display as a defaultdict - return "<Quoter %r>" % dict(self) + return "<%s %r>" % (self.__class__.__name__, dict(self)) def __missing__(self, b): # Handle a cache miss. Store quoted string in cache and return. @@ -852,12 +871,12 @@ def splittype(url): """splittype('type:opaquestring') --> 'type', 'opaquestring'.""" global _typeprog if _typeprog is None: - _typeprog = re.compile('^([^/:]+):') + _typeprog = re.compile('([^/:]+):(.*)', re.DOTALL) match = _typeprog.match(url) if match: - scheme = match.group(1) - return scheme.lower(), url[len(scheme) + 1:] + scheme, data = match.groups() + return scheme.lower(), data return None, url _hostprog = None @@ -865,38 +884,25 @@ def splithost(url): """splithost('//host[:port]/path') --> 'host[:port]', '/path'.""" global _hostprog if _hostprog is None: - _hostprog = re.compile('^//([^/?]*)(.*)$') + _hostprog = re.compile('//([^/?]*)(.*)', re.DOTALL) match = _hostprog.match(url) if match: - host_port = match.group(1) - path = match.group(2) - if path and not path.startswith('/'): + host_port, path = match.groups() + if path and path[0] != '/': path = '/' + path return host_port, path return None, url -_userprog = None def splituser(host): """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.""" - global _userprog - if _userprog is None: - _userprog = re.compile('^(.*)@(.*)$') + user, delim, host = host.rpartition('@') + return (user if delim else None), host - match = _userprog.match(host) - if match: return match.group(1, 2) - return None, host - -_passwdprog = None def splitpasswd(user): """splitpasswd('user:passwd') -> 'user', 'passwd'.""" - global _passwdprog - if _passwdprog is None: - _passwdprog = re.compile('^([^:]*):(.*)$',re.S) - - match = _passwdprog.match(user) - if match: return match.group(1, 2) - return user, None + user, delim, passwd = user.partition(':') + return user, (passwd if delim else None) # splittag('/path#tag') --> '/path', 'tag' _portprog = None @@ -904,7 +910,7 @@ def splitport(host): """splitport('host:port') --> 'host', 'port'.""" global _portprog if _portprog is None: - _portprog = re.compile('^(.*):([0-9]*)$') + _portprog = re.compile('(.*):([0-9]*)$', re.DOTALL) match = _portprog.match(host) if match: @@ -913,47 +919,34 @@ def splitport(host): return host, port return host, None -_nportprog = None def splitnport(host, defport=-1): """Split host and port, returning numeric port. Return given default port if no ':' found; defaults to -1. Return numerical port if a valid number are found after ':'. Return None if ':' but not a valid number.""" - global _nportprog - if _nportprog is None: - _nportprog = re.compile('^(.*):(.*)$') - - match = _nportprog.match(host) - if match: - host, port = match.group(1, 2) - if port: - try: - nport = int(port) - except ValueError: - nport = None - return host, nport + host, delim, port = host.rpartition(':') + if not delim: + host = port + elif port: + try: + nport = int(port) + except ValueError: + nport = None + return host, nport return host, defport -_queryprog = None def splitquery(url): """splitquery('/path?query') --> '/path', 'query'.""" - global _queryprog - if _queryprog is None: - _queryprog = re.compile('^(.*)\?([^?]*)$') - - match = _queryprog.match(url) - if match: return match.group(1, 2) + path, delim, query = url.rpartition('?') + if delim: + return path, query return url, None -_tagprog = None def splittag(url): """splittag('/path#tag') --> '/path', 'tag'.""" - global _tagprog - if _tagprog is None: - _tagprog = re.compile('^(.*)#([^#]*)$') - - match = _tagprog.match(url) - if match: return match.group(1, 2) + path, delim, tag = url.rpartition('#') + if delim: + return path, tag return url, None def splitattr(url): @@ -962,13 +955,7 @@ def splitattr(url): words = url.split(';') return words[0], words[1:] -_valueprog = None def splitvalue(attr): """splitvalue('attr=value') --> 'attr', 'value'.""" - global _valueprog - if _valueprog is None: - _valueprog = re.compile('^([^=]*)=(.*)$') - - match = _valueprog.match(attr) - if match: return match.group(1, 2) - return attr, None + attr, delim, value = attr.partition('=') + return attr, (value if delim else None) diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py index 5cf0cf2..2e436ec 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -916,6 +916,21 @@ class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): return response +class HTTPBasicPriorAuthHandler(HTTPBasicAuthHandler): + handler_order = 400 + + def http_request(self, req): + if not req.has_header('Authorization'): + user, passwd = self.passwd.find_user_password(None, req.host) + credentials = '{0}:{1}'.format(user, passwd).encode() + auth_str = base64.standard_b64encode(credentials).decode() + req.add_unredirected_header('Authorization', + 'Basic {}'.format(auth_str.strip())) + return req + + https_request = http_request + + # Return n random bytes. _randombytes = os.urandom diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py index 1d7b751..4fbb0cb 100644 --- a/Lib/urllib/robotparser.py +++ b/Lib/urllib/robotparser.py @@ -172,7 +172,7 @@ class RuleLine: return self.path == "*" or filename.startswith(self.path) def __str__(self): - return (self.allowance and "Allow" or "Disallow") + ": " + self.path + return ("Allow" if self.allowance else "Disallow") + ": " + self.path class Entry: |