diff options
Diffstat (limited to 'Lib/urllib')
| -rw-r--r-- | Lib/urllib/__init__.py | 0 | ||||
| -rw-r--r-- | Lib/urllib/error.py | 59 | ||||
| -rw-r--r-- | Lib/urllib/parse.py | 630 | ||||
| -rw-r--r-- | Lib/urllib/request.py | 2295 | ||||
| -rw-r--r-- | Lib/urllib/response.py | 83 | ||||
| -rw-r--r-- | Lib/urllib/robotparser.py | 191 |
6 files changed, 3258 insertions, 0 deletions
diff --git a/Lib/urllib/__init__.py b/Lib/urllib/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/Lib/urllib/__init__.py diff --git a/Lib/urllib/error.py b/Lib/urllib/error.py new file mode 100644 index 0000000..300c3fe --- /dev/null +++ b/Lib/urllib/error.py @@ -0,0 +1,59 @@ +"""Exception classes raised by urllib. + +The base exception class is URLError, which inherits from IOError. It +doesn't define any behavior of its own, but is the base class for all +exceptions defined in this package. + +HTTPError is an exception class that is also a valid HTTP response +instance. It behaves this way because HTTP protocol errors are valid +responses, with a status code, headers, and a body. In some contexts, +an application may want to handle an exception like a regular +response. +""" + +import urllib.response + +# do these error classes make sense? +# make sure all of the IOError stuff is overridden. we just want to be +# subtypes. + +class URLError(IOError): + # URLError is a sub-type of IOError, but it doesn't share any of + # the implementation. need to override __init__ and __str__. + # It sets self.args for compatibility with other EnvironmentError + # subclasses, but args doesn't have the typical format with errno in + # slot 0 and strerror in slot 1. This may be better than nothing. + def __init__(self, reason, filename=None): + self.args = reason, + self.reason = reason + if filename is not None: + self.filename = filename + + def __str__(self): + return '<urlopen error %s>' % self.reason + +class HTTPError(URLError, urllib.response.addinfourl): + """Raised when HTTP error occurs, but also acts like non-error return""" + __super_init = urllib.response.addinfourl.__init__ + + def __init__(self, url, code, msg, hdrs, fp): + self.code = code + self.msg = msg + self.hdrs = hdrs + self.fp = fp + self.filename = url + # The addinfourl classes depend on fp being a valid file + # object. In some cases, the HTTPError may not have a valid + # file object. If this happens, the simplest workaround is to + # not initialize the base classes. + if fp is not None: + self.__super_init(fp, hdrs, url, code) + + def __str__(self): + return 'HTTP Error %s: %s' % (self.code, self.msg) + +# exception raised when downloaded size does not match content-length +class ContentTooShortError(URLError): + def __init__(self, message, content): + URLError.__init__(self, message) + self.content = content diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py new file mode 100644 index 0000000..71cc369 --- /dev/null +++ b/Lib/urllib/parse.py @@ -0,0 +1,630 @@ +"""Parse (absolute and relative) URLs. + +See RFC 1808: "Relative Uniform Resource Locators", by R. Fielding, +UC Irvine, June 1995. +""" + +__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag", + "urlsplit", "urlunsplit"] + +# A classification of schemes ('' means apply by default) +uses_relative = ['ftp', 'http', 'gopher', 'nntp', 'imap', + 'wais', 'file', 'https', 'shttp', 'mms', + 'prospero', 'rtsp', 'rtspu', '', 'sftp'] +uses_netloc = ['ftp', 'http', 'gopher', 'nntp', 'telnet', + 'imap', 'wais', 'file', 'mms', 'https', 'shttp', + 'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '', + 'svn', 'svn+ssh', 'sftp'] +non_hierarchical = ['gopher', 'hdl', 'mailto', 'news', + 'telnet', 'wais', 'imap', 'snews', 'sip', 'sips'] +uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap', + 'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips', + 'mms', '', 'sftp'] +uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms', + 'gopher', 'rtsp', 'rtspu', 'sip', 'sips', ''] +uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news', + 'nntp', 'wais', 'https', 'shttp', 'snews', + 'file', 'prospero', ''] + +# Characters valid in scheme names +scheme_chars = ('abcdefghijklmnopqrstuvwxyz' + 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' + '0123456789' + '+-.') + +MAX_CACHE_SIZE = 20 +_parse_cache = {} + +def clear_cache(): + """Clear the parse cache.""" + _parse_cache.clear() + + +class ResultMixin(object): + """Shared methods for the parsed result objects.""" + + @property + def username(self): + netloc = self.netloc + if "@" in netloc: + userinfo = netloc.rsplit("@", 1)[0] + if ":" in userinfo: + userinfo = userinfo.split(":", 1)[0] + return userinfo + return None + + @property + def password(self): + netloc = self.netloc + if "@" in netloc: + userinfo = netloc.rsplit("@", 1)[0] + if ":" in userinfo: + return userinfo.split(":", 1)[1] + return None + + @property + def hostname(self): + netloc = self.netloc + if "@" in netloc: + netloc = netloc.rsplit("@", 1)[1] + if ":" in netloc: + netloc = netloc.split(":", 1)[0] + return netloc.lower() or None + + @property + def port(self): + netloc = self.netloc + if "@" in netloc: + netloc = netloc.rsplit("@", 1)[1] + if ":" in netloc: + port = netloc.split(":", 1)[1] + return int(port, 10) + return None + +from collections import namedtuple + +class SplitResult(namedtuple('SplitResult', 'scheme netloc path query fragment'), ResultMixin): + + __slots__ = () + + def geturl(self): + return urlunsplit(self) + + +class ParseResult(namedtuple('ParseResult', 'scheme netloc path params query fragment'), ResultMixin): + + __slots__ = () + + def geturl(self): + return urlunparse(self) + + +def urlparse(url, scheme='', allow_fragments=True): + """Parse a URL into 6 components: + <scheme>://<netloc>/<path>;<params>?<query>#<fragment> + Return a 6-tuple: (scheme, netloc, path, params, query, fragment). + Note that we don't break the components up in smaller bits + (e.g. netloc is a single string) and we don't expand % escapes.""" + tuple = urlsplit(url, scheme, allow_fragments) + scheme, netloc, url, query, fragment = tuple + if scheme in uses_params and ';' in url: + url, params = _splitparams(url) + else: + params = '' + return ParseResult(scheme, netloc, url, params, query, fragment) + +def _splitparams(url): + if '/' in url: + i = url.find(';', url.rfind('/')) + if i < 0: + return url, '' + else: + i = url.find(';') + return url[:i], url[i+1:] + +def _splitnetloc(url, start=0): + delim = len(url) # position of end of domain part of url, default is end + for c in '/?#': # look for delimiters; the order is NOT important + wdelim = url.find(c, start) # find first of this delim + if wdelim >= 0: # if found + delim = min(delim, wdelim) # use earliest delim position + return url[start:delim], url[delim:] # return (domain, rest) + +def urlsplit(url, scheme='', allow_fragments=True): + """Parse a URL into 5 components: + <scheme>://<netloc>/<path>?<query>#<fragment> + Return a 5-tuple: (scheme, netloc, path, query, fragment). + Note that we don't break the components up in smaller bits + (e.g. netloc is a single string) and we don't expand % escapes.""" + allow_fragments = bool(allow_fragments) + key = url, scheme, allow_fragments, type(url), type(scheme) + cached = _parse_cache.get(key, None) + if cached: + return cached + if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth + clear_cache() + netloc = query = fragment = '' + i = url.find(':') + if i > 0: + if url[:i] == 'http': # optimize the common case + scheme = url[:i].lower() + url = url[i+1:] + if url[:2] == '//': + netloc, url = _splitnetloc(url, 2) + if allow_fragments and '#' in url: + url, fragment = url.split('#', 1) + if '?' in url: + url, query = url.split('?', 1) + v = SplitResult(scheme, netloc, url, query, fragment) + _parse_cache[key] = v + return v + for c in url[:i]: + if c not in scheme_chars: + break + else: + scheme, url = url[:i].lower(), url[i+1:] + if scheme in uses_netloc and url[:2] == '//': + netloc, url = _splitnetloc(url, 2) + if allow_fragments and scheme in uses_fragment and '#' in url: + url, fragment = url.split('#', 1) + if scheme in uses_query and '?' in url: + url, query = url.split('?', 1) + v = SplitResult(scheme, netloc, url, query, fragment) + _parse_cache[key] = v + return v + +def urlunparse(components): + """Put a parsed URL back together again. This may result in a + slightly different, but equivalent URL, if the URL that was parsed + originally had redundant delimiters, e.g. a ? with an empty query + (the draft states that these are equivalent).""" + scheme, netloc, url, params, query, fragment = components + if params: + url = "%s;%s" % (url, params) + return urlunsplit((scheme, netloc, url, query, fragment)) + +def urlunsplit(components): + scheme, netloc, url, query, fragment = components + if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'): + if url and url[:1] != '/': url = '/' + url + url = '//' + (netloc or '') + url + if scheme: + url = scheme + ':' + url + if query: + url = url + '?' + query + if fragment: + url = url + '#' + fragment + return url + +def urljoin(base, url, allow_fragments=True): + """Join a base URL and a possibly relative URL to form an absolute + interpretation of the latter.""" + if not base: + return url + if not url: + return base + 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 url + if scheme in uses_netloc: + if netloc: + return urlunparse((scheme, netloc, path, + params, query, fragment)) + netloc = bnetloc + if path[:1] == '/': + return urlunparse((scheme, netloc, path, + params, query, fragment)) + if not (path or params or query): + return urlunparse((scheme, netloc, bpath, + bparams, bquery, 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 + else: + break + if segments == ['', '..']: + segments[-1] = '' + elif len(segments) >= 2 and segments[-1] == '..': + segments[-2:] = [''] + return urlunparse((scheme, netloc, '/'.join(segments), + params, query, fragment)) + +def urldefrag(url): + """Removes any existing fragment from URL. + + Returns a tuple of the defragmented URL and the fragment. If + the URL contained no fragments, the second element is the + empty string. + """ + if '#' in url: + s, n, p, a, q, frag = urlparse(url) + defrag = urlunparse((s, n, p, a, q, '')) + return defrag, frag + else: + return url, '' + + +_hextochr = dict(('%02x' % i, chr(i)) for i in range(256)) +_hextochr.update(('%02X' % i, chr(i)) for i in range(256)) + +def unquote(s): + """unquote('abc%20def') -> 'abc def'.""" + res = s.split('%') + for i in range(1, len(res)): + item = res[i] + try: + res[i] = _hextochr[item[:2]] + item[2:] + except KeyError: + res[i] = '%' + item + except UnicodeDecodeError: + res[i] = chr(int(item[:2], 16)) + item[2:] + return "".join(res) + +def unquote_plus(s): + """unquote('%7e/abc+def') -> '~/abc def'""" + s = s.replace('+', ' ') + return unquote(s) + +always_safe = ('ABCDEFGHIJKLMNOPQRSTUVWXYZ' + 'abcdefghijklmnopqrstuvwxyz' + '0123456789' '_.-') +_safe_quoters= {} + +class Quoter: + def __init__(self, safe): + self.cache = {} + self.safe = safe + always_safe + + def __call__(self, c): + try: + return self.cache[c] + except KeyError: + if ord(c) < 256: + res = (c in self.safe) and c or ('%%%02X' % ord(c)) + self.cache[c] = res + return res + else: + return "".join(['%%%02X' % i for i in c.encode("utf-8")]) + +def quote(s, safe = '/'): + """quote('abc def') -> 'abc%20def' + + Each part of a URL, e.g. the path info, the query, etc., has a + different set of reserved characters that must be quoted. + + RFC 2396 Uniform Resource Identifiers (URI): Generic Syntax lists + the following reserved characters. + + reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | + "$" | "," + + Each of these characters is reserved in some component of a URL, + but not necessarily in all of them. + + By default, the quote function is intended for quoting the path + section of a URL. Thus, it will not encode '/'. This character + is reserved, but in typical usage the quote function is being + called on a path where the existing slash characters are used as + reserved characters. + """ + cachekey = (safe, always_safe) + try: + quoter = _safe_quoters[cachekey] + except KeyError: + quoter = Quoter(safe) + _safe_quoters[cachekey] = quoter + res = map(quoter, s) + return ''.join(res) + +def quote_plus(s, safe = ''): + """Quote the query fragment of a URL; replacing ' ' with '+'""" + if ' ' in s: + s = quote(s, safe + ' ') + return s.replace(' ', '+') + return quote(s, safe) + +def urlencode(query,doseq=0): + """Encode a sequence of two-element tuples or dictionary into a URL query string. + + If any values in the query arg are sequences and doseq is true, each + sequence element is converted to a separate parameter. + + If the query arg is a sequence of two-element tuples, the order of the + parameters in the output will match the order of parameters in the + input. + """ + + if hasattr(query,"items"): + # mapping objects + query = query.items() + else: + # it's a bother at times that strings and string-like objects are + # sequences... + try: + # non-sequence items should not work with len() + # non-empty strings will fail this + if len(query) and not isinstance(query[0], tuple): + raise TypeError + # zero-length sequences of all types will get here and succeed, + # but that's a minor nit - since the original implementation + # allowed empty dicts that type of behavior probably should be + # preserved for consistency + except TypeError: + ty,va,tb = sys.exc_info() + raise TypeError("not a valid non-string sequence or mapping object").with_traceback(tb) + + l = [] + if not doseq: + # preserve old behavior + for k, v in query: + k = quote_plus(str(k)) + v = quote_plus(str(v)) + l.append(k + '=' + v) + else: + for k, v in query: + k = quote_plus(str(k)) + if isinstance(v, str): + v = quote_plus(v) + l.append(k + '=' + v) + elif isinstance(v, str): + # is there a reasonable way to convert to ASCII? + # encode generates a string, but "replace" or "ignore" + # lose information and "strict" can raise UnicodeError + v = quote_plus(v.encode("ASCII","replace")) + l.append(k + '=' + v) + else: + try: + # is this a sufficient test for sequence-ness? + x = len(v) + except TypeError: + # not a sequence + v = quote_plus(str(v)) + l.append(k + '=' + v) + else: + # loop over the sequence + for elt in v: + l.append(k + '=' + quote_plus(str(elt))) + return '&'.join(l) + +# Utilities to parse URLs (most of these return None for missing parts): +# unwrap('<URL:type://host/path>') --> 'type://host/path' +# splittype('type:opaquestring') --> 'type', 'opaquestring' +# splithost('//host[:port]/path') --> 'host[:port]', '/path' +# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]' +# splitpasswd('user:passwd') -> 'user', 'passwd' +# splitport('host:port') --> 'host', 'port' +# splitquery('/path?query') --> '/path', 'query' +# splittag('/path#tag') --> '/path', 'tag' +# splitattr('/path;attr1=value1;attr2=value2;...') -> +# '/path', ['attr1=value1', 'attr2=value2', ...] +# splitvalue('attr=value') --> 'attr', 'value' +# urllib.parse.unquote('abc%20def') -> 'abc def' +# quote('abc def') -> 'abc%20def') + +def toBytes(url): + """toBytes(u"URL") --> 'URL'.""" + # Most URL schemes require ASCII. If that changes, the conversion + # can be relaxed. + # XXX get rid of toBytes() + if isinstance(url, str): + try: + url = url.encode("ASCII").decode() + except UnicodeError: + raise UnicodeError("URL " + repr(url) + + " contains non-ASCII characters") + return url + +def unwrap(url): + """unwrap('<URL:type://host/path>') --> 'type://host/path'.""" + url = str(url).strip() + if url[:1] == '<' and url[-1:] == '>': + url = url[1:-1].strip() + if url[:4] == 'URL:': url = url[4:].strip() + return url + +_typeprog = None +def splittype(url): + """splittype('type:opaquestring') --> 'type', 'opaquestring'.""" + global _typeprog + if _typeprog is None: + import re + _typeprog = re.compile('^([^/:]+):') + + match = _typeprog.match(url) + if match: + scheme = match.group(1) + return scheme.lower(), url[len(scheme) + 1:] + return None, url + +_hostprog = None +def splithost(url): + """splithost('//host[:port]/path') --> 'host[:port]', '/path'.""" + global _hostprog + if _hostprog is None: + import re + _hostprog = re.compile('^//([^/?]*)(.*)$') + + match = _hostprog.match(url) + if match: return match.group(1, 2) + return None, url + +_userprog = None +def splituser(host): + """splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'.""" + global _userprog + if _userprog is None: + import re + _userprog = re.compile('^(.*)@(.*)$') + + match = _userprog.match(host) + if match: return map(unquote, match.group(1, 2)) + return None, host + +_passwdprog = None +def splitpasswd(user): + """splitpasswd('user:passwd') -> 'user', 'passwd'.""" + global _passwdprog + if _passwdprog is None: + import re + _passwdprog = re.compile('^([^:]*):(.*)$') + + match = _passwdprog.match(user) + if match: return match.group(1, 2) + return user, None + +# splittag('/path#tag') --> '/path', 'tag' +_portprog = None +def splitport(host): + """splitport('host:port') --> 'host', 'port'.""" + global _portprog + if _portprog is None: + import re + _portprog = re.compile('^(.*):([0-9]+)$') + + match = _portprog.match(host) + if match: return match.group(1, 2) + return host, None + +_nportprog = None +def splitnport(host, defport=-1): + """Split host and port, returning numeric port. + Return given default port if no ':' found; defaults to -1. + Return numerical port if a valid number are found after ':'. + Return None if ':' but not a valid number.""" + global _nportprog + if _nportprog is None: + import re + _nportprog = re.compile('^(.*):(.*)$') + + match = _nportprog.match(host) + if match: + host, port = match.group(1, 2) + try: + if not port: raise ValueError("no digits") + 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: + import re + _queryprog = re.compile('^(.*)\?([^?]*)$') + + match = _queryprog.match(url) + if match: return match.group(1, 2) + return url, None + +_tagprog = None +def splittag(url): + """splittag('/path#tag') --> '/path', 'tag'.""" + global _tagprog + if _tagprog is None: + import re + _tagprog = re.compile('^(.*)#([^#]*)$') + + match = _tagprog.match(url) + if match: return match.group(1, 2) + return url, None + +def splitattr(url): + """splitattr('/path;attr1=value1;attr2=value2;...') -> + '/path', ['attr1=value1', 'attr2=value2', ...].""" + words = url.split(';') + return words[0], words[1:] + +_valueprog = None +def splitvalue(attr): + """splitvalue('attr=value') --> 'attr', 'value'.""" + global _valueprog + if _valueprog is None: + import re + _valueprog = re.compile('^([^=]*)=(.*)$') + + match = _valueprog.match(attr) + if match: return match.group(1, 2) + return attr, None + +test_input = """ + http://a/b/c/d + + g:h = <URL:g:h> + http:g = <URL:http://a/b/c/g> + http: = <URL:http://a/b/c/d> + g = <URL:http://a/b/c/g> + ./g = <URL:http://a/b/c/g> + g/ = <URL:http://a/b/c/g/> + /g = <URL:http://a/g> + //g = <URL:http://g> + ?y = <URL:http://a/b/c/d?y> + g?y = <URL:http://a/b/c/g?y> + g?y/./x = <URL:http://a/b/c/g?y/./x> + . = <URL:http://a/b/c/> + ./ = <URL:http://a/b/c/> + .. = <URL:http://a/b/> + ../ = <URL:http://a/b/> + ../g = <URL:http://a/b/g> + ../.. = <URL:http://a/> + ../../g = <URL:http://a/g> + ../../../g = <URL:http://a/../g> + ./../g = <URL:http://a/b/g> + ./g/. = <URL:http://a/b/c/g/> + /./g = <URL:http://a/./g> + g/./h = <URL:http://a/b/c/g/h> + g/../h = <URL:http://a/b/c/h> + http:g = <URL:http://a/b/c/g> + http: = <URL:http://a/b/c/d> + http:?y = <URL:http://a/b/c/d?y> + http:g?y = <URL:http://a/b/c/g?y> + http:g?y/./x = <URL:http://a/b/c/g?y/./x> +""" + +def test(): + import sys + base = '' + if sys.argv[1:]: + fn = sys.argv[1] + if fn == '-': + fp = sys.stdin + else: + fp = open(fn) + else: + from io import StringIO + fp = StringIO(test_input) + for line in fp: + words = line.split() + if not words: + continue + url = words[0] + parts = urlparse(url) + print('%-10s : %s' % (url, parts)) + abs = urljoin(base, url) + if not base: + base = abs + wrapped = '<URL:%s>' % abs + print('%-10s = %s' % (url, wrapped)) + if len(words) == 3 and words[1] == '=': + if wrapped != words[2]: + print('EXPECTED', words[2], '!!!!!!!!!!') + +if __name__ == '__main__': + test() diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py new file mode 100644 index 0000000..cd4729a --- /dev/null +++ b/Lib/urllib/request.py @@ -0,0 +1,2295 @@ +# Issues in merging urllib and urllib2: +# 1. They both define a function named urlopen() + +"""An extensible library for opening URLs using a variety of protocols + +The simplest way to use this module is to call the urlopen function, +which accepts a string containing a URL or a Request object (described +below). It opens the URL and returns the results as file-like +object; the returned object has some extra methods described below. + +The OpenerDirector manages a collection of Handler objects that do +all the actual work. Each Handler implements a particular protocol or +option. The OpenerDirector is a composite object that invokes the +Handlers needed to open the requested URL. For example, the +HTTPHandler performs HTTP GET and POST requests and deals with +non-error returns. The HTTPRedirectHandler automatically deals with +HTTP 301, 302, 303 and 307 redirect errors, and the HTTPDigestAuthHandler +deals with digest authentication. + +urlopen(url, data=None) -- Basic usage is the same as original +urllib. pass the url and optionally data to post to an HTTP URL, and +get a file-like object back. One difference is that you can also pass +a Request instance instead of URL. Raises a URLError (subclass of +IOError); for HTTP errors, raises an HTTPError, which can also be +treated as a valid response. + +build_opener -- Function that creates a new OpenerDirector instance. +Will install the default handlers. Accepts one or more Handlers as +arguments, either instances or Handler classes that it will +instantiate. If one of the argument is a subclass of the default +handler, the argument will be installed instead of the default. + +install_opener -- Installs a new opener as the default opener. + +objects of interest: +OpenerDirector -- + +Request -- An object that encapsulates the state of a request. The +state can be as simple as the URL. It can also include extra HTTP +headers, e.g. a User-Agent. + +BaseHandler -- + +internals: +BaseHandler and parent +_call_chain conventions + +Example usage: + +import urllib2 + +# set up authentication info +authinfo = urllib2.HTTPBasicAuthHandler() +authinfo.add_password(realm='PDQ Application', + uri='https://mahler:8092/site-updates.py', + user='klem', + passwd='geheim$parole') + +proxy_support = urllib2.ProxyHandler({"http" : "http://ahad-haam:3128"}) + +# build a new opener that adds authentication and caching FTP handlers +opener = urllib2.build_opener(proxy_support, authinfo, urllib2.CacheFTPHandler) + +# install it +urllib2.install_opener(opener) + +f = urllib2.urlopen('http://www.python.org/') +""" + +# XXX issues: +# If an authentication error handler that tries to perform +# authentication for some reason but fails, how should the error be +# signalled? The client needs to know the HTTP error code. But if +# the handler knows that the problem was, e.g., that it didn't know +# that hash algo that requested in the challenge, it would be good to +# pass that information along to the client, too. +# ftp errors aren't handled cleanly +# check digest against correct (i.e. non-apache) implementation + +# Possible extensions: +# complex proxies XXX not sure what exactly was meant by this +# abstract factory for opener + +import base64 +import email +import hashlib +import http.client +import io +import os +import posixpath +import random +import re +import socket +import sys +import time +import urllib.parse, urllib.error, urllib.response +import bisect + +from io import StringIO + +# check for SSL +try: + import ssl +except: + _have_ssl = False +else: + _have_ssl = True +assert _have_ssl + +# used in User-Agent header sent +__version__ = sys.version[:3] + +_opener = None +def urlopen(url, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT): + global _opener + if _opener is None: + _opener = build_opener() + return _opener.open(url, data, timeout) + +def install_opener(opener): + global _opener + _opener = opener + +# TODO(jhylton): Make this work with the same global opener. +_urlopener = None +def urlretrieve(url, filename=None, reporthook=None, data=None): + global _urlopener + if not _urlopener: + _urlopener = FancyURLopener() + return _urlopener.retrieve(url, filename, reporthook, data) + +def urlcleanup(): + if _urlopener: + _urlopener.cleanup() + global _opener + if _opener: + _opener = None + +# copied from cookielib.py +_cut_port_re = re.compile(r":\d+$") +def request_host(request): + """Return request-host, as defined by RFC 2965. + + Variation from RFC: returned value is lowercased, for convenient + comparison. + + """ + url = request.get_full_url() + host = urllib.parse.urlparse(url)[1] + if host == "": + host = request.get_header("Host", "") + + # remove port, if present + host = _cut_port_re.sub("", host, 1) + return host.lower() + +class Request: + + def __init__(self, url, data=None, headers={}, + origin_req_host=None, unverifiable=False): + # unwrap('<URL:type://host/path>') --> 'type://host/path' + self.__original = urllib.parse.unwrap(url) + self.type = None + # self.__r_type is what's left after doing the splittype + self.host = None + self.port = None + self.data = data + self.headers = {} + for key, value in headers.items(): + self.add_header(key, value) + self.unredirected_hdrs = {} + if origin_req_host is None: + origin_req_host = request_host(self) + self.origin_req_host = origin_req_host + self.unverifiable = unverifiable + + def __getattr__(self, attr): + # XXX this is a fallback mechanism to guard against these + # methods getting called in a non-standard order. this may be + # too complicated and/or unnecessary. + # XXX should the __r_XXX attributes be public? + if attr[:12] == '_Request__r_': + name = attr[12:] + if hasattr(Request, 'get_' + name): + getattr(self, 'get_' + name)() + return getattr(self, attr) + raise AttributeError(attr) + + def get_method(self): + if self.has_data(): + return "POST" + else: + return "GET" + + # XXX these helper methods are lame + + def add_data(self, data): + self.data = data + + def has_data(self): + return self.data is not None + + def get_data(self): + return self.data + + def get_full_url(self): + return self.__original + + def get_type(self): + if self.type is None: + self.type, self.__r_type = urllib.parse.splittype(self.__original) + if self.type is None: + raise ValueError("unknown url type: %s" % self.__original) + return self.type + + def get_host(self): + if self.host is None: + self.host, self.__r_host = urllib.parse.splithost(self.__r_type) + if self.host: + self.host = urllib.parse.unquote(self.host) + return self.host + + def get_selector(self): + return self.__r_host + + def set_proxy(self, host, type): + self.host, self.type = host, type + self.__r_host = self.__original + + def get_origin_req_host(self): + return self.origin_req_host + + def is_unverifiable(self): + return self.unverifiable + + def add_header(self, key, val): + # useful for something like authentication + self.headers[key.capitalize()] = val + + def add_unredirected_header(self, key, val): + # will not be added to a redirected request + self.unredirected_hdrs[key.capitalize()] = val + + def has_header(self, header_name): + return (header_name in self.headers or + header_name in self.unredirected_hdrs) + + def get_header(self, header_name, default=None): + return self.headers.get( + header_name, + self.unredirected_hdrs.get(header_name, default)) + + def header_items(self): + hdrs = self.unredirected_hdrs.copy() + hdrs.update(self.headers) + return list(hdrs.items()) + +class OpenerDirector: + def __init__(self): + client_version = "Python-urllib/%s" % __version__ + self.addheaders = [('User-agent', client_version)] + # manage the individual handlers + self.handlers = [] + self.handle_open = {} + self.handle_error = {} + self.process_response = {} + self.process_request = {} + + def add_handler(self, handler): + if not hasattr(handler, "add_parent"): + raise TypeError("expected BaseHandler instance, got %r" % + type(handler)) + + added = False + for meth in dir(handler): + if meth in ["redirect_request", "do_open", "proxy_open"]: + # oops, coincidental match + continue + + i = meth.find("_") + protocol = meth[:i] + condition = meth[i+1:] + + if condition.startswith("error"): + j = condition.find("_") + i + 1 + kind = meth[j+1:] + try: + kind = int(kind) + except ValueError: + pass + lookup = self.handle_error.get(protocol, {}) + self.handle_error[protocol] = lookup + elif condition == "open": + kind = protocol + lookup = self.handle_open + elif condition == "response": + kind = protocol + lookup = self.process_response + elif condition == "request": + kind = protocol + lookup = self.process_request + else: + continue + + handlers = lookup.setdefault(kind, []) + if handlers: + bisect.insort(handlers, handler) + else: + handlers.append(handler) + added = True + + if added: + # the handlers must work in an specific order, the order + # is specified in a Handler attribute + bisect.insort(self.handlers, handler) + handler.add_parent(self) + + def close(self): + # Only exists for backwards compatibility. + pass + + def _call_chain(self, chain, kind, meth_name, *args): + # Handlers raise an exception if no one else should try to handle + # the request, or return None if they can't but another handler + # could. Otherwise, they return the response. + handlers = chain.get(kind, ()) + for handler in handlers: + func = getattr(handler, meth_name) + + result = func(*args) + if result is not None: + return result + + def open(self, fullurl, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT): + # accept a URL or a Request object + if isinstance(fullurl, str): + req = Request(fullurl, data) + else: + req = fullurl + if data is not None: + req.add_data(data) + + req.timeout = timeout + protocol = req.get_type() + + # pre-process request + meth_name = protocol+"_request" + for processor in self.process_request.get(protocol, []): + meth = getattr(processor, meth_name) + req = meth(req) + + response = self._open(req, data) + + # post-process response + meth_name = protocol+"_response" + for processor in self.process_response.get(protocol, []): + meth = getattr(processor, meth_name) + response = meth(req, response) + + return response + + def _open(self, req, data=None): + result = self._call_chain(self.handle_open, 'default', + 'default_open', req) + if result: + return result + + protocol = req.get_type() + result = self._call_chain(self.handle_open, protocol, protocol + + '_open', req) + if result: + return result + + return self._call_chain(self.handle_open, 'unknown', + 'unknown_open', req) + + def error(self, proto, *args): + if proto in ('http', 'https'): + # XXX http[s] protocols are special-cased + dict = self.handle_error['http'] # https is not different than http + proto = args[2] # YUCK! + meth_name = 'http_error_%s' % proto + http_err = 1 + orig_args = args + else: + dict = self.handle_error + meth_name = proto + '_error' + http_err = 0 + args = (dict, proto, meth_name) + args + result = self._call_chain(*args) + if result: + return result + + if http_err: + args = (dict, 'default', 'http_error_default') + orig_args + return self._call_chain(*args) + +# XXX probably also want an abstract factory that knows when it makes +# sense to skip a superclass in favor of a subclass and when it might +# make sense to include both + +def build_opener(*handlers): + """Create an opener object from a list of handlers. + + The opener will use several default handlers, including support + for HTTP and FTP. + + If any of the handlers passed as arguments are subclasses of the + default handlers, the default handlers will not be used. + """ + def isclass(obj): + return isinstance(obj, type) or hasattr(obj, "__bases__") + + opener = OpenerDirector() + default_classes = [ProxyHandler, UnknownHandler, HTTPHandler, + HTTPDefaultErrorHandler, HTTPRedirectHandler, + FTPHandler, FileHandler, HTTPErrorProcessor] + if hasattr(http.client, "HTTPSConnection"): + default_classes.append(HTTPSHandler) + else: + import pdb; pdb.set_trace() + skip = set() + for klass in default_classes: + for check in handlers: + if isclass(check): + if issubclass(check, klass): + skip.add(klass) + elif isinstance(check, klass): + skip.add(klass) + for klass in skip: + default_classes.remove(klass) + + for klass in default_classes: + opener.add_handler(klass()) + + for h in handlers: + if isclass(h): + h = h() + opener.add_handler(h) + return opener + +class BaseHandler: + handler_order = 500 + + def add_parent(self, parent): + self.parent = parent + + def close(self): + # Only exists for backwards compatibility + pass + + def __lt__(self, other): + if not hasattr(other, "handler_order"): + # Try to preserve the old behavior of having custom classes + # inserted after default ones (works only for custom user + # classes which are not aware of handler_order). + return True + return self.handler_order < other.handler_order + + +class HTTPErrorProcessor(BaseHandler): + """Process HTTP error responses.""" + handler_order = 1000 # after all other processing + + def http_response(self, request, response): + code, msg, hdrs = response.code, response.msg, response.info() + + # According to RFC 2616, "2xx" code indicates that the client's + # request was successfully received, understood, and accepted. + if not (200 <= code < 300): + response = self.parent.error( + 'http', request, response, code, msg, hdrs) + + return response + + https_response = http_response + +class HTTPDefaultErrorHandler(BaseHandler): + def http_error_default(self, req, fp, code, msg, hdrs): + raise urllib.error.HTTPError(req.get_full_url(), code, msg, hdrs, fp) + +class HTTPRedirectHandler(BaseHandler): + # maximum number of redirections to any single URL + # this is needed because of the state that cookies introduce + max_repeats = 4 + # maximum total number of redirections (regardless of URL) before + # assuming we're in a loop + max_redirections = 10 + + def redirect_request(self, req, fp, code, msg, headers, newurl): + """Return a Request or None in response to a redirect. + + This is called by the http_error_30x methods when a + redirection response is received. If a redirection should + take place, return a new Request to allow http_error_30x to + perform the redirect. Otherwise, raise HTTPError if no-one + else should try to handle this url. Return None if you can't + but another Handler might. + """ + m = req.get_method() + if (not (code in (301, 302, 303, 307) and m in ("GET", "HEAD") + or code in (301, 302, 303) and m == "POST")): + raise urllib.error.HTTPError(req.get_full_url(), + code, msg, headers, fp) + + # Strictly (according to RFC 2616), 301 or 302 in response to + # a POST MUST NOT cause a redirection without confirmation + # from the user (of urllib2, in this case). In practice, + # essentially all clients do redirect in this case, so we do + # the same. + # be conciliant with URIs containing a space + newurl = newurl.replace(' ', '%20') + CONTENT_HEADERS = ("content-length", "content-type") + newheaders = dict((k, v) for k, v in req.headers.items() + if k.lower() not in CONTENT_HEADERS) + return Request(newurl, + headers=newheaders, + origin_req_host=req.get_origin_req_host(), + unverifiable=True) + + # Implementation note: To avoid the server sending us into an + # infinite loop, the request object needs to track what URLs we + # have already seen. Do this by adding a handler-specific + # attribute to the Request object. + def http_error_302(self, req, fp, code, msg, headers): + # Some servers (incorrectly) return multiple Location headers + # (so probably same goes for URI). Use first header. + if "location" in headers: + newurl = headers["location"] + elif "uri" in headers: + newurl = headers["uri"] + else: + return + newurl = urllib.parse.urljoin(req.get_full_url(), newurl) + + # XXX Probably want to forget about the state of the current + # request, although that might interact poorly with other + # handlers that also use handler-specific request attributes + new = self.redirect_request(req, fp, code, msg, headers, newurl) + if new is None: + return + + # loop detection + # .redirect_dict has a key url if url was previously visited. + if hasattr(req, 'redirect_dict'): + visited = new.redirect_dict = req.redirect_dict + if (visited.get(newurl, 0) >= self.max_repeats or + len(visited) >= self.max_redirections): + raise urllib.error.HTTPError(req.get_full_url(), code, + self.inf_msg + msg, headers, fp) + else: + visited = new.redirect_dict = req.redirect_dict = {} + visited[newurl] = visited.get(newurl, 0) + 1 + + # Don't close the fp until we are sure that we won't use it + # with HTTPError. + fp.read() + fp.close() + + return self.parent.open(new) + + http_error_301 = http_error_303 = http_error_307 = http_error_302 + + inf_msg = "The HTTP server returned a redirect error that would " \ + "lead to an infinite loop.\n" \ + "The last 30x error message was:\n" + + +def _parse_proxy(proxy): + """Return (scheme, user, password, host/port) given a URL or an authority. + + If a URL is supplied, it must have an authority (host:port) component. + According to RFC 3986, having an authority component means the URL must + have two slashes after the scheme: + + >>> _parse_proxy('file:/ftp.example.com/') + Traceback (most recent call last): + ValueError: proxy URL with no authority: 'file:/ftp.example.com/' + + The first three items of the returned tuple may be None. + + Examples of authority parsing: + + >>> _parse_proxy('proxy.example.com') + (None, None, None, 'proxy.example.com') + >>> _parse_proxy('proxy.example.com:3128') + (None, None, None, 'proxy.example.com:3128') + + The authority component may optionally include userinfo (assumed to be + username:password): + + >>> _parse_proxy('joe:password@proxy.example.com') + (None, 'joe', 'password', 'proxy.example.com') + >>> _parse_proxy('joe:password@proxy.example.com:3128') + (None, 'joe', 'password', 'proxy.example.com:3128') + + Same examples, but with URLs instead: + + >>> _parse_proxy('http://proxy.example.com/') + ('http', None, None, 'proxy.example.com') + >>> _parse_proxy('http://proxy.example.com:3128/') + ('http', None, None, 'proxy.example.com:3128') + >>> _parse_proxy('http://joe:password@proxy.example.com/') + ('http', 'joe', 'password', 'proxy.example.com') + >>> _parse_proxy('http://joe:password@proxy.example.com:3128') + ('http', 'joe', 'password', 'proxy.example.com:3128') + + Everything after the authority is ignored: + + >>> _parse_proxy('ftp://joe:password@proxy.example.com/rubbish:3128') + ('ftp', 'joe', 'password', 'proxy.example.com') + + Test for no trailing '/' case: + + >>> _parse_proxy('http://joe:password@proxy.example.com') + ('http', 'joe', 'password', 'proxy.example.com') + + """ + scheme, r_scheme = urllib.parse.splittype(proxy) + if not r_scheme.startswith("/"): + # authority + scheme = None + authority = proxy + else: + # URL + if not r_scheme.startswith("//"): + raise ValueError("proxy URL with no authority: %r" % proxy) + # We have an authority, so for RFC 3986-compliant URLs (by ss 3. + # and 3.3.), path is empty or starts with '/' + end = r_scheme.find("/", 2) + if end == -1: + end = None + authority = r_scheme[2:end] + userinfo, hostport = urllib.parse.splituser(authority) + if userinfo is not None: + user, password = urllib.parse.splitpasswd(userinfo) + else: + user = password = None + return scheme, user, password, hostport + +class ProxyHandler(BaseHandler): + # Proxies must be in front + handler_order = 100 + + def __init__(self, proxies=None): + if proxies is None: + proxies = getproxies() + assert hasattr(proxies, 'keys'), "proxies must be a mapping" + self.proxies = proxies + for type, url in proxies.items(): + setattr(self, '%s_open' % type, + lambda r, proxy=url, type=type, meth=self.proxy_open: \ + meth(r, proxy, type)) + + def proxy_open(self, req, proxy, type): + orig_type = req.get_type() + proxy_type, user, password, hostport = _parse_proxy(proxy) + if proxy_type is None: + proxy_type = orig_type + if user and password: + user_pass = '%s:%s' % (unquote(user), + urllib.parse.unquote(password)) + creds = base64.b64encode(user_pass.encode()).decode("ascii") + req.add_header('Proxy-authorization', 'Basic ' + creds) + hostport = urllib.parse.unquote(hostport) + req.set_proxy(hostport, proxy_type) + if orig_type == proxy_type: + # let other handlers take care of it + return None + else: + # need to start over, because the other handlers don't + # grok the proxy's URL type + # e.g. if we have a constructor arg proxies like so: + # {'http': 'ftp://proxy.example.com'}, we may end up turning + # a request for http://acme.example.com/a into one for + # ftp://proxy.example.com/a + return self.parent.open(req) + +class HTTPPasswordMgr: + + def __init__(self): + self.passwd = {} + + def add_password(self, realm, uri, user, passwd): + # uri could be a single URI or a sequence + if isinstance(uri, str): + uri = [uri] + if not realm in self.passwd: + self.passwd[realm] = {} + for default_port in True, False: + reduced_uri = tuple( + [self.reduce_uri(u, default_port) for u in uri]) + self.passwd[realm][reduced_uri] = (user, passwd) + + def find_user_password(self, realm, authuri): + domains = self.passwd.get(realm, {}) + for default_port in True, False: + reduced_authuri = self.reduce_uri(authuri, default_port) + for uris, authinfo in domains.items(): + for uri in uris: + if self.is_suburi(uri, reduced_authuri): + return authinfo + return None, None + + def reduce_uri(self, uri, default_port=True): + """Accept authority or URI and extract only the authority and path.""" + # note HTTP URLs do not have a userinfo component + parts = urllib.parse.urlsplit(uri) + if parts[1]: + # URI + scheme = parts[0] + authority = parts[1] + path = parts[2] or '/' + else: + # host or host:port + scheme = None + authority = uri + path = '/' + host, port = urllib.parse.splitport(authority) + if default_port and port is None and scheme is not None: + dport = {"http": 80, + "https": 443, + }.get(scheme) + if dport is not None: + authority = "%s:%d" % (host, dport) + return authority, path + + def is_suburi(self, base, test): + """Check if test is below base in a URI tree + + Both args must be URIs in reduced form. + """ + if base == test: + return True + if base[0] != test[0]: + return False + common = posixpath.commonprefix((base[1], test[1])) + if len(common) == len(base[1]): + return True + return False + + +class HTTPPasswordMgrWithDefaultRealm(HTTPPasswordMgr): + + def find_user_password(self, realm, authuri): + user, password = HTTPPasswordMgr.find_user_password(self, realm, + authuri) + if user is not None: + return user, password + return HTTPPasswordMgr.find_user_password(self, None, authuri) + + +class AbstractBasicAuthHandler: + + # XXX this allows for multiple auth-schemes, but will stupidly pick + # the last one with a realm specified. + + # allow for double- and single-quoted realm values + # (single quotes are a violation of the RFC, but appear in the wild) + rx = re.compile('(?:.*,)*[ \t]*([^ \t]+)[ \t]+' + 'realm=(["\'])(.*?)\\2', re.I) + + # XXX could pre-emptively send auth info already accepted (RFC 2617, + # end of section 2, and section 1.2 immediately after "credentials" + # production). + + def __init__(self, password_mgr=None): + if password_mgr is None: + password_mgr = HTTPPasswordMgr() + self.passwd = password_mgr + self.add_password = self.passwd.add_password + + def http_error_auth_reqed(self, authreq, host, req, headers): + # host may be an authority (without userinfo) or a URL with an + # authority + # XXX could be multiple headers + authreq = headers.get(authreq, None) + if authreq: + mo = AbstractBasicAuthHandler.rx.search(authreq) + if mo: + scheme, quote, realm = mo.groups() + if scheme.lower() == 'basic': + return self.retry_http_basic_auth(host, req, realm) + + def retry_http_basic_auth(self, host, req, realm): + user, pw = self.passwd.find_user_password(realm, host) + if pw is not None: + raw = "%s:%s" % (user, pw) + auth = "Basic " + base64.b64encode(raw.encode()).decode("ascii") + if req.headers.get(self.auth_header, None) == auth: + return None + req.add_header(self.auth_header, auth) + return self.parent.open(req) + else: + return None + + +class HTTPBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): + + auth_header = 'Authorization' + + def http_error_401(self, req, fp, code, msg, headers): + url = req.get_full_url() + return self.http_error_auth_reqed('www-authenticate', + url, req, headers) + + +class ProxyBasicAuthHandler(AbstractBasicAuthHandler, BaseHandler): + + auth_header = 'Proxy-authorization' + + def http_error_407(self, req, fp, code, msg, headers): + # http_error_auth_reqed requires that there is no userinfo component in + # authority. Assume there isn't one, since urllib2 does not (and + # should not, RFC 3986 s. 3.2.1) support requests for URLs containing + # userinfo. + authority = req.get_host() + return self.http_error_auth_reqed('proxy-authenticate', + authority, req, headers) + + +def randombytes(n): + """Return n random bytes.""" + return os.urandom(n) + +class AbstractDigestAuthHandler: + # Digest authentication is specified in RFC 2617. + + # XXX The client does not inspect the Authentication-Info header + # in a successful response. + + # XXX It should be possible to test this implementation against + # a mock server that just generates a static set of challenges. + + # XXX qop="auth-int" supports is shaky + + def __init__(self, passwd=None): + if passwd is None: + passwd = HTTPPasswordMgr() + self.passwd = passwd + self.add_password = self.passwd.add_password + self.retried = 0 + self.nonce_count = 0 + + def reset_retry_count(self): + self.retried = 0 + + def http_error_auth_reqed(self, auth_header, host, req, headers): + authreq = headers.get(auth_header, None) + if self.retried > 5: + # Don't fail endlessly - if we failed once, we'll probably + # fail a second time. Hm. Unless the Password Manager is + # prompting for the information. Crap. This isn't great + # but it's better than the current 'repeat until recursion + # depth exceeded' approach <wink> + raise urllib.error.HTTPError(req.get_full_url(), 401, + "digest auth failed", + headers, None) + else: + self.retried += 1 + if authreq: + scheme = authreq.split()[0] + if scheme.lower() == 'digest': + return self.retry_http_digest_auth(req, authreq) + + def retry_http_digest_auth(self, req, auth): + token, challenge = auth.split(' ', 1) + chal = parse_keqv_list(filter(None, parse_http_list(challenge))) + auth = self.get_authorization(req, chal) + if auth: + auth_val = 'Digest %s' % auth + if req.headers.get(self.auth_header, None) == auth_val: + return None + req.add_unredirected_header(self.auth_header, auth_val) + resp = self.parent.open(req) + return resp + + def get_cnonce(self, nonce): + # The cnonce-value is an opaque + # quoted string value provided by the client and used by both client + # and server to avoid chosen plaintext attacks, to provide mutual + # authentication, and to provide some message integrity protection. + # This isn't a fabulous effort, but it's probably Good Enough. + s = "%s:%s:%s:" % (self.nonce_count, nonce, time.ctime()) + b = s.encode("ascii") + randombytes(8) + dig = hashlib.sha1(b).hexdigest() + return dig[:16] + + def get_authorization(self, req, chal): + try: + realm = chal['realm'] + nonce = chal['nonce'] + qop = chal.get('qop') + algorithm = chal.get('algorithm', 'MD5') + # mod_digest doesn't send an opaque, even though it isn't + # supposed to be optional + opaque = chal.get('opaque', None) + except KeyError: + return None + + H, KD = self.get_algorithm_impls(algorithm) + if H is None: + return None + + user, pw = self.passwd.find_user_password(realm, req.get_full_url()) + if user is None: + return None + + # XXX not implemented yet + if req.has_data(): + entdig = self.get_entity_digest(req.get_data(), chal) + else: + entdig = None + + A1 = "%s:%s:%s" % (user, realm, pw) + A2 = "%s:%s" % (req.get_method(), + # XXX selector: what about proxies and full urls + req.get_selector()) + if qop == 'auth': + self.nonce_count += 1 + ncvalue = '%08x' % self.nonce_count + cnonce = self.get_cnonce(nonce) + noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, H(A2)) + respdig = KD(H(A1), noncebit) + elif qop is None: + respdig = KD(H(A1), "%s:%s" % (nonce, H(A2))) + else: + # XXX handle auth-int. + raise urllib.error.URLError("qop '%s' is not supported." % qop) + + # XXX should the partial digests be encoded too? + + base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \ + 'response="%s"' % (user, realm, nonce, req.get_selector(), + respdig) + if opaque: + base += ', opaque="%s"' % opaque + if entdig: + base += ', digest="%s"' % entdig + base += ', algorithm="%s"' % algorithm + if qop: + base += ', qop=auth, nc=%s, cnonce="%s"' % (ncvalue, cnonce) + return base + + def get_algorithm_impls(self, algorithm): + # lambdas assume digest modules are imported at the top level + if algorithm == 'MD5': + H = lambda x: hashlib.md5(x.encode("ascii")).hexdigest() + elif algorithm == 'SHA': + H = lambda x: hashlib.sha1(x.encode("ascii")).hexdigest() + # XXX MD5-sess + KD = lambda s, d: H("%s:%s" % (s, d)) + return H, KD + + def get_entity_digest(self, data, chal): + # XXX not implemented yet + return None + + +class HTTPDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler): + """An authentication protocol defined by RFC 2069 + + Digest authentication improves on basic authentication because it + does not transmit passwords in the clear. + """ + + auth_header = 'Authorization' + handler_order = 490 # before Basic auth + + def http_error_401(self, req, fp, code, msg, headers): + host = urllib.parse.urlparse(req.get_full_url())[1] + retry = self.http_error_auth_reqed('www-authenticate', + host, req, headers) + self.reset_retry_count() + return retry + + +class ProxyDigestAuthHandler(BaseHandler, AbstractDigestAuthHandler): + + auth_header = 'Proxy-Authorization' + handler_order = 490 # before Basic auth + + def http_error_407(self, req, fp, code, msg, headers): + host = req.get_host() + retry = self.http_error_auth_reqed('proxy-authenticate', + host, req, headers) + self.reset_retry_count() + return retry + +class AbstractHTTPHandler(BaseHandler): + + def __init__(self, debuglevel=0): + self._debuglevel = debuglevel + + def set_http_debuglevel(self, level): + self._debuglevel = level + + def do_request_(self, request): + host = request.get_host() + if not host: + raise urllib.error.URLError('no host given') + + if request.has_data(): # POST + data = request.get_data() + if not request.has_header('Content-type'): + request.add_unredirected_header( + 'Content-type', + 'application/x-www-form-urlencoded') + if not request.has_header('Content-length'): + request.add_unredirected_header( + 'Content-length', '%d' % len(data)) + + scheme, sel = urllib.parse.splittype(request.get_selector()) + sel_host, sel_path = urllib.parse.splithost(sel) + if not request.has_header('Host'): + request.add_unredirected_header('Host', sel_host or host) + for name, value in self.parent.addheaders: + name = name.capitalize() + if not request.has_header(name): + request.add_unredirected_header(name, value) + + return request + + def do_open(self, http_class, req): + """Return an addinfourl object for the request, using http_class. + + http_class must implement the HTTPConnection API from http.client. + The addinfourl return value is a file-like object. It also + has methods and attributes including: + - info(): return a mimetools.Message object for the headers + - geturl(): return the original request URL + - code: HTTP status code + """ + host = req.get_host() + if not host: + raise urllib.error.URLError('no host given') + + h = http_class(host, timeout=req.timeout) # will parse host:port + headers = dict(req.headers) + headers.update(req.unredirected_hdrs) + + # TODO(jhylton): Should this be redesigned to handle + # persistent connections? + + # We want to make an HTTP/1.1 request, but the addinfourl + # class isn't prepared to deal with a persistent connection. + # It will try to read all remaining data from the socket, + # which will block while the server waits for the next request. + # So make sure the connection gets closed after the (only) + # request. + headers["Connection"] = "close" + headers = dict( + (name.title(), val) for name, val in headers.items()) + try: + h.request(req.get_method(), req.get_selector(), req.data, headers) + r = h.getresponse() + except socket.error as err: # XXX what error? + raise urllib.error.URLError(err) + + resp = urllib.response.addinfourl(r.fp, r.msg, req.get_full_url()) + resp.code = r.status + resp.msg = r.reason + return resp + + +class HTTPHandler(AbstractHTTPHandler): + + def http_open(self, req): + return self.do_open(http.client.HTTPConnection, req) + + http_request = AbstractHTTPHandler.do_request_ + +if hasattr(http.client, 'HTTPSConnection'): + class HTTPSHandler(AbstractHTTPHandler): + + def https_open(self, req): + return self.do_open(http.client.HTTPSConnection, req) + + https_request = AbstractHTTPHandler.do_request_ + +class HTTPCookieProcessor(BaseHandler): + def __init__(self, cookiejar=None): + import http.cookiejar + if cookiejar is None: + cookiejar = http.cookiejar.CookieJar() + self.cookiejar = cookiejar + + def http_request(self, request): + self.cookiejar.add_cookie_header(request) + return request + + def http_response(self, request, response): + self.cookiejar.extract_cookies(response, request) + return response + + https_request = http_request + https_response = http_response + +class UnknownHandler(BaseHandler): + def unknown_open(self, req): + type = req.get_type() + raise urllib.error.URLError('unknown url type: %s' % type) + +def parse_keqv_list(l): + """Parse list of key=value strings where keys are not duplicated.""" + parsed = {} + for elt in l: + k, v = elt.split('=', 1) + if v[0] == '"' and v[-1] == '"': + v = v[1:-1] + parsed[k] = v + return parsed + +def parse_http_list(s): + """Parse lists as described by RFC 2068 Section 2. + + In particular, parse comma-separated lists where the elements of + the list may include quoted-strings. A quoted-string could + contain a comma. A non-quoted string could have quotes in the + middle. Neither commas nor quotes count if they are escaped. + Only double-quotes count, not single-quotes. + """ + res = [] + part = '' + + escape = quote = False + for cur in s: + if escape: + part += cur + escape = False + continue + if quote: + if cur == '\\': + escape = True + continue + elif cur == '"': + quote = False + part += cur + continue + + if cur == ',': + res.append(part) + part = '' + continue + + if cur == '"': + quote = True + + part += cur + + # append last part + if part: + res.append(part) + + return [part.strip() for part in res] + +class FileHandler(BaseHandler): + # Use local file or FTP depending on form of URL + def file_open(self, req): + url = req.get_selector() + if url[:2] == '//' and url[2:3] != '/': + req.type = 'ftp' + return self.parent.open(req) + else: + return self.open_local_file(req) + + # names for the localhost + names = None + def get_names(self): + if FileHandler.names is None: + try: + FileHandler.names = (socket.gethostbyname('localhost'), + socket.gethostbyname(socket.gethostname())) + except socket.gaierror: + FileHandler.names = (socket.gethostbyname('localhost'),) + return FileHandler.names + + # not entirely sure what the rules are here + def open_local_file(self, req): + import email.utils + import mimetypes + host = req.get_host() + file = req.get_selector() + localfile = url2pathname(file) + try: + stats = os.stat(localfile) + size = stats.st_size + modified = email.utils.formatdate(stats.st_mtime, usegmt=True) + mtype = mimetypes.guess_type(file)[0] + headers = email.message_from_string( + 'Content-type: %s\nContent-length: %d\nLast-modified: %s\n' % + (mtype or 'text/plain', size, modified)) + if host: + host, port = urllib.parse.splitport(host) + if not host or \ + (not port and _safe_gethostbyname(host) in self.get_names()): + return urllib.response.addinfourl(open(localfile, 'rb'), + headers, 'file:'+file) + except OSError as msg: + # urllib2 users shouldn't expect OSErrors coming from urlopen() + raise urllib.error.URLError(msg) + raise urllib.error.URLError('file not on local host') + +def _safe_gethostbyname(host): + try: + return socket.gethostbyname(host) + except socket.gaierror: + return None + +class FTPHandler(BaseHandler): + def ftp_open(self, req): + import ftplib + import mimetypes + host = req.get_host() + if not host: + raise urllib.error.URLError('ftp error: no host given') + host, port = urllib.parse.splitport(host) + if port is None: + port = ftplib.FTP_PORT + else: + port = int(port) + + # username/password handling + user, host = urllib.parse.splituser(host) + if user: + user, passwd = urllib.parse.splitpasswd(user) + else: + passwd = None + host = urllib.parse.unquote(host) + user = urllib.parse.unquote(user or '') + passwd = urllib.parse.unquote(passwd or '') + + try: + host = socket.gethostbyname(host) + except socket.error as msg: + raise urllib.error.URLError(msg) + path, attrs = urllib.parse.splitattr(req.get_selector()) + dirs = path.split('/') + dirs = list(map(urllib.parse.unquote, dirs)) + dirs, file = dirs[:-1], dirs[-1] + if dirs and not dirs[0]: + dirs = dirs[1:] + try: + fw = self.connect_ftp(user, passwd, host, port, dirs, req.timeout) + type = file and 'I' or 'D' + for attr in attrs: + attr, value = urllib.parse.splitvalue(attr) + if attr.lower() == 'type' and \ + value in ('a', 'A', 'i', 'I', 'd', 'D'): + type = value.upper() + fp, retrlen = fw.retrfile(file, type) + headers = "" + mtype = mimetypes.guess_type(req.get_full_url())[0] + if mtype: + headers += "Content-type: %s\n" % mtype + if retrlen is not None and retrlen >= 0: + headers += "Content-length: %d\n" % retrlen + headers = email.message_from_string(headers) + return urllib.response.addinfourl(fp, headers, req.get_full_url()) + except ftplib.all_errors as msg: + exc = urllib.error.URLError('ftp error: %s' % msg) + raise exc.with_traceback(sys.exc_info()[2]) + + def connect_ftp(self, user, passwd, host, port, dirs, timeout): + fw = ftpwrapper(user, passwd, host, port, dirs, timeout) + return fw + +class CacheFTPHandler(FTPHandler): + # XXX would be nice to have pluggable cache strategies + # XXX this stuff is definitely not thread safe + def __init__(self): + self.cache = {} + self.timeout = {} + self.soonest = 0 + self.delay = 60 + self.max_conns = 16 + + def setTimeout(self, t): + self.delay = t + + def setMaxConns(self, m): + self.max_conns = m + + def connect_ftp(self, user, passwd, host, port, dirs, timeout): + key = user, host, port, '/'.join(dirs), timeout + if key in self.cache: + self.timeout[key] = time.time() + self.delay + else: + self.cache[key] = ftpwrapper(user, passwd, host, port, + dirs, timeout) + self.timeout[key] = time.time() + self.delay + self.check_cache() + return self.cache[key] + + def check_cache(self): + # first check for old ones + t = time.time() + if self.soonest <= t: + for k, v in list(self.timeout.items()): + if v < t: + self.cache[k].close() + del self.cache[k] + del self.timeout[k] + self.soonest = min(list(self.timeout.values())) + + # then check the size + if len(self.cache) == self.max_conns: + for k, v in list(self.timeout.items()): + if v == self.soonest: + del self.cache[k] + del self.timeout[k] + break + self.soonest = min(list(self.timeout.values())) + +# Code move from the old urllib module + +MAXFTPCACHE = 10 # Trim the ftp cache beyond this size + +# Helper for non-unix systems +if os.name == 'mac': + from macurl2path import url2pathname, pathname2url +elif os.name == 'nt': + from nturl2path import url2pathname, pathname2url +else: + def url2pathname(pathname): + """OS-specific conversion from a relative URL of the 'file' scheme + to a file system path; not recommended for general use.""" + return urllib.parse.unquote(pathname) + + def pathname2url(pathname): + """OS-specific conversion from a file system path to a relative URL + of the 'file' scheme; not recommended for general use.""" + return urllib.parse.quote(pathname) + +# This really consists of two pieces: +# (1) a class which handles opening of all sorts of URLs +# (plus assorted utilities etc.) +# (2) a set of functions for parsing URLs +# XXX Should these be separated out into different modules? + + +ftpcache = {} +class URLopener: + """Class to open URLs. + This is a class rather than just a subroutine because we may need + more than one set of global protocol-specific options. + Note -- this is a base class for those who don't want the + automatic handling of errors type 302 (relocated) and 401 + (authorization needed).""" + + __tempfiles = None + + version = "Python-urllib/%s" % __version__ + + # Constructor + def __init__(self, proxies=None, **x509): + if proxies is None: + proxies = getproxies() + assert hasattr(proxies, 'keys'), "proxies must be a mapping" + self.proxies = proxies + self.key_file = x509.get('key_file') + self.cert_file = x509.get('cert_file') + self.addheaders = [('User-Agent', self.version)] + self.__tempfiles = [] + self.__unlink = os.unlink # See cleanup() + self.tempcache = None + # Undocumented feature: if you assign {} to tempcache, + # it is used to cache files retrieved with + # self.retrieve(). This is not enabled by default + # since it does not work for changing documents (and I + # haven't got the logic to check expiration headers + # yet). + self.ftpcache = ftpcache + # Undocumented feature: you can use a different + # ftp cache by assigning to the .ftpcache member; + # in case you want logically independent URL openers + # XXX This is not threadsafe. Bah. + + def __del__(self): + self.close() + + def close(self): + self.cleanup() + + def cleanup(self): + # This code sometimes runs when the rest of this module + # has already been deleted, so it can't use any globals + # or import anything. + if self.__tempfiles: + for file in self.__tempfiles: + try: + self.__unlink(file) + except OSError: + pass + del self.__tempfiles[:] + if self.tempcache: + self.tempcache.clear() + + def addheader(self, *args): + """Add a header to be used by the HTTP interface only + e.g. u.addheader('Accept', 'sound/basic')""" + self.addheaders.append(args) + + # External interface + def open(self, fullurl, data=None): + """Use URLopener().open(file) instead of open(file, 'r').""" + fullurl = urllib.parse.unwrap(urllib.parse.toBytes(fullurl)) + if self.tempcache and fullurl in self.tempcache: + filename, headers = self.tempcache[fullurl] + fp = open(filename, 'rb') + return urllib.response.addinfourl(fp, headers, fullurl) + urltype, url = urllib.parse.splittype(fullurl) + if not urltype: + urltype = 'file' + if urltype in self.proxies: + proxy = self.proxies[urltype] + urltype, proxyhost = urllib.parse.splittype(proxy) + host, selector = urllib.parse.splithost(proxyhost) + url = (host, fullurl) # Signal special case to open_*() + else: + proxy = None + name = 'open_' + urltype + self.type = urltype + name = name.replace('-', '_') + if not hasattr(self, name): + if proxy: + return self.open_unknown_proxy(proxy, fullurl, data) + else: + return self.open_unknown(fullurl, data) + try: + if data is None: + return getattr(self, name)(url) + else: + return getattr(self, name)(url, data) + except socket.error as msg: + raise IOError('socket error', msg).with_traceback(sys.exc_info()[2]) + + def open_unknown(self, fullurl, data=None): + """Overridable interface to open unknown URL type.""" + type, url = urllib.parse.splittype(fullurl) + raise IOError('url error', 'unknown url type', type) + + def open_unknown_proxy(self, proxy, fullurl, data=None): + """Overridable interface to open unknown URL type.""" + type, url = urllib.parse.splittype(fullurl) + raise IOError('url error', 'invalid proxy for %s' % type, proxy) + + # External interface + def retrieve(self, url, filename=None, reporthook=None, data=None): + """retrieve(url) returns (filename, headers) for a local object + or (tempfilename, headers) for a remote object.""" + url = urllib.parse.unwrap(urllib.parse.toBytes(url)) + if self.tempcache and url in self.tempcache: + return self.tempcache[url] + type, url1 = urllib.parse.splittype(url) + if filename is None and (not type or type == 'file'): + try: + fp = self.open_local_file(url1) + hdrs = fp.info() + del fp + return url2pathname(urllib.parse.splithost(url1)[1]), hdrs + except IOError as msg: + pass + fp = self.open(url, data) + headers = fp.info() + if filename: + tfp = open(filename, 'wb') + else: + import tempfile + garbage, path = urllib.parse.splittype(url) + garbage, path = urllib.parse.splithost(path or "") + path, garbage = urllib.parse.splitquery(path or "") + path, garbage = urllib.parse.splitattr(path or "") + suffix = os.path.splitext(path)[1] + (fd, filename) = tempfile.mkstemp(suffix) + self.__tempfiles.append(filename) + tfp = os.fdopen(fd, 'wb') + result = filename, headers + if self.tempcache is not None: + self.tempcache[url] = result + bs = 1024*8 + size = -1 + read = 0 + blocknum = 0 + if reporthook: + if "content-length" in headers: + size = int(headers["Content-Length"]) + reporthook(blocknum, bs, size) + while 1: + block = fp.read(bs) + if not block: + break + read += len(block) + tfp.write(block) + blocknum += 1 + if reporthook: + reporthook(blocknum, bs, size) + fp.close() + tfp.close() + del fp + del tfp + + # raise exception if actual size does not match content-length header + if size >= 0 and read < size: + raise urllib.error.ContentTooShortError( + "retrieval incomplete: got only %i out of %i bytes" + % (read, size), result) + + return result + + # Each method named open_<type> knows how to open that type of URL + + def _open_generic_http(self, connection_factory, url, data): + """Make an HTTP connection using connection_class. + + This is an internal method that should be called from + open_http() or open_https(). + + Arguments: + - connection_factory should take a host name and return an + HTTPConnection instance. + - url is the url to retrieval or a host, relative-path pair. + - data is payload for a POST request or None. + """ + + user_passwd = None + proxy_passwd= None + if isinstance(url, str): + host, selector = urllib.parse.splithost(url) + if host: + user_passwd, host = urllib.parse.splituser(host) + host = urllib.parse.unquote(host) + realhost = host + else: + host, selector = url + # check whether the proxy contains authorization information + proxy_passwd, host = urllib.parse.splituser(host) + # now we proceed with the url we want to obtain + urltype, rest = urllib.parse.splittype(selector) + url = rest + user_passwd = None + if urltype.lower() != 'http': + realhost = None + else: + realhost, rest = urllib.parse.splithost(rest) + if realhost: + user_passwd, realhost = urllib.parse.splituser(realhost) + if user_passwd: + selector = "%s://%s%s" % (urltype, realhost, rest) + if proxy_bypass(realhost): + host = realhost + + #print "proxy via http:", host, selector + if not host: raise IOError('http error', 'no host given') + + if proxy_passwd: + import base64 + proxy_auth = base64.b64encode(proxy_passwd).strip() + else: + proxy_auth = None + + if user_passwd: + import base64 + auth = base64.b64encode(user_passwd).strip() + else: + auth = None + http_conn = connection_factory(host) + # XXX We should fix urllib so that it works with HTTP/1.1. + http_conn._http_vsn = 10 + http_conn._http_vsn_str = "HTTP/1.0" + + headers = {} + if proxy_auth: + headers["Proxy-Authorization"] = "Basic %s" % proxy_auth + if auth: + headers["Authorization"] = "Basic %s" % auth + if realhost: + headers["Host"] = realhost + for header, value in self.addheaders: + headers[header] = value + + if data is not None: + headers["Content-Type"] = "application/x-www-form-urlencoded" + http_conn.request("POST", selector, data, headers) + else: + http_conn.request("GET", selector, headers=headers) + + try: + response = http_conn.getresponse() + except http.client.BadStatusLine: + # something went wrong with the HTTP status line + raise urllib.error.URLError("http protocol error: bad status line") + + # According to RFC 2616, "2xx" code indicates that the client's + # request was successfully received, understood, and accepted. + if 200 <= response.status < 300: + return urllib.response.addinfourl(response.fp, response.msg, + "http:" + url, + response.status) + else: + return self.http_error( + url, response.fp, + response.status, response.reason, response.msg, data) + + def open_http(self, url, data=None): + """Use HTTP protocol.""" + return self._open_generic_http(http.client.HTTPConnection, url, data) + + def http_error(self, url, fp, errcode, errmsg, headers, data=None): + """Handle http errors. + + Derived class can override this, or provide specific handlers + named http_error_DDD where DDD is the 3-digit error code.""" + # First check if there's a specific handler for this error + name = 'http_error_%d' % errcode + if hasattr(self, name): + method = getattr(self, name) + if data is None: + result = method(url, fp, errcode, errmsg, headers) + else: + result = method(url, fp, errcode, errmsg, headers, data) + if result: return result + return self.http_error_default(url, fp, errcode, errmsg, headers) + + def http_error_default(self, url, fp, errcode, errmsg, headers): + """Default error handler: close the connection and raise IOError.""" + void = fp.read() + fp.close() + raise urllib.error.HTTPError(url, errcode, errmsg, headers, None) + + if _have_ssl: + def _https_connection(self, host): + return http.client.HTTPSConnection(host, + key_file=self.key_file, + cert_file=self.cert_file) + + def open_https(self, url, data=None): + """Use HTTPS protocol.""" + return self._open_generic_http(self._https_connection, url, data) + + def open_file(self, url): + """Use local file or FTP depending on form of URL.""" + if not isinstance(url, str): + raise URLError('file error', 'proxy support for file protocol currently not implemented') + if url[:2] == '//' and url[2:3] != '/' and url[2:12].lower() != 'localhost/': + return self.open_ftp(url) + else: + return self.open_local_file(url) + + def open_local_file(self, url): + """Use local file.""" + import mimetypes, email.utils + from io import StringIO + host, file = urllib.parse.splithost(url) + localname = url2pathname(file) + try: + stats = os.stat(localname) + except OSError as e: + raise URLError(e.errno, e.strerror, e.filename) + size = stats.st_size + modified = email.utils.formatdate(stats.st_mtime, usegmt=True) + mtype = mimetypes.guess_type(url)[0] + headers = email.message_from_string( + 'Content-Type: %s\nContent-Length: %d\nLast-modified: %s\n' % + (mtype or 'text/plain', size, modified)) + if not host: + urlfile = file + if file[:1] == '/': + urlfile = 'file://' + file + return urllib.response.addinfourl(open(localname, 'rb'), + headers, urlfile) + host, port = urllib.parse.splitport(host) + if (not port + and socket.gethostbyname(host) in (localhost(), thishost())): + urlfile = file + if file[:1] == '/': + urlfile = 'file://' + file + return urllib.response.addinfourl(open(localname, 'rb'), + headers, urlfile) + raise URLError('local file error', 'not on local host') + + def open_ftp(self, url): + """Use FTP protocol.""" + if not isinstance(url, str): + raise URLError('ftp error', 'proxy support for ftp protocol currently not implemented') + import mimetypes + from io import StringIO + host, path = urllib.parse.splithost(url) + if not host: raise URLError('ftp error', 'no host given') + host, port = urllib.parse.splitport(host) + user, host = urllib.parse.splituser(host) + if user: user, passwd = urllib.parse.splitpasswd(user) + else: passwd = None + host = urllib.parse.unquote(host) + user = urllib.parse.unquote(user or '') + passwd = urllib.parse.unquote(passwd or '') + host = socket.gethostbyname(host) + if not port: + import ftplib + port = ftplib.FTP_PORT + else: + port = int(port) + path, attrs = urllib.parse.splitattr(path) + path = urllib.parse.unquote(path) + dirs = path.split('/') + dirs, file = dirs[:-1], dirs[-1] + if dirs and not dirs[0]: dirs = dirs[1:] + if dirs and not dirs[0]: dirs[0] = '/' + key = user, host, port, '/'.join(dirs) + # XXX thread unsafe! + if len(self.ftpcache) > MAXFTPCACHE: + # Prune the cache, rather arbitrarily + for k in self.ftpcache.keys(): + if k != key: + v = self.ftpcache[k] + del self.ftpcache[k] + v.close() + try: + if not key in self.ftpcache: + self.ftpcache[key] = \ + ftpwrapper(user, passwd, host, port, dirs) + if not file: type = 'D' + else: type = 'I' + for attr in attrs: + attr, value = urllib.parse.splitvalue(attr) + if attr.lower() == 'type' and \ + value in ('a', 'A', 'i', 'I', 'd', 'D'): + type = value.upper() + (fp, retrlen) = self.ftpcache[key].retrfile(file, type) + mtype = mimetypes.guess_type("ftp:" + url)[0] + headers = "" + if mtype: + headers += "Content-Type: %s\n" % mtype + if retrlen is not None and retrlen >= 0: + headers += "Content-Length: %d\n" % retrlen + headers = email.message_from_string(headers) + return urllib.response.addinfourl(fp, headers, "ftp:" + url) + except ftperrors() as msg: + raise URLError('ftp error', msg).with_traceback(sys.exc_info()[2]) + + def open_data(self, url, data=None): + """Use "data" URL.""" + if not isinstance(url, str): + raise URLError('data error', 'proxy support for data protocol currently not implemented') + # ignore POSTed data + # + # syntax of data URLs: + # dataurl := "data:" [ mediatype ] [ ";base64" ] "," data + # mediatype := [ type "/" subtype ] *( ";" parameter ) + # data := *urlchar + # parameter := attribute "=" value + try: + [type, data] = url.split(',', 1) + except ValueError: + raise IOError('data error', 'bad data URL') + if not type: + type = 'text/plain;charset=US-ASCII' + semi = type.rfind(';') + if semi >= 0 and '=' not in type[semi:]: + encoding = type[semi+1:] + type = type[:semi] + else: + encoding = '' + msg = [] + msg.append('Date: %s'%time.strftime('%a, %d %b %Y %T GMT', + time.gmtime(time.time()))) + msg.append('Content-type: %s' % type) + if encoding == 'base64': + import base64 + data = base64.decodestring(data) + else: + data = urllib.parse.unquote(data) + msg.append('Content-Length: %d' % len(data)) + msg.append('') + msg.append(data) + msg = '\n'.join(msg) + headers = mimetools.message_from_string(msg) + #f.fileno = None # needed for addinfourl + return urllib.response.addinfourl(f, headers, url) + + +class FancyURLopener(URLopener): + """Derived class with handlers for errors we can handle (perhaps).""" + + def __init__(self, *args, **kwargs): + URLopener.__init__(self, *args, **kwargs) + self.auth_cache = {} + self.tries = 0 + self.maxtries = 10 + + def http_error_default(self, url, fp, errcode, errmsg, headers): + """Default error handling -- don't raise an exception.""" + return urllib.response.addinfourl(fp, headers, "http:" + url, errcode) + + def http_error_302(self, url, fp, errcode, errmsg, headers, data=None): + """Error 302 -- relocated (temporarily).""" + self.tries += 1 + if self.maxtries and self.tries >= self.maxtries: + if hasattr(self, "http_error_500"): + meth = self.http_error_500 + else: + meth = self.http_error_default + self.tries = 0 + return meth(url, fp, 500, + "Internal Server Error: Redirect Recursion", headers) + result = self.redirect_internal(url, fp, errcode, errmsg, headers, + data) + self.tries = 0 + return result + + def redirect_internal(self, url, fp, errcode, errmsg, headers, data): + if 'location' in headers: + newurl = headers['location'] + elif 'uri' in headers: + newurl = headers['uri'] + else: + return + void = fp.read() + fp.close() + # In case the server sent a relative URL, join with original: + newurl = basejoin(self.type + ":" + url, newurl) + return self.open(newurl) + + def http_error_301(self, url, fp, errcode, errmsg, headers, data=None): + """Error 301 -- also relocated (permanently).""" + return self.http_error_302(url, fp, errcode, errmsg, headers, data) + + def http_error_303(self, url, fp, errcode, errmsg, headers, data=None): + """Error 303 -- also relocated (essentially identical to 302).""" + return self.http_error_302(url, fp, errcode, errmsg, headers, data) + + def http_error_307(self, url, fp, errcode, errmsg, headers, data=None): + """Error 307 -- relocated, but turn POST into error.""" + if data is None: + return self.http_error_302(url, fp, errcode, errmsg, headers, data) + else: + return self.http_error_default(url, fp, errcode, errmsg, headers) + + def http_error_401(self, url, fp, errcode, errmsg, headers, data=None): + """Error 401 -- authentication required. + This function supports Basic authentication only.""" + if not 'www-authenticate' in headers: + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + stuff = headers['www-authenticate'] + import re + match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff) + if not match: + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + scheme, realm = match.groups() + if scheme.lower() != 'basic': + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + name = 'retry_' + self.type + '_basic_auth' + if data is None: + return getattr(self,name)(url, realm) + else: + return getattr(self,name)(url, realm, data) + + def http_error_407(self, url, fp, errcode, errmsg, headers, data=None): + """Error 407 -- proxy authentication required. + This function supports Basic authentication only.""" + if not 'proxy-authenticate' in headers: + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + stuff = headers['proxy-authenticate'] + import re + match = re.match('[ \t]*([^ \t]+)[ \t]+realm="([^"]*)"', stuff) + if not match: + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + scheme, realm = match.groups() + if scheme.lower() != 'basic': + URLopener.http_error_default(self, url, fp, + errcode, errmsg, headers) + name = 'retry_proxy_' + self.type + '_basic_auth' + if data is None: + return getattr(self,name)(url, realm) + else: + return getattr(self,name)(url, realm, data) + + def retry_proxy_http_basic_auth(self, url, realm, data=None): + host, selector = urllib.parse.splithost(url) + newurl = 'http://' + host + selector + proxy = self.proxies['http'] + urltype, proxyhost = urllib.parse.splittype(proxy) + proxyhost, proxyselector = urllib.parse.splithost(proxyhost) + i = proxyhost.find('@') + 1 + proxyhost = proxyhost[i:] + user, passwd = self.get_user_passwd(proxyhost, realm, i) + if not (user or passwd): return None + proxyhost = "%s:%s@%s" % (urllib.parse.quote(user, safe=''), + quote(passwd, safe=''), proxyhost) + self.proxies['http'] = 'http://' + proxyhost + proxyselector + if data is None: + return self.open(newurl) + else: + return self.open(newurl, data) + + def retry_proxy_https_basic_auth(self, url, realm, data=None): + host, selector = urllib.parse.splithost(url) + newurl = 'https://' + host + selector + proxy = self.proxies['https'] + urltype, proxyhost = urllib.parse.splittype(proxy) + proxyhost, proxyselector = urllib.parse.splithost(proxyhost) + i = proxyhost.find('@') + 1 + proxyhost = proxyhost[i:] + user, passwd = self.get_user_passwd(proxyhost, realm, i) + if not (user or passwd): return None + proxyhost = "%s:%s@%s" % (urllib.parse.quote(user, safe=''), + quote(passwd, safe=''), proxyhost) + self.proxies['https'] = 'https://' + proxyhost + proxyselector + if data is None: + return self.open(newurl) + else: + return self.open(newurl, data) + + def retry_http_basic_auth(self, url, realm, data=None): + host, selector = urllib.parse.splithost(url) + i = host.find('@') + 1 + host = host[i:] + user, passwd = self.get_user_passwd(host, realm, i) + if not (user or passwd): return None + host = "%s:%s@%s" % (urllib.parse.quote(user, safe=''), + quote(passwd, safe=''), host) + newurl = 'http://' + host + selector + if data is None: + return self.open(newurl) + else: + return self.open(newurl, data) + + def retry_https_basic_auth(self, url, realm, data=None): + host, selector = urllib.parse.splithost(url) + i = host.find('@') + 1 + host = host[i:] + user, passwd = self.get_user_passwd(host, realm, i) + if not (user or passwd): return None + host = "%s:%s@%s" % (urllib.parse.quote(user, safe=''), + quote(passwd, safe=''), host) + newurl = 'https://' + host + selector + if data is None: + return self.open(newurl) + else: + return self.open(newurl, data) + + def get_user_passwd(self, host, realm, clear_cache = 0): + key = realm + '@' + host.lower() + if key in self.auth_cache: + if clear_cache: + del self.auth_cache[key] + else: + return self.auth_cache[key] + user, passwd = self.prompt_user_passwd(host, realm) + if user or passwd: self.auth_cache[key] = (user, passwd) + return user, passwd + + def prompt_user_passwd(self, host, realm): + """Override this in a GUI environment!""" + import getpass + try: + user = input("Enter username for %s at %s: " % (realm, host)) + passwd = getpass.getpass("Enter password for %s in %s at %s: " % + (user, realm, host)) + return user, passwd + except KeyboardInterrupt: + print() + return None, None + + +# Utility functions + +_localhost = None +def localhost(): + """Return the IP address of the magic hostname 'localhost'.""" + global _localhost + if _localhost is None: + _localhost = socket.gethostbyname('localhost') + return _localhost + +_thishost = None +def thishost(): + """Return the IP address of the current host.""" + global _thishost + if _thishost is None: + _thishost = socket.gethostbyname(socket.gethostname()) + return _thishost + +_ftperrors = None +def ftperrors(): + """Return the set of errors raised by the FTP class.""" + global _ftperrors + if _ftperrors is None: + import ftplib + _ftperrors = ftplib.all_errors + return _ftperrors + +_noheaders = None +def noheaders(): + """Return an empty mimetools.Message object.""" + global _noheaders + if _noheaders is None: + _noheaders = mimetools.message_from_string("") + return _noheaders + + +# Utility classes + +class ftpwrapper: + """Class used by open_ftp() for cache of open FTP connections.""" + + def __init__(self, user, passwd, host, port, dirs, timeout=None): + self.user = user + self.passwd = passwd + self.host = host + self.port = port + self.dirs = dirs + self.timeout = timeout + self.init() + + def init(self): + import ftplib + self.busy = 0 + self.ftp = ftplib.FTP() + self.ftp.connect(self.host, self.port, self.timeout) + self.ftp.login(self.user, self.passwd) + for dir in self.dirs: + self.ftp.cwd(dir) + + def retrfile(self, file, type): + import ftplib + self.endtransfer() + if type in ('d', 'D'): cmd = 'TYPE A'; isdir = 1 + else: cmd = 'TYPE ' + type; isdir = 0 + try: + self.ftp.voidcmd(cmd) + except ftplib.all_errors: + self.init() + self.ftp.voidcmd(cmd) + conn = None + if file and not isdir: + # Try to retrieve as a file + try: + cmd = 'RETR ' + file + conn = self.ftp.ntransfercmd(cmd) + except ftplib.error_perm as reason: + if str(reason)[:3] != '550': + raise urllib.error.URLError('ftp error', reason).with_traceback(sys.exc_info()[2]) + if not conn: + # Set transfer mode to ASCII! + self.ftp.voidcmd('TYPE A') + # Try a directory listing. Verify that directory exists. + if file: + pwd = self.ftp.pwd() + try: + try: + self.ftp.cwd(file) + except ftplib.error_perm as reason: + raise urllib.error.URLError('ftp error', reason) from reason + finally: + self.ftp.cwd(pwd) + cmd = 'LIST ' + file + else: + cmd = 'LIST' + conn = self.ftp.ntransfercmd(cmd) + self.busy = 1 + # Pass back both a suitably decorated object and a retrieval length + return (urllib.response.addclosehook(conn[0].makefile('rb'), + self.endtransfer), conn[1]) + def endtransfer(self): + if not self.busy: + return + self.busy = 0 + try: + self.ftp.voidresp() + except ftperrors(): + pass + + def close(self): + self.endtransfer() + try: + self.ftp.close() + except ftperrors(): + pass + +# Proxy handling +def getproxies_environment(): + """Return a dictionary of scheme -> proxy server URL mappings. + + Scan the environment for variables named <scheme>_proxy; + this seems to be the standard convention. If you need a + different way, you can pass a proxies dictionary to the + [Fancy]URLopener constructor. + + """ + proxies = {} + for name, value in os.environ.items(): + name = name.lower() + if name == 'no_proxy': + # handled in proxy_bypass_environment + continue + if value and name[-6:] == '_proxy': + proxies[name[:-6]] = value + return proxies + +def proxy_bypass_environment(host): + """Test if proxies should not be used for a particular host. + + Checks the environment for a variable named no_proxy, which should + be a list of DNS suffixes separated by commas, or '*' for all hosts. + """ + no_proxy = os.environ.get('no_proxy', '') or os.environ.get('NO_PROXY', '') + # '*' is special case for always bypass + if no_proxy == '*': + return 1 + # strip port off host + hostonly, port = urllib.parse.splitport(host) + # check if the host ends with any of the DNS suffixes + for name in no_proxy.split(','): + if name and (hostonly.endswith(name) or host.endswith(name)): + return 1 + # otherwise, don't bypass + return 0 + + +if sys.platform == 'darwin': + def getproxies_internetconfig(): + """Return a dictionary of scheme -> proxy server URL mappings. + + By convention the mac uses Internet Config to store + proxies. An HTTP proxy, for instance, is stored under + the HttpProxy key. + + """ + try: + import ic + except ImportError: + return {} + + try: + config = ic.IC() + except ic.error: + return {} + proxies = {} + # HTTP: + if 'UseHTTPProxy' in config and config['UseHTTPProxy']: + try: + value = config['HTTPProxyHost'] + except ic.error: + pass + else: + proxies['http'] = 'http://%s' % value + # FTP: XXX To be done. + # Gopher: XXX To be done. + return proxies + + def proxy_bypass(host): + if getproxies_environment(): + return proxy_bypass_environment(host) + else: + return 0 + + def getproxies(): + return getproxies_environment() or getproxies_internetconfig() + +elif os.name == 'nt': + def getproxies_registry(): + """Return a dictionary of scheme -> proxy server URL mappings. + + Win32 uses the registry to store proxies. + + """ + proxies = {} + try: + import _winreg + except ImportError: + # Std module, so should be around - but you never know! + return proxies + try: + internetSettings = _winreg.OpenKey(_winreg.HKEY_CURRENT_USER, + r'Software\Microsoft\Windows\CurrentVersion\Internet Settings') + proxyEnable = _winreg.QueryValueEx(internetSettings, + 'ProxyEnable')[0] + if proxyEnable: + # Returned as Unicode but problems if not converted to ASCII + proxyServer = str(_winreg.QueryValueEx(internetSettings, + 'ProxyServer')[0]) + if '=' in proxyServer: + # Per-protocol settings + for p in proxyServer.split(';'): + protocol, address = p.split('=', 1) + # See if address has a type:// prefix + import re + if not re.match('^([^/:]+)://', address): + address = '%s://%s' % (protocol, address) + proxies[protocol] = address + else: + # Use one setting for all protocols + if proxyServer[:5] == 'http:': + proxies['http'] = proxyServer + else: + proxies['http'] = 'http://%s' % proxyServer + proxies['ftp'] = 'ftp://%s' % proxyServer + internetSettings.Close() + except (WindowsError, ValueError, TypeError): + # Either registry key not found etc, or the value in an + # unexpected format. + # proxies already set up to be empty so nothing to do + pass + return proxies + + def getproxies(): + """Return a dictionary of scheme -> proxy server URL mappings. + + Returns settings gathered from the environment, if specified, + or the registry. + + """ + return getproxies_environment() or getproxies_registry() + + def proxy_bypass_registry(host): + try: + import _winreg + import re + except ImportError: + # Std modules, so should be around - but you never know! + return 0 + try: + internetSettings = _winreg.OpenKey(_winreg.HKEY_CURRENT_USER, + r'Software\Microsoft\Windows\CurrentVersion\Internet Settings') + proxyEnable = _winreg.QueryValueEx(internetSettings, + 'ProxyEnable')[0] + proxyOverride = str(_winreg.QueryValueEx(internetSettings, + 'ProxyOverride')[0]) + # ^^^^ Returned as Unicode but problems if not converted to ASCII + except WindowsError: + return 0 + if not proxyEnable or not proxyOverride: + return 0 + # try to make a host list from name and IP address. + rawHost, port = urllib.parse.splitport(host) + host = [rawHost] + try: + addr = socket.gethostbyname(rawHost) + if addr != rawHost: + host.append(addr) + except socket.error: + pass + try: + fqdn = socket.getfqdn(rawHost) + if fqdn != rawHost: + host.append(fqdn) + except socket.error: + pass + # make a check value list from the registry entry: replace the + # '<local>' string by the localhost entry and the corresponding + # canonical entry. + proxyOverride = proxyOverride.split(';') + i = 0 + while i < len(proxyOverride): + if proxyOverride[i] == '<local>': + proxyOverride[i:i+1] = ['localhost', + '127.0.0.1', + socket.gethostname(), + socket.gethostbyname( + socket.gethostname())] + i += 1 + # print proxyOverride + # now check if we match one of the registry values. + for test in proxyOverride: + test = test.replace(".", r"\.") # mask dots + test = test.replace("*", r".*") # change glob sequence + test = test.replace("?", r".") # change glob char + for val in host: + # print "%s <--> %s" %( test, val ) + if re.match(test, val, re.I): + return 1 + return 0 + + def proxy_bypass(host): + """Return a dictionary of scheme -> proxy server URL mappings. + + Returns settings gathered from the environment, if specified, + or the registry. + + """ + if getproxies_environment(): + return proxy_bypass_environment(host) + else: + return proxy_bypass_registry(host) + +else: + # By default use environment variables + getproxies = getproxies_environment + proxy_bypass = proxy_bypass_environment diff --git a/Lib/urllib/response.py b/Lib/urllib/response.py new file mode 100644 index 0000000..1352622 --- /dev/null +++ b/Lib/urllib/response.py @@ -0,0 +1,83 @@ +"""Response classes used by urllib. + +The base class, addbase, defines a minimal file-like interface, +including read() and readline(). The typical response object is an +addinfourl instance, which defines an info() method that returns +headers and a geturl() method that returns the url. +""" + +class addbase(object): + """Base class for addinfo and addclosehook.""" + + # XXX Add a method to expose the timeout on the underlying socket? + + def __init__(self, fp): + # TODO(jhylton): Is there a better way to delegate using io? + self.fp = fp + self.read = self.fp.read + self.readline = self.fp.readline + # TODO(jhylton): Make sure an object with readlines() is also iterable + if hasattr(self.fp, "readlines"): self.readlines = self.fp.readlines + if hasattr(self.fp, "fileno"): + self.fileno = self.fp.fileno + else: + self.fileno = lambda: None + if hasattr(self.fp, "__iter__"): + self.__iter__ = self.fp.__iter__ + if hasattr(self.fp, "__next__"): + self.__next__ = self.fp.__next__ + + def __repr__(self): + return '<%s at %r whose fp = %r>' % (self.__class__.__name__, + id(self), self.fp) + + def close(self): + self.read = None + self.readline = None + self.readlines = None + self.fileno = None + if self.fp: self.fp.close() + self.fp = None + +class addclosehook(addbase): + """Class to add a close hook to an open file.""" + + def __init__(self, fp, closehook, *hookargs): + addbase.__init__(self, fp) + self.closehook = closehook + self.hookargs = hookargs + + def close(self): + addbase.close(self) + if self.closehook: + self.closehook(*self.hookargs) + self.closehook = None + self.hookargs = None + +class addinfo(addbase): + """class to add an info() method to an open file.""" + + def __init__(self, fp, headers): + addbase.__init__(self, fp) + self.headers = headers + + def info(self): + return self.headers + +class addinfourl(addbase): + """class to add info() and geturl() methods to an open file.""" + + def __init__(self, fp, headers, url, code=None): + addbase.__init__(self, fp) + self.headers = headers + self.url = url + self.code = code + + def info(self): + return self.headers + + def getcode(self): + return self.code + + def geturl(self): + return self.url diff --git a/Lib/urllib/robotparser.py b/Lib/urllib/robotparser.py new file mode 100644 index 0000000..a91df8d --- /dev/null +++ b/Lib/urllib/robotparser.py @@ -0,0 +1,191 @@ +""" robotparser.py + + Copyright (C) 2000 Bastian Kleineidam + + You can choose between two licenses when using this package: + 1) GNU GPLv2 + 2) PSF license for Python 2.2 + + The robots.txt Exclusion Protocol is implemented as specified in + http://info.webcrawler.com/mak/projects/robots/norobots-rfc.html +""" + +import urllib.parse, urllib.request + +__all__ = ["RobotFileParser"] + +class RobotFileParser: + """ This class provides a set of methods to read, parse and answer + questions about a single robots.txt file. + + """ + + def __init__(self, url=''): + self.entries = [] + self.default_entry = None + self.disallow_all = False + self.allow_all = False + self.set_url(url) + self.last_checked = 0 + + def mtime(self): + """Returns the time the robots.txt file was last fetched. + + This is useful for long-running web spiders that need to + check for new robots.txt files periodically. + + """ + return self.last_checked + + def modified(self): + """Sets the time the robots.txt file was last fetched to the + current time. + + """ + import time + self.last_checked = time.time() + + def set_url(self, url): + """Sets the URL referring to a robots.txt file.""" + self.url = url + self.host, self.path = urllib.parse.urlparse(url)[1:3] + + def read(self): + """Reads the robots.txt URL and feeds it to the parser.""" + try: + f = urllib.request.urlopen(self.url) + except urllib.error.HTTPError as err: + if err.code in (401, 403): + self.disallow_all = True + elif err.code >= 400: + self.allow_all = True + else: + self.parse(f.read().splitlines()) + + def _add_entry(self, entry): + if "*" in entry.useragents: + # the default entry is considered last + self.default_entry = entry + else: + self.entries.append(entry) + + def parse(self, lines): + """Parse the input lines from a robots.txt file. + + We allow that a user-agent: line is not preceded by + one or more blank lines. + """ + state = 0 + entry = Entry() + + for line in lines: + if not line: + if state == 1: + entry = Entry() + state = 0 + elif state == 2: + self._add_entry(entry) + entry = Entry() + state = 0 + # remove optional comment and strip line + i = line.find('#') + if i >= 0: + line = line[:i] + line = line.strip() + if not line: + continue + line = line.split(':', 1) + if len(line) == 2: + line[0] = line[0].strip().lower() + line[1] = urllib.parse.unquote(line[1].strip()) + if line[0] == "user-agent": + if state == 2: + self._add_entry(entry) + entry = Entry() + entry.useragents.append(line[1]) + state = 1 + elif line[0] == "disallow": + if state != 0: + entry.rulelines.append(RuleLine(line[1], False)) + state = 2 + elif line[0] == "allow": + if state != 0: + entry.rulelines.append(RuleLine(line[1], True)) + if state == 2: + self.entries.append(entry) + + + def can_fetch(self, useragent, url): + """using the parsed robots.txt decide if useragent can fetch url""" + if self.disallow_all: + return False + if self.allow_all: + return True + # search for given user agent matches + # the first match counts + url = urllib.parse.quote(urllib.parse.urlparse(urllib.parse.unquote(url))[2]) or "/" + for entry in self.entries: + if entry.applies_to(useragent): + return entry.allowance(url) + # try the default entry last + if self.default_entry: + return self.default_entry.allowance(url) + # agent not found ==> access granted + return True + + def __str__(self): + return ''.join([str(entry) + "\n" for entry in self.entries]) + + +class RuleLine: + """A rule line is a single "Allow:" (allowance==True) or "Disallow:" + (allowance==False) followed by a path.""" + def __init__(self, path, allowance): + if path == '' and not allowance: + # an empty value means allow all + allowance = True + self.path = urllib.parse.quote(path) + self.allowance = allowance + + def applies_to(self, filename): + return self.path == "*" or filename.startswith(self.path) + + def __str__(self): + return (self.allowance and "Allow" or "Disallow") + ": " + self.path + + +class Entry: + """An entry has one or more user-agents and zero or more rulelines""" + def __init__(self): + self.useragents = [] + self.rulelines = [] + + def __str__(self): + ret = [] + for agent in self.useragents: + ret.extend(["User-agent: ", agent, "\n"]) + for line in self.rulelines: + ret.extend([str(line), "\n"]) + return ''.join(ret) + + def applies_to(self, useragent): + """check if this entry applies to the specified agent""" + # split the name token and make it lower case + useragent = useragent.split("/")[0].lower() + for agent in self.useragents: + if agent == '*': + # we have the catch-all agent + return True + agent = agent.lower() + if agent in useragent: + return True + return False + + def allowance(self, filename): + """Preconditions: + - our agent applies to this entry + - filename is URL decoded""" + for line in self.rulelines: + if line.applies_to(filename): + return line.allowance + return True |