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 1.12 by root, Thu Jun 5 16:33:02 2008 UTC vs.
Revision 1.29 by root, Wed Oct 22 23:28:11 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 = '1.0'; 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;
… …
59# changing these is evil 63# changing these is evil
60our $MAX_PERSISTENT_PER_HOST = 2; 64our $MAX_PERSISTENT_PER_HOST = 2;
61our $MAX_PER_HOST = 4; 65our $MAX_PER_HOST = 4;
62 66
63our $PROXY; 67our $PROXY;
68our $ACTIVE = 0;
64 69
65my %KA_COUNT; # number of open keep-alive connections per host 70my %KA_COUNT; # number of open keep-alive connections per host
66my %CO_SLOT; # number of open connections, and wait queue, per host 71my %CO_SLOT; # number of open connections, and wait queue, per host
67 72
68=item http_get $url, key => value..., $cb->($data, $headers) 73=item http_get $url, key => value..., $cb->($data, $headers)
69 74
70Executes 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
71additional parameters. 76additional parameters and the return value.
72 77
73=item http_head $url, key => value..., $cb->($data, $headers) 78=item http_head $url, key => value..., $cb->($data, $headers)
74 79
75Executes an HTTP-HEAD request. See the http_request function for details on 80Executes an HTTP-HEAD request. See the http_request function for details
76additional parameters. 81on additional parameters and the return value.
77 82
78=item http_post $url, $body, key => value..., $cb->($data, $headers) 83=item http_post $url, $body, key => value..., $cb->($data, $headers)
79 84
80Executes an HTTP-POST request with a request body of C<$bod>. See the 85Executes an HTTP-POST request with a request body of C<$body>. See the
81http_request function for details on additional parameters. 86http_request function for details on additional parameters and the return
87value.
82 88
83=item http_request $method => $url, key => value..., $cb->($data, $headers) 89=item http_request $method => $url, key => value..., $cb->($data, $headers)
84 90
85Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL 91Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
86must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
87 98
88The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
89(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
90response headers as second argument. 101response headers as second argument.
91 102
92All the headers in that hash are lowercased. In addition to the response 103All the headers in that hash are lowercased. In addition to the response
93headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and 104headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
94C<Reason> contain the three parts of the HTTP Status-Line of the same 105contain the three parts of the HTTP Status-Line of the same name. The
106pseudo-header C<URL> contains the original URL (which can differ from the
107requested URL when following redirects).
108
95name. If the server sends a header multiple lines, then their contents 109If the server sends a header multiple lines, then their contents will be
96will be joined together with C<\x00>. 110joined together with C<\x00>.
97 111
98If an internal error occurs, such as not being able to resolve a hostname, 112If an internal error occurs, such as not being able to resolve a hostname,
99then C<$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>
100and the C<Reason> pseudo-header will contain an error message. 114and the C<Reason> pseudo-header will contain an error message.
101 115
… …
181 use Data::Dumper; 195 use Data::Dumper;
182 print Dumper $hdr; 196 print Dumper $hdr;
183 } 197 }
184 ; 198 ;
185 199
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 $request;
209
186=cut 210=cut
187 211
188sub _slot_schedule; 212sub _slot_schedule;
189sub _slot_schedule($) { 213sub _slot_schedule($) {
190 my $host = shift; 214 my $host = shift;
191 215
192 while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { 216 while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
193 if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { 217 if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
194 # somebody wants that slot 218 # somebody wants that slot
195 ++$CO_SLOT{$host}[0]; 219 ++$CO_SLOT{$host}[0];
220 ++$ACTIVE;
196 221
197 $cb->(AnyEvent::Util::guard { 222 $cb->(AnyEvent::Util::guard {
223 --$ACTIVE;
198 --$CO_SLOT{$host}[0]; 224 --$CO_SLOT{$host}[0];
199 _slot_schedule $host; 225 _slot_schedule $host;
200 }); 226 });
201 } else { 227 } else {
202 # nobody wants the slot, maybe we can forget about it 228 # nobody wants the slot, maybe we can forget about it
… …
211 push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; 237 push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
212 238
213 _slot_schedule $_[0]; 239 _slot_schedule $_[0];
214} 240}
215 241
216sub http_request($$$;@) { 242sub http_request($$@) {
217 my $cb = pop; 243 my $cb = pop;
218 my ($method, $url, %arg) = @_; 244 my ($method, $url, %arg) = @_;
219 245
220 my %hdr; 246 my %hdr;
221 247
… …
225 while (my ($k, $v) = each %$hdr) { 251 while (my ($k, $v) = each %$hdr) {
226 $hdr{lc $k} = $v; 252 $hdr{lc $k} = $v;
227 } 253 }
228 } 254 }
229 255
230 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 256 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
231 257
232 return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) 258 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
233 if $recurse < 0; 259 if $recurse < 0;
234 260
235 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
236 my $timeout = $arg{timeout} || $TIMEOUT; 262 my $timeout = $arg{timeout} || $TIMEOUT;
237 263
… …
242 268
243 $scheme = lc $scheme; 269 $scheme = lc $scheme;
244 270
245 my $uport = $scheme eq "http" ? 80 271 my $uport = $scheme eq "http" ? 80
246 : $scheme eq "https" ? 443 272 : $scheme eq "https" ? 443
247 : 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 });
274
275 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
248 276
249 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 277 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
250 or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); 278 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
251 279
252 my $uhost = $1; 280 my $uhost = $1;
253 $uport = $2 if defined $2; 281 $uport = $2 if defined $2;
254 282
255 $uhost =~ s/^\[(.*)\]$/$1/; 283 $uhost =~ s/^\[(.*)\]$/$1/;
256 $upath .= "?$query" if length $query; 284 $upath .= "?$query" if length $query;
257 285
258 $upath =~ s%^/?%/%; 286 $upath =~ s%^/?%/%;
259
260 $hdr{referer} ||= "$scheme://$authority$upath";
261 287
262 # cookie processing 288 # cookie processing
263 if (my $jar = $arg{cookie_jar}) { 289 if (my $jar = $arg{cookie_jar}) {
264 %$jar = () if $jar->{version} < 1; 290 %$jar = () if $jar->{version} < 1;
265 291
… …
302 328
303 return unless $state{connect_guard}; 329 return unless $state{connect_guard};
304 330
305 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 331 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
306 $state{fh} = shift 332 $state{fh} = shift
307 or return $cb->(undef, { Status => 599, Reason => "$!" }); 333 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
308 334
309 delete $state{connect_guard}; # reduce memory usage, save a tree 335 delete $state{connect_guard}; # reduce memory usage, save a tree
310 336
311 # get handle 337 # get handle
312 $state{handle} = new AnyEvent::Handle 338 $state{handle} = new AnyEvent::Handle
… …
324 } 350 }
325 351
326 # (re-)configure handle 352 # (re-)configure handle
327 $state{handle}->timeout ($timeout); 353 $state{handle}->timeout ($timeout);
328 $state{handle}->on_error (sub { 354 $state{handle}->on_error (sub {
355 my $errno = "$!";
329 %state = (); 356 %state = ();
330 $cb->(undef, { Status => 599, Reason => "$!" }); 357 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
331 }); 358 });
332 $state{handle}->on_eof (sub { 359 $state{handle}->on_eof (sub {
333 %state = (); 360 %state = ();
334 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 361 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
335 }); 362 });
336 363
337 # send request 364 # send request
338 $state{handle}->push_write ( 365 $state{handle}->push_write (
339 "$method $rpath HTTP/1.0\015\012" 366 "$method $rpath HTTP/1.0\015\012"
… …
344 371
345 %hdr = (); # reduce memory usage, save a kitten 372 %hdr = (); # reduce memory usage, save a kitten
346 373
347 # status line 374 # status line
348 $state{handle}->push_read (line => qr/\015?\012/, sub { 375 $state{handle}->push_read (line => qr/\015?\012/, sub {
349 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix 376 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
350 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); 377 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
351 378
352 my %hdr = ( # response headers 379 my %hdr = ( # response headers
353 HTTPVersion => "\x00$1", 380 HTTPVersion => "\x00$1",
354 Status => "\x00$2", 381 Status => "\x00$2",
355 Reason => "\x00$3", 382 Reason => "\x00$3",
383 URL => "\x00$url"
356 ); 384 );
357 385
358 # headers, could be optimized a bit 386 # headers, could be optimized a bit
359 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 387 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
360 for ("$_[1]\012") { 388 for ("$_[1]\012") {
… …
367 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 395 ((?: [^\015\012]+ | \015?\012[\011\040] )*)
368 \015?\012 396 \015?\012
369 /gxc; 397 /gxc;
370 398
371 /\G$/ 399 /\G$/
372 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); 400 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
373 } 401 }
374 402
375 substr $_, 0, 1, "" 403 substr $_, 0, 1, ""
376 for values %hdr; 404 for values %hdr;
377 405
… …
386 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 414 my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
387 415
388 my $cdom = (delete $kv{domain}) || $uhost; 416 my $cdom = (delete $kv{domain}) || $uhost;
389 my $cpath = (delete $kv{path}) || "/"; 417 my $cpath = (delete $kv{path}) || "/";
390 418
391 $cdom =~ s/^.?/./; # make sure it starts with a "." 419 $cdom =~ s/^\.?/./; # make sure it starts with a "."
392 420
393 next if $cdom =~ /\.$/; 421 next if $cdom =~ /\.$/;
394 422
395 # this is not rfc-like and not netscape-like. go figure. 423 # this is not rfc-like and not netscape-like. go figure.
396 my $ndots = $cdom =~ y/.//; 424 my $ndots = $cdom =~ y/.//;
… …
400 $arg{cookie_jar}{version} = 1; 428 $arg{cookie_jar}{version} = 1;
401 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 429 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
402 } 430 }
403 } 431 }
404 432
405 if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) {
406 # microsoft and other assholes don't give a shit for following standards, 433 # microsoft and other shitheads don't give a shit for following standards,
407 # try to support a common form of broken Location header. 434 # try to support some common forms of broken Location headers.
435 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
436 $_[1]{location} =~ s/^\.\/+//;
437
408 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; 438 my $url = "$scheme://$uhost:$uport";
409 439
440 unless ($_[1]{location} =~ s/^\///) {
441 $url .= $upath;
442 $url =~ s/\/[^\/]*$//;
443 }
444
445 $_[1]{location} = "$url/$_[1]{location}";
446 }
447
448 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
449 # apparently, mozilla et al. just change POST to GET here
450 # more research is needed before we do the same
410 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); 451 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
452 } elsif ($_[1]{Status} == 303 && $recurse) {
453 # even http/1.1 is unlear on how to mutate the method
454 $method = "GET" unless $method eq "HEAD";
455 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
456 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
457 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
411 } else { 458 } else {
412 $cb->($_[0], $_[1]); 459 $cb->($_[0], $_[1]);
413 } 460 }
414 }; 461 };
415 462
… …
443 }; 490 };
444 491
445 defined wantarray && AnyEvent::Util::guard { %state = () } 492 defined wantarray && AnyEvent::Util::guard { %state = () }
446} 493}
447 494
448sub http_get($$;@) { 495sub http_get($@) {
449 unshift @_, "GET"; 496 unshift @_, "GET";
450 &http_request 497 &http_request
451} 498}
452 499
453sub http_head($$;@) { 500sub http_head($@) {
454 unshift @_, "HEAD"; 501 unshift @_, "HEAD";
455 &http_request 502 &http_request
456} 503}
457 504
458sub http_post($$$;@) { 505sub http_post($$@) {
506 my $url = shift;
459 unshift @_, "POST", "body"; 507 unshift @_, "POST", $url, "body";
460 &http_request 508 &http_request
461} 509}
462 510
463=back 511=back
464 512
… …
490 538
491The maximum time to cache a persistent connection, in seconds (default: 2). 539The maximum time to cache a persistent connection, in seconds (default: 2).
492 540
493Not implemented currently. 541Not implemented currently.
494 542
543=item $AnyEvent::HTTP::ACTIVE
544
545The number of active connections. This is not the number of currently
546running requests, but the number of currently open and non-idle TCP
547connections. This number of can be useful for load-leveling.
548
495=back 549=back
496 550
497=cut 551=cut
498 552
499sub set_proxy($) { 553sub set_proxy($) {
… …
507 561
508L<AnyEvent>. 562L<AnyEvent>.
509 563
510=head1 AUTHOR 564=head1 AUTHOR
511 565
512 Marc Lehmann <schmorp@schmorp.de> 566 Marc Lehmann <schmorp@schmorp.de>
513 http://home.schmorp.de/ 567 http://home.schmorp.de/
514 568
515=cut 569=cut
516 570
5171 5711
518 572

Diff Legend

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