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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.3 by root, Wed Jun 4 11:58:36 2008 UTC vs.
Revision 1.91 by root, Mon Jan 3 01:03:29 2011 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
12	run a supported event loop.	16	run a supported event loop.
13		17
		18	This module implements a simple, stateless and non-blocking HTTP
		19	client. It supports GET, POST and other request methods, cookies and more,
		20	all on a very low level. It can follow redirects supports proxies and
		21	automatically limits the number of connections to the values specified in
		22	the RFC.
		23
		24	It should generally be a "good client" that is enough for most HTTP
		25	tasks. Simple tasks should be simple, but complex tasks should still be
		26	possible as the user retains control over request and response headers.
		27
		28	The caller is responsible for authentication management, cookies (if
		29	the simplistic implementation in this module doesn't suffice), referer
		30	and other high-level protocol details for which this module offers only
		31	limited support.
		32
14	=head2 METHODS	33	=head2 METHODS
15		34
16	=over 4	35	=over 4
17		36
18	=cut	37	=cut
19		38
20	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
21		40
22	use strict;	41	use common::sense;
23	no warnings;
24		42
25	use Carp;	43	use Errno ();
26		44
27	use AnyEvent ();	45	use AnyEvent 5.0 ();
28	use AnyEvent::Util ();	46	use AnyEvent::Util ();
29	use AnyEvent::Socket ();
30	use AnyEvent::Handle ();	47	use AnyEvent::Handle ();
31		48
32	use base Exporter::;	49	use base Exporter::;
33		50
34	our $VERSION = '1.0';	51	our $VERSION = '1.5';
35		52
36	our @EXPORT = qw(http_get http_request);	53	our @EXPORT = qw(http_get http_post http_head http_request);
37		54
38	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	55	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
39	our $MAX_RECURSE = 10;	56	our $MAX_RECURSE = 10;
40	our $MAX_PERSISTENT = 8;	57	our $MAX_PERSISTENT = 8;
41	our $PERSISTENT_TIMEOUT = 2;	58	our $PERSISTENT_TIMEOUT = 2;
42	our $TIMEOUT = 300;	59	our $TIMEOUT = 300;
43		60
44	# changing these is evil	61	# changing these is evil
45	our $MAX_PERSISTENT_PER_HOST = 2;	62	our $MAX_PERSISTENT_PER_HOST = 2;
46	our $MAX_PER_HOST = 4; # not respected yet :(	63	our $MAX_PER_HOST = 4;
47		64
48	our $PROXY;	65	our $PROXY;
		66	our $ACTIVE = 0;
49		67
50	my %KA_COUNT; # number of open keep-alive connections per host	68	my %KA_COUNT; # number of open keep-alive connections per host
		69	my %CO_SLOT; # number of open connections, and wait queue, per host
51		70
52	=item http_get $url, key => value..., $cb->($data, $headers)	71	=item http_get $url, key => value..., $cb->($data, $headers)
53		72
54	Executes an HTTP-GET request. See the http_request function for details on	73	Executes an HTTP-GET request. See the http_request function for details on
55	additional parameters.	74	additional parameters and the return value.
56		75
		76	=item http_head $url, key => value..., $cb->($data, $headers)
		77
		78	Executes an HTTP-HEAD request. See the http_request function for details
		79	on additional parameters and the return value.
		80
57	=item http_get $url, $body, key => value..., $cb->($data, $headers)	81	=item http_post $url, $body, key => value..., $cb->($data, $headers)
58		82
59	Executes an HTTP-POST request with a requets body of C<$bod>. See the	83	Executes an HTTP-POST request with a request body of C<$body>. See the
60	http_request function for details on additional parameters.	84	http_request function for details on additional parameters and the return
		85	value.
61		86
62	=item http_request $method => $url, key => value..., $cb->($data, $headers)	87	=item http_request $method => $url, key => value..., $cb->($data, $headers)
63		88
64	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	89	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
65	must be an absolute http or https URL.	90	must be an absolute http or https URL.
66		91
		92	When called in void context, nothing is returned. In other contexts,
		93	C<http_request> returns a "cancellation guard" - you have to keep the
		94	object at least alive until the callback get called. If the object gets
		95	destroyed before the callback is called, the request will be cancelled.
		96
67	The callback will be called with the response data as first argument	97	The callback will be called with the response body data as first argument
68	(or C<undef> if it wasn't available due to errors), and a hash-ref with	98	(or C<undef> if an error occured), and a hash-ref with response headers
69	response headers as second argument.	99	(and trailers) as second argument.
70		100
71	All the headers in that has are lowercased. In addition to the response	101	All the headers in that hash are lowercased. In addition to the response
72	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	102	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
73	C<Reason> contain the three parts of the HTTP Status-Line of the same	103	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
74	name.	104	three parts of the HTTP Status-Line of the same name. If an error occurs
		105	during the body phase of a request, then the original C<Status> and
		106	C<Reason> values from the header are available as C<OrigStatus> and
		107	C<OrigReason>.
		108
		109	The pseudo-header C<URL> contains the actual URL (which can differ from
		110	the requested URL when following redirects - for example, you might get
		111	an error that your URL scheme is not supported even though your URL is a
		112	valid http URL because it redirected to an ftp URL, in which case you can
		113	look at the URL pseudo header).
		114
		115	The pseudo-header C<Redirect> only exists when the request was a result
		116	of an internal redirect. In that case it is an array reference with
		117	the C<($data, $headers)> from the redirect response. Note that this
		118	response could in turn be the result of a redirect itself, and C<<
		119	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		120	response, and so on.
		121
		122	If the server sends a header multiple times, then their contents will be
		123	joined together with a comma (C<,>), as per the HTTP spec.
75		124
76	If an internal error occurs, such as not being able to resolve a hostname,	125	If an internal error occurs, such as not being able to resolve a hostname,
77	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	126	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be
78	and the C<Reason> pseudo-header will contain an error message.	127	C<590>-C<599> and the C<Reason> pseudo-header will contain an error
		128	message. Currently the following status codes are used:
		129
		130	=over 4
		131
		132	=item 595 - errors during connection etsbalishment, proxy handshake.
		133
		134	=item 596 - errors during TLS negotiation, request sending and header processing.
		135
		136	=item 597 - errors during body receiving or processing.
		137
		138	=item 598 - user aborted request via C<on_header> or C<on_body>.
		139
		140	=item 599 - other, usually nonretryable, errors (garbled URL etc.).
		141
		142	=back
		143
		144	A typical callback might look like this:
		145
		146	sub {
		147	my ($body, $hdr) = @_;
		148
		149	if ($hdr->{Status} =~ /^2/) {
		150	... everything should be ok
		151	} else {
		152	print "error, $hdr->{Status} $hdr->{Reason}\n";
		153	}
		154	}
79		155
80	Additional parameters are key-value pairs, and are fully optional. They	156	Additional parameters are key-value pairs, and are fully optional. They
81	include:	157	include:
82		158
83	=over 4	159	=over 4
…		…
87	Whether to recurse requests or not, e.g. on redirects, authentication	163	Whether to recurse requests or not, e.g. on redirects, authentication
88	retries and so on, and how often to do so.	164	retries and so on, and how often to do so.
89		165
90	=item headers => hashref	166	=item headers => hashref
91		167
92	The request headers to use.	168	The request headers to use. Currently, C<http_request> may provide its own
		169	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
		170	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		171	(this can be suppressed by using C<undef> for these headers in which case
		172	they won't be sent at all).
		173
		174	You really should provide your own C<User-Agent:> header value that is
		175	appropriate for your program - I wouldn't be surprised if the default
		176	AnyEvent string gets blocked by webservers sooner or later.
93		177
94	=item timeout => $seconds	178	=item timeout => $seconds
95		179
96	The time-out to use for various stages - each connect attempt will reset	180	The time-out to use for various stages - each connect attempt will reset
97	the timeout, as will read or write activity. Default timeout is 5 minutes.	181	the timeout, as will read or write activity, i.e. this is not an overall
		182	timeout.
		183
		184	Default timeout is 5 minutes.
98		185
99	=item proxy => [$host, $port[, $scheme]] or undef	186	=item proxy => [$host, $port[, $scheme]] or undef
100		187
101	Use the given http proxy for all requests. If not specified, then the	188	Use the given http proxy for all requests. If not specified, then the
102	default proxy (as specified by C<$ENV{http_proxy}>) is used.	189	default proxy (as specified by C<$ENV{http_proxy}>) is used.
103		190
104	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	191	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
105	HTTPS.	192	HTTPS.
106		193
107	=item body => $string	194	=item body => $string
108		195
109	The request body, usually empty. Will be-sent as-is (future versions of	196	The request body, usually empty. Will be sent as-is (future versions of
110	this module might offer more options).	197	this module might offer more options).
111		198
		199	=item cookie_jar => $hash_ref
		200
		201	Passing this parameter enables (simplified) cookie-processing, loosely
		202	based on the original netscape specification.
		203
		204	The C<$hash_ref> must be an (initially empty) hash reference which
		205	will get updated automatically. It is possible to save the cookie jar
		206	to persistent storage with something like JSON or Storable - see the
		207	C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove
		208	expired or session-only cookies, and also for documentation on the format
		209	of the cookie jar.
		210
		211	Note that this cookie implementation is not meant to be complete. If
		212	you want complete cookie management you have to do that on your
		213	own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites
		214	working. Cookies are a privacy disaster, do not use them unless required
		215	to.
		216
		217	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		218	headers will be set and handled by this module, otherwise they will be
		219	left untouched.
		220
		221	=item tls_ctx => $scheme \| $tls_ctx
		222
		223	Specifies the AnyEvent::TLS context to be used for https connections. This
		224	parameter follows the same rules as the C<tls_ctx> parameter to
		225	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		226	C<high> can be specified, which give you a predefined low-security (no
		227	verification, highest compatibility) and high-security (CA and common-name
		228	verification) TLS context.
		229
		230	The default for this option is C<low>, which could be interpreted as "give
		231	me the page, no matter what".
		232
		233	=item on_prepare => $callback->($fh)
		234
		235	In rare cases you need to "tune" the socket before it is used to
		236	connect (for exmaple, to bind it on a given IP address). This parameter
		237	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		238	and behaves exactly the same way (e.g. it has to provide a
		239	timeout). See the description for the C<$prepare_cb> argument of
		240	C<AnyEvent::Socket::tcp_connect> for details.
		241
		242	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		243
		244	In even rarer cases you want total control over how AnyEvent::HTTP
		245	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		246	to do this, but you can provide your own C<tcp_connect> function -
		247	obviously, it has to follow the same calling conventions, except that it
		248	may always return a connection guard object.
		249
		250	There are probably lots of weird uses for this function, starting from
		251	tracing the hosts C<http_request> actually tries to connect, to (inexact
		252	but fast) host => IP address caching or even socks protocol support.
		253
		254	=item on_header => $callback->($headers)
		255
		256	When specified, this callback will be called with the header hash as soon
		257	as headers have been successfully received from the remote server (not on
		258	locally-generated errors).
		259
		260	It has to return either true (in which case AnyEvent::HTTP will continue),
		261	or false, in which case AnyEvent::HTTP will cancel the download (and call
		262	the finish callback with an error code of C<598>).
		263
		264	This callback is useful, among other things, to quickly reject unwanted
		265	content, which, if it is supposed to be rare, can be faster than first
		266	doing a C<HEAD> request.
		267
		268	The downside is that cancelling the request makes it impossible to re-use
		269	the connection. Also, the C<on_header> callback will not receive any
		270	trailer (headers sent after the response body).
		271
		272	Example: cancel the request unless the content-type is "text/html".
		273
		274	on_header => sub {
		275	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		276	},
		277
		278	=item on_body => $callback->($partial_body, $headers)
		279
		280	When specified, all body data will be passed to this callback instead of
		281	to the completion callback. The completion callback will get the empty
		282	string instead of the body data.
		283
		284	It has to return either true (in which case AnyEvent::HTTP will continue),
		285	or false, in which case AnyEvent::HTTP will cancel the download (and call
		286	the completion callback with an error code of C<598>).
		287
		288	The downside to cancelling the request is that it makes it impossible to
		289	re-use the connection.
		290
		291	This callback is useful when the data is too large to be held in memory
		292	(so the callback writes it to a file) or when only some information should
		293	be extracted, or when the body should be processed incrementally.
		294
		295	It is usually preferred over doing your own body handling via
		296	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		297	only used to create a connection, C<want_body_handle> is the better
		298	alternative, as it allows you to install your own event handler, reducing
		299	resource usage.
		300
		301	=item want_body_handle => $enable
		302
		303	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		304	changes considerably: after parsing the headers, and instead of
		305	downloading the body (if any), the completion callback will be
		306	called. Instead of the C<$body> argument containing the body data, the
		307	callback will receive the L<AnyEvent::Handle> object associated with the
		308	connection. In error cases, C<undef> will be passed. When there is no body
		309	(e.g. status C<304>), the empty string will be passed.
		310
		311	The handle object might or might not be in TLS mode, might be connected to
		312	a proxy, be a persistent connection etc., and configured in unspecified
		313	ways. The user is responsible for this handle (it will not be used by this
		314	module anymore).
		315
		316	This is useful with some push-type services, where, after the initial
		317	headers, an interactive protocol is used (typical example would be the
		318	push-style twitter API which starts a JSON/XML stream).
		319
		320	If you think you need this, first have a look at C<on_body>, to see if
		321	that doesn't solve your problem in a better way.
		322
112	=back	323	=back
113		324
114	=back	325	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		326	the response body.
		327
		328	http_request GET => "http://www.nethype.de/", sub {
		329	my ($body, $hdr) = @_;
		330	print "$body\n";
		331	};
		332
		333	Example: do a HTTP HEAD request on https://www.google.com/, use a
		334	timeout of 30 seconds.
		335
		336	http_request
		337	GET => "https://www.google.com",
		338	headers => { "user-agent" => "MySearchClient 1.0" },
		339	timeout => 30,
		340	sub {
		341	my ($body, $hdr) = @_;
		342	use Data::Dumper;
		343	print Dumper $hdr;
		344	}
		345	;
		346
		347	Example: do another simple HTTP GET request, but immediately try to
		348	cancel it.
		349
		350	my $request = http_request GET => "http://www.nethype.de/", sub {
		351	my ($body, $hdr) = @_;
		352	print "$body\n";
		353	};
		354
		355	undef $request;
115		356
116	=cut	357	=cut
117		358
		359	sub _slot_schedule;
		360	sub _slot_schedule($) {
		361	my $host = shift;
		362
		363	while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
		364	if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
		365	# somebody wants that slot
		366	++$CO_SLOT{$host}[0];
		367	++$ACTIVE;
		368
		369	$cb->(AnyEvent::Util::guard {
		370	--$ACTIVE;
		371	--$CO_SLOT{$host}[0];
		372	_slot_schedule $host;
		373	});
		374	} else {
		375	# nobody wants the slot, maybe we can forget about it
		376	delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0];
		377	last;
		378	}
		379	}
		380	}
		381
		382	# wait for a free slot on host, call callback
		383	sub _get_slot($$) {
		384	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
		385
		386	_slot_schedule $_[0];
		387	}
		388
		389	#############################################################################
		390
		391	# expire cookies
		392	sub cookie_jar_expire($;$) {
		393	my ($jar, $session_end) = @_;
		394
		395	%$jar = () if $jar->{version} != 1;
		396
		397	my $anow = AE::now;
		398
		399	while (my ($chost, $paths) = each %$jar) {
		400	next unless ref $paths;
		401
		402	while (my ($cpath, $cookies) = each %$paths) {
		403	while (my ($cookie, $kv) = each %$cookies) {
		404	if (exists $kv->{_expires}) {
		405	delete $cookies->{$cookie}
		406	if $anow > $kv->{_expires};
		407	} elsif ($session_end) {
		408	delete $cookies->{$cookie};
		409	}
		410	}
		411
		412	delete $paths->{$cpath}
		413	unless %$cookies;
		414	}
		415
		416	delete $jar->{$chost}
		417	unless %$paths;
		418	}
		419	}
		420
		421	# extract cookies from jar
		422	sub cookie_jar_extract($$$$) {
		423	my ($jar, $uscheme, $uhost, $upath) = @_;
		424
		425	%$jar = () if $jar->{version} != 1;
		426
		427	my @cookies;
		428
		429	while (my ($chost, $paths) = each %$jar) {
		430	next unless ref $paths;
		431
		432	if ($chost =~ /^\./) {
		433	next unless $chost eq substr $uhost, -length $chost;
		434	} elsif ($chost =~ /\./) {
		435	next unless $chost eq $uhost;
		436	} else {
		437	next;
		438	}
		439
		440	while (my ($cpath, $cookies) = each %$paths) {
		441	next unless $cpath eq substr $upath, 0, length $cpath;
		442
		443	while (my ($cookie, $kv) = each %$cookies) {
		444	next if $uscheme ne "https" && exists $kv->{secure};
		445
		446	if (exists $kv->{_expires} and AE::now > $kv->{_expires}) {
		447	delete $cookies->{$cookie};
		448	next;
		449	}
		450
		451	my $value = $kv->{value};
		452
		453	if ($value =~ /[=;,[:space:]]/) {
		454	$value =~ s/([\\"])/\\$1/g;
		455	$value = "\"$value\"";
		456	}
		457
		458	push @cookies, "$cookie=$value";
		459	}
		460	}
		461	}
		462
		463	\@cookies
		464	}
		465
		466	# parse set_cookie header into jar
		467	sub cookie_jar_set_cookie($$$$) {
		468	my ($jar, $set_cookie, $uhost, $date) = @_;
		469
		470	my $anow = int AE::now;
		471	my $snow; # server-now
		472
		473	for ($set_cookie) {
		474	# parse NAME=VALUE
		475	my @kv;
		476
		477	# expires is not http-compliant in the original cookie-spec,
		478	# we support the official date format and some extensions
		479	while (
		480	m{
		481	\G\s*
		482	(?:
		483	expires \s=\s ([A-Z][a-z][a-z]+,\ [^,;]+)
		484	\| ([^=;,[:space:]]+) (?: \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) ) )?
		485	)
		486	}gcxsi
		487	) {
		488	my $name = $2;
		489	my $value = $4;
		490
		491	if (defined $1) {
		492	# expires
		493	$name = "expires";
		494	$value = $1;
		495	} elsif (defined $3) {
		496	# quoted
		497	$value = $3;
		498	$value =~ s/\\(.)/$1/gs;
		499	}
		500
		501	push @kv, lc $name, $value;
		502
		503	last unless /\G\s*;/gc;
		504	}
		505
		506	last unless @kv;
		507
		508	my $name = shift @kv;
		509	my %kv = (value => shift @kv, @kv);
		510
		511	if (exists $kv{"max-age"}) {
		512	$kv{_expires} = $anow + delete $kv{"max-age"};
		513	} elsif (exists $kv{expires}) {
		514	$snow \|\|= parse_date ($date) \|\| $anow;
		515	$kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow);
		516	} else {
		517	delete $kv{_expires};
		518	}
		519
		520	my $cdom;
		521	my $cpath = (delete $kv{path}) \|\| "/";
		522
		523	if (exists $kv{domain}) {
		524	$cdom = delete $kv{domain};
		525
		526	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		527
		528	next if $cdom =~ /\.$/;
		529
		530	# this is not rfc-like and not netscape-like. go figure.
		531	my $ndots = $cdom =~ y/.//;
		532	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		533	} else {
		534	$cdom = $uhost;
		535	}
		536
		537	# store it
		538	$jar->{version} = 1;
		539	$jar->{lc $cdom}{$cpath}{$name} = \%kv;
		540
		541	redo if /\G\s*,/gc;
		542	}
		543	}
		544
		545	# continue to parse $_ for headers and place them into the arg
		546	sub parse_hdr() {
		547	my %hdr;
		548
		549	# things seen, not parsed:
		550	# p3pP="NON CUR OTPi OUR NOR UNI"
		551
		552	$hdr{lc $1} .= ",$2"
		553	while /\G
		554	([^:\000-\037]*):
		555	[\011\040]*
		556	((?: [^\012]+ \| \012[\011\040] )*)
		557	\012
		558	/gxc;
		559
		560	/\G$/
		561	or return;
		562
		563	# remove the "," prefix we added to all headers above
		564	substr $_, 0, 1, ""
		565	for values %hdr;
		566
		567	\%hdr
		568	}
		569
		570	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		571
		572	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		573	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		574
118	sub http_request($$$;@) {	575	sub http_request($$@) {
119	my $cb = pop;	576	my $cb = pop;
120	my ($method, $url, %arg) = @_;	577	my ($method, $url, %arg) = @_;
121		578
122	my %hdr;	579	my %hdr;
123		580
		581	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		582	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
		583
124	$method = uc $method;	584	$method = uc $method;
125		585
126	if (my $hdr = delete $arg{headers}) {	586	if (my $hdr = $arg{headers}) {
127	while (my ($k, $v) = each %$hdr) {	587	while (my ($k, $v) = each %$hdr) {
128	$hdr{lc $k} = $v;	588	$hdr{lc $k} = $v;
129	}	589	}
130	}	590	}
131		591
		592	# pseudo headers for all subsequent responses
		593	my @pseudo = (URL => $url);
		594	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		595
		596	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
		597
		598	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
		599	if $recurse < 0;
		600
132	my $proxy = $arg{proxy} \|\| $PROXY;	601	my $proxy = $arg{proxy} \|\| $PROXY;
133	my $timeout = $arg{timeout} \|\| $TIMEOUT;	602	my $timeout = $arg{timeout} \|\| $TIMEOUT;
134	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;
135		603
136	$hdr{"user-agent"} \|\|= $USERAGENT;	604	my ($uscheme, $uauthority, $upath, $query, $fragment) =
		605	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
137		606
138	my ($host, $port, $path, $scheme);	607	$uscheme = lc $uscheme;
		608
		609	my $uport = $uscheme eq "http" ? 80
		610	: $uscheme eq "https" ? 443
		611	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
		612
		613	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
		614	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
		615
		616	my $uhost = lc $1;
		617	$uport = $2 if defined $2;
		618
		619	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		620	unless exists $hdr{host};
		621
		622	$uhost =~ s/^\[(.*)\]$/$1/;
		623	$upath .= $query if length $query;
		624
		625	$upath =~ s%^/?%/%;
		626
		627	# cookie processing
		628	if (my $jar = $arg{cookie_jar}) {
		629	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
		630
		631	$hdr{cookie} = join "; ", @$cookies
		632	if @$cookies;
		633	}
		634
		635	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
139		636
140	if ($proxy) {	637	if ($proxy) {
141	($host, $port, $scheme) = @$proxy;	638	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
142	$path = $url;	639
		640	$rscheme = "http" unless defined $rscheme;
		641
		642	# don't support https requests over https-proxy transport,
		643	# can't be done with tls as spec'ed, unless you double-encrypt.
		644	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
		645
		646	$rhost = lc $rhost;
		647	$rscheme = lc $rscheme;
143	} else {	648	} else {
144	($scheme, my $authority, $path, my $query, my $fragment) =	649	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
145	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
146
147	$port = $scheme eq "http" ? 80
148	: $scheme eq "https" ? 443
149	: croak "$url: only http and https URLs supported";
150
151	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
152	or croak "$authority: unparsable URL";
153
154	$host = $1;
155	$port = $2 if defined $2;
156
157	$host =~ s/^\[(.*)\]$/$1/;
158	$path .= "?$query" if length $query;
159
160	$path = "/" unless $path;
161
162	$hdr{host} = $host = lc $host;
163	}	650	}
164		651
165	$scheme = lc $scheme;	652	# leave out fragment and query string, just a heuristic
		653	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		654	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
166		655
167	my %state;
168
169	$state{body} = delete $arg{body};
170
171	$hdr{"content-length"} = length $state{body};	656	$hdr{"content-length"} = length $arg{body}
		657	if length $arg{body} \|\| $method ne "GET";
172		658
173	$state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub {	659	my $idempotent = $method =~ /^(?:GET\|HEAD\|PUT\|DELETE\|OPTIONS\|TRACE)$/;
		660
		661	# default value for keepalive is true iff the request is for an idempotent method
		662	my $keepalive = exists $arg{keepalive}
		663	? $arg{keepalive}*1
		664	: $idempotent ? $PERSISTENT_TIMEOUT : 0;
		665
		666	$hdr{connection} = ($keepalive ? "" : "close ") . "Te"; #1.1
		667	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		668
		669	my %state = (connect_guard => 1);
		670
		671	my $ae_error = 595; # connecting
		672
		673	# handle actual, non-tunneled, request
		674	my $handle_actual_request = sub {
		675	$ae_error = 596; # request phase
		676
		677	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		678
		679	# send request
		680	$state{handle}->push_write (
		681	"$method $rpath HTTP/1.1\015\012"
		682	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		683	. "\015\012"
		684	. (delete $arg{body})
		685	);
		686
		687	# return if error occured during push_write()
		688	return unless %state;
		689
		690	# reduce memory usage, save a kitten, also re-use it for the response headers.
		691	%hdr = ();
		692
		693	# status line and headers
		694	$state{read_response} = sub {
		695	for ("$_[1]") {
		696	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		697
		698	/^HTTP\/0([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]) )? \012/gxci
		699	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		700
		701	# 100 Continue handling
		702	# should not happen as we don't send expect: 100-continue,
		703	# but we handle it just in case.
		704	# since we send the request body regardless, if we get an error
		705	# we are out of-sync, which we currently do NOT handle correctly.
		706	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		707	if $2 eq 100;
		708
		709	push @pseudo,
		710	HTTPVersion => $1,
		711	Status => $2,
		712	Reason => $3,
		713	;
		714
		715	my $hdr = parse_hdr
		716	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		717
		718	%hdr = (%$hdr, @pseudo);
		719	}
		720
		721	# redirect handling
		722	# microsoft and other shitheads don't give a shit for following standards,
		723	# try to support some common forms of broken Location headers.
		724	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		725	$hdr{location} =~ s/^\.\/+//;
		726
		727	my $url = "$rscheme://$uhost:$uport";
		728
		729	unless ($hdr{location} =~ s/^\///) {
		730	$url .= $upath;
		731	$url =~ s/\/[^\/]*$//;
		732	}
		733
		734	$hdr{location} = "$url/$hdr{location}";
		735	}
		736
		737	my $redirect;
		738
		739	if ($recurse) {
		740	my $status = $hdr{Status};
		741
		742	# industry standard is to redirect POST as GET for
		743	# 301, 302 and 303, in contrast to HTTP/1.0 and 1.1.
		744	# also, the UA should ask the user for 301 and 307 and POST,
		745	# industry standard seems to be to simply follow.
		746	# we go with the industry standard.
		747	if ($status == 301 or $status == 302 or $status == 303) {
		748	# HTTP/1.1 is unclear on how to mutate the method
		749	$method = "GET" unless $method eq "HEAD";
		750	$redirect = 1;
		751	} elsif ($status == 307) {
		752	$redirect = 1;
		753	}
		754	}
		755
		756	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		757	my $may_keep_alive = $_[3];
		758
		759	$state{handle}->destroy if $state{handle};
		760	%state = ();
		761
		762	if (defined $_[1]) {
		763	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		764	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		765	}
		766
		767	# set-cookie processing
		768	if ($arg{cookie_jar}) {
		769	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date};
		770	}
		771
		772	if ($redirect && exists $hdr{location}) {
		773	# we ignore any errors, as it is very common to receive
		774	# Content-Length != 0 but no actual body
		775	# we also access %hdr, as $_[1] might be an erro
		776	http_request (
		777	$method => $hdr{location},
		778	%arg,
		779	recurse => $recurse - 1,
		780	Redirect => [$_[0], \%hdr],
		781	$cb);
		782	} else {
		783	$cb->($_[0], \%hdr);
		784	}
		785	};
		786
		787	$ae_error = 597; # body phase
		788
		789	my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct...
		790
		791	my $len = $chunked ? undef : $hdr{"content-length"};
		792
		793	# body handling, many different code paths
		794	# - no body expected
		795	# - want_body_handle
		796	# - te chunked
		797	# - 2x length known (with or without on_body)
		798	# - 2x length not known (with or without on_body)
		799	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		800	$finish->(undef, 598 => "Request cancelled by on_header");
		801	} elsif (
		802	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		803	or $method eq "HEAD"
		804	or (defined $len && $len == 0) # == 0, not !, because "0 " is true
		805	) {
		806	# no body
		807	$finish->("", undef, undef, 1);
		808
		809	} elsif (!$redirect && $arg{want_body_handle}) {
		810	$_[0]->on_eof (undef);
		811	$_[0]->on_error (undef);
		812	$_[0]->on_read (undef);
		813
		814	$finish->(delete $state{handle});
		815
		816	} elsif ($chunked) {
		817	my $cl = 0;
		818	my $body = undef;
		819	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		820
		821	$state{read_chunk} = sub {
		822	$_[1] =~ /^([0-9a-fA-F]+)/
		823	or $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		824
		825	my $len = hex $1;
		826
		827	if ($len) {
		828	$cl += $len;
		829
		830	$_[0]->push_read (chunk => $len, sub {
		831	$on_body->($_[1], \%hdr)
		832	or return $finish->(undef, 598 => "Request cancelled by on_body");
		833
		834	$_[0]->push_read (line => sub {
		835	length $_[1]
		836	and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding");
		837	$_[0]->push_read (line => $state{read_chunk});
		838	});
		839	});
		840	} else {
		841	$hdr{"content-length"} \|\|= $cl;
		842
		843	$_[0]->push_read (line => $qr_nlnl, sub {
		844	if (length $_[1]) {
		845	for ("$_[1]") {
		846	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		847
		848	my $hdr = parse_hdr
		849	or return $finish->(undef, $ae_error => "Garbled response trailers");
		850
		851	%hdr = (%hdr, %$hdr);
		852	}
		853	}
		854
		855	$finish->($body, undef, undef, 1);
		856	});
		857	}
		858	};
		859
		860	$_[0]->push_read (line => $state{read_chunk});
		861
		862	} elsif ($arg{on_body}) {
		863	if (defined $len) {
		864	$_[0]->on_read (sub {
		865	$len -= length $_[0]{rbuf};
		866
		867	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		868	or return $finish->(undef, 598 => "Request cancelled by on_body");
		869
		870	$len > 0
		871	or $finish->("", undef, undef, 1);
		872	});
		873	} else {
		874	$_[0]->on_eof (sub {
		875	$finish->("");
		876	});
		877	$_[0]->on_read (sub {
		878	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		879	or $finish->(undef, 598 => "Request cancelled by on_body");
		880	});
		881	}
		882	} else {
		883	$_[0]->on_eof (undef);
		884
		885	if (defined $len) {
		886	$_[0]->on_read (sub {
		887	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		888	if $len <= length $_[0]{rbuf};
		889	});
		890	} else {
		891	$_[0]->on_error (sub {
		892	($! == Errno::EPIPE \|\| !$!)
		893	? $finish->(delete $_[0]{rbuf})
		894	: $finish->(undef, $ae_error => $_[2]);
		895	});
		896	$_[0]->on_read (sub { });
		897	}
		898	}
		899	};
		900
		901	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		902	};
		903
		904	my $connect_cb = sub {
174	$state{fh} = shift	905	$state{fh} = shift
		906	or do {
		907	my $err = "$!";
		908	%state = ();
175	or return $cb->(undef, { Status => 599, Reason => "$!" });	909	return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err });
		910	};
176		911
177	delete $state{connect_guard}; # reduce memory usage, save a tree	912	return unless delete $state{connect_guard};
178		913
179	# get handle	914	# get handle
180	$state{handle} = new AnyEvent::Handle	915	$state{handle} = new AnyEvent::Handle
181	fh => $state{fh},	916	fh => $state{fh},
182	($scheme eq "https" ? (tls => "connect") : ());	917	peername => $rhost,
		918	tls_ctx => $arg{tls_ctx},
		919	# these need to be reconfigured on keepalive handles
		920	timeout => $timeout,
		921	on_error => sub {
		922	%state = ();
		923	$cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] });
		924	},
		925	on_eof => sub {
		926	%state = ();
		927	$cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" });
		928	},
		929	;
183		930
184	# limit the number of persistent connections	931	# limit the number of persistent connections
		932	# keepalive not yet supported
185	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	933	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
186	++$KA_COUNT{$_[1]};	934	# ++$KA_COUNT{$_[1]};
187	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	935	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		936	# --$KA_COUNT{$_[1]}
		937	# };
188	$hdr{connection} = "keep-alive";	938	# $hdr{connection} = "keep-alive";
189	delete $hdr{connection}; # keep-alive not yet supported
190	} else {
191	delete $hdr{connection};
192	}	939	# }
193		940
194	# (re-)configure handle	941	$state{handle}->starttls ("connect") if $rscheme eq "https";
195	$state{handle}->timeout ($timeout);
196	$state{handle}->on_error (sub {
197	%state = ();
198	$cb->(undef, { Status => 599, Reason => "$!" });
199	});
200	$state{handle}->on_eof (sub {
201	%state = ();
202	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });
203	});
204		942
205	# send request	943	# now handle proxy-CONNECT method
206	$state{handle}->push_write (	944	if ($proxy && $uscheme eq "https") {
207	"$method $path HTTP/1.0\015\012"	945	# oh dear, we have to wrap it into a connect request
208	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
209	. "\015\012"
210	. (delete $state{body})
211	);
212		946
213	%hdr = (); # reduce memory usage, save a kitten	947	# maybe re-use $uauthority with patched port?
214		948	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012");
215	# status line
216	$state{handle}->push_read (line => qr/\015?\012/, sub {	949	$state{handle}->push_read (line => $qr_nlnl, sub {
217	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix	950	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
218	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));	951	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
219		952
220	my %hdr = ( # response headers	953	if ($2 == 200) {
221	HTTPVersion => ",$1",	954	$rpath = $upath;
222	Status => ",$2",	955	$handle_actual_request->();
223	Reason => ",$3",
224	);
225
226	# headers, could be optimized a bit
227	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
228	for ("$_[1]\012") {
229	# we support spaces in field names, as lotus domino
230	# creates them.
231	$hdr{lc $1} .= ",$2"
232	while /\G
233	([^:\000-\037]+):
234	[\011\040]*
235	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
236	\015?\012
237	/gxc;
238
239	/\G$/
240	or return $cb->(undef, { Status => 599, Reason => "garbled response headers" });
241	}
242
243	substr $_, 0, 1, ""
244	for values %hdr;
245
246	if ($method ne "HEAD") {
247	if (exists $hdr{"content-length"}) {
248	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
249	# could cache persistent connection now
250	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
251	# but we don't, due to misdesigns, this is annoyingly complex
252	};
253
254	%state = ();
255	$cb->($_[1], \%hdr);
256	});
257	} else {	956	} else {
258	# too bad, need to read until we get an error or EOF,
259	# no way to detect winged data.
260	$_[0]->on_error (sub {
261	%state = ();	957	%state = ();
262	$cb->($_[0]{rbuf}, \%hdr);	958	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
263	});
264	$_[0]->on_eof (undef);
265	$_[0]->on_read (sub { });
266	}
267	}	959	}
268	});	960	});
		961	} else {
		962	$handle_actual_request->();
269	});	963	}
270	}, sub {	964	};
271	$timeout	965
		966	_get_slot $uhost, sub {
		967	$state{slot_guard} = shift;
		968
		969	return unless $state{connect_guard};
		970
		971	my $tcp_connect = $arg{tcp_connect}
		972	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		973
		974	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
272	};	975	};
273		976
274	defined wantarray && AnyEvent::Util::guard { %state = () }	977	defined wantarray && AnyEvent::Util::guard { %state = () }
275	}	978	}
276		979
277	sub http_get($$;@) {	980	sub http_get($@) {
278	unshift @_, "GET";	981	unshift @_, "GET";
279	&http_request	982	&http_request
280	}	983	}
281		984
282	sub http_post($$$;@) {	985	sub http_head($@) {
283	unshift @_, "POST", "body";	986	unshift @_, "HEAD";
284	&http_request	987	&http_request
285	}	988	}
286		989
		990	sub http_post($$@) {
		991	my $url = shift;
		992	unshift @_, "POST", $url, "body";
		993	&http_request
		994	}
		995
		996	=back
		997
		998	=head2 DNS CACHING
		999
		1000	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		1001	the actual connection, which in turn uses AnyEvent::DNS to resolve
		1002	hostnames. The latter is a simple stub resolver and does no caching
		1003	on its own. If you want DNS caching, you currently have to provide
		1004	your own default resolver (by storing a suitable resolver object in
		1005	C<$AnyEvent::DNS::RESOLVER>).
		1006
287	=head2 GLOBAL FUNCTIONS AND VARIABLES	1007	=head2 GLOBAL FUNCTIONS AND VARIABLES
288		1008
289	=over 4	1009	=over 4
290		1010
291	=item AnyEvent::HTTP::set_proxy "proxy-url"	1011	=item AnyEvent::HTTP::set_proxy "proxy-url"
292		1012
293	Sets the default proxy server to use. The proxy-url must begin with a	1013	Sets the default proxy server to use. The proxy-url must begin with a
294	string of the form C<http://host:port> (optionally C<https:...>).	1014	string of the form C<http://host:port> (optionally C<https:...>), croaks
		1015	otherwise.
		1016
		1017	To clear an already-set proxy, use C<undef>.
		1018
		1019	=item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end]
		1020
		1021	Remove all cookies from the cookie jar that have been expired. If
		1022	C<$session_end> is given and true, then additionally remove all session
		1023	cookies.
		1024
		1025	You should call this function (with a true C<$session_end>) before you
		1026	save cookies to disk, and you should call this function after loading them
		1027	again. If you have a long-running program you can additonally call this
		1028	function from time to time.
		1029
		1030	A cookie jar is initially an empty hash-reference that is managed by this
		1031	module. It's format is subject to change, but currently it is like this:
		1032
		1033	The key C<version> has to contain C<1>, otherwise the hash gets
		1034	emptied. All other keys are hostnames or IP addresses pointing to
		1035	hash-references. The key for these inner hash references is the
		1036	server path for which this cookie is meant, and the values are again
		1037	hash-references. The keys of those hash-references is the cookie name, and
		1038	the value, you guessed it, is another hash-reference, this time with the
		1039	key-value pairs from the cookie, except for C<expires> and C<max-age>,
		1040	which have been replaced by a C<_expires> key that contains the cookie
		1041	expiry timestamp.
		1042
		1043	Here is an example of a cookie jar with a single cookie, so you have a
		1044	chance of understanding the above paragraph:
		1045
		1046	{
		1047	version => 1,
		1048	"10.0.0.1" => {
		1049	"/" => {
		1050	"mythweb_id" => {
		1051	_expires => 1293917923,
		1052	value => "ooRung9dThee3ooyXooM1Ohm",
		1053	},
		1054	},
		1055	},
		1056	}
		1057
		1058	=item $date = AnyEvent::HTTP::format_date $timestamp
		1059
		1060	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		1061	Date (RFC 2616).
		1062
		1063	=item $timestamp = AnyEvent::HTTP::parse_date $date
		1064
		1065	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a
		1066	bunch of minor variations of those, and returns the corresponding POSIX
		1067	timestamp, or C<undef> if the date cannot be parsed.
295		1068
296	=item $AnyEvent::HTTP::MAX_RECURSE	1069	=item $AnyEvent::HTTP::MAX_RECURSE
297		1070
298	The default value for the C<recurse> request parameter (default: C<10>).	1071	The default value for the C<recurse> request parameter (default: C<10>).
299		1072
300	=item $AnyEvent::HTTP::USERAGENT	1073	=item $AnyEvent::HTTP::USERAGENT
301		1074
302	The default value for the C<User-Agent> header (the default is	1075	The default value for the C<User-Agent> header (the default is
303	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	1076	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
304		1077
305	=item $AnyEvent::HTTP::MAX_PERSISTENT	1078	=item $AnyEvent::HTTP::MAX_PER_HOST
306		1079
307	The maximum number of persistent connections to keep open (default: 8).	1080	The maximum number of concurrent connections to the same host (identified
		1081	by the hostname). If the limit is exceeded, then the additional requests
		1082	are queued until previous connections are closed.
308		1083
309	Not implemented currently.	1084	The default value for this is C<4>, and it is highly advisable to not
		1085	increase it.
310		1086
311	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT	1087	=item $AnyEvent::HTTP::ACTIVE
312		1088
313	The maximum time to cache a persistent connection, in seconds (default: 2).	1089	The number of active connections. This is not the number of currently
314		1090	running requests, but the number of currently open and non-idle TCP
315	Not implemented currently.	1091	connections. This number of can be useful for load-leveling.
316		1092
317	=back	1093	=back
318		1094
319	=cut	1095	=cut
320		1096
		1097	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		1098	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		1099
		1100	sub format_date($) {
		1101	my ($time) = @_;
		1102
		1103	# RFC 822/1123 format
		1104	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		1105
		1106	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		1107	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		1108	$H, $M, $S;
		1109	}
		1110
		1111	sub parse_date($) {
		1112	my ($date) = @_;
		1113
		1114	my ($d, $m, $y, $H, $M, $S);
		1115
		1116	if ($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$/) {
		1117	# RFC 822/1123, required by RFC 2616 (with " ")
		1118	# cookie dates (with "-")
		1119
		1120	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1121
		1122	} elsif ($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$/) {
		1123	# RFC 850
		1124	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1125
		1126	} elsif ($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])$/) {
		1127	# ISO C's asctime
		1128	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1129	}
		1130	# other formats fail in the loop below
		1131
		1132	for (0..11) {
		1133	if ($m eq $month[$_]) {
		1134	require Time::Local;
		1135	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1136	}
		1137	}
		1138
		1139	undef
		1140	}
		1141
321	sub set_proxy($) {	1142	sub set_proxy($) {
		1143	if (length $_[0]) {
322	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1144	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1145	or Carp::croak "$_[0]: invalid proxy URL";
		1146	$PROXY = [$2, $3 \|\| 3128, $1]
		1147	} else {
		1148	undef $PROXY;
		1149	}
323	}	1150	}
324		1151
325	# initialise proxy from environment	1152	# initialise proxy from environment
		1153	eval {
326	set_proxy $ENV{http_proxy};	1154	set_proxy $ENV{http_proxy};
		1155	};
		1156
		1157	=head2 SOCKS PROXIES
		1158
		1159	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1160	compile your perl to support socks, or use an external program such as
		1161	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1162	transparently.
		1163
		1164	Alternatively, for AnyEvent::HTTP only, you can use your own
		1165	C<tcp_connect> function that does the proxy handshake - here is an example
		1166	that works with socks4a proxies:
		1167
		1168	use Errno;
		1169	use AnyEvent::Util;
		1170	use AnyEvent::Socket;
		1171	use AnyEvent::Handle;
		1172
		1173	# host, port and username of/for your socks4a proxy
		1174	my $socks_host = "10.0.0.23";
		1175	my $socks_port = 9050;
		1176	my $socks_user = "";
		1177
		1178	sub socks4a_connect {
		1179	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1180
		1181	my $hdl = new AnyEvent::Handle
		1182	connect => [$socks_host, $socks_port],
		1183	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1184	on_error => sub { $connect_cb->() },
		1185	;
		1186
		1187	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1188
		1189	$hdl->push_read (chunk => 8, sub {
		1190	my ($hdl, $chunk) = @_;
		1191	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1192
		1193	if ($status == 0x5a) {
		1194	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1195	} else {
		1196	$! = Errno::ENXIO; $connect_cb->();
		1197	}
		1198	});
		1199
		1200	$hdl
		1201	}
		1202
		1203	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1204	possibly after switching off other proxy types:
		1205
		1206	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1207
		1208	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1209	my ($data, $headers) = @_;
		1210	...
		1211	};
327		1212
328	=head1 SEE ALSO	1213	=head1 SEE ALSO
329		1214
330	L<AnyEvent>.	1215	L<AnyEvent>.
331		1216
332	=head1 AUTHOR	1217	=head1 AUTHOR
333		1218
334	Marc Lehmann <schmorp@schmorp.de>	1219	Marc Lehmann <schmorp@schmorp.de>
335	http://home.schmorp.de/	1220	http://home.schmorp.de/
		1221
		1222	With many thanks to Дмитрий Шалашов, who provided countless
		1223	testcases and bugreports.
336		1224
337	=cut	1225	=cut
338		1226
339	1	1227	1
340		1228

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.3 by root, Wed Jun 4 11:58:36 2008 UTC vs. Revision 1.91 by root, Mon Jan 3 01:03:29 2011 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.3 by root, Wed Jun 4 11:58:36 2008 UTC vs.
Revision 1.91 by root, Mon Jan 3 01:03:29 2011 UTC