[ViewVC] Diff of: cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.01';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
71	my %CO_SLOT; # number of open connections, and wait queue, per host	70	my %CO_SLOT; # number of open connections, and wait queue, per host
72		71
73	=item http_get $url, key => value..., $cb->($data, $headers)	72	=item http_get $url, key => value..., $cb->($data, $headers)
74		73
75	Executes an HTTP-GET request. See the http_request function for details on	74	Executes an HTTP-GET request. See the http_request function for details on
76	additional parameters.	75	additional parameters and the return value.
77		76
78	=item http_head $url, key => value..., $cb->($data, $headers)	77	=item http_head $url, key => value..., $cb->($data, $headers)
79		78
80	Executes an HTTP-HEAD request. See the http_request function for details on	79	Executes an HTTP-HEAD request. See the http_request function for details
81	additional parameters.	80	on additional parameters and the return value.
82		81
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	82	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		83
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	84	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	85	http_request function for details on additional parameters and the return
		86	value.
87		87
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	88	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		89
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	91	must be an absolute http or https URL.
92		92
		93	When called in void context, nothing is returned. In other contexts,
		94	C<http_request> returns a "cancellation guard" - you have to keep the
		95	object at least alive until the callback get called. If the object gets
		96	destroyed before the callback is called, the request will be cancelled.
		97
93	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers
95	response headers as second argument.	100	(and trailers) as second argument.
96		101
97	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
		105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
		110	The pseudo-header C<URL> contains the actual URL (which can differ from
		111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
100	name. If the server sends a header multiple lines, then their contents	123	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
102		125
103	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
105	and the C<Reason> pseudo-header will contain an error message.	128	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		129	message. Currently the following status codes are used:
		130
		131	=over 4
		132
		133	=item 595 - errors during connection etsbalishment, proxy handshake.
		134
		135	=item 596 - errors during TLS negotiation, request sending and header processing.
		136
		137	=item 597 - errors during body receiving or processing.
		138
		139	=item 598 - user aborted request via C<on_header> or C<on_body>.
		140
		141	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		142
		143	=back
106		144
107	A typical callback might look like this:	145	A typical callback might look like this:
108		146
109	sub {	147	sub {
110	my ($body, $hdr) = @_;	148	my ($body, $hdr) = @_;
…		…
126	Whether to recurse requests or not, e.g. on redirects, authentication	164	Whether to recurse requests or not, e.g. on redirects, authentication
127	retries and so on, and how often to do so.	165	retries and so on, and how often to do so.
128		166
129	=item headers => hashref	167	=item headers => hashref
130		168
131	The request headers to use. Currently, C<http_request> may provide its	169	The request headers to use. Currently, C<http_request> may provide its own
132	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	170	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
133	and will provide defaults for C<User-Agent:> and C<Referer:>.	171	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		172	(this can be suppressed by using C<undef> for these headers in which case
		173	they won't be sent at all).
134		174
135	=item timeout => $seconds	175	=item timeout => $seconds
136		176
137	The time-out to use for various stages - each connect attempt will reset	177	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	178	the timeout, as will read or write activity, i.e. this is not an overall
		179	timeout.
		180
		181	Default timeout is 5 minutes.
139		182
140	=item proxy => [$host, $port[, $scheme]] or undef	183	=item proxy => [$host, $port[, $scheme]] or undef
141		184
142	Use the given http proxy for all requests. If not specified, then the	185	Use the given http proxy for all requests. If not specified, then the
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	186	default proxy (as specified by C<$ENV{http_proxy}>) is used.
144		187
145	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	188	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
146	HTTPS.	189	HTTPS.
147		190
148	=item body => $string	191	=item body => $string
149		192
150	The request body, usually empty. Will be-sent as-is (future versions of	193	The request body, usually empty. Will be sent as-is (future versions of
151	this module might offer more options).	194	this module might offer more options).
152		195
153	=item cookie_jar => $hash_ref	196	=item cookie_jar => $hash_ref
154		197
155	Passing this parameter enables (simplified) cookie-processing, loosely	198	Passing this parameter enables (simplified) cookie-processing, loosely
156	based on the original netscape specification.	199	based on the original netscape specification.
157		200
158	The C<$hash_ref> must be an (initially empty) hash reference which will	201	The C<$hash_ref> must be an (initially empty) hash reference which
159	get updated automatically. It is possible to save the cookie_jar to	202	will get updated automatically. It is possible to save the cookie jar
160	persistent storage with something like JSON or Storable, but this is not	203	to persistent storage with something like JSON or Storable - see the
161	recommended, as expire times are currently being ignored.	204	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		205	expired or session-only cookies, and also for documentation on the format
		206	of the cookie jar.
162		207
163	Note that this cookie implementation is not of very high quality, nor	208	Note that this cookie implementation is not meant to be complete. If
164	meant to be complete. If you want complete cookie management you have to	209	you want complete cookie management you have to do that on your
165	do that on your own. C<cookie_jar> is meant as a quick fix to get some	210	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
166	cookie-using sites working. Cookies are a privacy disaster, do not use	211	working. Cookies are a privacy disaster, do not use them unless required
167	them unless required to.	212	to.
		213
		214	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		215	headers will be set and handled by this module, otherwise they will be
		216	left untouched.
		217
		218	=item tls_ctx => $scheme \| $tls_ctx
		219
		220	Specifies the AnyEvent::TLS context to be used for https connections. This
		221	parameter follows the same rules as the C<tls_ctx> parameter to
		222	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		223	C<high> can be specified, which give you a predefined low-security (no
		224	verification, highest compatibility) and high-security (CA and common-name
		225	verification) TLS context.
		226
		227	The default for this option is C<low>, which could be interpreted as "give
		228	me the page, no matter what".
		229
		230	=item on_prepare => $callback->($fh)
		231
		232	In rare cases you need to "tune" the socket before it is used to
		233	connect (for exmaple, to bind it on a given IP address). This parameter
		234	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		235	and behaves exactly the same way (e.g. it has to provide a
		236	timeout). See the description for the C<$prepare_cb> argument of
		237	C<AnyEvent::Socket::tcp_connect> for details.
		238
		239	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		240
		241	In even rarer cases you want total control over how AnyEvent::HTTP
		242	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		243	to do this, but you can provide your own C<tcp_connect> function -
		244	obviously, it has to follow the same calling conventions, except that it
		245	may always return a connection guard object.
		246
		247	There are probably lots of weird uses for this function, starting from
		248	tracing the hosts C<http_request> actually tries to connect, to (inexact
		249	but fast) host => IP address caching or even socks protocol support.
		250
		251	=item on_header => $callback->($headers)
		252
		253	When specified, this callback will be called with the header hash as soon
		254	as headers have been successfully received from the remote server (not on
		255	locally-generated errors).
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the finish callback with an error code of C<598>).
		260
		261	This callback is useful, among other things, to quickly reject unwanted
		262	content, which, if it is supposed to be rare, can be faster than first
		263	doing a C<HEAD> request.
		264
		265	The downside is that cancelling the request makes it impossible to re-use
		266	the connection. Also, the C<on_header> callback will not receive any
		267	trailer (headers sent after the response body).
		268
		269	Example: cancel the request unless the content-type is "text/html".
		270
		271	on_header => sub {
		272	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		273	},
		274
		275	=item on_body => $callback->($partial_body, $headers)
		276
		277	When specified, all body data will be passed to this callback instead of
		278	to the completion callback. The completion callback will get the empty
		279	string instead of the body data.
		280
		281	It has to return either true (in which case AnyEvent::HTTP will continue),
		282	or false, in which case AnyEvent::HTTP will cancel the download (and call
		283	the completion callback with an error code of C<598>).
		284
		285	The downside to cancelling the request is that it makes it impossible to
		286	re-use the connection.
		287
		288	This callback is useful when the data is too large to be held in memory
		289	(so the callback writes it to a file) or when only some information should
		290	be extracted, or when the body should be processed incrementally.
		291
		292	It is usually preferred over doing your own body handling via
		293	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		294	only used to create a connection, C<want_body_handle> is the better
		295	alternative, as it allows you to install your own event handler, reducing
		296	resource usage.
		297
		298	=item want_body_handle => $enable
		299
		300	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		301	changes considerably: after parsing the headers, and instead of
		302	downloading the body (if any), the completion callback will be
		303	called. Instead of the C<$body> argument containing the body data, the
		304	callback will receive the L<AnyEvent::Handle> object associated with the
		305	connection. In error cases, C<undef> will be passed. When there is no body
		306	(e.g. status C<304>), the empty string will be passed.
		307
		308	The handle object might or might not be in TLS mode, might be connected to
		309	a proxy, be a persistent connection etc., and configured in unspecified
		310	ways. The user is responsible for this handle (it will not be used by this
		311	module anymore).
		312
		313	This is useful with some push-type services, where, after the initial
		314	headers, an interactive protocol is used (typical example would be the
		315	push-style twitter API which starts a JSON/XML stream).
		316
		317	If you think you need this, first have a look at C<on_body>, to see if
		318	that doesn't solve your problem in a better way.
168		319
169	=back	320	=back
170		321
171	Example: make a simple HTTP GET request for http://www.nethype.de/	322	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		323	the response body.
172		324
173	http_request GET => "http://www.nethype.de/", sub {	325	http_request GET => "http://www.nethype.de/", sub {
174	my ($body, $hdr) = @_;	326	my ($body, $hdr) = @_;
175	print "$body\n";	327	print "$body\n";
176	};	328	};
177		329
178	Example: make a HTTP HEAD request on https://www.google.com/, use a	330	Example: do a HTTP HEAD request on https://www.google.com/, use a
179	timeout of 30 seconds.	331	timeout of 30 seconds.
180		332
181	http_request	333	http_request
182	GET => "https://www.google.com",	334	GET => "https://www.google.com",
183	timeout => 30,	335	timeout => 30,
…		…
185	my ($body, $hdr) = @_;	337	my ($body, $hdr) = @_;
186	use Data::Dumper;	338	use Data::Dumper;
187	print Dumper $hdr;	339	print Dumper $hdr;
188	}	340	}
189	;	341	;
		342
		343	Example: do another simple HTTP GET request, but immediately try to
		344	cancel it.
		345
		346	my $request = http_request GET => "http://www.nethype.de/", sub {
		347	my ($body, $hdr) = @_;
		348	print "$body\n";
		349	};
		350
		351	undef $request;
190		352
191	=cut	353	=cut
192		354
193	sub _slot_schedule;	355	sub _slot_schedule;
194	sub _slot_schedule($) {	356	sub _slot_schedule($) {
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	380	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		381
220	_slot_schedule $_[0];	382	_slot_schedule $_[0];
221	}	383	}
222		384
		385	#############################################################################
		386
		387	# expire cookies
		388	sub cookie_jar_expire($;$) {
		389	my ($jar, $session_end) = @_;
		390
		391	%$jar = () if $jar->{version} != 1;
		392
		393	my $anow = AE::now;
		394
		395	while (my ($chost, $paths) = each %$jar) {
		396	next unless ref $paths;
		397
		398	while (my ($cpath, $cookies) = each %$paths) {
		399	while (my ($cookie, $kv) = each %$cookies) {
		400	if (exists $kv->{_expires}) {
		401	delete $cookies->{$cookie}
		402	if $anow > $kv->{_expires};
		403	} elsif ($session_end) {
		404	delete $cookies->{$cookie};
		405	}
		406	}
		407
		408	delete $paths->{$cpath}
		409	unless %$cookies;
		410	}
		411
		412	delete $jar->{$chost}
		413	unless %$paths;
		414	}
		415	}
		416
		417	# extract cookies from jar
		418	sub cookie_jar_extract($$$$) {
		419	my ($jar, $uscheme, $uhost, $upath) = @_;
		420
		421	$uhost = lc $uhost;
		422
		423	%$jar = () if $jar->{version} != 1;
		424
		425	my @cookies;
		426
		427	while (my ($chost, $paths) = each %$jar) {
		428	next unless ref $paths;
		429
		430	if ($chost =~ /^\./) {
		431	next unless $chost eq substr $uhost, -length $chost;
		432	} elsif ($chost =~ /\./) {
		433	next unless $chost eq $uhost;
		434	} else {
		435	next;
		436	}
		437
		438	while (my ($cpath, $cookies) = each %$paths) {
		439	next unless $cpath eq substr $upath, 0, length $cpath;
		440
		441	while (my ($cookie, $kv) = each %$cookies) {
		442	next if $uscheme ne "https" && exists $kv->{secure};
		443
		444	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		445	delete $cookies->{$cookie};
		446	next;
		447	}
		448
		449	my $value = $kv->{value};
		450
		451	if ($value =~ /[=;,[:space:]]/) {
		452	$value =~ s/([\\"])/\\$1/g;
		453	$value = "\"$value\"";
		454	}
		455
		456	push @cookies, "$cookie=$value";
		457	}
		458	}
		459	}
		460
		461	\@cookies
		462	}
		463
		464	# parse set_cookie header into jar
		465	sub cookie_jar_set_cookie($$$$) {
		466	my ($jar, $set_cookie, $uhost, $date) = @_;
		467
		468	my $anow = int AE::now;
		469	my $snow; # server-now
		470
		471	for ($set_cookie) {
		472	# parse NAME=VALUE
		473	my @kv;
		474
		475	# expires is not http-compliant in the original cookie-spec,
		476	# we support the official date format and some extensions
		477	while (
		478	m{
		479	\G\s*
		480	(?:
		481	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		482	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) ) )?
		483	)
		484	}gcxsi
		485	) {
		486	my $name = $2;
		487	my $value = $4;
		488
		489	if (defined $1) {
		490	# expires
		491	$name = "expires";
		492	$value = $1;
		493	} elsif (defined $3) {
		494	# quoted
		495	$value = $3;
		496	$value =~ s/\\(.)/$1/gs;
		497	}
		498
		499	push @kv, lc $name, $value;
		500
		501	last unless /\G\s*;/gc;
		502	}
		503
		504	last unless @kv;
		505
		506	my $name = shift @kv;
		507	my %kv = (value => shift @kv, @kv);
		508
		509	if (exists $kv{"max-age"}) {
		510	$kv{_expires} = $anow + delete $kv{"max-age"};
		511	} elsif (exists $kv{expires}) {
		512	$snow \|\|= parse_date ($date) \|\| $anow;
		513	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		514	} else {
		515	delete $kv{_expires};
		516	}
		517
		518	my $cdom;
		519	my $cpath = (delete $kv{path}) \|\| "/";
		520
		521	if (exists $kv{domain}) {
		522	$cdom = delete $kv{domain};
		523
		524	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		525
		526	next if $cdom =~ /\.$/;
		527
		528	# this is not rfc-like and not netscape-like. go figure.
		529	my $ndots = $cdom =~ y/.//;
		530	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		531	} else {
		532	$cdom = $uhost;
		533	}
		534
		535	# store it
		536	$jar->{version} = 1;
		537	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		538
		539	redo if /\G\s*,/gc;
		540	}
		541	}
		542
		543	# continue to parse $_ for headers and place them into the arg
		544	sub parse_hdr() {
		545	my %hdr;
		546
		547	# things seen, not parsed:
		548	# p3pP="NON CUR OTPi OUR NOR UNI"
		549
		550	$hdr{lc $1} .= ",$2"
		551	while /\G
		552	([^:\000-\037]*):
		553	[\011\040]*
		554	((?: [^\012]+ \| \012[\011\040] )*)
		555	\012
		556	/gxc;
		557
		558	/\G$/
		559	or return;
		560
		561	# remove the "," prefix we added to all headers above
		562	substr $_, 0, 1, ""
		563	for values %hdr;
		564
		565	\%hdr
		566	}
		567
		568	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		569
		570	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		571	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		572
223	sub http_request($$@) {	573	sub http_request($$@) {
224	my $cb = pop;	574	my $cb = pop;
225	my ($method, $url, %arg) = @_;	575	my ($method, $url, %arg) = @_;
226		576
227	my %hdr;	577	my %hdr;
		578
		579	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		580	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
228		581
229	$method = uc $method;	582	$method = uc $method;
230		583
231	if (my $hdr = $arg{headers}) {	584	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	585	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	586	$hdr{lc $k} = $v;
234	}	587	}
235	}	588	}
236		589
		590	# pseudo headers for all subsequent responses
		591	my @pseudo = (URL => $url);
		592	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		593
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	594	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		595
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	596	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
240	if $recurse < 0;	597	if $recurse < 0;
241		598
242	my $proxy = $arg{proxy} \|\| $PROXY;	599	my $proxy = $arg{proxy} \|\| $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	600	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		601
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	602	my ($uscheme, $uauthority, $upath, $query, $fragment) =
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	603	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
249		604
250	$scheme = lc $scheme;	605	$uscheme = lc $uscheme;
251		606
252	my $uport = $scheme eq "http" ? 80	607	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	608	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	609	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
255		610
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	611	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	612	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
260		613
261	my $uhost = $1;	614	my $uhost = $1;
262	$uport = $2 if defined $2;	615	$uport = $2 if defined $2;
263		616
		617	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		618	unless exists $hdr{host};
		619
264	$uhost =~ s/^\[(.*)\]$/$1/;	620	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	621	$upath .= $query if length $query;
266		622
267	$upath =~ s%^/?%/%;	623	$upath =~ s%^/?%/%;
268		624
269	# cookie processing	625	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	626	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	627	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
272		628
273	my @cookie;
274
275	while (my ($chost, $v) = each %$jar) {
276	next unless $chost eq substr $uhost, -length $chost;
277	next unless $chost =~ /^\./;
278
279	while (my ($cpath, $v) = each %$v) {
280	next unless $cpath eq substr $upath, 0, length $cpath;
281
282	while (my ($k, $v) = each %$v) {
283	next if $scheme ne "https" && exists $v->{secure};
284	push @cookie, "$k=$v->{value}";
285	}
286	}
287	}
288
289	$hdr{cookie} = join "; ", @cookie	629	$hdr{cookie} = join "; ", @$cookies
290	if @cookie;	630	if @$cookies;
291	}	631	}
292		632
293	my ($rhost, $rport, $rpath); # request host, port, path	633	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
294		634
295	if ($proxy) {	635	if ($proxy) {
296	($rhost, $rport, $scheme) = @$proxy;	636	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
297	$rpath = $url;	637
		638	$rscheme = "http" unless defined $rscheme;
		639
		640	# don't support https requests over https-proxy transport,
		641	# can't be done with tls as spec'ed, unless you double-encrypt.
		642	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
298	} else {	643	} else {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	644	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
300	$hdr{host} = $uhost;
301	}	645	}
302		646
		647	# leave out fragment and query string, just a heuristic
		648	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		649	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		650
303	$hdr{"content-length"} = length $arg{body};	651	$hdr{"content-length"} = length $arg{body}
		652	if length $arg{body} \|\| $method ne "GET";
		653
		654	$hdr{connection} = "close TE"; #1.1
		655	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
304		656
305	my %state = (connect_guard => 1);	657	my %state = (connect_guard => 1);
306		658
307	_get_slot $uhost, sub {	659	_get_slot $uhost, sub {
308	$state{slot_guard} = shift;	660	$state{slot_guard} = shift;
309		661
310	return unless $state{connect_guard};	662	return unless $state{connect_guard};
311		663
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	664	my $ae_error = 595; # connecting
313	$state{fh} = shift
314	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
315		665
316	delete $state{connect_guard}; # reduce memory usage, save a tree	666	# handle actual, non-tunneled, request
		667	my $handle_actual_request = sub {
		668	$ae_error = 596; # request phase
317		669
318	# get handle	670	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
319	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());
322
323	# limit the number of persistent connections
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
327	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {
330	delete $hdr{connection};
331	}
332
333	# (re-)configure handle
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {
336	my $errno = "$!";
337	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
339	});
340	$state{handle}->on_eof (sub {
341	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
343	});
344		671
345	# send request	672	# send request
346	$state{handle}->push_write (	673	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"	674	"$method $rpath HTTP/1.1\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	675	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
349	. "\015\012"	676	. "\015\012"
350	. (delete $arg{body})	677	. (delete $arg{body})
351	);	678	);
352		679
		680	# return if error occured during push_write()
		681	return unless %state;
		682
353	%hdr = (); # reduce memory usage, save a kitten	683	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
354		684
355	# status line	685	# status line and headers
356	$state{handle}->push_read (line => qr/\015?\012/, sub {	686	$state{read_response} = sub {
357	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
358	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
359
360	my %hdr = ( # response headers
361	HTTPVersion => "\x00$1",
362	Status => "\x00$2",
363	Reason => "\x00$3",
364	URL => "\x00$url"
365	);
366
367	# headers, could be optimized a bit
368	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
369	for ("$_[1]\012") {	687	for ("$_[1]") {
370	# we support spaces in field names, as lotus domino	688	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
371	# creates them.
372	$hdr{lc $1} .= "\x00$2"
373	while /\G
374	([^:\000-\037]+):
375	[\011\040]*
376	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
377	\015?\012
378	/gxc;
379		689
		690	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		691	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		692
		693	# 100 Continue handling
		694	# should not happen as we don't send expect: 100-continue,
		695	# but we handle it just in case.
		696	# since we send the request body regardless, if we get an error
		697	# we are out of-sync, which we currently do NOT handle correctly.
		698	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		699	if $2 eq 100;
		700
		701	push @pseudo,
		702	HTTPVersion => $1,
		703	Status => $2,
		704	Reason => $3,
380	/\G$/	705	;
		706
		707	my $hdr = parse_hdr
381	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	708	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		709
		710	%hdr = (%$hdr, @pseudo);
		711	}
		712
		713	# redirect handling
		714	# microsoft and other shitheads don't give a shit for following standards,
		715	# try to support some common forms of broken Location headers.
		716	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		717	$hdr{location} =~ s/^\.\/+//;
		718
		719	my $url = "$rscheme://$uhost:$uport";
		720
		721	unless ($hdr{location} =~ s/^\///) {
		722	$url .= $upath;
		723	$url =~ s/\/[^\/]*$//;
382	}	724	}
383		725
384	substr $_, 0, 1, ""	726	$hdr{location} = "$url/$hdr{location}";
385	for values %hdr;	727	}
386		728
387	my $finish = sub {	729	my $redirect;
		730
		731	if ($recurse) {
		732	my $status = $hdr{Status};
		733
		734	# industry standard is to redirect POST as GET for
		735	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		736	# also, the UA should ask the user for 301 and 307 and POST,
		737	# industry standard seems to be to simply follow.
		738	# we go with the industry standard.
		739	if ($status == 301 or $status == 302 or $status == 303) {
		740	# HTTP/1.1 is unclear on how to mutate the method
		741	$method = "GET" unless $method eq "HEAD";
		742	$redirect = 1;
		743	} elsif ($status == 307) {
		744	$redirect = 1;
		745	}
		746	}
		747
		748	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		749	my $may_keep_alive = $_[3];
		750
		751	$state{handle}->destroy if $state{handle};
388	%state = ();	752	%state = ();
389		753
		754	if (defined $_[1]) {
		755	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		756	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		757	}
		758
390	# set-cookie processing	759	# set-cookie processing
391	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	760	if ($arg{cookie_jar}) {
392	for (split /\x00/, $hdr{"set-cookie"}) {	761	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
393	my ($cookie, @arg) = split /;\s*/;	762	}
394	my ($name, $value) = split /=/, $cookie, 2;
395	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
396
397	my $cdom = (delete $kv{domain}) \|\| $uhost;
398	my $cpath = (delete $kv{path}) \|\| "/";
399
400	$cdom =~ s/^.?/./; # make sure it starts with a "."
401		763
402	next if $cdom =~ /\.$/;	764	if ($redirect && exists $hdr{location}) {
403		765	# we ignore any errors, as it is very common to receive
404	# this is not rfc-like and not netscape-like. go figure.	766	# Content-Length != 0 but no actual body
405	my $ndots = $cdom =~ y/.//;	767	# we also access %hdr, as $_[1] might be an erro
406	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	768	http_request (
407		769	$method => $hdr{location},
		770	%arg,
		771	recurse => $recurse - 1,
		772	Redirect => [$_[0], \%hdr],
		773	$cb);
		774	} else {
		775	$cb->($_[0], \%hdr);
		776	}
		777	};
		778
		779	$ae_error = 597; # body phase
		780
		781	my $len = $hdr{"content-length"};
		782
		783	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		784	$finish->(undef, 598 => "Request cancelled by on_header");
		785	} elsif (
		786	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		787	or $method eq "HEAD"
		788	or (defined $len && !$len)
		789	) {
		790	# no body
		791	$finish->("", undef, undef, 1);
		792	} else {
		793	# body handling, many different code paths
		794	# - no body expected
		795	# - want_body_handle
		796	# - te chunked
		797	# - 2x length known (with or without on_body)
		798	# - 2x length not known (with or without on_body)
		799	if (!$redirect && $arg{want_body_handle}) {
		800	$_[0]->on_eof (undef);
		801	$_[0]->on_error (undef);
		802	$_[0]->on_read (undef);
		803
		804	$finish->(delete $state{handle});
		805
		806	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		807	my $cl = 0;
		808	my $body = undef;
		809	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		810
		811	$state{read_chunk} = sub {
		812	$_[1] =~ /^([0-9a-fA-F]+)/
		813	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		814
		815	my $len = hex $1;
		816
		817	if ($len) {
		818	$cl += $len;
		819
		820	$_[0]->push_read (chunk => $len, sub {
		821	$on_body->($_[1], \%hdr)
		822	or return $finish->(undef, 598 => "Request cancelled by on_body");
		823
		824	$_[0]->push_read (line => sub {
		825	length $_[1]
		826	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		827	$_[0]->push_read (line => $state{read_chunk});
		828	});
408	# store it	829	});
409	$arg{cookie_jar}{version} = 1;	830	} else {
410	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	831	$hdr{"content-length"} \|\|= $cl;
		832
		833	$_[0]->push_read (line => $qr_nlnl, sub {
		834	if (length $_[1]) {
		835	for ("$_[1]") {
		836	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		837
		838	my $hdr = parse_hdr
		839	or return $finish->(undef, $ae_error => "Garbled response trailers");
		840
		841	%hdr = (%hdr, %$hdr);
		842	}
		843	}
		844
		845	$finish->($body, undef, undef, 1);
		846	});
411	}	847	}
412	}	848	};
413		849
414	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	850	$_[0]->push_read (line => $state{read_chunk});
415	# microsoft and other assholes don't give a shit for following standards,
416	# try to support a common form of broken Location header.
417	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
418		851
419	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	852	} elsif ($arg{on_body}) {
420	} else {	853	if ($len) {
421	$cb->($_[0], $_[1]);	854	$_[0]->on_read (sub {
422	}	855	$len -= length $_[0]{rbuf};
423	};
424		856
425	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	857	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
426	$finish->(undef, \%hdr);	858	or return $finish->(undef, 598 => "Request cancelled by on_body");
427	} else {	859
428	if (exists $hdr{"content-length"}) {
429	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
430	# could cache persistent connection now
431	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
432	# but we don't, due to misdesigns, this is annoyingly complex
433	};	860	$len > 0
434		861	or $finish->("", undef, undef, 1);
435	$finish->($_[1], \%hdr);
436	});	862	});
437	} else {	863	} else {
438	# too bad, need to read until we get an error or EOF,	864	$_[0]->on_eof (sub {
439	# no way to detect winged data.	865	$finish->("");
		866	});
		867	$_[0]->on_read (sub {
		868	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		869	or $finish->(undef, 598 => "Request cancelled by on_body");
		870	});
		871	}
		872	} else {
		873	$_[0]->on_eof (undef);
		874
		875	if ($len) {
		876	$_[0]->on_read (sub {
		877	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		878	if $len <= length $_[0]{rbuf};
		879	});
		880	} else {
440	$_[0]->on_error (sub {	881	$_[0]->on_error (sub {
		882	($! == Errno::EPIPE \|\| !$!)
441	$finish->($_[0]{rbuf}, \%hdr);	883	? $finish->(delete $_[0]{rbuf})
		884	: $finish->(undef, $ae_error => $_[2]);
442	});	885	});
443	$_[0]->on_eof (undef);
444	$_[0]->on_read (sub { });	886	$_[0]->on_read (sub { });
445	}	887	}
446	}	888	}
		889	}
		890	};
		891
		892	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		893	};
		894
		895	my $connect_cb = sub {
		896	$state{fh} = shift
		897	or do {
		898	my $err = "$!";
		899	%state = ();
		900	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
		901	};
		902
		903	return unless delete $state{connect_guard};
		904
		905	# get handle
		906	$state{handle} = new AnyEvent::Handle
		907	fh => $state{fh},
		908	peername => $rhost,
		909	tls_ctx => $arg{tls_ctx},
		910	# these need to be reconfigured on keepalive handles
		911	timeout => $timeout,
		912	on_error => sub {
		913	%state = ();
		914	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
		915	},
		916	on_eof => sub {
		917	%state = ();
		918	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
		919	},
		920	;
		921
		922	# limit the number of persistent connections
		923	# keepalive not yet supported
		924	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		925	# ++$KA_COUNT{$_[1]};
		926	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		927	# --$KA_COUNT{$_[1]}
		928	# };
		929	# $hdr{connection} = "keep-alive";
		930	# }
		931
		932	$state{handle}->starttls ("connect") if $rscheme eq "https";
		933
		934	# now handle proxy-CONNECT method
		935	if ($proxy && $uscheme eq "https") {
		936	# oh dear, we have to wrap it into a connect request
		937
		938	# maybe re-use $uauthority with patched port?
		939	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		940	$state{handle}->push_read (line => $qr_nlnl, sub {
		941	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		942	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		943
		944	if ($2 == 200) {
		945	$rpath = $upath;
		946	$handle_actual_request->();
		947	} else {
		948	%state = ();
		949	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		950	}
447	});	951	});
		952	} else {
		953	$handle_actual_request->();
448	});	954	}
449	}, sub {
450	$timeout
451	};	955	};
		956
		957	my $tcp_connect = $arg{tcp_connect}
		958	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		959
		960	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
452	};	961	};
453		962
454	defined wantarray && AnyEvent::Util::guard { %state = () }	963	defined wantarray && AnyEvent::Util::guard { %state = () }
455	}	964	}
456		965
…		…
463	unshift @_, "HEAD";	972	unshift @_, "HEAD";
464	&http_request	973	&http_request
465	}	974	}
466		975
467	sub http_post($$@) {	976	sub http_post($$@) {
		977	my $url = shift;
468	unshift @_, "POST", "body";	978	unshift @_, "POST", $url, "body";
469	&http_request	979	&http_request
470	}	980	}
471		981
472	=back	982	=back
473		983
		984	=head2 DNS CACHING
		985
		986	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		987	the actual connection, which in turn uses AnyEvent::DNS to resolve
		988	hostnames. The latter is a simple stub resolver and does no caching
		989	on its own. If you want DNS caching, you currently have to provide
		990	your own default resolver (by storing a suitable resolver object in
		991	C<$AnyEvent::DNS::RESOLVER>).
		992
474	=head2 GLOBAL FUNCTIONS AND VARIABLES	993	=head2 GLOBAL FUNCTIONS AND VARIABLES
475		994
476	=over 4	995	=over 4
477		996
478	=item AnyEvent::HTTP::set_proxy "proxy-url"	997	=item AnyEvent::HTTP::set_proxy "proxy-url"
479		998
480	Sets the default proxy server to use. The proxy-url must begin with a	999	Sets the default proxy server to use. The proxy-url must begin with a
481	string of the form C<http://host:port> (optionally C<https:...>).	1000	string of the form C<http://host:port> (optionally C<https:...>), croaks
		1001	otherwise.
		1002
		1003	To clear an already-set proxy, use C<undef>.
		1004
		1005	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1006
		1007	Remove all cookies from the cookie jar that have been expired. If
		1008	C<$session_end> is given and true, then additionally remove all session
		1009	cookies.
		1010
		1011	You should call this function (with a true C<$session_end>) before you
		1012	save cookies to disk, and you should call this function after loading them
		1013	again. If you have a long-running program you can additonally call this
		1014	function from time to time.
		1015
		1016	A cookie jar is initially an empty hash-reference that is managed by this
		1017	module. It's format is subject to change, but currently it is like this:
		1018
		1019	The key C<version> has to contain C<1>, otherwise the hash gets
		1020	emptied. All other keys are hostnames or IP addresses pointing to
		1021	hash-references. The key for these inner hash references is the
		1022	server path for which this cookie is meant, and the values are again
		1023	hash-references. The keys of those hash-references is the cookie name, and
		1024	the value, you guessed it, is another hash-reference, this time with the
		1025	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1026	which have been replaced by a C<_expires> key that contains the cookie
		1027	expiry timestamp.
		1028
		1029	Here is an example of a cookie jar with a single cookie, so you have a
		1030	chance of understanding the above paragraph:
		1031
		1032	{
		1033	version => 1,
		1034	"10.0.0.1" => {
		1035	"/" => {
		1036	"mythweb_id" => {
		1037	_expires => 1293917923,
		1038	value => "ooRung9dThee3ooyXooM1Ohm",
		1039	},
		1040	},
		1041	},
		1042	}
		1043
		1044	=item $date = AnyEvent::HTTP::format_date $timestamp
		1045
		1046	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1047	Date (RFC 2616).
		1048
		1049	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1050
		1051	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1052	bunch of minor variations of those, and returns the corresponding POSIX
		1053	timestamp, or C<undef> if the date cannot be parsed.
482		1054
483	=item $AnyEvent::HTTP::MAX_RECURSE	1055	=item $AnyEvent::HTTP::MAX_RECURSE
484		1056
485	The default value for the C<recurse> request parameter (default: C<10>).	1057	The default value for the C<recurse> request parameter (default: C<10>).
486		1058
487	=item $AnyEvent::HTTP::USERAGENT	1059	=item $AnyEvent::HTTP::USERAGENT
488		1060
489	The default value for the C<User-Agent> header (the default is	1061	The default value for the C<User-Agent> header (the default is
490	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1062	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
491		1063
492	=item $AnyEvent::HTTP::MAX_PERSISTENT	1064	=item $AnyEvent::HTTP::MAX_PER_HOST
493		1065
494	The maximum number of persistent connections to keep open (default: 8).	1066	The maximum number of concurrent connections to the same host (identified
		1067	by the hostname). If the limit is exceeded, then the additional requests
		1068	are queued until previous connections are closed.
495		1069
496	Not implemented currently.	1070	The default value for this is C<4>, and it is highly advisable to not
497		1071	increase it.
498	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
499
500	The maximum time to cache a persistent connection, in seconds (default: 2).
501
502	Not implemented currently.
503		1072
504	=item $AnyEvent::HTTP::ACTIVE	1073	=item $AnyEvent::HTTP::ACTIVE
505		1074
506	The number of active connections. This is not the number of currently	1075	The number of active connections. This is not the number of currently
507	running requests, but the number of currently open and non-idle TCP	1076	running requests, but the number of currently open and non-idle TCP
…		…
509		1078
510	=back	1079	=back
511		1080
512	=cut	1081	=cut
513		1082
		1083	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1084	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1085
		1086	sub format_date($) {
		1087	my ($time) = @_;
		1088
		1089	# RFC 822/1123 format
		1090	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1091
		1092	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1093	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1094	$H, $M, $S;
		1095	}
		1096
		1097	sub parse_date($) {
		1098	my ($date) = @_;
		1099
		1100	my ($d, $m, $y, $H, $M, $S);
		1101
		1102	if ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
		1103	# RFC 822/1123, required by RFC 2616 (with " ")
		1104	# cookie dates (with "-")
		1105
		1106	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1107
		1108	} elsif ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) {
		1109	# RFC 850
		1110	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1111
		1112	} elsif ($date =~ /^[A-Z][a-z][a-z]+ ([A-Z][a-z][a-z]) ([0-9 ]?[0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) ([0-9][0-9][0-9][0-9])$/) {
		1113	# ISO C's asctime
		1114	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1115	}
		1116	# other formats fail in the loop below
		1117
		1118	for (0..11) {
		1119	if ($m eq $month[$_]) {
		1120	require Time::Local;
		1121	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1122	}
		1123	}
		1124
		1125	undef
		1126	}
		1127
514	sub set_proxy($) {	1128	sub set_proxy($) {
		1129	if (length $_[0]) {
515	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1130	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1131	or Carp::croak "$_[0]: invalid proxy URL";
		1132	$PROXY = [$2, $3 \|\| 3128, $1]
		1133	} else {
		1134	undef $PROXY;
		1135	}
516	}	1136	}
517		1137
518	# initialise proxy from environment	1138	# initialise proxy from environment
		1139	eval {
519	set_proxy $ENV{http_proxy};	1140	set_proxy $ENV{http_proxy};
		1141	};
		1142
		1143	=head2 SOCKS PROXIES
		1144
		1145	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1146	compile your perl to support socks, or use an external program such as
		1147	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1148	transparently.
		1149
		1150	Alternatively, for AnyEvent::HTTP only, you can use your own
		1151	C<tcp_connect> function that does the proxy handshake - here is an example
		1152	that works with socks4a proxies:
		1153
		1154	use Errno;
		1155	use AnyEvent::Util;
		1156	use AnyEvent::Socket;
		1157	use AnyEvent::Handle;
		1158
		1159	# host, port and username of/for your socks4a proxy
		1160	my $socks_host = "10.0.0.23";
		1161	my $socks_port = 9050;
		1162	my $socks_user = "";
		1163
		1164	sub socks4a_connect {
		1165	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1166
		1167	my $hdl = new AnyEvent::Handle
		1168	connect => [$socks_host, $socks_port],
		1169	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1170	on_error => sub { $connect_cb->() },
		1171	;
		1172
		1173	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1174
		1175	$hdl->push_read (chunk => 8, sub {
		1176	my ($hdl, $chunk) = @_;
		1177	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1178
		1179	if ($status == 0x5a) {
		1180	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1181	} else {
		1182	$! = Errno::ENXIO; $connect_cb->();
		1183	}
		1184	});
		1185
		1186	$hdl
		1187	}
		1188
		1189	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1190	possibly after switching off other proxy types:
		1191
		1192	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1193
		1194	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1195	my ($data, $headers) = @_;
		1196	...
		1197	};
520		1198
521	=head1 SEE ALSO	1199	=head1 SEE ALSO
522		1200
523	L<AnyEvent>.	1201	L<AnyEvent>.
524		1202
525	=head1 AUTHOR	1203	=head1 AUTHOR
526		1204
527	Marc Lehmann <schmorp@schmorp.de>	1205	Marc Lehmann <schmorp@schmorp.de>
528	http://home.schmorp.de/	1206	http://home.schmorp.de/
529		1207
		1208	With many thanks to Дмитрий Шалашов, who provided countless
		1209	testcases and bugreports.
		1210
530	=cut	1211	=cut
531		1212
532	1	1213	1
533		1214

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs. Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.19 by elmex, Mon Jun 9 13:02:13 2008 UTC vs.
Revision 1.83 by root, Sun Jan 2 05:02:28 2011 UTC