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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC vs.
Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC

…		…
43		43
44	use Errno ();	44	use Errno ();
45		45
46	use AnyEvent 5.0 ();	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 = '1.44';	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 $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$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;
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	95	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response body data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if an error occured), and a hash-ref with response headers as	99	(or C<undef> if an error occured), and a hash-ref with response headers
101	second argument.	100	(and trailers) as second argument.
102		101
103	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
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. 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
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	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.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	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,
…		…
136	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
137	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
138		152
139	=item headers => hashref	153	=item headers => hashref
140		154
141	The request headers to use. Currently, C<http_request> may provide its	155	The request headers to use. Currently, C<http_request> may provide its own
142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
143	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
144	suppressed by using C<undef> for these headers in which case they won't be	158	(this can be suppressed by using C<undef> for these headers in which case
145	sent at all).	159	they won't be sent at all).
146		160
147	=item timeout => $seconds	161	=item timeout => $seconds
148		162
149	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
150	the timeout, as will read or write activity, i.e. this is not an overall	164	the timeout, as will read or write activity, i.e. this is not an overall
…		…
160	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
161	HTTPS.	175	HTTPS.
162		176
163	=item body => $string	177	=item body => $string
164		178
165	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be sent as-is (future versions of
166	this module might offer more options).	180	this module might offer more options).
167		181
168	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
169		183
170	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
171	based on the original netscape specification.	185	based on the original netscape specification.
172		186
173	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
174	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie jar to
175	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
176	recommended, as expiry times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
177		191
178	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not meant to be complete. If
179	meant to be complete. If you want complete cookie management you have to	193	you want complete cookie management you have to do that on your
180	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
181	cookie-using sites working. Cookies are a privacy disaster, do not use	195	working. Cookies are a privacy disaster, do not use them unless required
182	them unless required to.	196	to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be set and handled by this module, otherwise they will be
		200	left untouched.
183		201
184	=item tls_ctx => $scheme \| $tls_ctx	202	=item tls_ctx => $scheme \| $tls_ctx
185		203
186	Specifies the AnyEvent::TLS context to be used for https connections. This	204	Specifies the AnyEvent::TLS context to be used for https connections. This
187	parameter follows the same rules as the C<tls_ctx> parameter to	205	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
200	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	218	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
201	and behaves exactly the same way (e.g. it has to provide a	219	and behaves exactly the same way (e.g. it has to provide a
202	timeout). See the description for the C<$prepare_cb> argument of	220	timeout). See the description for the C<$prepare_cb> argument of
203	C<AnyEvent::Socket::tcp_connect> for details.	221	C<AnyEvent::Socket::tcp_connect> for details.
204		222
		223	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		224
		225	In even rarer cases you want total control over how AnyEvent::HTTP
		226	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		227	to do this, but you can provide your own C<tcp_connect> function -
		228	obviously, it has to follow the same calling conventions, except that it
		229	may always return a connection guard object.
		230
		231	There are probably lots of weird uses for this function, starting from
		232	tracing the hosts C<http_request> actually tries to connect, to (inexact
		233	but fast) host => IP address caching or even socks protocol support.
		234
205	=item on_header => $callback->($headers)	235	=item on_header => $callback->($headers)
206		236
207	When specified, this callback will be called with the header hash as soon	237	When specified, this callback will be called with the header hash as soon
208	as headers have been successfully received from the remote server (not on	238	as headers have been successfully received from the remote server (not on
209	locally-generated errors).	239	locally-generated errors).
…		…
214		244
215	This callback is useful, among other things, to quickly reject unwanted	245	This callback is useful, among other things, to quickly reject unwanted
216	content, which, if it is supposed to be rare, can be faster than first	246	content, which, if it is supposed to be rare, can be faster than first
217	doing a C<HEAD> request.	247	doing a C<HEAD> request.
218		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
219	Example: cancel the request unless the content-type is "text/html".	253	Example: cancel the request unless the content-type is "text/html".
220		254
221	on_header => sub {	255	on_header => sub {
222	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
223	},	257	},
…		…
229	string instead of the body data.	263	string instead of the body data.
230		264
231	It has to return either true (in which case AnyEvent::HTTP will continue),	265	It has to return either true (in which case AnyEvent::HTTP will continue),
232	or false, in which case AnyEvent::HTTP will cancel the download (and call	266	or false, in which case AnyEvent::HTTP will cancel the download (and call
233	the completion callback with an error code of C<598>).	267	the completion callback with an error code of C<598>).
		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
234		271
235	This callback is useful when the data is too large to be held in memory	272	This callback is useful when the data is too large to be held in memory
236	(so the callback writes it to a file) or when only some information should	273	(so the callback writes it to a file) or when only some information should
237	be extracted, or when the body should be processed incrementally.	274	be extracted, or when the body should be processed incrementally.
238		275
…		…
264	If you think you need this, first have a look at C<on_body>, to see if	301	If you think you need this, first have a look at C<on_body>, to see if
265	that doesn't solve your problem in a better way.	302	that doesn't solve your problem in a better way.
266		303
267	=back	304	=back
268		305
269	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
270		308
271	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
272	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
273	print "$body\n";	311	print "$body\n";
274	};	312	};
275		313
276	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
277	timeout of 30 seconds.	315	timeout of 30 seconds.
278		316
279	http_request	317	http_request
280	GET => "https://www.google.com",	318	GET => "https://www.google.com",
281	timeout => 30,	319	timeout => 30,
…		…
284	use Data::Dumper;	322	use Data::Dumper;
285	print Dumper $hdr;	323	print Dumper $hdr;
286	}	324	}
287	;	325	;
288		326
289	Example: make another simple HTTP GET request, but immediately try to	327	Example: do another simple HTTP GET request, but immediately try to
290	cancel it.	328	cancel it.
291		329
292	my $request = http_request GET => "http://www.nethype.de/", sub {	330	my $request = http_request GET => "http://www.nethype.de/", sub {
293	my ($body, $hdr) = @_;	331	my ($body, $hdr) = @_;
294	print "$body\n";	332	print "$body\n";
…		…
326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
327		365
328	_slot_schedule $_[0];	366	_slot_schedule $_[0];
329	}	367	}
330		368
331	our $qr_nl = qr{\015?\012};	369	# continue to parse $_ for headers and place them into the arg
		370	sub parse_hdr() {
		371	my %hdr;
		372
		373	# things seen, not parsed:
		374	# p3pP="NON CUR OTPi OUR NOR UNI"
		375
		376	$hdr{lc $1} .= ",$2"
		377	while /\G
		378	([^:\000-\037]*):
		379	[\011\040]*
		380	((?: [^\012]+ \| \012[\011\040] )*)
		381	\012
		382	/gxc;
		383
		384	/\G$/
		385	or return;
		386
		387	# remove the "," prefix we added to all headers above
		388	substr $_, 0, 1, ""
		389	for values %hdr;
		390
		391	\%hdr
		392	}
		393
332	our $qr_nlnl = qr{(?<![^\012])\015?\012};	394	our $qr_nlnl = qr{(?<![^\012])\015?\012};
333		395
334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	396	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	397	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
336		398
…		…
349	while (my ($k, $v) = each %$hdr) {	411	while (my ($k, $v) = each %$hdr) {
350	$hdr{lc $k} = $v;	412	$hdr{lc $k} = $v;
351	}	413	}
352	}	414	}
353		415
		416	# pseudo headers for all subsequent responses
		417	my @pseudo = (URL => $url);
		418	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		419
354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	420	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
355		421
356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	422	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
357	if $recurse < 0;	423	if $recurse < 0;
358		424
359	my $proxy = $arg{proxy} \|\| $PROXY;	425	my $proxy = $arg{proxy} \|\| $PROXY;
360	my $timeout = $arg{timeout} \|\| $TIMEOUT;	426	my $timeout = $arg{timeout} \|\| $TIMEOUT;
361		427
362	my ($uscheme, $uauthority, $upath, $query, $fragment) =	428	my ($uscheme, $uauthority, $upath, $query, $fragment) =
363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	429	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
364		430
365	$uscheme = lc $uscheme;	431	$uscheme = lc $uscheme;
366		432
367	my $uport = $uscheme eq "http" ? 80	433	my $uport = $uscheme eq "http" ? 80
368	: $uscheme eq "https" ? 443	434	: $uscheme eq "https" ? 443
369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	435	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
370		436
371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	437	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	438	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
373		439
374	my $uhost = $1;	440	my $uhost = $1;
375	$uport = $2 if defined $2;	441	$uport = $2 if defined $2;
376		442
377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	443	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
378	unless exists $hdr{host};	444	unless exists $hdr{host};
379		445
380	$uhost =~ s/^\[(.*)\]$/$1/;	446	$uhost =~ s/^\[(.*)\]$/$1/;
381	$upath .= "?$query" if length $query;	447	$upath .= $query if length $query;
382		448
383	$upath =~ s%^/?%/%;	449	$upath =~ s%^/?%/%;
384		450
385	# cookie processing	451	# cookie processing
386	if (my $jar = $arg{cookie_jar}) {	452	if (my $jar = $arg{cookie_jar}) {
387	%$jar = () if $jar->{version} != 1;	453	%$jar = () if $jar->{version} != 1;
388		454
389	my @cookie;	455	my @cookie;
390		456
391	while (my ($chost, $v) = each %$jar) {	457	while (my ($chost, $paths) = each %$jar) {
392	if ($chost =~ /^\./) {	458	if ($chost =~ /^\./) {
393	next unless $chost eq substr $uhost, -length $chost;	459	next unless $chost eq substr $uhost, -length $chost;
394	} elsif ($chost =~ /\./) {	460	} elsif ($chost =~ /\./) {
395	next unless $chost eq $uhost;	461	next unless $chost eq $uhost;
396	} else {	462	} else {
397	next;	463	next;
398	}	464	}
399		465
400	while (my ($cpath, $v) = each %$v) {	466	while (my ($cpath, $cookies) = each %$paths) {
401	next unless $cpath eq substr $upath, 0, length $cpath;	467	next unless $cpath eq substr $upath, 0, length $cpath;
402		468
403	while (my ($k, $v) = each %$v) {	469	while (my ($cookie, $kv) = each %$cookies) {
404	next if $uscheme ne "https" && exists $v->{secure};	470	next if $uscheme ne "https" && exists $kv->{secure};
		471
		472	if (exists $kv->{expires}) {
		473	if (AE::now > parse_date ($kv->{expires})) {
		474	delete $cookies->{$cookie};
		475	next;
		476	}
		477	}
		478
405	my $value = $v->{value};	479	my $value = $kv->{value};
406	$value =~ s/([\\"])/\\$1/g;	480	$value =~ s/([\\"])/\\$1/g;
407	push @cookie, "$k=\"$value\"";	481	push @cookie, "$cookie=\"$value\"";
408	}	482	}
409	}	483	}
410	}	484	}
411		485
412	$hdr{cookie} = join "; ", @cookie	486	$hdr{cookie} = join "; ", @cookie
…		…
426	} else {	500	} else {
427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	501	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
428	}	502	}
429		503
430	# leave out fragment and query string, just a heuristic	504	# leave out fragment and query string, just a heuristic
431	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	505	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
432	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};	506	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
433		507
434	$hdr{"content-length"} = length $arg{body}	508	$hdr{"content-length"} = length $arg{body}
435	if length $arg{body} \|\| $method ne "GET";	509	if length $arg{body} \|\| $method ne "GET";
436		510
		511	$hdr{connection} = "close TE"; #1.1
		512	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		513
437	my %state = (connect_guard => 1);	514	my %state = (connect_guard => 1);
438		515
439	_get_slot $uhost, sub {	516	_get_slot $uhost, sub {
440	$state{slot_guard} = shift;	517	$state{slot_guard} = shift;
441		518
442	return unless $state{connect_guard};	519	return unless $state{connect_guard};
443		520
444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	521	my $connect_cb = sub {
445	$state{fh} = shift	522	$state{fh} = shift
446	or do {	523	or do {
447	my $err = "$!";	524	my $err = "$!";
448	%state = ();	525	%state = ();
449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });	526	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
450	};	527	};
451		528
452	pop; # free memory, save a tree	529	pop; # free memory, save a tree
453		530
454	return unless delete $state{connect_guard};	531	return unless delete $state{connect_guard};
455		532
456	# get handle	533	# get handle
457	$state{handle} = new AnyEvent::Handle	534	$state{handle} = new AnyEvent::Handle
458	fh => $state{fh},	535	fh => $state{fh},
		536	peername => $rhost,
		537	tls_ctx => $arg{tls_ctx},
		538	# these need to be reconfigured on keepalive handles
459	timeout => $timeout,	539	timeout => $timeout,
460	peername => $rhost,	540	on_error => sub {
461	tls_ctx => $arg{tls_ctx};	541	%state = ();
		542	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		543	},
		544	on_eof => sub {
		545	%state = ();
		546	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		547	},
		548	;
462		549
463	# limit the number of persistent connections	550	# limit the number of persistent connections
464	# keepalive not yet supported	551	# keepalive not yet supported
465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	552	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
466	++$KA_COUNT{$_[1]};	553	# ++$KA_COUNT{$_[1]};
467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	554	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
468	--$KA_COUNT{$_[1]}	555	# --$KA_COUNT{$_[1]}
469	};	556	# };
470	$hdr{connection} = "keep-alive";	557	# $hdr{connection} = "keep-alive";
471	} else {
472	delete $hdr{connection};
473	}	558	# }
474
475	# (re-)configure handle
476	$state{handle}->on_error (sub {
477	%state = ();
478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
479	});
480	$state{handle}->on_eof (sub {
481	%state = ();
482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
483	});
484		559
485	$state{handle}->starttls ("connect") if $rscheme eq "https";	560	$state{handle}->starttls ("connect") if $rscheme eq "https";
486		561
487	# handle actual, non-tunneled, request	562	# handle actual, non-tunneled, request
488	my $handle_actual_request = sub {	563	my $handle_actual_request = sub {
489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	564	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
490		565
491	# send request	566	# send request
492	$state{handle}->push_write (	567	$state{handle}->push_write (
493	"$method $rpath HTTP/1.0\015\012"	568	"$method $rpath HTTP/1.1\015\012"
494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	569	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
495	. "\015\012"	570	. "\015\012"
496	. (delete $arg{body})	571	. (delete $arg{body})
497	);	572	);
498		573
		574	# return if error occured during push_write()
		575	return unless %state;
		576
499	%hdr = (); # reduce memory usage, save a kitten	577	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
500		578
501	# status line	579	# status line and headers
502	$state{handle}->push_read (line => $qr_nl, sub {	580	$state{read_response} = sub {
503	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
504	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
505
506	my %hdr = ( # response headers
507	HTTPVersion => ",$1",
508	Status => ",$2",
509	Reason => ",$3",
510	URL => ",$url"
511	);
512
513	# headers, could be optimized a bit
514	$state{handle}->unshift_read (line => $qr_nlnl, sub {
515	for ("$_[1]") {	581	for ("$_[1]") {
516	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	582	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
517		583
518	# things seen, not parsed:	584	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
519	# p3pP="NON CUR OTPi OUR NOR UNI"	585	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
520		586
521	$hdr{lc $1} .= ",$2"	587	# 100 Continue handling
522	while /\G	588	# should not happen as we don't send expect: 100-continue,
523	([^:\000-\037]*):	589	# but we handle it just in case.
524	[\011\040]*	590	# since we send the request body regardless, if we get an error
525	((?: [^\012]+ \| \012[\011\040] )*)	591	# we are out of-sync, which we currently do NOT handle correctly.
526	\012	592	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
527	/gxc;	593	if $2 eq 100;
528		594
		595	push @pseudo,
		596	HTTPVersion => $1,
		597	Status => $2,
		598	Reason => $3,
529	/\G$/	599	;
		600
		601	my $hdr = parse_hdr
530	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));	602	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		603
		604	%hdr = (%$hdr, @pseudo);
		605	}
		606
		607	# redirect handling
		608	# microsoft and other shitheads don't give a shit for following standards,
		609	# try to support some common forms of broken Location headers.
		610	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		611	$hdr{location} =~ s/^\.\/+//;
		612
		613	my $url = "$rscheme://$uhost:$uport";
		614
		615	unless ($hdr{location} =~ s/^\///) {
		616	$url .= $upath;
		617	$url =~ s/\/[^\/]*$//;
531	}	618	}
532		619
533	substr $_, 0, 1, ""
534	for values %hdr;
535
536	# redirect handling
537	# microsoft and other shitheads don't give a shit for following standards,
538	# try to support some common forms of broken Location headers.
539	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
540	$hdr{location} =~ s/^\.\/+//;
541
542	my $url = "$rscheme://$uhost:$uport";
543
544	unless ($hdr{location} =~ s/^\///) {
545	$url .= $upath;
546	$url =~ s/\/[^\/]*$//;
547	}
548
549	$hdr{location} = "$url/$hdr{location}";	620	$hdr{location} = "$url/$hdr{location}";
		621	}
		622
		623	my $redirect;
		624
		625	if ($recurse) {
		626	my $status = $hdr{Status};
		627
		628	# industry standard is to redirect POST as GET for
		629	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		630	# also, the UA should ask the user for 301 and 307 and POST,
		631	# industry standard seems to be to simply follow.
		632	# we go with the industry standard.
		633	if ($status == 301 or $status == 302 or $status == 303) {
		634	# HTTP/1.1 is unclear on how to mutate the method
		635	$method = "GET" unless $method eq "HEAD";
		636	$redirect = 1;
		637	} elsif ($status == 307) {
		638	$redirect = 1;
550	}	639	}
		640	}
551		641
		642	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
552	my $redirect;	643	my $keepalive = pop;
553		644
		645	$state{handle}->destroy if $state{handle};
		646	%state = ();
		647
		648	if (defined $_[1]) {
		649	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		650	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		651	}
		652
		653	# set-cookie processing
554	if ($recurse) {	654	if ($arg{cookie_jar}) {
555	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	655	for ($hdr{"set-cookie"}) {
556	# apparently, mozilla et al. just change POST to GET here	656	# parse NAME=VALUE
557	# more research is needed before we do the same	657	my @kv;
		658
		659	while (
		660	m{
		661	\G\s*
		662	(?:
		663	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		664	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		665	)
		666	}gcxsi
		667	) {
		668	my $name = $2;
		669	my $value = $4;
		670
		671	unless (defined $name) {
		672	# expires
		673	$name = "expires";
		674	$value = $1;
		675	} elsif (!defined $value) {
		676	# quoted
		677	$value = $3;
		678	$value =~ s/\\(.)/$1/gs;
		679	}
		680
		681	push @kv, lc $name, $value;
		682
		683	last unless /\G\s*;/gc;
		684	}
		685
		686	last unless @kv;
		687
		688	my $name = shift @kv;
		689	my %kv = (value => shift @kv, @kv);
		690
		691	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		692	if exists $kv{"max-age"};
		693
		694	my $cdom;
		695	my $cpath = (delete $kv{path}) \|\| "/";
		696
		697	if (exists $kv{domain}) {
		698	$cdom = delete $kv{domain};
		699
		700	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		701
		702	next if $cdom =~ /\.$/;
		703
		704	# this is not rfc-like and not netscape-like. go figure.
		705	my $ndots = $cdom =~ y/.//;
		706	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		707	} else {
		708	$cdom = $uhost;
		709	}
		710
558	$redirect = 1;	711	# store it
559	} elsif ($hdr{Status} == 303) {	712	$arg{cookie_jar}{version} = 1;
560	# even http/1.1 is unclear on how to mutate the method	713	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
561	$method = "GET" unless $method eq "HEAD";	714
562	$redirect = 1;	715	redo if /\G\s*,/gc;
563	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
564	$redirect = 1;
565	}	716	}
566	}	717	}
567		718
568	my $finish = sub {
569	$state{handle}->destroy if $state{handle};
570	%state = ();
571
572	# set-cookie processing
573	if ($arg{cookie_jar}) {
574	for ($_[1]{"set-cookie"}) {
575	# parse NAME=VALUE
576	my @kv;
577
578	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
579	my $name = $1;
580	my $value = $3;
581
582	unless ($value) {
583	$value = $2;
584	$value =~ s/\\(.)/$1/gs;
585	}
586
587	push @kv, $name => $value;
588
589	last unless /\G\s*;/gc;
590	}
591
592	last unless @kv;
593
594	my $name = shift @kv;
595	my %kv = (value => shift @kv, @kv);
596
597	my $cdom;
598	my $cpath = (delete $kv{path}) \|\| "/";
599
600	if (exists $kv{domain}) {
601	$cdom = delete $kv{domain};
602
603	$cdom =~ s/^\.?/./; # make sure it starts with a "."
604
605	next if $cdom =~ /\.$/;
606
607	# this is not rfc-like and not netscape-like. go figure.
608	my $ndots = $cdom =~ y/.//;
609	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
610	} else {
611	$cdom = $uhost;
612	}
613
614	# store it
615	$arg{cookie_jar}{version} = 1;
616	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
617
618	redo if /\G\s*,/gc;
619	}
620	}
621
622	if ($redirect && exists $hdr{location}) {	719	if ($redirect && exists $hdr{location}) {
623	# we ignore any errors, as it is very common to receive	720	# we ignore any errors, as it is very common to receive
624	# Content-Length != 0 but no actual body	721	# Content-Length != 0 but no actual body
625	# we also access %hdr, as $_[1] might be an erro	722	# we also access %hdr, as $_[1] might be an erro
626	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);	723	http_request (
627	} else {	724	$method => $hdr{location},
628	$cb->($_[0], $_[1]);
629	}	725	%arg,
		726	recurse => $recurse - 1,
		727	Redirect => [$_[0], \%hdr],
630	};	728	$cb);
631
632	my $len = $hdr{"content-length"};
633
634	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
635	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
636	} elsif (
637	$hdr{Status} =~ /^(?:1..\|[23]04)$/
638	or $method eq "HEAD"
639	or (defined $len && !$len)
640	) {
641	# no body
642	$finish->("", \%hdr);
643	} else {	729	} else {
		730	$cb->($_[0], \%hdr);
		731	}
		732	};
		733
		734	my $len = $hdr{"content-length"};
		735
		736	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		737	$finish->(undef, 598 => "Request cancelled by on_header");
		738	} elsif (
		739	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		740	or $method eq "HEAD"
		741	or (defined $len && !$len)
		742	) {
		743	# no body
		744	$finish->("", undef, undef, 1);
		745	} else {
644	# body handling, four different code paths	746	# body handling, many different code paths
645	# for want_body_handle, on_body (2x), normal (2x)	747	# - no body expected
646	# we might read too much here, but it does not matter yet (no pers. connections)	748	# - want_body_handle
		749	# - te chunked
		750	# - 2x length known (with or without on_body)
		751	# - 2x length not known (with or without on_body)
647	if (!$redirect && $arg{want_body_handle}) {	752	if (!$redirect && $arg{want_body_handle}) {
648	$_[0]->on_eof (undef);	753	$_[0]->on_eof (undef);
649	$_[0]->on_error (undef);	754	$_[0]->on_error (undef);
650	$_[0]->on_read (undef);	755	$_[0]->on_read (undef);
651		756
652	$finish->(delete $state{handle}, \%hdr);	757	$finish->(delete $state{handle});
653		758
654	} elsif ($arg{on_body}) {	759	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		760	my $cl = 0;
		761	my $body = undef;
		762	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		763
655	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });	764	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		765
		766	my $read_chunk; $read_chunk = sub {
		767	$_[1] =~ /^([0-9a-fA-F]+)/
		768	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		769
		770	my $len = hex $1;
		771
656	if ($len) {	772	if ($len) {
657	$_[0]->on_eof (undef);	773	$cl += $len;
		774
		775	$_[0]->push_read (chunk => $len, sub {
		776	$on_body->($_[1], \%hdr)
		777	or return $finish->(undef, 598 => "Request cancelled by on_body");
		778
658	$_[0]->on_read (sub {	779	$_[0]->push_read (line => sub {
659	$len -= length $_[0]{rbuf};	780	length $_[1]
660		781	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
661	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	782	$_[0]->push_read (line => $read_chunk);
662	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
663
664	$len > 0	783	});
665	or $finish->("", \%hdr);
666	});	784	});
667	} else {	785	} else {
668	$_[0]->on_eof (sub {	786	$hdr{"content-length"} \|\|= $cl;
669	$finish->("", \%hdr);	787
		788	$_[0]->push_read (line => $qr_nlnl, sub {
		789	if (length $_[1]) {
		790	for ("$_[1]") {
		791	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		792
		793	my $hdr = parse_hdr
		794	or return $finish->(undef, 599 => "Garbled response trailers");
		795
		796	%hdr = (%hdr, %$hdr);
		797	}
670	});	798	}
671	$_[0]->on_read (sub {	799
672	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	800	$finish->($body, undef, undef, 1);
673	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
674	});	801	});
675	}	802	}
		803	};
		804
		805	$_[0]->push_read (line => $read_chunk);
		806
		807	} elsif ($arg{on_body}) {
		808	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		809
		810	if ($len) {
		811	$_[0]->on_read (sub {
		812	$len -= length $_[0]{rbuf};
		813
		814	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		815	or return $finish->(undef, 598 => "Request cancelled by on_body");
		816
		817	$len > 0
		818	or $finish->("", undef, undef, 1);
		819	});
676	} else {	820	} else {
677	$_[0]->on_eof (undef);	821	$_[0]->on_eof (sub {
678		822	$finish->("");
679	if ($len) {	823	});
680	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
681	$_[0]->on_read (sub {	824	$_[0]->on_read (sub {
		825	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		826	or $finish->(undef, 598 => "Request cancelled by on_body");
		827	});
		828	}
		829	} else {
		830	$_[0]->on_eof (undef);
		831
		832	if ($len) {
		833	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		834	$_[0]->on_read (sub {
682	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	835	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
683	if $len <= length $_[0]{rbuf};	836	if $len <= length $_[0]{rbuf};
684	});	837	});
685	} else {	838	} else {
686	$_[0]->on_error (sub {	839	$_[0]->on_error (sub {
687	$! == Errno::EPIPE \|\| !$!	840	($! == Errno::EPIPE \|\| !$!)
688	? $finish->(delete $_[0]{rbuf}, \%hdr)	841	? $finish->(delete $_[0]{rbuf})
689	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });	842	: $finish->(undef, 599 => $_[2]);
690	});	843	});
691	$_[0]->on_read (sub { });	844	$_[0]->on_read (sub { });
692	}
693	}	845	}
694	}	846	}
695	});	847	}
696	});	848	};
		849
		850	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
697	};	851	};
698		852
699	# now handle proxy-CONNECT method	853	# now handle proxy-CONNECT method
700	if ($proxy && $uscheme eq "https") {	854	if ($proxy && $uscheme eq "https") {
701	# oh dear, we have to wrap it into a connect request	855	# oh dear, we have to wrap it into a connect request
702		856
703	# maybe re-use $uauthority with patched port?	857	# maybe re-use $uauthority with patched port?
704	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	858	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
705	$state{handle}->push_read (line => $qr_nlnl, sub {	859	$state{handle}->push_read (line => $qr_nlnl, sub {
706	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	860	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
707	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	861	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
708		862
709	if ($2 == 200) {	863	if ($2 == 200) {
710	$rpath = $upath;	864	$rpath = $upath;
711	&$handle_actual_request;	865	&$handle_actual_request;
712	} else {	866	} else {
713	%state = ();	867	%state = ();
714	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	868	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
715	}	869	}
716	});	870	});
717	} else {	871	} else {
718	&$handle_actual_request;	872	&$handle_actual_request;
719	}	873	}
		874	};
720		875
721	}, $arg{on_prepare} \|\| sub { $timeout };	876	my $tcp_connect = $arg{tcp_connect}
		877	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		878
		879	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		880
722	};	881	};
723		882
724	defined wantarray && AnyEvent::Util::guard { %state = () }	883	defined wantarray && AnyEvent::Util::guard { %state = () }
725	}	884	}
726		885
…		…
740	&http_request	899	&http_request
741	}	900	}
742		901
743	=back	902	=back
744		903
		904	=head2 DNS CACHING
		905
		906	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		907	the actual connection, which in turn uses AnyEvent::DNS to resolve
		908	hostnames. The latter is a simple stub resolver and does no caching
		909	on its own. If you want DNS caching, you currently have to provide
		910	your own default resolver (by storing a suitable resolver object in
		911	C<$AnyEvent::DNS::RESOLVER>).
		912
745	=head2 GLOBAL FUNCTIONS AND VARIABLES	913	=head2 GLOBAL FUNCTIONS AND VARIABLES
746		914
747	=over 4	915	=over 4
748		916
749	=item AnyEvent::HTTP::set_proxy "proxy-url"	917	=item AnyEvent::HTTP::set_proxy "proxy-url"
…		…
752	string of the form C<http://host:port> (optionally C<https:...>), croaks	920	string of the form C<http://host:port> (optionally C<https:...>), croaks
753	otherwise.	921	otherwise.
754		922
755	To clear an already-set proxy, use C<undef>.	923	To clear an already-set proxy, use C<undef>.
756		924
		925	=item $date = AnyEvent::HTTP::format_date $timestamp
		926
		927	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		928	Date (RFC 2616).
		929
		930	=item $timestamp = AnyEvent::HTTP::parse_date $date
		931
		932	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		933	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		934	be parsed.
		935
757	=item $AnyEvent::HTTP::MAX_RECURSE	936	=item $AnyEvent::HTTP::MAX_RECURSE
758		937
759	The default value for the C<recurse> request parameter (default: C<10>).	938	The default value for the C<recurse> request parameter (default: C<10>).
760		939
761	=item $AnyEvent::HTTP::USERAGENT	940	=item $AnyEvent::HTTP::USERAGENT
…		…
779	connections. This number of can be useful for load-leveling.	958	connections. This number of can be useful for load-leveling.
780		959
781	=back	960	=back
782		961
783	=cut	962	=cut
		963
		964	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		965	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		966
		967	sub format_date($) {
		968	my ($time) = @_;
		969
		970	# RFC 822/1123 format
		971	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		972
		973	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		974	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		975	$H, $M, $S;
		976	}
		977
		978	sub parse_date($) {
		979	my ($date) = @_;
		980
		981	my ($d, $m, $y, $H, $M, $S);
		982
		983	if ($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$/) {
		984	# RFC 822/1123, required by RFC 2616 (with " ")
		985	# cookie dates (with "-")
		986
		987	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		988
		989	} elsif ($date =~ /^[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$/) {
		990	# RFC 850
		991	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		992
		993	} elsif ($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])$/) {
		994	# ISO C's asctime
		995	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		996	}
		997	# other formats fail in the loop below
		998
		999	for (0..11) {
		1000	if ($m eq $month[$_]) {
		1001	require Time::Local;
		1002	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1003	}
		1004	}
		1005
		1006	undef
		1007	}
784		1008
785	sub set_proxy($) {	1009	sub set_proxy($) {
786	if (length $_[0]) {	1010	if (length $_[0]) {
787	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	1011	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
788	or Carp::croak "$_[0]: invalid proxy URL";	1012	or Carp::croak "$_[0]: invalid proxy URL";
…		…
795	# initialise proxy from environment	1019	# initialise proxy from environment
796	eval {	1020	eval {
797	set_proxy $ENV{http_proxy};	1021	set_proxy $ENV{http_proxy};
798	};	1022	};
799		1023
		1024	=head2 SOCKS PROXIES
		1025
		1026	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1027	compile your perl to support socks, or use an external program such as
		1028	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1029	transparently.
		1030
		1031	Alternatively, for AnyEvent::HTTP only, you can use your own
		1032	C<tcp_connect> function that does the proxy handshake - here is an example
		1033	that works with socks4a proxies:
		1034
		1035	use Errno;
		1036	use AnyEvent::Util;
		1037	use AnyEvent::Socket;
		1038	use AnyEvent::Handle;
		1039
		1040	# host, port and username of/for your socks4a proxy
		1041	my $socks_host = "10.0.0.23";
		1042	my $socks_port = 9050;
		1043	my $socks_user = "";
		1044
		1045	sub socks4a_connect {
		1046	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1047
		1048	my $hdl = new AnyEvent::Handle
		1049	connect => [$socks_host, $socks_port],
		1050	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1051	on_error => sub { $connect_cb->() },
		1052	;
		1053
		1054	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1055
		1056	$hdl->push_read (chunk => 8, sub {
		1057	my ($hdl, $chunk) = @_;
		1058	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1059
		1060	if ($status == 0x5a) {
		1061	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1062	} else {
		1063	$! = Errno::ENXIO; $connect_cb->();
		1064	}
		1065	});
		1066
		1067	$hdl
		1068	}
		1069
		1070	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1071	possibly after switching off other proxy types:
		1072
		1073	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1074
		1075	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1076	my ($data, $headers) = @_;
		1077	...
		1078	};
		1079
800	=head1 SEE ALSO	1080	=head1 SEE ALSO
801		1081
802	L<AnyEvent>.	1082	L<AnyEvent>.
803		1083
804	=head1 AUTHOR	1084	=head1 AUTHOR

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC vs. Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.53 by root, Sat Dec 5 15:37:07 2009 UTC vs.
Revision 1.70 by root, Fri Dec 31 20:31:47 2010 UTC