ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/AnyEvent-HTTP/HTTP.pm
(Generate patch)

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.16 by root, Fri Jun 6 12:57:48 2008 UTC vs.
Revision 1.30 by root, Thu Oct 23 02:46:20 2008 UTC

… …
3AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client 3AnyEvent::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
11This module is an L<AnyEvent> user, you need to make sure that you use and 15This module is an L<AnyEvent> user, you need to make sure that you use and
12run a supported event loop. 16run a supported event loop.
… …
44use AnyEvent::Socket (); 48use AnyEvent::Socket ();
45use AnyEvent::Handle (); 49use AnyEvent::Handle ();
46 50
47use base Exporter::; 51use base Exporter::;
48 52
49our $VERSION = '1.01'; 53our $VERSION = '1.05';
50 54
51our @EXPORT = qw(http_get http_request); 55our @EXPORT = qw(http_get http_post http_head http_request);
52 56
53our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; 57our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
54our $MAX_RECURSE = 10; 58our $MAX_RECURSE = 10;
55our $MAX_PERSISTENT = 8; 59our $MAX_PERSISTENT = 8;
56our $PERSISTENT_TIMEOUT = 2; 60our $PERSISTENT_TIMEOUT = 2;
… …
67my %CO_SLOT; # number of open connections, and wait queue, per host 71my %CO_SLOT; # number of open connections, and wait queue, per host
68 72
69=item http_get $url, key => value..., $cb->($data, $headers) 73=item http_get $url, key => value..., $cb->($data, $headers)
70 74
71Executes an HTTP-GET request. See the http_request function for details on 75Executes an HTTP-GET request. See the http_request function for details on
72additional parameters. 76additional parameters and the return value.
73 77
74=item http_head $url, key => value..., $cb->($data, $headers) 78=item http_head $url, key => value..., $cb->($data, $headers)
75 79
76Executes an HTTP-HEAD request. See the http_request function for details on 80Executes an HTTP-HEAD request. See the http_request function for details
77additional parameters. 81on additional parameters and the return value.
78 82
79=item http_post $url, $body, key => value..., $cb->($data, $headers) 83=item http_post $url, $body, key => value..., $cb->($data, $headers)
80 84
81Executes an HTTP-POST request with a request body of C<$bod>. See the 85Executes an HTTP-POST request with a request body of C<$body>. See the
82http_request function for details on additional parameters. 86http_request function for details on additional parameters and the return
87value.
83 88
84=item http_request $method => $url, key => value..., $cb->($data, $headers) 89=item http_request $method => $url, key => value..., $cb->($data, $headers)
85 90
86Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL 91Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
87must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
88 98
89The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
90(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
91response headers as second argument. 101response headers as second argument.
92 102
93All the headers in that hash are lowercased. In addition to the response 103All the headers in that hash are lowercased. In addition to the response
94headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and 104headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
95C<Reason> contain the three parts of the HTTP Status-Line of the same 105contain the three parts of the HTTP Status-Line of the same name. The
106pseudo-header C<URL> contains the original URL (which can differ from the
107requested URL when following redirects).
108
96name. If the server sends a header multiple lines, then their contents 109If the server sends a header multiple lines, then their contents will be
97will be joined together with C<\x00>. 110joined together with C<\x00>.
98 111
99If an internal error occurs, such as not being able to resolve a hostname, 112If an internal error occurs, such as not being able to resolve a hostname,
100then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> 113then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>
101and the C<Reason> pseudo-header will contain an error message. 114and the C<Reason> pseudo-header will contain an error message.
102 115
… …
181 my ($body, $hdr) = @_; 194 my ($body, $hdr) = @_;
182 use Data::Dumper; 195 use Data::Dumper;
183 print Dumper $hdr; 196 print Dumper $hdr;
184 } 197 }
185 ; 198 ;
199
200Example: make another simple HTTP GET request, but immediately try to
201cancel it.
202
203 my $request = http_request GET => "http://www.nethype.de/", sub {
204 my ($body, $hdr) = @_;
205 print "$body\n";
206 };
207
208 undef $request;
186 209
187=cut 210=cut
188 211
189sub _slot_schedule; 212sub _slot_schedule;
190sub _slot_schedule($) { 213sub _slot_schedule($) {
… …
228 while (my ($k, $v) = each %$hdr) { 251 while (my ($k, $v) = each %$hdr) {
229 $hdr{lc $k} = $v; 252 $hdr{lc $k} = $v;
230 } 253 }
231 } 254 }
232 255
233 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 256 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
234 257
235 return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) 258 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
236 if $recurse < 0; 259 if $recurse < 0;
237 260
238 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
239 my $timeout = $arg{timeout} || $TIMEOUT; 262 my $timeout = $arg{timeout} || $TIMEOUT;
240 263
… …
245 268
246 $scheme = lc $scheme; 269 $scheme = lc $scheme;
247 270
248 my $uport = $scheme eq "http" ? 80 271 my $uport = $scheme eq "http" ? 80
249 : $scheme eq "https" ? 443 272 : $scheme eq "https" ? 443
250 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); 273 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });
251 274
252 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic 275 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
253 276
254 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 277 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
255 or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); 278 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
256 279
257 my $uhost = $1; 280 my $uhost = $1;
258 $uport = $2 if defined $2; 281 $uport = $2 if defined $2;
259 282
260 $uhost =~ s/^\[(.*)\]$/$1/; 283 $uhost =~ s/^\[(.*)\]$/$1/;
… …
267 %$jar = () if $jar->{version} < 1; 290 %$jar = () if $jar->{version} < 1;
268 291
269 my @cookie; 292 my @cookie;
270 293
271 while (my ($chost, $v) = each %$jar) { 294 while (my ($chost, $v) = each %$jar) {
295 if ($chost =~ /^\./) {
272 next unless $chost eq substr $uhost, -length $chost; 296 next unless $chost eq substr $uhost, -length $chost;
273 next unless $chost =~ /^\./; 297 } elsif ($chost =~ /\./) {
298 next unless $chost eq $uhost;
299 } else {
300 next;
301 }
274 302
275 while (my ($cpath, $v) = each %$v) { 303 while (my ($cpath, $v) = each %$v) {
276 next unless $cpath eq substr $upath, 0, length $cpath; 304 next unless $cpath eq substr $upath, 0, length $cpath;
277 305
278 while (my ($k, $v) = each %$v) { 306 while (my ($k, $v) = each %$v) {
… …
305 333
306 return unless $state{connect_guard}; 334 return unless $state{connect_guard};
307 335
308 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 336 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
309 $state{fh} = shift 337 $state{fh} = shift
310 or return $cb->(undef, { Status => 599, Reason => "$!" }); 338 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
311 339
312 delete $state{connect_guard}; # reduce memory usage, save a tree 340 delete $state{connect_guard}; # reduce memory usage, save a tree
313 341
314 # get handle 342 # get handle
315 $state{handle} = new AnyEvent::Handle 343 $state{handle} = new AnyEvent::Handle
… …
329 # (re-)configure handle 357 # (re-)configure handle
330 $state{handle}->timeout ($timeout); 358 $state{handle}->timeout ($timeout);
331 $state{handle}->on_error (sub { 359 $state{handle}->on_error (sub {
332 my $errno = "$!"; 360 my $errno = "$!";
333 %state = (); 361 %state = ();
334 $cb->(undef, { Status => 599, Reason => $errno }); 362 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
335 }); 363 });
336 $state{handle}->on_eof (sub { 364 $state{handle}->on_eof (sub {
337 %state = (); 365 %state = ();
338 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 366 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
339 }); 367 });
340 368
341 # send request 369 # send request
342 $state{handle}->push_write ( 370 $state{handle}->push_write (
343 "$method $rpath HTTP/1.0\015\012" 371 "$method $rpath HTTP/1.0\015\012"
… …
348 376
349 %hdr = (); # reduce memory usage, save a kitten 377 %hdr = (); # reduce memory usage, save a kitten
350 378
351 # status line 379 # status line
352 $state{handle}->push_read (line => qr/\015?\012/, sub { 380 $state{handle}->push_read (line => qr/\015?\012/, sub {
353 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix 381 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
354 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); 382 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
355 383
356 my %hdr = ( # response headers 384 my %hdr = ( # response headers
357 HTTPVersion => "\x00$1", 385 HTTPVersion => "\x00$1",
358 Status => "\x00$2", 386 Status => "\x00$2",
359 Reason => "\x00$3", 387 Reason => "\x00$3",
388 URL => "\x00$url"
360 ); 389 );
361 390
362 # headers, could be optimized a bit 391 # headers, could be optimized a bit
363 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 392 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
364 for ("$_[1]\012") { 393 for ("$_[1]\012") {
365 # we support spaces in field names, as lotus domino 394 # we support spaces in field names, as lotus domino
366 # creates them. 395 # creates them (actually spaces around seperators
396 # are strictly allowed in http, they are a security issue).
367 $hdr{lc $1} .= "\x00$2" 397 $hdr{lc $1} .= "\x00$2"
368 while /\G 398 while /\G
369 ([^:\000-\037]+): 399 ([^:\000-\037]+):
370 [\011\040]* 400 [\011\040]*
371 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 401 ((?: [^\015\012]+ | \015?\012[\011\040] )*)
372 \015?\012 402 \015?\012
373 /gxc; 403 /gxc;
374 404
375 /\G$/ 405 /\G$/
376 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); 406 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
377 } 407 }
378 408
379 substr $_, 0, 1, "" 409 substr $_, 0, 1, ""
380 for values %hdr; 410 for values %hdr;
381 411
382 my $finish = sub { 412 my $finish = sub {
413 # TODO: use destroy method, when/if available
414 #$state{handle}->destroy;
415 $state{handle}->on_eof (undef);
416 $state{handle}->on_error (undef);
383 %state = (); 417 %state = ();
384 418
385 # set-cookie processing 419 # set-cookie processing
386 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { 420 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
387 for (split /\x00/, $hdr{"set-cookie"}) { 421 for (split /\x00/, $hdr{"set-cookie"}) {
388 my ($cookie, @arg) = split /;\s*/; 422 my ($cookie, @arg) = split /;\s*/;
389 my ($name, $value) = split /=/, $cookie, 2; 423 my ($name, $value) = split /=/, $cookie, 2;
390 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 424 my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
391 425
392 my $cdom = (delete $kv{domain}) || $uhost; 426 my $cdom;
393 my $cpath = (delete $kv{path}) || "/"; 427 my $cpath = (delete $kv{path}) || "/";
428
429 if (exists $kv{domain}) {
430 $cdom = delete $kv{domain};
394 431
395 $cdom =~ s/^.?/./; # make sure it starts with a "." 432 $cdom =~ s/^\.?/./; # make sure it starts with a "."
396 433
397 next if $cdom =~ /\.$/; 434 next if $cdom =~ /\.$/;
398 435
399 # this is not rfc-like and not netscape-like. go figure. 436 # this is not rfc-like and not netscape-like. go figure.
400 my $ndots = $cdom =~ y/.//; 437 my $ndots = $cdom =~ y/.//;
401 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); 438 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
439 } else {
440 $cdom = $uhost;
441 }
402 442
403 # store it 443 # store it
404 $arg{cookie_jar}{version} = 1; 444 $arg{cookie_jar}{version} = 1;
405 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 445 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
406 } 446 }
407 } 447 }
408 448
409 if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
410 # microsoft and other assholes don't give a shit for following standards, 449 # microsoft and other shitheads don't give a shit for following standards,
411 # try to support a common form of broken Location header. 450 # try to support some common forms of broken Location headers.
451 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
452 $_[1]{location} =~ s/^\.\/+//;
453
412 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; 454 my $url = "$scheme://$uhost:$uport";
413 455
456 unless ($_[1]{location} =~ s/^\///) {
457 $url .= $upath;
458 $url =~ s/\/[^\/]*$//;
459 }
460
461 $_[1]{location} = "$url/$_[1]{location}";
462 }
463
464 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
465 # apparently, mozilla et al. just change POST to GET here
466 # more research is needed before we do the same
414 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); 467 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
468 } elsif ($_[1]{Status} == 303 && $recurse) {
469 # even http/1.1 is unclear on how to mutate the method
470 $method = "GET" unless $method eq "HEAD";
471 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
472 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
473 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
415 } else { 474 } else {
416 $cb->($_[0], $_[1]); 475 $cb->($_[0], $_[1]);
417 } 476 }
418 }; 477 };
419 478
… …
458 unshift @_, "HEAD"; 517 unshift @_, "HEAD";
459 &http_request 518 &http_request
460} 519}
461 520
462sub http_post($$@) { 521sub http_post($$@) {
522 my $url = shift;
463 unshift @_, "POST", "body"; 523 unshift @_, "POST", $url, "body";
464 &http_request 524 &http_request
465} 525}
466 526
467=back 527=back
468 528
… …
517 577
518L<AnyEvent>. 578L<AnyEvent>.
519 579
520=head1 AUTHOR 580=head1 AUTHOR
521 581
522 Marc Lehmann <schmorp@schmorp.de> 582 Marc Lehmann <schmorp@schmorp.de>
523 http://home.schmorp.de/ 583 http://home.schmorp.de/
524 584
525=cut 585=cut
526 586
5271 5871
528 588

Diff Legend

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