whoami7 - Manager
:
/
home
/
fresvfqn
/
waterdamagerestorationandrepairsmithtown.com
/
Compressed
/
Upload File:
files >> //home/fresvfqn/waterdamagerestorationandrepairsmithtown.com/Compressed/http.zip
PK � [��MZ#, #, cookiejar.pynu �[��� r"""HTTP cookie handling for web clients. This module has (now fairly distant) origins in Gisle Aas' Perl module HTTP::Cookies, from the libwww-perl library. Docstrings, comments and debug strings in this code refer to the attributes of the HTTP cookie system as cookie-attributes, to distinguish them clearly from Python attributes. Class diagram (note that BSDDBCookieJar and the MSIE* classes are not distributed with the Python standard library, but are available from http://wwwsearch.sf.net/): CookieJar____ / \ \ FileCookieJar \ \ / | \ \ \ MozillaCookieJar | LWPCookieJar \ \ | | \ | ---MSIEBase | \ | / | | \ | / MSIEDBCookieJar BSDDBCookieJar |/ MSIECookieJar """ __all__ = ['Cookie', 'CookieJar', 'CookiePolicy', 'DefaultCookiePolicy', 'FileCookieJar', 'LWPCookieJar', 'LoadError', 'MozillaCookieJar'] import os import copy import datetime import re import time import urllib.parse, urllib.request import threading as _threading import http.client # only for the default HTTP port from calendar import timegm debug = False # set to True to enable debugging via the logging module logger = None def _debug(*args): if not debug: return global logger if not logger: import logging logger = logging.getLogger("http.cookiejar") return logger.debug(*args) DEFAULT_HTTP_PORT = str(http.client.HTTP_PORT) MISSING_FILENAME_TEXT = ("a filename was not supplied (nor was the CookieJar " "instance initialised with one)") def _warn_unhandled_exception(): # There are a few catch-all except: statements in this module, for # catching input that's bad in unexpected ways. Warn if any # exceptions are caught there. import io, warnings, traceback f = io.StringIO() traceback.print_exc(None, f) msg = f.getvalue() warnings.warn("http.cookiejar bug!\n%s" % msg, stacklevel=2) # Date/time conversion # ----------------------------------------------------------------------------- EPOCH_YEAR = 1970 def _timegm(tt): year, month, mday, hour, min, sec = tt[:6] if ((year >= EPOCH_YEAR) and (1 <= month <= 12) and (1 <= mday <= 31) and (0 <= hour <= 24) and (0 <= min <= 59) and (0 <= sec <= 61)): return timegm(tt) else: return None DAYS = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"] MONTHS = ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"] MONTHS_LOWER = [] for month in MONTHS: MONTHS_LOWER.append(month.lower()) def time2isoz(t=None): """Return a string representing time in seconds since epoch, t. If the function is called without an argument, it will use the current time. The format of the returned string is like "YYYY-MM-DD hh:mm:ssZ", representing Universal Time (UTC, aka GMT). An example of this format is: 1994-11-24 08:49:37Z """ if t is None: dt = datetime.datetime.utcnow() else: dt = datetime.datetime.utcfromtimestamp(t) return "%04d-%02d-%02d %02d:%02d:%02dZ" % ( dt.year, dt.month, dt.day, dt.hour, dt.minute, dt.second) def time2netscape(t=None): """Return a string representing time in seconds since epoch, t. If the function is called without an argument, it will use the current time. The format of the returned string is like this: Wed, DD-Mon-YYYY HH:MM:SS GMT """ if t is None: dt = datetime.datetime.utcnow() else: dt = datetime.datetime.utcfromtimestamp(t) return "%s, %02d-%s-%04d %02d:%02d:%02d GMT" % ( DAYS[dt.weekday()], dt.day, MONTHS[dt.month-1], dt.year, dt.hour, dt.minute, dt.second) UTC_ZONES = {"GMT": None, "UTC": None, "UT": None, "Z": None} TIMEZONE_RE = re.compile(r"^([-+])?(\d\d?):?(\d\d)?$", re.ASCII) def offset_from_tz_string(tz): offset = None if tz in UTC_ZONES: offset = 0 else: m = TIMEZONE_RE.search(tz) if m: offset = 3600 * int(m.group(2)) if m.group(3): offset = offset + 60 * int(m.group(3)) if m.group(1) == '-': offset = -offset return offset def _str2time(day, mon, yr, hr, min, sec, tz): yr = int(yr) if yr > datetime.MAXYEAR: return None # translate month name to number # month numbers start with 1 (January) try: mon = MONTHS_LOWER.index(mon.lower())+1 except ValueError: # maybe it's already a number try: imon = int(mon) except ValueError: return None if 1 <= imon <= 12: mon = imon else: return None # make sure clock elements are defined if hr is None: hr = 0 if min is None: min = 0 if sec is None: sec = 0 day = int(day) hr = int(hr) min = int(min) sec = int(sec) if yr < 1000: # find "obvious" year cur_yr = time.localtime(time.time())[0] m = cur_yr % 100 tmp = yr yr = yr + cur_yr - m m = m - tmp if abs(m) > 50: if m > 0: yr = yr + 100 else: yr = yr - 100 # convert UTC time tuple to seconds since epoch (not timezone-adjusted) t = _timegm((yr, mon, day, hr, min, sec, tz)) if t is not None: # adjust time using timezone string, to get absolute time since epoch if tz is None: tz = "UTC" tz = tz.upper() offset = offset_from_tz_string(tz) if offset is None: return None t = t - offset return t STRICT_DATE_RE = re.compile( r"^[SMTWF][a-z][a-z], (\d\d) ([JFMASOND][a-z][a-z]) " r"(\d\d\d\d) (\d\d):(\d\d):(\d\d) GMT$", re.ASCII) WEEKDAY_RE = re.compile( r"^(?:Sun|Mon|Tue|Wed|Thu|Fri|Sat)[a-z]*,?\s*", re.I | re.ASCII) LOOSE_HTTP_DATE_RE = re.compile( r"""^ (\d\d?) # day (?:\s+|[-\/]) (\w+) # month (?:\s+|[-\/]) (\d+) # year (?: (?:\s+|:) # separator before clock (\d\d?):(\d\d) # hour:min (?::(\d\d))? # optional seconds )? # optional clock \s* (?: ([-+]?\d{2,4}|(?![APap][Mm]\b)[A-Za-z]+) # timezone \s* )? (?: \(\w+\) # ASCII representation of timezone in parens. \s* )?$""", re.X | re.ASCII) def http2time(text): """Returns time in seconds since epoch of time represented by a string. Return value is an integer. None is returned if the format of str is unrecognized, the time is outside the representable range, or the timezone string is not recognized. If the string contains no timezone, UTC is assumed. The timezone in the string may be numerical (like "-0800" or "+0100") or a string timezone (like "UTC", "GMT", "BST" or "EST"). Currently, only the timezone strings equivalent to UTC (zero offset) are known to the function. The function loosely parses the following formats: Wed, 09 Feb 1994 22:23:32 GMT -- HTTP format Tuesday, 08-Feb-94 14:15:29 GMT -- old rfc850 HTTP format Tuesday, 08-Feb-1994 14:15:29 GMT -- broken rfc850 HTTP format 09 Feb 1994 22:23:32 GMT -- HTTP format (no weekday) 08-Feb-94 14:15:29 GMT -- rfc850 format (no weekday) 08-Feb-1994 14:15:29 GMT -- broken rfc850 format (no weekday) The parser ignores leading and trailing whitespace. The time may be absent. If the year is given with only 2 digits, the function will select the century that makes the year closest to the current date. """ # fast exit for strictly conforming string m = STRICT_DATE_RE.search(text) if m: g = m.groups() mon = MONTHS_LOWER.index(g[1].lower()) + 1 tt = (int(g[2]), mon, int(g[0]), int(g[3]), int(g[4]), float(g[5])) return _timegm(tt) # No, we need some messy parsing... # clean up text = text.lstrip() text = WEEKDAY_RE.sub("", text, 1) # Useless weekday # tz is time zone specifier string day, mon, yr, hr, min, sec, tz = [None]*7 # loose regexp parse m = LOOSE_HTTP_DATE_RE.search(text) if m is not None: day, mon, yr, hr, min, sec, tz = m.groups() else: return None # bad format return _str2time(day, mon, yr, hr, min, sec, tz) ISO_DATE_RE = re.compile( r"""^ (\d{4}) # year [-\/]? (\d\d?) # numerical month [-\/]? (\d\d?) # day (?: (?:\s+|[-:Tt]) # separator before clock (\d\d?):?(\d\d) # hour:min (?::?(\d\d(?:\.\d*)?))? # optional seconds (and fractional) )? # optional clock \s* (?: ([-+]?\d\d?:?(:?\d\d)? |Z|z) # timezone (Z is "zero meridian", i.e. GMT) \s* )?$""", re.X | re. ASCII) def iso2time(text): """ As for http2time, but parses the ISO 8601 formats: 1994-02-03 14:15:29 -0100 -- ISO 8601 format 1994-02-03 14:15:29 -- zone is optional 1994-02-03 -- only date 1994-02-03T14:15:29 -- Use T as separator 19940203T141529Z -- ISO 8601 compact format 19940203 -- only date """ # clean up text = text.lstrip() # tz is time zone specifier string day, mon, yr, hr, min, sec, tz = [None]*7 # loose regexp parse m = ISO_DATE_RE.search(text) if m is not None: # XXX there's an extra bit of the timezone I'm ignoring here: is # this the right thing to do? yr, mon, day, hr, min, sec, tz, _ = m.groups() else: return None # bad format return _str2time(day, mon, yr, hr, min, sec, tz) # Header parsing # ----------------------------------------------------------------------------- def unmatched(match): """Return unmatched part of re.Match object.""" start, end = match.span(0) return match.string[:start]+match.string[end:] HEADER_TOKEN_RE = re.compile(r"^\s*([^=\s;,]+)") HEADER_QUOTED_VALUE_RE = re.compile(r"^\s*=\s*\"([^\"\\]*(?:\\.[^\"\\]*)*)\"") HEADER_VALUE_RE = re.compile(r"^\s*=\s*([^\s;,]*)") HEADER_ESCAPE_RE = re.compile(r"\\(.)") def split_header_words(header_values): r"""Parse header values into a list of lists containing key,value pairs. The function knows how to deal with ",", ";" and "=" as well as quoted values after "=". A list of space separated tokens are parsed as if they were separated by ";". If the header_values passed as argument contains multiple values, then they are treated as if they were a single value separated by comma ",". This means that this function is useful for parsing header fields that follow this syntax (BNF as from the HTTP/1.1 specification, but we relax the requirement for tokens). headers = #header header = (token | parameter) *( [";"] (token | parameter)) token = 1*<any CHAR except CTLs or separators> separators = "(" | ")" | "<" | ">" | "@" | "," | ";" | ":" | "\" | <"> | "/" | "[" | "]" | "?" | "=" | "{" | "}" | SP | HT quoted-string = ( <"> *(qdtext | quoted-pair ) <"> ) qdtext = <any TEXT except <">> quoted-pair = "\" CHAR parameter = attribute "=" value attribute = token value = token | quoted-string Each header is represented by a list of key/value pairs. The value for a simple token (not part of a parameter) is None. Syntactically incorrect headers will not necessarily be parsed as you would want. This is easier to describe with some examples: >>> split_header_words(['foo="bar"; port="80,81"; discard, bar=baz']) [[('foo', 'bar'), ('port', '80,81'), ('discard', None)], [('bar', 'baz')]] >>> split_header_words(['text/html; charset="iso-8859-1"']) [[('text/html', None), ('charset', 'iso-8859-1')]] >>> split_header_words([r'Basic realm="\"foo\bar\""']) [[('Basic', None), ('realm', '"foobar"')]] """ assert not isinstance(header_values, str) result = [] for text in header_values: orig_text = text pairs = [] while text: m = HEADER_TOKEN_RE.search(text) if m: text = unmatched(m) name = m.group(1) m = HEADER_QUOTED_VALUE_RE.search(text) if m: # quoted value text = unmatched(m) value = m.group(1) value = HEADER_ESCAPE_RE.sub(r"\1", value) else: m = HEADER_VALUE_RE.search(text) if m: # unquoted value text = unmatched(m) value = m.group(1) value = value.rstrip() else: # no value, a lone token value = None pairs.append((name, value)) elif text.lstrip().startswith(","): # concatenated headers, as per RFC 2616 section 4.2 text = text.lstrip()[1:] if pairs: result.append(pairs) pairs = [] else: # skip junk non_junk, nr_junk_chars = re.subn(r"^[=\s;]*", "", text) assert nr_junk_chars > 0, ( "split_header_words bug: '%s', '%s', %s" % (orig_text, text, pairs)) text = non_junk if pairs: result.append(pairs) return result HEADER_JOIN_ESCAPE_RE = re.compile(r"([\"\\])") def join_header_words(lists): """Do the inverse (almost) of the conversion done by split_header_words. Takes a list of lists of (key, value) pairs and produces a single header value. Attribute values are quoted if needed. >>> join_header_words([[("text/plain", None), ("charset", "iso-8859-1")]]) 'text/plain; charset="iso-8859-1"' >>> join_header_words([[("text/plain", None)], [("charset", "iso-8859-1")]]) 'text/plain, charset="iso-8859-1"' """ headers = [] for pairs in lists: attr = [] for k, v in pairs: if v is not None: if not re.search(r"^\w+$", v): v = HEADER_JOIN_ESCAPE_RE.sub(r"\\\1", v) # escape " and \ v = '"%s"' % v k = "%s=%s" % (k, v) attr.append(k) if attr: headers.append("; ".join(attr)) return ", ".join(headers) def strip_quotes(text): if text.startswith('"'): text = text[1:] if text.endswith('"'): text = text[:-1] return text def parse_ns_headers(ns_headers): """Ad-hoc parser for Netscape protocol cookie-attributes. The old Netscape cookie format for Set-Cookie can for instance contain an unquoted "," in the expires field, so we have to use this ad-hoc parser instead of split_header_words. XXX This may not make the best possible effort to parse all the crap that Netscape Cookie headers contain. Ronald Tschalar's HTTPClient parser is probably better, so could do worse than following that if this ever gives any trouble. Currently, this is also used for parsing RFC 2109 cookies. """ known_attrs = ("expires", "domain", "path", "secure", # RFC 2109 attrs (may turn up in Netscape cookies, too) "version", "port", "max-age") result = [] for ns_header in ns_headers: pairs = [] version_set = False # XXX: The following does not strictly adhere to RFCs in that empty # names and values are legal (the former will only appear once and will # be overwritten if multiple occurrences are present). This is # mostly to deal with backwards compatibility. for ii, param in enumerate(ns_header.split(';')): param = param.strip() key, sep, val = param.partition('=') key = key.strip() if not key: if ii == 0: break else: continue # allow for a distinction between present and empty and missing # altogether val = val.strip() if sep else None if ii != 0: lc = key.lower() if lc in known_attrs: key = lc if key == "version": # This is an RFC 2109 cookie. if val is not None: val = strip_quotes(val) version_set = True elif key == "expires": # convert expires date to seconds since epoch if val is not None: val = http2time(strip_quotes(val)) # None if invalid pairs.append((key, val)) if pairs: if not version_set: pairs.append(("version", "0")) result.append(pairs) return result IPV4_RE = re.compile(r"\.\d+$", re.ASCII) def is_HDN(text): """Return True if text is a host domain name.""" # XXX # This may well be wrong. Which RFC is HDN defined in, if any (for # the purposes of RFC 2965)? # For the current implementation, what about IPv6? Remember to look # at other uses of IPV4_RE also, if change this. if IPV4_RE.search(text): return False if text == "": return False if text[0] == "." or text[-1] == ".": return False return True def domain_match(A, B): """Return True if domain A domain-matches domain B, according to RFC 2965. A and B may be host domain names or IP addresses. RFC 2965, section 1: Host names can be specified either as an IP address or a HDN string. Sometimes we compare one host name with another. (Such comparisons SHALL be case-insensitive.) Host A's name domain-matches host B's if * their host name strings string-compare equal; or * A is a HDN string and has the form NB, where N is a non-empty name string, B has the form .B', and B' is a HDN string. (So, x.y.com domain-matches .Y.com but not Y.com.) Note that domain-match is not a commutative operation: a.b.c.com domain-matches .c.com, but not the reverse. """ # Note that, if A or B are IP addresses, the only relevant part of the # definition of the domain-match algorithm is the direct string-compare. A = A.lower() B = B.lower() if A == B: return True if not is_HDN(A): return False i = A.rfind(B) if i == -1 or i == 0: # A does not have form NB, or N is the empty string return False if not B.startswith("."): return False if not is_HDN(B[1:]): return False return True def liberal_is_HDN(text): """Return True if text is a sort-of-like a host domain name. For accepting/blocking domains. """ if IPV4_RE.search(text): return False return True def user_domain_match(A, B): """For blocking/accepting domains. A and B may be host domain names or IP addresses. """ A = A.lower() B = B.lower() if not (liberal_is_HDN(A) and liberal_is_HDN(B)): if A == B: # equal IP addresses return True return False initial_dot = B.startswith(".") if initial_dot and A.endswith(B): return True if not initial_dot and A == B: return True return False cut_port_re = re.compile(r":\d+$", re.ASCII) def request_host(request): """Return request-host, as defined by RFC 2965. Variation from RFC: returned value is lowercased, for convenient comparison. """ url = request.get_full_url() host = urllib.parse.urlparse(url)[1] if host == "": host = request.get_header("Host", "") # remove port, if present host = cut_port_re.sub("", host, 1) return host.lower() def eff_request_host(request): """Return a tuple (request-host, effective request-host name). As defined by RFC 2965, except both are lowercased. """ erhn = req_host = request_host(request) if req_host.find(".") == -1 and not IPV4_RE.search(req_host): erhn = req_host + ".local" return req_host, erhn def request_path(request): """Path component of request-URI, as defined by RFC 2965.""" url = request.get_full_url() parts = urllib.parse.urlsplit(url) path = escape_path(parts.path) if not path.startswith("/"): # fix bad RFC 2396 absoluteURI path = "/" + path return path def request_port(request): host = request.host i = host.find(':') if i >= 0: port = host[i+1:] try: int(port) except ValueError: _debug("nonnumeric port: '%s'", port) return None else: port = DEFAULT_HTTP_PORT return port # Characters in addition to A-Z, a-z, 0-9, '_', '.', and '-' that don't # need to be escaped to form a valid HTTP URL (RFCs 2396 and 1738). HTTP_PATH_SAFE = "%/;:@&=+$,!~*'()" ESCAPED_CHAR_RE = re.compile(r"%([0-9a-fA-F][0-9a-fA-F])") def uppercase_escaped_char(match): return "%%%s" % match.group(1).upper() def escape_path(path): """Escape any invalid characters in HTTP URL, and uppercase all escapes.""" # There's no knowing what character encoding was used to create URLs # containing %-escapes, but since we have to pick one to escape invalid # path characters, we pick UTF-8, as recommended in the HTML 4.0 # specification: # http://www.w3.org/TR/REC-html40/appendix/notes.html#h-B.2.1 # And here, kind of: draft-fielding-uri-rfc2396bis-03 # (And in draft IRI specification: draft-duerst-iri-05) # (And here, for new URI schemes: RFC 2718) path = urllib.parse.quote(path, HTTP_PATH_SAFE) path = ESCAPED_CHAR_RE.sub(uppercase_escaped_char, path) return path def reach(h): """Return reach of host h, as defined by RFC 2965, section 1. The reach R of a host name H is defined as follows: * If - H is the host domain name of a host; and, - H has the form A.B; and - A has no embedded (that is, interior) dots; and - B has at least one embedded dot, or B is the string "local". then the reach of H is .B. * Otherwise, the reach of H is H. >>> reach("www.acme.com") '.acme.com' >>> reach("acme.com") 'acme.com' >>> reach("acme.local") '.local' """ i = h.find(".") if i >= 0: #a = h[:i] # this line is only here to show what a is b = h[i+1:] i = b.find(".") if is_HDN(h) and (i >= 0 or b == "local"): return "."+b return h def is_third_party(request): """ RFC 2965, section 3.3.6: An unverifiable transaction is to a third-party host if its request- host U does not domain-match the reach R of the request-host O in the origin transaction. """ req_host = request_host(request) if not domain_match(req_host, reach(request.origin_req_host)): return True else: return False class Cookie: """HTTP Cookie. This class represents both Netscape and RFC 2965 cookies. This is deliberately a very simple class. It just holds attributes. It's possible to construct Cookie instances that don't comply with the cookie standards. CookieJar.make_cookies is the factory function for Cookie objects -- it deals with cookie parsing, supplying defaults, and normalising to the representation used in this class. CookiePolicy is responsible for checking them to see whether they should be accepted from and returned to the server. Note that the port may be present in the headers, but unspecified ("Port" rather than"Port=80", for example); if this is the case, port is None. """ def __init__(self, version, name, value, port, port_specified, domain, domain_specified, domain_initial_dot, path, path_specified, secure, expires, discard, comment, comment_url, rest, rfc2109=False, ): if version is not None: version = int(version) if expires is not None: expires = int(float(expires)) if port is None and port_specified is True: raise ValueError("if port is None, port_specified must be false") self.version = version self.name = name self.value = value self.port = port self.port_specified = port_specified # normalise case, as per RFC 2965 section 3.3.3 self.domain = domain.lower() self.domain_specified = domain_specified # Sigh. We need to know whether the domain given in the # cookie-attribute had an initial dot, in order to follow RFC 2965 # (as clarified in draft errata). Needed for the returned $Domain # value. self.domain_initial_dot = domain_initial_dot self.path = path self.path_specified = path_specified self.secure = secure self.expires = expires self.discard = discard self.comment = comment self.comment_url = comment_url self.rfc2109 = rfc2109 self._rest = copy.copy(rest) def has_nonstandard_attr(self, name): return name in self._rest def get_nonstandard_attr(self, name, default=None): return self._rest.get(name, default) def set_nonstandard_attr(self, name, value): self._rest[name] = value def is_expired(self, now=None): if now is None: now = time.time() if (self.expires is not None) and (self.expires <= now): return True return False def __str__(self): if self.port is None: p = "" else: p = ":"+self.port limit = self.domain + p + self.path if self.value is not None: namevalue = "%s=%s" % (self.name, self.value) else: namevalue = self.name return "<Cookie %s for %s>" % (namevalue, limit) def __repr__(self): args = [] for name in ("version", "name", "value", "port", "port_specified", "domain", "domain_specified", "domain_initial_dot", "path", "path_specified", "secure", "expires", "discard", "comment", "comment_url", ): attr = getattr(self, name) args.append("%s=%s" % (name, repr(attr))) args.append("rest=%s" % repr(self._rest)) args.append("rfc2109=%s" % repr(self.rfc2109)) return "%s(%s)" % (self.__class__.__name__, ", ".join(args)) class CookiePolicy: """Defines which cookies get accepted from and returned to server. May also modify cookies, though this is probably a bad idea. The subclass DefaultCookiePolicy defines the standard rules for Netscape and RFC 2965 cookies -- override that if you want a customized policy. """ def set_ok(self, cookie, request): """Return true if (and only if) cookie should be accepted from server. Currently, pre-expired cookies never get this far -- the CookieJar class deletes such cookies itself. """ raise NotImplementedError() def return_ok(self, cookie, request): """Return true if (and only if) cookie should be returned to server.""" raise NotImplementedError() def domain_return_ok(self, domain, request): """Return false if cookies should not be returned, given cookie domain. """ return True def path_return_ok(self, path, request): """Return false if cookies should not be returned, given cookie path. """ return True class DefaultCookiePolicy(CookiePolicy): """Implements the standard rules for accepting and returning cookies.""" DomainStrictNoDots = 1 DomainStrictNonDomain = 2 DomainRFC2965Match = 4 DomainLiberal = 0 DomainStrict = DomainStrictNoDots|DomainStrictNonDomain def __init__(self, blocked_domains=None, allowed_domains=None, netscape=True, rfc2965=False, rfc2109_as_netscape=None, hide_cookie2=False, strict_domain=False, strict_rfc2965_unverifiable=True, strict_ns_unverifiable=False, strict_ns_domain=DomainLiberal, strict_ns_set_initial_dollar=False, strict_ns_set_path=False, secure_protocols=("https", "wss") ): """Constructor arguments should be passed as keyword arguments only.""" self.netscape = netscape self.rfc2965 = rfc2965 self.rfc2109_as_netscape = rfc2109_as_netscape self.hide_cookie2 = hide_cookie2 self.strict_domain = strict_domain self.strict_rfc2965_unverifiable = strict_rfc2965_unverifiable self.strict_ns_unverifiable = strict_ns_unverifiable self.strict_ns_domain = strict_ns_domain self.strict_ns_set_initial_dollar = strict_ns_set_initial_dollar self.strict_ns_set_path = strict_ns_set_path self.secure_protocols = secure_protocols if blocked_domains is not None: self._blocked_domains = tuple(blocked_domains) else: self._blocked_domains = () if allowed_domains is not None: allowed_domains = tuple(allowed_domains) self._allowed_domains = allowed_domains def blocked_domains(self): """Return the sequence of blocked domains (as a tuple).""" return self._blocked_domains def set_blocked_domains(self, blocked_domains): """Set the sequence of blocked domains.""" self._blocked_domains = tuple(blocked_domains) def is_blocked(self, domain): for blocked_domain in self._blocked_domains: if user_domain_match(domain, blocked_domain): return True return False def allowed_domains(self): """Return None, or the sequence of allowed domains (as a tuple).""" return self._allowed_domains def set_allowed_domains(self, allowed_domains): """Set the sequence of allowed domains, or None.""" if allowed_domains is not None: allowed_domains = tuple(allowed_domains) self._allowed_domains = allowed_domains def is_not_allowed(self, domain): if self._allowed_domains is None: return False for allowed_domain in self._allowed_domains: if user_domain_match(domain, allowed_domain): return False return True def set_ok(self, cookie, request): """ If you override .set_ok(), be sure to call this method. If it returns false, so should your subclass (assuming your subclass wants to be more strict about which cookies to accept). """ _debug(" - checking cookie %s=%s", cookie.name, cookie.value) assert cookie.name is not None for n in "version", "verifiability", "name", "path", "domain", "port": fn_name = "set_ok_"+n fn = getattr(self, fn_name) if not fn(cookie, request): return False return True def set_ok_version(self, cookie, request): if cookie.version is None: # Version is always set to 0 by parse_ns_headers if it's a Netscape # cookie, so this must be an invalid RFC 2965 cookie. _debug(" Set-Cookie2 without version attribute (%s=%s)", cookie.name, cookie.value) return False if cookie.version > 0 and not self.rfc2965: _debug(" RFC 2965 cookies are switched off") return False elif cookie.version == 0 and not self.netscape: _debug(" Netscape cookies are switched off") return False return True def set_ok_verifiability(self, cookie, request): if request.unverifiable and is_third_party(request): if cookie.version > 0 and self.strict_rfc2965_unverifiable: _debug(" third-party RFC 2965 cookie during " "unverifiable transaction") return False elif cookie.version == 0 and self.strict_ns_unverifiable: _debug(" third-party Netscape cookie during " "unverifiable transaction") return False return True def set_ok_name(self, cookie, request): # Try and stop servers setting V0 cookies designed to hack other # servers that know both V0 and V1 protocols. if (cookie.version == 0 and self.strict_ns_set_initial_dollar and cookie.name.startswith("$")): _debug(" illegal name (starts with '$'): '%s'", cookie.name) return False return True def set_ok_path(self, cookie, request): if cookie.path_specified: req_path = request_path(request) if ((cookie.version > 0 or (cookie.version == 0 and self.strict_ns_set_path)) and not self.path_return_ok(cookie.path, request)): _debug(" path attribute %s is not a prefix of request " "path %s", cookie.path, req_path) return False return True def set_ok_domain(self, cookie, request): if self.is_blocked(cookie.domain): _debug(" domain %s is in user block-list", cookie.domain) return False if self.is_not_allowed(cookie.domain): _debug(" domain %s is not in user allow-list", cookie.domain) return False if cookie.domain_specified: req_host, erhn = eff_request_host(request) domain = cookie.domain if self.strict_domain and (domain.count(".") >= 2): # XXX This should probably be compared with the Konqueror # (kcookiejar.cpp) and Mozilla implementations, but it's a # losing battle. i = domain.rfind(".") j = domain.rfind(".", 0, i) if j == 0: # domain like .foo.bar tld = domain[i+1:] sld = domain[j+1:i] if sld.lower() in ("co", "ac", "com", "edu", "org", "net", "gov", "mil", "int", "aero", "biz", "cat", "coop", "info", "jobs", "mobi", "museum", "name", "pro", "travel", "eu") and len(tld) == 2: # domain like .co.uk _debug(" country-code second level domain %s", domain) return False if domain.startswith("."): undotted_domain = domain[1:] else: undotted_domain = domain embedded_dots = (undotted_domain.find(".") >= 0) if not embedded_dots and domain != ".local": _debug(" non-local domain %s contains no embedded dot", domain) return False if cookie.version == 0: if (not erhn.endswith(domain) and (not erhn.startswith(".") and not ("."+erhn).endswith(domain))): _debug(" effective request-host %s (even with added " "initial dot) does not end with %s", erhn, domain) return False if (cookie.version > 0 or (self.strict_ns_domain & self.DomainRFC2965Match)): if not domain_match(erhn, domain): _debug(" effective request-host %s does not domain-match " "%s", erhn, domain) return False if (cookie.version > 0 or (self.strict_ns_domain & self.DomainStrictNoDots)): host_prefix = req_host[:-len(domain)] if (host_prefix.find(".") >= 0 and not IPV4_RE.search(req_host)): _debug(" host prefix %s for domain %s contains a dot", host_prefix, domain) return False return True def set_ok_port(self, cookie, request): if cookie.port_specified: req_port = request_port(request) if req_port is None: req_port = "80" else: req_port = str(req_port) for p in cookie.port.split(","): try: int(p) except ValueError: _debug(" bad port %s (not numeric)", p) return False if p == req_port: break else: _debug(" request port (%s) not found in %s", req_port, cookie.port) return False return True def return_ok(self, cookie, request): """ If you override .return_ok(), be sure to call this method. If it returns false, so should your subclass (assuming your subclass wants to be more strict about which cookies to return). """ # Path has already been checked by .path_return_ok(), and domain # blocking done by .domain_return_ok(). _debug(" - checking cookie %s=%s", cookie.name, cookie.value) for n in "version", "verifiability", "secure", "expires", "port", "domain": fn_name = "return_ok_"+n fn = getattr(self, fn_name) if not fn(cookie, request): return False return True def return_ok_version(self, cookie, request): if cookie.version > 0 and not self.rfc2965: _debug(" RFC 2965 cookies are switched off") return False elif cookie.version == 0 and not self.netscape: _debug(" Netscape cookies are switched off") return False return True def return_ok_verifiability(self, cookie, request): if request.unverifiable and is_third_party(request): if cookie.version > 0 and self.strict_rfc2965_unverifiable: _debug(" third-party RFC 2965 cookie during unverifiable " "transaction") return False elif cookie.version == 0 and self.strict_ns_unverifiable: _debug(" third-party Netscape cookie during unverifiable " "transaction") return False return True def return_ok_secure(self, cookie, request): if cookie.secure and request.type not in self.secure_protocols: _debug(" secure cookie with non-secure request") return False return True def return_ok_expires(self, cookie, request): if cookie.is_expired(self._now): _debug(" cookie expired") return False return True def return_ok_port(self, cookie, request): if cookie.port: req_port = request_port(request) if req_port is None: req_port = "80" for p in cookie.port.split(","): if p == req_port: break else: _debug(" request port %s does not match cookie port %s", req_port, cookie.port) return False return True def return_ok_domain(self, cookie, request): req_host, erhn = eff_request_host(request) domain = cookie.domain if domain and not domain.startswith("."): dotdomain = "." + domain else: dotdomain = domain # strict check of non-domain cookies: Mozilla does this, MSIE5 doesn't if (cookie.version == 0 and (self.strict_ns_domain & self.DomainStrictNonDomain) and not cookie.domain_specified and domain != erhn): _debug(" cookie with unspecified domain does not string-compare " "equal to request domain") return False if cookie.version > 0 and not domain_match(erhn, domain): _debug(" effective request-host name %s does not domain-match " "RFC 2965 cookie domain %s", erhn, domain) return False if cookie.version == 0 and not ("."+erhn).endswith(dotdomain): _debug(" request-host %s does not match Netscape cookie domain " "%s", req_host, domain) return False return True def domain_return_ok(self, domain, request): # Liberal check of. This is here as an optimization to avoid # having to load lots of MSIE cookie files unless necessary. req_host, erhn = eff_request_host(request) if not req_host.startswith("."): req_host = "."+req_host if not erhn.startswith("."): erhn = "."+erhn if domain and not domain.startswith("."): dotdomain = "." + domain else: dotdomain = domain if not (req_host.endswith(dotdomain) or erhn.endswith(dotdomain)): #_debug(" request domain %s does not match cookie domain %s", # req_host, domain) return False if self.is_blocked(domain): _debug(" domain %s is in user block-list", domain) return False if self.is_not_allowed(domain): _debug(" domain %s is not in user allow-list", domain) return False return True def path_return_ok(self, path, request): _debug("- checking cookie path=%s", path) req_path = request_path(request) pathlen = len(path) if req_path == path: return True elif (req_path.startswith(path) and (path.endswith("/") or req_path[pathlen:pathlen+1] == "/")): return True _debug(" %s does not path-match %s", req_path, path) return False def vals_sorted_by_key(adict): keys = sorted(adict.keys()) return map(adict.get, keys) def deepvalues(mapping): """Iterates over nested mapping, depth-first, in sorted order by key.""" values = vals_sorted_by_key(mapping) for obj in values: mapping = False try: obj.items except AttributeError: pass else: mapping = True yield from deepvalues(obj) if not mapping: yield obj # Used as second parameter to dict.get() method, to distinguish absent # dict key from one with a None value. class Absent: pass class CookieJar: """Collection of HTTP cookies. You may not need to know about this class: try urllib.request.build_opener(HTTPCookieProcessor).open(url). """ non_word_re = re.compile(r"\W") quote_re = re.compile(r"([\"\\])") strict_domain_re = re.compile(r"\.?[^.]*") domain_re = re.compile(r"[^.]*") dots_re = re.compile(r"^\.+") magic_re = re.compile(r"^\#LWP-Cookies-(\d+\.\d+)", re.ASCII) def __init__(self, policy=None): if policy is None: policy = DefaultCookiePolicy() self._policy = policy self._cookies_lock = _threading.RLock() self._cookies = {} def set_policy(self, policy): self._policy = policy def _cookies_for_domain(self, domain, request): cookies = [] if not self._policy.domain_return_ok(domain, request): return [] _debug("Checking %s for cookies to return", domain) cookies_by_path = self._cookies[domain] for path in cookies_by_path.keys(): if not self._policy.path_return_ok(path, request): continue cookies_by_name = cookies_by_path[path] for cookie in cookies_by_name.values(): if not self._policy.return_ok(cookie, request): _debug(" not returning cookie") continue _debug(" it's a match") cookies.append(cookie) return cookies def _cookies_for_request(self, request): """Return a list of cookies to be returned to server.""" cookies = [] for domain in self._cookies.keys(): cookies.extend(self._cookies_for_domain(domain, request)) return cookies def _cookie_attrs(self, cookies): """Return a list of cookie-attributes to be returned to server. like ['foo="bar"; $Path="/"', ...] The $Version attribute is also added when appropriate (currently only once per request). """ # add cookies in order of most specific (ie. longest) path first cookies.sort(key=lambda a: len(a.path), reverse=True) version_set = False attrs = [] for cookie in cookies: # set version of Cookie header # XXX # What should it be if multiple matching Set-Cookie headers have # different versions themselves? # Answer: there is no answer; was supposed to be settled by # RFC 2965 errata, but that may never appear... version = cookie.version if not version_set: version_set = True if version > 0: attrs.append("$Version=%s" % version) # quote cookie value if necessary # (not for Netscape protocol, which already has any quotes # intact, due to the poorly-specified Netscape Cookie: syntax) if ((cookie.value is not None) and self.non_word_re.search(cookie.value) and version > 0): value = self.quote_re.sub(r"\\\1", cookie.value) else: value = cookie.value # add cookie-attributes to be returned in Cookie header if cookie.value is None: attrs.append(cookie.name) else: attrs.append("%s=%s" % (cookie.name, value)) if version > 0: if cookie.path_specified: attrs.append('$Path="%s"' % cookie.path) if cookie.domain.startswith("."): domain = cookie.domain if (not cookie.domain_initial_dot and domain.startswith(".")): domain = domain[1:] attrs.append('$Domain="%s"' % domain) if cookie.port is not None: p = "$Port" if cookie.port_specified: p = p + ('="%s"' % cookie.port) attrs.append(p) return attrs def add_cookie_header(self, request): """Add correct Cookie: header to request (urllib.request.Request object). The Cookie2 header is also added unless policy.hide_cookie2 is true. """ _debug("add_cookie_header") self._cookies_lock.acquire() try: self._policy._now = self._now = int(time.time()) cookies = self._cookies_for_request(request) attrs = self._cookie_attrs(cookies) if attrs: if not request.has_header("Cookie"): request.add_unredirected_header( "Cookie", "; ".join(attrs)) # if necessary, advertise that we know RFC 2965 if (self._policy.rfc2965 and not self._policy.hide_cookie2 and not request.has_header("Cookie2")): for cookie in cookies: if cookie.version != 1: request.add_unredirected_header("Cookie2", '$Version="1"') break finally: self._cookies_lock.release() self.clear_expired_cookies() def _normalized_cookie_tuples(self, attrs_set): """Return list of tuples containing normalised cookie information. attrs_set is the list of lists of key,value pairs extracted from the Set-Cookie or Set-Cookie2 headers. Tuples are name, value, standard, rest, where name and value are the cookie name and value, standard is a dictionary containing the standard cookie-attributes (discard, secure, version, expires or max-age, domain, path and port) and rest is a dictionary containing the rest of the cookie-attributes. """ cookie_tuples = [] boolean_attrs = "discard", "secure" value_attrs = ("version", "expires", "max-age", "domain", "path", "port", "comment", "commenturl") for cookie_attrs in attrs_set: name, value = cookie_attrs[0] # Build dictionary of standard cookie-attributes (standard) and # dictionary of other cookie-attributes (rest). # Note: expiry time is normalised to seconds since epoch. V0 # cookies should have the Expires cookie-attribute, and V1 cookies # should have Max-Age, but since V1 includes RFC 2109 cookies (and # since V0 cookies may be a mish-mash of Netscape and RFC 2109), we # accept either (but prefer Max-Age). max_age_set = False bad_cookie = False standard = {} rest = {} for k, v in cookie_attrs[1:]: lc = k.lower() # don't lose case distinction for unknown fields if lc in value_attrs or lc in boolean_attrs: k = lc if k in boolean_attrs and v is None: # boolean cookie-attribute is present, but has no value # (like "discard", rather than "port=80") v = True if k in standard: # only first value is significant continue if k == "domain": if v is None: _debug(" missing value for domain attribute") bad_cookie = True break # RFC 2965 section 3.3.3 v = v.lower() if k == "expires": if max_age_set: # Prefer max-age to expires (like Mozilla) continue if v is None: _debug(" missing or invalid value for expires " "attribute: treating as session cookie") continue if k == "max-age": max_age_set = True try: v = int(v) except ValueError: _debug(" missing or invalid (non-numeric) value for " "max-age attribute") bad_cookie = True break # convert RFC 2965 Max-Age to seconds since epoch # XXX Strictly you're supposed to follow RFC 2616 # age-calculation rules. Remember that zero Max-Age # is a request to discard (old and new) cookie, though. k = "expires" v = self._now + v if (k in value_attrs) or (k in boolean_attrs): if (v is None and k not in ("port", "comment", "commenturl")): _debug(" missing value for %s attribute" % k) bad_cookie = True break standard[k] = v else: rest[k] = v if bad_cookie: continue cookie_tuples.append((name, value, standard, rest)) return cookie_tuples def _cookie_from_cookie_tuple(self, tup, request): # standard is dict of standard cookie-attributes, rest is dict of the # rest of them name, value, standard, rest = tup domain = standard.get("domain", Absent) path = standard.get("path", Absent) port = standard.get("port", Absent) expires = standard.get("expires", Absent) # set the easy defaults version = standard.get("version", None) if version is not None: try: version = int(version) except ValueError: return None # invalid version, ignore cookie secure = standard.get("secure", False) # (discard is also set if expires is Absent) discard = standard.get("discard", False) comment = standard.get("comment", None) comment_url = standard.get("commenturl", None) # set default path if path is not Absent and path != "": path_specified = True path = escape_path(path) else: path_specified = False path = request_path(request) i = path.rfind("/") if i != -1: if version == 0: # Netscape spec parts company from reality here path = path[:i] else: path = path[:i+1] if len(path) == 0: path = "/" # set default domain domain_specified = domain is not Absent # but first we have to remember whether it starts with a dot domain_initial_dot = False if domain_specified: domain_initial_dot = bool(domain.startswith(".")) if domain is Absent: req_host, erhn = eff_request_host(request) domain = erhn elif not domain.startswith("."): domain = "."+domain # set default port port_specified = False if port is not Absent: if port is None: # Port attr present, but has no value: default to request port. # Cookie should then only be sent back on that port. port = request_port(request) else: port_specified = True port = re.sub(r"\s+", "", port) else: # No port attr present. Cookie can be sent back on any port. port = None # set default expires and discard if expires is Absent: expires = None discard = True elif expires <= self._now: # Expiry date in past is request to delete cookie. This can't be # in DefaultCookiePolicy, because can't delete cookies there. try: self.clear(domain, path, name) except KeyError: pass _debug("Expiring cookie, domain='%s', path='%s', name='%s'", domain, path, name) return None return Cookie(version, name, value, port, port_specified, domain, domain_specified, domain_initial_dot, path, path_specified, secure, expires, discard, comment, comment_url, rest) def _cookies_from_attrs_set(self, attrs_set, request): cookie_tuples = self._normalized_cookie_tuples(attrs_set) cookies = [] for tup in cookie_tuples: cookie = self._cookie_from_cookie_tuple(tup, request) if cookie: cookies.append(cookie) return cookies def _process_rfc2109_cookies(self, cookies): rfc2109_as_ns = getattr(self._policy, 'rfc2109_as_netscape', None) if rfc2109_as_ns is None: rfc2109_as_ns = not self._policy.rfc2965 for cookie in cookies: if cookie.version == 1: cookie.rfc2109 = True if rfc2109_as_ns: # treat 2109 cookies as Netscape cookies rather than # as RFC2965 cookies cookie.version = 0 def make_cookies(self, response, request): """Return sequence of Cookie objects extracted from response object.""" # get cookie-attributes for RFC 2965 and Netscape protocols headers = response.info() rfc2965_hdrs = headers.get_all("Set-Cookie2", []) ns_hdrs = headers.get_all("Set-Cookie", []) self._policy._now = self._now = int(time.time()) rfc2965 = self._policy.rfc2965 netscape = self._policy.netscape if ((not rfc2965_hdrs and not ns_hdrs) or (not ns_hdrs and not rfc2965) or (not rfc2965_hdrs and not netscape) or (not netscape and not rfc2965)): return [] # no relevant cookie headers: quick exit try: cookies = self._cookies_from_attrs_set( split_header_words(rfc2965_hdrs), request) except Exception: _warn_unhandled_exception() cookies = [] if ns_hdrs and netscape: try: # RFC 2109 and Netscape cookies ns_cookies = self._cookies_from_attrs_set( parse_ns_headers(ns_hdrs), request) except Exception: _warn_unhandled_exception() ns_cookies = [] self._process_rfc2109_cookies(ns_cookies) # Look for Netscape cookies (from Set-Cookie headers) that match # corresponding RFC 2965 cookies (from Set-Cookie2 headers). # For each match, keep the RFC 2965 cookie and ignore the Netscape # cookie (RFC 2965 section 9.1). Actually, RFC 2109 cookies are # bundled in with the Netscape cookies for this purpose, which is # reasonable behaviour. if rfc2965: lookup = {} for cookie in cookies: lookup[(cookie.domain, cookie.path, cookie.name)] = None def no_matching_rfc2965(ns_cookie, lookup=lookup): key = ns_cookie.domain, ns_cookie.path, ns_cookie.name return key not in lookup ns_cookies = filter(no_matching_rfc2965, ns_cookies) if ns_cookies: cookies.extend(ns_cookies) return cookies def set_cookie_if_ok(self, cookie, request): """Set a cookie if policy says it's OK to do so.""" self._cookies_lock.acquire() try: self._policy._now = self._now = int(time.time()) if self._policy.set_ok(cookie, request): self.set_cookie(cookie) finally: self._cookies_lock.release() def set_cookie(self, cookie): """Set a cookie, without checking whether or not it should be set.""" c = self._cookies self._cookies_lock.acquire() try: if cookie.domain not in c: c[cookie.domain] = {} c2 = c[cookie.domain] if cookie.path not in c2: c2[cookie.path] = {} c3 = c2[cookie.path] c3[cookie.name] = cookie finally: self._cookies_lock.release() def extract_cookies(self, response, request): """Extract cookies from response, where allowable given the request.""" _debug("extract_cookies: %s", response.info()) self._cookies_lock.acquire() try: for cookie in self.make_cookies(response, request): if self._policy.set_ok(cookie, request): _debug(" setting cookie: %s", cookie) self.set_cookie(cookie) finally: self._cookies_lock.release() def clear(self, domain=None, path=None, name=None): """Clear some cookies. Invoking this method without arguments will clear all cookies. If given a single argument, only cookies belonging to that domain will be removed. If given two arguments, cookies belonging to the specified path within that domain are removed. If given three arguments, then the cookie with the specified name, path and domain is removed. Raises KeyError if no matching cookie exists. """ if name is not None: if (domain is None) or (path is None): raise ValueError( "domain and path must be given to remove a cookie by name") del self._cookies[domain][path][name] elif path is not None: if domain is None: raise ValueError( "domain must be given to remove cookies by path") del self._cookies[domain][path] elif domain is not None: del self._cookies[domain] else: self._cookies = {} def clear_session_cookies(self): """Discard all session cookies. Note that the .save() method won't save session cookies anyway, unless you ask otherwise by passing a true ignore_discard argument. """ self._cookies_lock.acquire() try: for cookie in self: if cookie.discard: self.clear(cookie.domain, cookie.path, cookie.name) finally: self._cookies_lock.release() def clear_expired_cookies(self): """Discard all expired cookies. You probably don't need to call this method: expired cookies are never sent back to the server (provided you're using DefaultCookiePolicy), this method is called by CookieJar itself every so often, and the .save() method won't save expired cookies anyway (unless you ask otherwise by passing a true ignore_expires argument). """ self._cookies_lock.acquire() try: now = time.time() for cookie in self: if cookie.is_expired(now): self.clear(cookie.domain, cookie.path, cookie.name) finally: self._cookies_lock.release() def __iter__(self): return deepvalues(self._cookies) def __len__(self): """Return number of contained cookies.""" i = 0 for cookie in self: i = i + 1 return i def __repr__(self): r = [] for cookie in self: r.append(repr(cookie)) return "<%s[%s]>" % (self.__class__.__name__, ", ".join(r)) def __str__(self): r = [] for cookie in self: r.append(str(cookie)) return "<%s[%s]>" % (self.__class__.__name__, ", ".join(r)) # derives from OSError for backwards-compatibility with Python 2.4.0 class LoadError(OSError): pass class FileCookieJar(CookieJar): """CookieJar that can be loaded from and saved to a file.""" def __init__(self, filename=None, delayload=False, policy=None): """ Cookies are NOT loaded from the named file until either the .load() or .revert() method is called. """ CookieJar.__init__(self, policy) if filename is not None: filename = os.fspath(filename) self.filename = filename self.delayload = bool(delayload) def save(self, filename=None, ignore_discard=False, ignore_expires=False): """Save cookies to a file.""" raise NotImplementedError() def load(self, filename=None, ignore_discard=False, ignore_expires=False): """Load cookies from a file.""" if filename is None: if self.filename is not None: filename = self.filename else: raise ValueError(MISSING_FILENAME_TEXT) with open(filename) as f: self._really_load(f, filename, ignore_discard, ignore_expires) def revert(self, filename=None, ignore_discard=False, ignore_expires=False): """Clear all cookies and reload cookies from a saved file. Raises LoadError (or OSError) if reversion is not successful; the object's state will not be altered if this happens. """ if filename is None: if self.filename is not None: filename = self.filename else: raise ValueError(MISSING_FILENAME_TEXT) self._cookies_lock.acquire() try: old_state = copy.deepcopy(self._cookies) self._cookies = {} try: self.load(filename, ignore_discard, ignore_expires) except OSError: self._cookies = old_state raise finally: self._cookies_lock.release() def lwp_cookie_str(cookie): """Return string representation of Cookie in the LWP cookie file format. Actually, the format is extended a bit -- see module docstring. """ h = [(cookie.name, cookie.value), ("path", cookie.path), ("domain", cookie.domain)] if cookie.port is not None: h.append(("port", cookie.port)) if cookie.path_specified: h.append(("path_spec", None)) if cookie.port_specified: h.append(("port_spec", None)) if cookie.domain_initial_dot: h.append(("domain_dot", None)) if cookie.secure: h.append(("secure", None)) if cookie.expires: h.append(("expires", time2isoz(float(cookie.expires)))) if cookie.discard: h.append(("discard", None)) if cookie.comment: h.append(("comment", cookie.comment)) if cookie.comment_url: h.append(("commenturl", cookie.comment_url)) keys = sorted(cookie._rest.keys()) for k in keys: h.append((k, str(cookie._rest[k]))) h.append(("version", str(cookie.version))) return join_header_words([h]) class LWPCookieJar(FileCookieJar): """ The LWPCookieJar saves a sequence of "Set-Cookie3" lines. "Set-Cookie3" is the format used by the libwww-perl library, not known to be compatible with any browser, but which is easy to read and doesn't lose information about RFC 2965 cookies. Additional methods as_lwp_str(ignore_discard=True, ignore_expired=True) """ def as_lwp_str(self, ignore_discard=True, ignore_expires=True): """Return cookies as a string of "\\n"-separated "Set-Cookie3" headers. ignore_discard and ignore_expires: see docstring for FileCookieJar.save """ now = time.time() r = [] for cookie in self: if not ignore_discard and cookie.discard: continue if not ignore_expires and cookie.is_expired(now): continue r.append("Set-Cookie3: %s" % lwp_cookie_str(cookie)) return "\n".join(r+[""]) def save(self, filename=None, ignore_discard=False, ignore_expires=False): if filename is None: if self.filename is not None: filename = self.filename else: raise ValueError(MISSING_FILENAME_TEXT) with open(filename, "w") as f: # There really isn't an LWP Cookies 2.0 format, but this indicates # that there is extra information in here (domain_dot and # port_spec) while still being compatible with libwww-perl, I hope. f.write("#LWP-Cookies-2.0\n") f.write(self.as_lwp_str(ignore_discard, ignore_expires)) def _really_load(self, f, filename, ignore_discard, ignore_expires): magic = f.readline() if not self.magic_re.search(magic): msg = ("%r does not look like a Set-Cookie3 (LWP) format " "file" % filename) raise LoadError(msg) now = time.time() header = "Set-Cookie3:" boolean_attrs = ("port_spec", "path_spec", "domain_dot", "secure", "discard") value_attrs = ("version", "port", "path", "domain", "expires", "comment", "commenturl") try: while 1: line = f.readline() if line == "": break if not line.startswith(header): continue line = line[len(header):].strip() for data in split_header_words([line]): name, value = data[0] standard = {} rest = {} for k in boolean_attrs: standard[k] = False for k, v in data[1:]: if k is not None: lc = k.lower() else: lc = None # don't lose case distinction for unknown fields if (lc in value_attrs) or (lc in boolean_attrs): k = lc if k in boolean_attrs: if v is None: v = True standard[k] = v elif k in value_attrs: standard[k] = v else: rest[k] = v h = standard.get expires = h("expires") discard = h("discard") if expires is not None: expires = iso2time(expires) if expires is None: discard = True domain = h("domain") domain_specified = domain.startswith(".") c = Cookie(h("version"), name, value, h("port"), h("port_spec"), domain, domain_specified, h("domain_dot"), h("path"), h("path_spec"), h("secure"), expires, discard, h("comment"), h("commenturl"), rest) if not ignore_discard and c.discard: continue if not ignore_expires and c.is_expired(now): continue self.set_cookie(c) except OSError: raise except Exception: _warn_unhandled_exception() raise LoadError("invalid Set-Cookie3 format file %r: %r" % (filename, line)) class MozillaCookieJar(FileCookieJar): """ WARNING: you may want to backup your browser's cookies file if you use this class to save cookies. I *think* it works, but there have been bugs in the past! This class differs from CookieJar only in the format it uses to save and load cookies to and from a file. This class uses the Mozilla/Netscape `cookies.txt' format. lynx uses this file format, too. Don't expect cookies saved while the browser is running to be noticed by the browser (in fact, Mozilla on unix will overwrite your saved cookies if you change them on disk while it's running; on Windows, you probably can't save at all while the browser is running). Note that the Mozilla/Netscape format will downgrade RFC2965 cookies to Netscape cookies on saving. In particular, the cookie version and port number information is lost, together with information about whether or not Path, Port and Discard were specified by the Set-Cookie2 (or Set-Cookie) header, and whether or not the domain as set in the HTTP header started with a dot (yes, I'm aware some domains in Netscape files start with a dot and some don't -- trust me, you really don't want to know any more about this). Note that though Mozilla and Netscape use the same format, they use slightly different headers. The class saves cookies using the Netscape header by default (Mozilla can cope with that). """ magic_re = re.compile("#( Netscape)? HTTP Cookie File") header = """\ # Netscape HTTP Cookie File # http://curl.haxx.se/rfc/cookie_spec.html # This is a generated file! Do not edit. """ def _really_load(self, f, filename, ignore_discard, ignore_expires): now = time.time() magic = f.readline() if not self.magic_re.search(magic): raise LoadError( "%r does not look like a Netscape format cookies file" % filename) try: while 1: line = f.readline() if line == "": break # last field may be absent, so keep any trailing tab if line.endswith("\n"): line = line[:-1] # skip comments and blank lines XXX what is $ for? if (line.strip().startswith(("#", "$")) or line.strip() == ""): continue domain, domain_specified, path, secure, expires, name, value = \ line.split("\t") secure = (secure == "TRUE") domain_specified = (domain_specified == "TRUE") if name == "": # cookies.txt regards 'Set-Cookie: foo' as a cookie # with no name, whereas http.cookiejar regards it as a # cookie with no value. name = value value = None initial_dot = domain.startswith(".") assert domain_specified == initial_dot discard = False if expires == "": expires = None discard = True # assume path_specified is false c = Cookie(0, name, value, None, False, domain, domain_specified, initial_dot, path, False, secure, expires, discard, None, None, {}) if not ignore_discard and c.discard: continue if not ignore_expires and c.is_expired(now): continue self.set_cookie(c) except OSError: raise except Exception: _warn_unhandled_exception() raise LoadError("invalid Netscape format cookies file %r: %r" % (filename, line)) def save(self, filename=None, ignore_discard=False, ignore_expires=False): if filename is None: if self.filename is not None: filename = self.filename else: raise ValueError(MISSING_FILENAME_TEXT) with open(filename, "w") as f: f.write(self.header) now = time.time() for cookie in self: if not ignore_discard and cookie.discard: continue if not ignore_expires and cookie.is_expired(now): continue if cookie.secure: secure = "TRUE" else: secure = "FALSE" if cookie.domain.startswith("."): initial_dot = "TRUE" else: initial_dot = "FALSE" if cookie.expires is not None: expires = str(cookie.expires) else: expires = "" if cookie.value is None: # cookies.txt regards 'Set-Cookie: foo' as a cookie # with no name, whereas http.cookiejar regards it as a # cookie with no value. name = "" value = cookie.name else: name = cookie.name value = cookie.value f.write( "\t".join([cookie.domain, initial_dot, cookie.path, secure, expires, name, value])+ "\n") PK � [��� �� client.pynu �[��� r"""HTTP/1.1 client library <intro stuff goes here> <other stuff, too> HTTPConnection goes through a number of "states", which define when a client may legally make another request or fetch the response for a particular request. This diagram details these state transitions: (null) | | HTTPConnection() v Idle | | putrequest() v Request-started | | ( putheader() )* endheaders() v Request-sent |\_____________________________ | | getresponse() raises | response = getresponse() | ConnectionError v v Unread-response Idle [Response-headers-read] |\____________________ | | | response.read() | putrequest() v v Idle Req-started-unread-response ______/| / | response.read() | | ( putheader() )* endheaders() v v Request-started Req-sent-unread-response | | response.read() v Request-sent This diagram presents the following rules: -- a second request may not be started until {response-headers-read} -- a response [object] cannot be retrieved until {request-sent} -- there is no differentiation between an unread response body and a partially read response body Note: this enforcement is applied by the HTTPConnection class. The HTTPResponse class does not enforce this state machine, which implies sophisticated clients may accelerate the request/response pipeline. Caution should be taken, though: accelerating the states beyond the above pattern may imply knowledge of the server's connection-close behavior for certain requests. For example, it is impossible to tell whether the server will close the connection UNTIL the response headers have been read; this means that further requests cannot be placed into the pipeline until it is known that the server will NOT be closing the connection. Logical State __state __response ------------- ------- ---------- Idle _CS_IDLE None Request-started _CS_REQ_STARTED None Request-sent _CS_REQ_SENT None Unread-response _CS_IDLE <response_class> Req-started-unread-response _CS_REQ_STARTED <response_class> Req-sent-unread-response _CS_REQ_SENT <response_class> """ import email.parser import email.message import http import io import re import socket import collections.abc from urllib.parse import urlsplit # HTTPMessage, parse_headers(), and the HTTP status code constants are # intentionally omitted for simplicity __all__ = ["HTTPResponse", "HTTPConnection", "HTTPException", "NotConnected", "UnknownProtocol", "UnknownTransferEncoding", "UnimplementedFileMode", "IncompleteRead", "InvalidURL", "ImproperConnectionState", "CannotSendRequest", "CannotSendHeader", "ResponseNotReady", "BadStatusLine", "LineTooLong", "RemoteDisconnected", "error", "responses"] HTTP_PORT = 80 HTTPS_PORT = 443 _UNKNOWN = 'UNKNOWN' # connection states _CS_IDLE = 'Idle' _CS_REQ_STARTED = 'Request-started' _CS_REQ_SENT = 'Request-sent' # hack to maintain backwards compatibility globals().update(http.HTTPStatus.__members__) # another hack to maintain backwards compatibility # Mapping status codes to official W3C names responses = {v: v.phrase for v in http.HTTPStatus.__members__.values()} # maximal line length when calling readline(). _MAXLINE = 65536 _MAXHEADERS = 100 # Header name/value ABNF (http://tools.ietf.org/html/rfc7230#section-3.2) # # VCHAR = %x21-7E # obs-text = %x80-FF # header-field = field-name ":" OWS field-value OWS # field-name = token # field-value = *( field-content / obs-fold ) # field-content = field-vchar [ 1*( SP / HTAB ) field-vchar ] # field-vchar = VCHAR / obs-text # # obs-fold = CRLF 1*( SP / HTAB ) # ; obsolete line folding # ; see Section 3.2.4 # token = 1*tchar # # tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*" # / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~" # / DIGIT / ALPHA # ; any VCHAR, except delimiters # # VCHAR defined in http://tools.ietf.org/html/rfc5234#appendix-B.1 # the patterns for both name and value are more lenient than RFC # definitions to allow for backwards compatibility _is_legal_header_name = re.compile(rb'[^:\s][^:\r\n]*').fullmatch _is_illegal_header_value = re.compile(rb'\n(?![ \t])|\r(?![ \t\n])').search # These characters are not allowed within HTTP URL paths. # See https://tools.ietf.org/html/rfc3986#section-3.3 and the # https://tools.ietf.org/html/rfc3986#appendix-A pchar definition. # Prevents CVE-2019-9740. Includes control characters such as \r\n. # We don't restrict chars above \x7f as putrequest() limits us to ASCII. _contains_disallowed_url_pchar_re = re.compile('[\x00-\x20\x7f]') # Arguably only these _should_ allowed: # _is_allowed_url_pchars_re = re.compile(r"^[/!$&'()*+,;=:@%a-zA-Z0-9._~-]+$") # We are more lenient for assumed real world compatibility purposes. # These characters are not allowed within HTTP method names # to prevent http header injection. _contains_disallowed_method_pchar_re = re.compile('[\x00-\x1f]') # We always set the Content-Length header for these methods because some # servers will otherwise respond with a 411 _METHODS_EXPECTING_BODY = {'PATCH', 'POST', 'PUT'} def _encode(data, name='data'): """Call data.encode("latin-1") but show a better error message.""" try: return data.encode("latin-1") except UnicodeEncodeError as err: raise UnicodeEncodeError( err.encoding, err.object, err.start, err.end, "%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') " "if you want to send it encoded in UTF-8." % (name.title(), data[err.start:err.end], name)) from None class HTTPMessage(email.message.Message): # XXX The only usage of this method is in # http.server.CGIHTTPRequestHandler. Maybe move the code there so # that it doesn't need to be part of the public API. The API has # never been defined so this could cause backwards compatibility # issues. def getallmatchingheaders(self, name): """Find all header lines matching a given header name. Look through the list of headers and find all lines matching a given header name (and their continuation lines). A list of the lines is returned, without interpretation. If the header does not occur, an empty list is returned. If the header occurs multiple times, all occurrences are returned. Case is not important in the header name. """ name = name.lower() + ':' n = len(name) lst = [] hit = 0 for line in self.keys(): if line[:n].lower() == name: hit = 1 elif not line[:1].isspace(): hit = 0 if hit: lst.append(line) return lst def _read_headers(fp): """Reads potential header lines into a list from a file pointer. Length of line is limited by _MAXLINE, and number of headers is limited by _MAXHEADERS. """ headers = [] while True: line = fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("header line") headers.append(line) if len(headers) > _MAXHEADERS: raise HTTPException("got more than %d headers" % _MAXHEADERS) if line in (b'\r\n', b'\n', b''): break return headers def parse_headers(fp, _class=HTTPMessage): """Parses only RFC2822 headers from a file pointer. email Parser wants to see strings rather than bytes. But a TextIOWrapper around self.rfile would buffer too many bytes from the stream, bytes which we later need to read as bytes. So we read the correct bytes here, as bytes, for email Parser to parse. """ headers = _read_headers(fp) hstring = b''.join(headers).decode('iso-8859-1') return email.parser.Parser(_class=_class).parsestr(hstring) class HTTPResponse(io.BufferedIOBase): # See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details. # The bytes from the socket object are iso-8859-1 strings. # See RFC 2616 sec 2.2 which notes an exception for MIME-encoded # text following RFC 2047. The basic status line parsing only # accepts iso-8859-1. def __init__(self, sock, debuglevel=0, method=None, url=None): # If the response includes a content-length header, we need to # make sure that the client doesn't read more than the # specified number of bytes. If it does, it will block until # the server times out and closes the connection. This will # happen if a self.fp.read() is done (without a size) whether # self.fp is buffered or not. So, no self.fp.read() by # clients unless they know what they are doing. self.fp = sock.makefile("rb") self.debuglevel = debuglevel self._method = method # The HTTPResponse object is returned via urllib. The clients # of http and urllib expect different attributes for the # headers. headers is used here and supports urllib. msg is # provided as a backwards compatibility layer for http # clients. self.headers = self.msg = None # from the Status-Line of the response self.version = _UNKNOWN # HTTP-Version self.status = _UNKNOWN # Status-Code self.reason = _UNKNOWN # Reason-Phrase self.chunked = _UNKNOWN # is "chunked" being used? self.chunk_left = _UNKNOWN # bytes left to read in current chunk self.length = _UNKNOWN # number of bytes left in response self.will_close = _UNKNOWN # conn will close at end of response def _read_status(self): line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1") if len(line) > _MAXLINE: raise LineTooLong("status line") if self.debuglevel > 0: print("reply:", repr(line)) if not line: # Presumably, the server closed the connection before # sending a valid response. raise RemoteDisconnected("Remote end closed connection without" " response") try: version, status, reason = line.split(None, 2) except ValueError: try: version, status = line.split(None, 1) reason = "" except ValueError: # empty version will cause next test to fail. version = "" if not version.startswith("HTTP/"): self._close_conn() raise BadStatusLine(line) # The status code is a three-digit number try: status = int(status) if status < 100 or status > 999: raise BadStatusLine(line) except ValueError: raise BadStatusLine(line) return version, status, reason def begin(self): if self.headers is not None: # we've already started reading the response return # read until we get a non-100 response while True: version, status, reason = self._read_status() if status != CONTINUE: break # skip the header from the 100 response skipped_headers = _read_headers(self.fp) if self.debuglevel > 0: print("headers:", skipped_headers) del skipped_headers self.code = self.status = status self.reason = reason.strip() if version in ("HTTP/1.0", "HTTP/0.9"): # Some servers might still return "0.9", treat it as 1.0 anyway self.version = 10 elif version.startswith("HTTP/1."): self.version = 11 # use HTTP/1.1 code for HTTP/1.x where x>=1 else: raise UnknownProtocol(version) self.headers = self.msg = parse_headers(self.fp) if self.debuglevel > 0: for hdr, val in self.headers.items(): print("header:", hdr + ":", val) # are we using the chunked-style of transfer encoding? tr_enc = self.headers.get("transfer-encoding") if tr_enc and tr_enc.lower() == "chunked": self.chunked = True self.chunk_left = None else: self.chunked = False # will the connection close at the end of the response? self.will_close = self._check_close() # do we have a Content-Length? # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked" self.length = None length = self.headers.get("content-length") if length and not self.chunked: try: self.length = int(length) except ValueError: self.length = None else: if self.length < 0: # ignore nonsensical negative lengths self.length = None else: self.length = None # does the body have a fixed length? (of zero) if (status == NO_CONTENT or status == NOT_MODIFIED or 100 <= status < 200 or # 1xx codes self._method == "HEAD"): self.length = 0 # if the connection remains open, and we aren't using chunked, and # a content-length was not provided, then assume that the connection # WILL close. if (not self.will_close and not self.chunked and self.length is None): self.will_close = True def _check_close(self): conn = self.headers.get("connection") if self.version == 11: # An HTTP/1.1 proxy is assumed to stay open unless # explicitly closed. if conn and "close" in conn.lower(): return True return False # Some HTTP/1.0 implementations have support for persistent # connections, using rules different than HTTP/1.1. # For older HTTP, Keep-Alive indicates persistent connection. if self.headers.get("keep-alive"): return False # At least Akamai returns a "Connection: Keep-Alive" header, # which was supposed to be sent by the client. if conn and "keep-alive" in conn.lower(): return False # Proxy-Connection is a netscape hack. pconn = self.headers.get("proxy-connection") if pconn and "keep-alive" in pconn.lower(): return False # otherwise, assume it will close return True def _close_conn(self): fp = self.fp self.fp = None fp.close() def close(self): try: super().close() # set "closed" flag finally: if self.fp: self._close_conn() # These implementations are for the benefit of io.BufferedReader. # XXX This class should probably be revised to act more like # the "raw stream" that BufferedReader expects. def flush(self): super().flush() if self.fp: self.fp.flush() def readable(self): """Always returns True""" return True # End of "raw stream" methods def isclosed(self): """True if the connection is closed.""" # NOTE: it is possible that we will not ever call self.close(). This # case occurs when will_close is TRUE, length is None, and we # read up to the last byte, but NOT past it. # # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be # called, meaning self.isclosed() is meaningful. return self.fp is None def read(self, amt=None): if self.fp is None: return b"" if self._method == "HEAD": self._close_conn() return b"" if amt is not None: # Amount is given, implement using readinto b = bytearray(amt) n = self.readinto(b) return memoryview(b)[:n].tobytes() else: # Amount is not given (unbounded read) so we must check self.length # and self.chunked if self.chunked: return self._readall_chunked() if self.length is None: s = self.fp.read() else: try: s = self._safe_read(self.length) except IncompleteRead: self._close_conn() raise self.length = 0 self._close_conn() # we read everything return s def readinto(self, b): """Read up to len(b) bytes into bytearray b and return the number of bytes read. """ if self.fp is None: return 0 if self._method == "HEAD": self._close_conn() return 0 if self.chunked: return self._readinto_chunked(b) if self.length is not None: if len(b) > self.length: # clip the read to the "end of response" b = memoryview(b)[0:self.length] # we do not use _safe_read() here because this may be a .will_close # connection, and the user is reading more bytes than will be provided # (for example, reading in 1k chunks) n = self.fp.readinto(b) if not n and b: # Ideally, we would raise IncompleteRead if the content-length # wasn't satisfied, but it might break compatibility. self._close_conn() elif self.length is not None: self.length -= n if not self.length: self._close_conn() return n def _read_next_chunk_size(self): # Read the next chunk size from the file line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("chunk size") i = line.find(b";") if i >= 0: line = line[:i] # strip chunk-extensions try: return int(line, 16) except ValueError: # close the connection as protocol synchronisation is # probably lost self._close_conn() raise def _read_and_discard_trailer(self): # read and discard trailer up to the CRLF terminator ### note: we shouldn't have any trailers! while True: line = self.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("trailer line") if not line: # a vanishingly small number of sites EOF without # sending the trailer break if line in (b'\r\n', b'\n', b''): break def _get_chunk_left(self): # return self.chunk_left, reading a new chunk if necessary. # chunk_left == 0: at the end of the current chunk, need to close it # chunk_left == None: No current chunk, should read next. # This function returns non-zero or None if the last chunk has # been read. chunk_left = self.chunk_left if not chunk_left: # Can be 0 or None if chunk_left is not None: # We are at the end of chunk, discard chunk end self._safe_read(2) # toss the CRLF at the end of the chunk try: chunk_left = self._read_next_chunk_size() except ValueError: raise IncompleteRead(b'') if chunk_left == 0: # last chunk: 1*("0") [ chunk-extension ] CRLF self._read_and_discard_trailer() # we read everything; close the "file" self._close_conn() chunk_left = None self.chunk_left = chunk_left return chunk_left def _readall_chunked(self): assert self.chunked != _UNKNOWN value = [] try: while True: chunk_left = self._get_chunk_left() if chunk_left is None: break value.append(self._safe_read(chunk_left)) self.chunk_left = 0 return b''.join(value) except IncompleteRead: raise IncompleteRead(b''.join(value)) def _readinto_chunked(self, b): assert self.chunked != _UNKNOWN total_bytes = 0 mvb = memoryview(b) try: while True: chunk_left = self._get_chunk_left() if chunk_left is None: return total_bytes if len(mvb) <= chunk_left: n = self._safe_readinto(mvb) self.chunk_left = chunk_left - n return total_bytes + n temp_mvb = mvb[:chunk_left] n = self._safe_readinto(temp_mvb) mvb = mvb[n:] total_bytes += n self.chunk_left = 0 except IncompleteRead: raise IncompleteRead(bytes(b[0:total_bytes])) def _safe_read(self, amt): """Read the number of bytes requested. This function should be used when <amt> bytes "should" be present for reading. If the bytes are truly not available (due to EOF), then the IncompleteRead exception can be used to detect the problem. """ data = self.fp.read(amt) if len(data) < amt: raise IncompleteRead(data, amt-len(data)) return data def _safe_readinto(self, b): """Same as _safe_read, but for reading into a buffer.""" amt = len(b) n = self.fp.readinto(b) if n < amt: raise IncompleteRead(bytes(b[:n]), amt-n) return n def read1(self, n=-1): """Read with at most one underlying system call. If at least one byte is buffered, return that instead. """ if self.fp is None or self._method == "HEAD": return b"" if self.chunked: return self._read1_chunked(n) if self.length is not None and (n < 0 or n > self.length): n = self.length result = self.fp.read1(n) if not result and n: self._close_conn() elif self.length is not None: self.length -= len(result) return result def peek(self, n=-1): # Having this enables IOBase.readline() to read more than one # byte at a time if self.fp is None or self._method == "HEAD": return b"" if self.chunked: return self._peek_chunked(n) return self.fp.peek(n) def readline(self, limit=-1): if self.fp is None or self._method == "HEAD": return b"" if self.chunked: # Fallback to IOBase readline which uses peek() and read() return super().readline(limit) if self.length is not None and (limit < 0 or limit > self.length): limit = self.length result = self.fp.readline(limit) if not result and limit: self._close_conn() elif self.length is not None: self.length -= len(result) return result def _read1_chunked(self, n): # Strictly speaking, _get_chunk_left() may cause more than one read, # but that is ok, since that is to satisfy the chunked protocol. chunk_left = self._get_chunk_left() if chunk_left is None or n == 0: return b'' if not (0 <= n <= chunk_left): n = chunk_left # if n is negative or larger than chunk_left read = self.fp.read1(n) self.chunk_left -= len(read) if not read: raise IncompleteRead(b"") return read def _peek_chunked(self, n): # Strictly speaking, _get_chunk_left() may cause more than one read, # but that is ok, since that is to satisfy the chunked protocol. try: chunk_left = self._get_chunk_left() except IncompleteRead: return b'' # peek doesn't worry about protocol if chunk_left is None: return b'' # eof # peek is allowed to return more than requested. Just request the # entire chunk, and truncate what we get. return self.fp.peek(chunk_left)[:chunk_left] def fileno(self): return self.fp.fileno() def getheader(self, name, default=None): '''Returns the value of the header matching *name*. If there are multiple matching headers, the values are combined into a single string separated by commas and spaces. If no matching header is found, returns *default* or None if the *default* is not specified. If the headers are unknown, raises http.client.ResponseNotReady. ''' if self.headers is None: raise ResponseNotReady() headers = self.headers.get_all(name) or default if isinstance(headers, str) or not hasattr(headers, '__iter__'): return headers else: return ', '.join(headers) def getheaders(self): """Return list of (header, value) tuples.""" if self.headers is None: raise ResponseNotReady() return list(self.headers.items()) # We override IOBase.__iter__ so that it doesn't check for closed-ness def __iter__(self): return self # For compatibility with old-style urllib responses. def info(self): '''Returns an instance of the class mimetools.Message containing meta-information associated with the URL. When the method is HTTP, these headers are those returned by the server at the head of the retrieved HTML page (including Content-Length and Content-Type). When the method is FTP, a Content-Length header will be present if (as is now usual) the server passed back a file length in response to the FTP retrieval request. A Content-Type header will be present if the MIME type can be guessed. When the method is local-file, returned headers will include a Date representing the file's last-modified time, a Content-Length giving file size, and a Content-Type containing a guess at the file's type. See also the description of the mimetools module. ''' return self.headers def geturl(self): '''Return the real URL of the page. In some cases, the HTTP server redirects a client to another URL. The urlopen() function handles this transparently, but in some cases the caller needs to know which URL the client was redirected to. The geturl() method can be used to get at this redirected URL. ''' return self.url def getcode(self): '''Return the HTTP status code that was sent with the response, or None if the URL is not an HTTP URL. ''' return self.status class HTTPConnection: _http_vsn = 11 _http_vsn_str = 'HTTP/1.1' response_class = HTTPResponse default_port = HTTP_PORT auto_open = 1 debuglevel = 0 @staticmethod def _is_textIO(stream): """Test whether a file-like object is a text or a binary stream. """ return isinstance(stream, io.TextIOBase) @staticmethod def _get_content_length(body, method): """Get the content-length based on the body. If the body is None, we set Content-Length: 0 for methods that expect a body (RFC 7230, Section 3.3.2). We also set the Content-Length for any method if the body is a str or bytes-like object and not a file. """ if body is None: # do an explicit check for not None here to distinguish # between unset and set but empty if method.upper() in _METHODS_EXPECTING_BODY: return 0 else: return None if hasattr(body, 'read'): # file-like object. return None try: # does it implement the buffer protocol (bytes, bytearray, array)? mv = memoryview(body) return mv.nbytes except TypeError: pass if isinstance(body, str): return len(body) return None def __init__(self, host, port=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None, blocksize=8192): self.timeout = timeout self.source_address = source_address self.blocksize = blocksize self.sock = None self._buffer = [] self.__response = None self.__state = _CS_IDLE self._method = None self._tunnel_host = None self._tunnel_port = None self._tunnel_headers = {} (self.host, self.port) = self._get_hostport(host, port) self._validate_host(self.host) # This is stored as an instance variable to allow unit # tests to replace it with a suitable mockup self._create_connection = socket.create_connection def set_tunnel(self, host, port=None, headers=None): """Set up host and port for HTTP CONNECT tunnelling. In a connection that uses HTTP CONNECT tunneling, the host passed to the constructor is used as a proxy server that relays all communication to the endpoint passed to `set_tunnel`. This done by sending an HTTP CONNECT request to the proxy server when the connection is established. This method must be called before the HTTP connection has been established. The headers argument should be a mapping of extra HTTP headers to send with the CONNECT request. """ if self.sock: raise RuntimeError("Can't set up tunnel for established connection") self._tunnel_host, self._tunnel_port = self._get_hostport(host, port) if headers: self._tunnel_headers = headers else: self._tunnel_headers.clear() def _get_hostport(self, host, port): if port is None: i = host.rfind(':') j = host.rfind(']') # ipv6 addresses have [...] if i > j: try: port = int(host[i+1:]) except ValueError: if host[i+1:] == "": # http://foo.com:/ == http://foo.com/ port = self.default_port else: raise InvalidURL("nonnumeric port: '%s'" % host[i+1:]) host = host[:i] else: port = self.default_port if host and host[0] == '[' and host[-1] == ']': host = host[1:-1] return (host, port) def set_debuglevel(self, level): self.debuglevel = level def _tunnel(self): connect_str = "CONNECT %s:%d HTTP/1.0\r\n" % (self._tunnel_host, self._tunnel_port) connect_bytes = connect_str.encode("ascii") self.send(connect_bytes) for header, value in self._tunnel_headers.items(): header_str = "%s: %s\r\n" % (header, value) header_bytes = header_str.encode("latin-1") self.send(header_bytes) self.send(b'\r\n') response = self.response_class(self.sock, method=self._method) (version, code, message) = response._read_status() if code != http.HTTPStatus.OK: self.close() raise OSError("Tunnel connection failed: %d %s" % (code, message.strip())) while True: line = response.fp.readline(_MAXLINE + 1) if len(line) > _MAXLINE: raise LineTooLong("header line") if not line: # for sites which EOF without sending a trailer break if line in (b'\r\n', b'\n', b''): break if self.debuglevel > 0: print('header:', line.decode()) def connect(self): """Connect to the host and port specified in __init__.""" self.sock = self._create_connection( (self.host,self.port), self.timeout, self.source_address) self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) if self._tunnel_host: self._tunnel() def close(self): """Close the connection to the HTTP server.""" self.__state = _CS_IDLE try: sock = self.sock if sock: self.sock = None sock.close() # close it manually... there may be other refs finally: response = self.__response if response: self.__response = None response.close() def send(self, data): """Send `data' to the server. ``data`` can be a string object, a bytes object, an array object, a file-like object that supports a .read() method, or an iterable object. """ if self.sock is None: if self.auto_open: self.connect() else: raise NotConnected() if self.debuglevel > 0: print("send:", repr(data)) if hasattr(data, "read") : if self.debuglevel > 0: print("sendIng a read()able") encode = self._is_textIO(data) if encode and self.debuglevel > 0: print("encoding file using iso-8859-1") while 1: datablock = data.read(self.blocksize) if not datablock: break if encode: datablock = datablock.encode("iso-8859-1") self.sock.sendall(datablock) return try: self.sock.sendall(data) except TypeError: if isinstance(data, collections.abc.Iterable): for d in data: self.sock.sendall(d) else: raise TypeError("data should be a bytes-like object " "or an iterable, got %r" % type(data)) def _output(self, s): """Add a line of output to the current request buffer. Assumes that the line does *not* end with \\r\\n. """ self._buffer.append(s) def _read_readable(self, readable): if self.debuglevel > 0: print("sendIng a read()able") encode = self._is_textIO(readable) if encode and self.debuglevel > 0: print("encoding file using iso-8859-1") while True: datablock = readable.read(self.blocksize) if not datablock: break if encode: datablock = datablock.encode("iso-8859-1") yield datablock def _send_output(self, message_body=None, encode_chunked=False): """Send the currently buffered request and clear the buffer. Appends an extra \\r\\n to the buffer. A message_body may be specified, to be appended to the request. """ self._buffer.extend((b"", b"")) msg = b"\r\n".join(self._buffer) del self._buffer[:] self.send(msg) if message_body is not None: # create a consistent interface to message_body if hasattr(message_body, 'read'): # Let file-like take precedence over byte-like. This # is needed to allow the current position of mmap'ed # files to be taken into account. chunks = self._read_readable(message_body) else: try: # this is solely to check to see if message_body # implements the buffer API. it /would/ be easier # to capture if PyObject_CheckBuffer was exposed # to Python. memoryview(message_body) except TypeError: try: chunks = iter(message_body) except TypeError: raise TypeError("message_body should be a bytes-like " "object or an iterable, got %r" % type(message_body)) else: # the object implements the buffer interface and # can be passed directly into socket methods chunks = (message_body,) for chunk in chunks: if not chunk: if self.debuglevel > 0: print('Zero length chunk ignored') continue if encode_chunked and self._http_vsn == 11: # chunked encoding chunk = f'{len(chunk):X}\r\n'.encode('ascii') + chunk \ + b'\r\n' self.send(chunk) if encode_chunked and self._http_vsn == 11: # end chunked transfer self.send(b'0\r\n\r\n') def putrequest(self, method, url, skip_host=False, skip_accept_encoding=False): """Send a request to the server. `method' specifies an HTTP request method, e.g. 'GET'. `url' specifies the object being requested, e.g. '/index.html'. `skip_host' if True does not add automatically a 'Host:' header `skip_accept_encoding' if True does not add automatically an 'Accept-Encoding:' header """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # in certain cases, we cannot issue another request on this connection. # this occurs when: # 1) we are in the process of sending a request. (_CS_REQ_STARTED) # 2) a response to a previous request has signalled that it is going # to close the connection upon completion. # 3) the headers for the previous response have not been read, thus # we cannot determine whether point (2) is true. (_CS_REQ_SENT) # # if there is no prior response, then we can request at will. # # if point (2) is true, then we will have passed the socket to the # response (effectively meaning, "there is no prior response"), and # will open a new one when a new request is made. # # Note: if a prior response exists, then we *can* start a new request. # We are not allowed to begin fetching the response to this new # request, however, until that prior response is complete. # if self.__state == _CS_IDLE: self.__state = _CS_REQ_STARTED else: raise CannotSendRequest(self.__state) self._validate_method(method) # Save the method for use later in the response phase self._method = method url = url or '/' self._validate_path(url) request = '%s %s %s' % (method, url, self._http_vsn_str) self._output(self._encode_request(request)) if self._http_vsn == 11: # Issue some standard headers for better HTTP/1.1 compliance if not skip_host: # this header is issued *only* for HTTP/1.1 # connections. more specifically, this means it is # only issued when the client uses the new # HTTPConnection() class. backwards-compat clients # will be using HTTP/1.0 and those clients may be # issuing this header themselves. we should NOT issue # it twice; some web servers (such as Apache) barf # when they see two Host: headers # If we need a non-standard port,include it in the # header. If the request is going through a proxy, # but the host of the actual URL, not the host of the # proxy. netloc = '' if url.startswith('http'): nil, netloc, nil, nil, nil = urlsplit(url) if netloc: try: netloc_enc = netloc.encode("ascii") except UnicodeEncodeError: netloc_enc = netloc.encode("idna") self.putheader('Host', netloc_enc) else: if self._tunnel_host: host = self._tunnel_host port = self._tunnel_port else: host = self.host port = self.port try: host_enc = host.encode("ascii") except UnicodeEncodeError: host_enc = host.encode("idna") # As per RFC 273, IPv6 address should be wrapped with [] # when used as Host header if host.find(':') >= 0: host_enc = b'[' + host_enc + b']' if port == self.default_port: self.putheader('Host', host_enc) else: host_enc = host_enc.decode("ascii") self.putheader('Host', "%s:%s" % (host_enc, port)) # note: we are assuming that clients will not attempt to set these # headers since *this* library must deal with the # consequences. this also means that when the supporting # libraries are updated to recognize other forms, then this # code should be changed (removed or updated). # we only want a Content-Encoding of "identity" since we don't # support encodings such as x-gzip or x-deflate. if not skip_accept_encoding: self.putheader('Accept-Encoding', 'identity') # we can accept "chunked" Transfer-Encodings, but no others # NOTE: no TE header implies *only* "chunked" #self.putheader('TE', 'chunked') # if TE is supplied in the header, then it must appear in a # Connection header. #self.putheader('Connection', 'TE') else: # For HTTP/1.0, the server will assume "not chunked" pass def _encode_request(self, request): # ASCII also helps prevent CVE-2019-9740. return request.encode('ascii') def _validate_method(self, method): """Validate a method name for putrequest.""" # prevent http header injection match = _contains_disallowed_method_pchar_re.search(method) if match: raise ValueError( f"method can't contain control characters. {method!r} " f"(found at least {match.group()!r})") def _validate_path(self, url): """Validate a url for putrequest.""" # Prevent CVE-2019-9740. match = _contains_disallowed_url_pchar_re.search(url) if match: raise InvalidURL(f"URL can't contain control characters. {url!r} " f"(found at least {match.group()!r})") def _validate_host(self, host): """Validate a host so it doesn't contain control characters.""" # Prevent CVE-2019-18348. match = _contains_disallowed_url_pchar_re.search(host) if match: raise InvalidURL(f"URL can't contain control characters. {host!r} " f"(found at least {match.group()!r})") def putheader(self, header, *values): """Send a request header line to the server. For example: h.putheader('Accept', 'text/html') """ if self.__state != _CS_REQ_STARTED: raise CannotSendHeader() if hasattr(header, 'encode'): header = header.encode('ascii') if not _is_legal_header_name(header): raise ValueError('Invalid header name %r' % (header,)) values = list(values) for i, one_value in enumerate(values): if hasattr(one_value, 'encode'): values[i] = one_value.encode('latin-1') elif isinstance(one_value, int): values[i] = str(one_value).encode('ascii') if _is_illegal_header_value(values[i]): raise ValueError('Invalid header value %r' % (values[i],)) value = b'\r\n\t'.join(values) header = header + b': ' + value self._output(header) def endheaders(self, message_body=None, *, encode_chunked=False): """Indicate that the last header line has been sent to the server. This method sends the request to the server. The optional message_body argument can be used to pass a message body associated with the request. """ if self.__state == _CS_REQ_STARTED: self.__state = _CS_REQ_SENT else: raise CannotSendHeader() self._send_output(message_body, encode_chunked=encode_chunked) def request(self, method, url, body=None, headers={}, *, encode_chunked=False): """Send a complete request to the server.""" self._send_request(method, url, body, headers, encode_chunked) def _send_request(self, method, url, body, headers, encode_chunked): # Honor explicitly requested Host: and Accept-Encoding: headers. header_names = frozenset(k.lower() for k in headers) skips = {} if 'host' in header_names: skips['skip_host'] = 1 if 'accept-encoding' in header_names: skips['skip_accept_encoding'] = 1 self.putrequest(method, url, **skips) # chunked encoding will happen if HTTP/1.1 is used and either # the caller passes encode_chunked=True or the following # conditions hold: # 1. content-length has not been explicitly set # 2. the body is a file or iterable, but not a str or bytes-like # 3. Transfer-Encoding has NOT been explicitly set by the caller if 'content-length' not in header_names: # only chunk body if not explicitly set for backwards # compatibility, assuming the client code is already handling the # chunking if 'transfer-encoding' not in header_names: # if content-length cannot be automatically determined, fall # back to chunked encoding encode_chunked = False content_length = self._get_content_length(body, method) if content_length is None: if body is not None: if self.debuglevel > 0: print('Unable to determine size of %r' % body) encode_chunked = True self.putheader('Transfer-Encoding', 'chunked') else: self.putheader('Content-Length', str(content_length)) else: encode_chunked = False for hdr, value in headers.items(): self.putheader(hdr, value) if isinstance(body, str): # RFC 2616 Section 3.7.1 says that text default has a # default charset of iso-8859-1. body = _encode(body, 'body') self.endheaders(body, encode_chunked=encode_chunked) def getresponse(self): """Get the response from the server. If the HTTPConnection is in the correct state, returns an instance of HTTPResponse or of whatever object is returned by the response_class variable. If a request has not been sent or if a previous response has not be handled, ResponseNotReady is raised. If the HTTP response indicates that the connection should be closed, then it will be closed before the response is returned. When the connection is closed, the underlying socket is closed. """ # if a prior response has been completed, then forget about it. if self.__response and self.__response.isclosed(): self.__response = None # if a prior response exists, then it must be completed (otherwise, we # cannot read this response's header to determine the connection-close # behavior) # # note: if a prior response existed, but was connection-close, then the # socket and response were made independent of this HTTPConnection # object since a new request requires that we open a whole new # connection # # this means the prior response had one of two states: # 1) will_close: this connection was reset and the prior socket and # response operate independently # 2) persistent: the response was retained and we await its # isclosed() status to become true. # if self.__state != _CS_REQ_SENT or self.__response: raise ResponseNotReady(self.__state) if self.debuglevel > 0: response = self.response_class(self.sock, self.debuglevel, method=self._method) else: response = self.response_class(self.sock, method=self._method) try: try: response.begin() except ConnectionError: self.close() raise assert response.will_close != _UNKNOWN self.__state = _CS_IDLE if response.will_close: # this effectively passes the connection to the response self.close() else: # remember this, so we can tell when it is complete self.__response = response return response except: response.close() raise try: import ssl except ImportError: pass else: class HTTPSConnection(HTTPConnection): "This class allows communication via SSL." default_port = HTTPS_PORT # XXX Should key_file and cert_file be deprecated in favour of context? def __init__(self, host, port=None, key_file=None, cert_file=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None, *, context=None, check_hostname=None, blocksize=8192): super(HTTPSConnection, self).__init__(host, port, timeout, source_address, blocksize=blocksize) if (key_file is not None or cert_file is not None or check_hostname is not None): import warnings warnings.warn("key_file, cert_file and check_hostname are " "deprecated, use a custom context instead.", DeprecationWarning, 2) self.key_file = key_file self.cert_file = cert_file if context is None: context = ssl._create_default_https_context() # enable PHA for TLS 1.3 connections if available if context.post_handshake_auth is not None: context.post_handshake_auth = True will_verify = context.verify_mode != ssl.CERT_NONE if check_hostname is None: check_hostname = context.check_hostname if check_hostname and not will_verify: raise ValueError("check_hostname needs a SSL context with " "either CERT_OPTIONAL or CERT_REQUIRED") if key_file or cert_file: context.load_cert_chain(cert_file, key_file) # cert and key file means the user wants to authenticate. # enable TLS 1.3 PHA implicitly even for custom contexts. if context.post_handshake_auth is not None: context.post_handshake_auth = True self._context = context if check_hostname is not None: self._context.check_hostname = check_hostname def connect(self): "Connect to a host on a given (SSL) port." super().connect() if self._tunnel_host: server_hostname = self._tunnel_host else: server_hostname = self.host self.sock = self._context.wrap_socket(self.sock, server_hostname=server_hostname) __all__.append("HTTPSConnection") class HTTPException(Exception): # Subclasses that define an __init__ must call Exception.__init__ # or define self.args. Otherwise, str() will fail. pass class NotConnected(HTTPException): pass class InvalidURL(HTTPException): pass class UnknownProtocol(HTTPException): def __init__(self, version): self.args = version, self.version = version class UnknownTransferEncoding(HTTPException): pass class UnimplementedFileMode(HTTPException): pass class IncompleteRead(HTTPException): def __init__(self, partial, expected=None): self.args = partial, self.partial = partial self.expected = expected def __repr__(self): if self.expected is not None: e = ', %i more expected' % self.expected else: e = '' return '%s(%i bytes read%s)' % (self.__class__.__name__, len(self.partial), e) __str__ = object.__str__ class ImproperConnectionState(HTTPException): pass class CannotSendRequest(ImproperConnectionState): pass class CannotSendHeader(ImproperConnectionState): pass class ResponseNotReady(ImproperConnectionState): pass class BadStatusLine(HTTPException): def __init__(self, line): if not line: line = repr(line) self.args = line, self.line = line class LineTooLong(HTTPException): def __init__(self, line_type): HTTPException.__init__(self, "got more than %d bytes when reading %s" % (_MAXLINE, line_type)) class RemoteDisconnected(ConnectionResetError, BadStatusLine): def __init__(self, *pos, **kw): BadStatusLine.__init__(self, "") ConnectionResetError.__init__(self, *pos, **kw) # for backwards compatibility error = HTTPException PK � [�q5��; �; "