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 1.14 by root, Thu Jun 5 17:29:01 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;
… …
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($) {
… …
214 push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; 237 push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
215 238
216 _slot_schedule $_[0]; 239 _slot_schedule $_[0];
217} 240}
218 241
219sub http_request($$$;@) { 242sub http_request($$@) {
220 my $cb = pop; 243 my $cb = pop;
221 my ($method, $url, %arg) = @_; 244 my ($method, $url, %arg) = @_;
222 245
223 my %hdr; 246 my %hdr;
224 247
… …
228 while (my ($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/;
… …
305 328
306 return unless $state{connect_guard}; 329 return unless $state{connect_guard};
307 330
308 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 331 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
309 $state{fh} = shift 332 $state{fh} = shift
310 or return $cb->(undef, { Status => 599, Reason => "$!" }); 333 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
311 334
312 delete $state{connect_guard}; # reduce memory usage, save a tree 335 delete $state{connect_guard}; # reduce memory usage, save a tree
313 336
314 # get handle 337 # get handle
315 $state{handle} = new AnyEvent::Handle 338 $state{handle} = new AnyEvent::Handle
… …
329 # (re-)configure handle 352 # (re-)configure handle
330 $state{handle}->timeout ($timeout); 353 $state{handle}->timeout ($timeout);
331 $state{handle}->on_error (sub { 354 $state{handle}->on_error (sub {
332 my $errno = "$!"; 355 my $errno = "$!";
333 %state = (); 356 %state = ();
334 $cb->(undef, { Status => 599, Reason => $errno }); 357 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
335 }); 358 });
336 $state{handle}->on_eof (sub { 359 $state{handle}->on_eof (sub {
337 %state = (); 360 %state = ();
338 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 361 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
339 }); 362 });
340 363
341 # send request 364 # send request
342 $state{handle}->push_write ( 365 $state{handle}->push_write (
343 "$method $rpath HTTP/1.0\015\012" 366 "$method $rpath HTTP/1.0\015\012"
… …
348 371
349 %hdr = (); # reduce memory usage, save a kitten 372 %hdr = (); # reduce memory usage, save a kitten
350 373
351 # status line 374 # status line
352 $state{handle}->push_read (line => qr/\015?\012/, sub { 375 $state{handle}->push_read (line => qr/\015?\012/, sub {
353 $_[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
354 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 }));
355 378
356 my %hdr = ( # response headers 379 my %hdr = ( # response headers
357 HTTPVersion => "\x00$1", 380 HTTPVersion => "\x00$1",
358 Status => "\x00$2", 381 Status => "\x00$2",
359 Reason => "\x00$3", 382 Reason => "\x00$3",
383 URL => "\x00$url"
360 ); 384 );
361 385
362 # headers, could be optimized a bit 386 # headers, could be optimized a bit
363 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 387 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
364 for ("$_[1]\012") { 388 for ("$_[1]\012") {
… …
371 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 395 ((?: [^\015\012]+ | \015?\012[\011\040] )*)
372 \015?\012 396 \015?\012
373 /gxc; 397 /gxc;
374 398
375 /\G$/ 399 /\G$/
376 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 }));
377 } 401 }
378 402
379 substr $_, 0, 1, "" 403 substr $_, 0, 1, ""
380 for values %hdr; 404 for values %hdr;
381 405
… …
390 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 414 my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
391 415
392 my $cdom = (delete $kv{domain}) || $uhost; 416 my $cdom = (delete $kv{domain}) || $uhost;
393 my $cpath = (delete $kv{path}) || "/"; 417 my $cpath = (delete $kv{path}) || "/";
394 418
395 $cdom =~ s/^.?/./; # make sure it starts with a "." 419 $cdom =~ s/^\.?/./; # make sure it starts with a "."
396 420
397 next if $cdom =~ /\.$/; 421 next if $cdom =~ /\.$/;
398 422
399 # this is not rfc-like and not netscape-like. go figure. 423 # this is not rfc-like and not netscape-like. go figure.
400 my $ndots = $cdom =~ y/.//; 424 my $ndots = $cdom =~ y/.//;
… …
404 $arg{cookie_jar}{version} = 1; 428 $arg{cookie_jar}{version} = 1;
405 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 429 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
406 } 430 }
407 } 431 }
408 432
409 if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
410 # microsoft and other assholes don't give a shit for following standards, 433 # microsoft and other shitheads don't give a shit for following standards,
411 # try to support a common form of broken Location header. 434 # try to support some common forms of broken Location headers.
435 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
436 $_[1]{location} =~ s/^\.\/+//;
437
412 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; 438 my $url = "$scheme://$uhost:$uport";
413 439
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 && $method ne "POST") {
449 # apparently, mozilla et al. just change POST to GET here
450 # more research is needed before we do the same
414 http_request ($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);
415 } else { 458 } else {
416 $cb->($_[0], $_[1]); 459 $cb->($_[0], $_[1]);
417 } 460 }
418 }; 461 };
419 462
… …
447 }; 490 };
448 491
449 defined wantarray && AnyEvent::Util::guard { %state = () } 492 defined wantarray && AnyEvent::Util::guard { %state = () }
450} 493}
451 494
452sub http_get($$;@) { 495sub http_get($@) {
453 unshift @_, "GET"; 496 unshift @_, "GET";
454 &http_request 497 &http_request
455} 498}
456 499
457sub http_head($$;@) { 500sub http_head($@) {
458 unshift @_, "HEAD"; 501 unshift @_, "HEAD";
459 &http_request 502 &http_request
460} 503}
461 504
462sub http_post($$$;@) { 505sub http_post($$@) {
506 my $url = shift;
463 unshift @_, "POST", "body"; 507 unshift @_, "POST", $url, "body";
464 &http_request 508 &http_request
465} 509}
466 510
467=back 511=back
468 512
… …
517 561
518L<AnyEvent>. 562L<AnyEvent>.
519 563
520=head1 AUTHOR 564=head1 AUTHOR
521 565
522 Marc Lehmann <schmorp@schmorp.de> 566 Marc Lehmann <schmorp@schmorp.de>
523 http://home.schmorp.de/ 567 http://home.schmorp.de/
524 568
525=cut 569=cut
526 570
5271 5711
528 572

Diff Legend

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