… | |
… | |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::HTTP; |
7 | use AnyEvent::HTTP; |
|
|
8 | |
|
|
9 | http_get "http://www.nethype.de/", sub { print $_[1] }; |
|
|
10 | |
|
|
11 | # ... do something else here |
8 | |
12 | |
9 | =head1 DESCRIPTION |
13 | =head1 DESCRIPTION |
10 | |
14 | |
11 | This module is an L<AnyEvent> user, you need to make sure that you use and |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
12 | run a supported event loop. |
16 | run a supported event loop. |
… | |
… | |
44 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
45 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
46 | |
50 | |
47 | use base Exporter::; |
51 | use base Exporter::; |
48 | |
52 | |
49 | our $VERSION = '1.0'; |
53 | our $VERSION = '1.03'; |
50 | |
54 | |
51 | our @EXPORT = qw(http_get http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
52 | |
56 | |
53 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
54 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
55 | our $MAX_PERSISTENT = 8; |
59 | our $MAX_PERSISTENT = 8; |
56 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $PERSISTENT_TIMEOUT = 2; |
… | |
… | |
59 | # changing these is evil |
63 | # changing these is evil |
60 | our $MAX_PERSISTENT_PER_HOST = 2; |
64 | our $MAX_PERSISTENT_PER_HOST = 2; |
61 | our $MAX_PER_HOST = 4; |
65 | our $MAX_PER_HOST = 4; |
62 | |
66 | |
63 | our $PROXY; |
67 | our $PROXY; |
|
|
68 | our $ACTIVE = 0; |
64 | |
69 | |
65 | my %KA_COUNT; # number of open keep-alive connections per host |
70 | my %KA_COUNT; # number of open keep-alive connections per host |
66 | my %CO_SLOT; # number of open connections, and wait queue, per host |
71 | my %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, $headers) |
… | |
… | |
88 | The callback will be called with the response data as first argument |
93 | The callback will be called with the response data as first argument |
89 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
90 | response headers as second argument. |
95 | response headers as second argument. |
91 | |
96 | |
92 | All the headers in that hash are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
93 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
94 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
|
|
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
101 | requested URL when following redirects). |
|
|
102 | |
95 | name. If the server sends a header multiple lines, then their contents |
103 | If the server sends a header multiple lines, then their contents will be |
96 | will be joined together with C<\x00>. |
104 | joined together with C<\x00>. |
97 | |
105 | |
98 | If an internal error occurs, such as not being able to resolve a hostname, |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
99 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
107 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
100 | and the C<Reason> pseudo-header will contain an error message. |
108 | and the C<Reason> pseudo-header will contain an error message. |
101 | |
109 | |
… | |
… | |
191 | |
199 | |
192 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
200 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
193 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
201 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
194 | # somebody wants that slot |
202 | # somebody wants that slot |
195 | ++$CO_SLOT{$host}[0]; |
203 | ++$CO_SLOT{$host}[0]; |
|
|
204 | ++$ACTIVE; |
196 | |
205 | |
197 | $cb->(AnyEvent::Util::guard { |
206 | $cb->(AnyEvent::Util::guard { |
|
|
207 | --$ACTIVE; |
198 | --$CO_SLOT{$host}[0]; |
208 | --$CO_SLOT{$host}[0]; |
199 | _slot_schedule $host; |
209 | _slot_schedule $host; |
200 | }); |
210 | }); |
201 | } else { |
211 | } else { |
202 | # nobody wants the slot, maybe we can forget about it |
212 | # nobody wants the slot, maybe we can forget about it |
… | |
… | |
211 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
212 | |
222 | |
213 | _slot_schedule $_[0]; |
223 | _slot_schedule $_[0]; |
214 | } |
224 | } |
215 | |
225 | |
216 | sub http_request($$$;@) { |
226 | sub http_request($$@) { |
217 | my $cb = pop; |
227 | my $cb = pop; |
218 | my ($method, $url, %arg) = @_; |
228 | my ($method, $url, %arg) = @_; |
219 | |
229 | |
220 | my %hdr; |
230 | my %hdr; |
221 | |
231 | |
… | |
… | |
225 | while (my ($k, $v) = each %$hdr) { |
235 | while (my ($k, $v) = each %$hdr) { |
226 | $hdr{lc $k} = $v; |
236 | $hdr{lc $k} = $v; |
227 | } |
237 | } |
228 | } |
238 | } |
229 | |
239 | |
230 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
240 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
231 | |
241 | |
232 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
233 | if $recurse < 0; |
243 | if $recurse < 0; |
234 | |
244 | |
235 | my $proxy = $arg{proxy} || $PROXY; |
245 | my $proxy = $arg{proxy} || $PROXY; |
236 | my $timeout = $arg{timeout} || $TIMEOUT; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
237 | |
247 | |
… | |
… | |
242 | |
252 | |
243 | $scheme = lc $scheme; |
253 | $scheme = lc $scheme; |
244 | |
254 | |
245 | my $uport = $scheme eq "http" ? 80 |
255 | my $uport = $scheme eq "http" ? 80 |
246 | : $scheme eq "https" ? 443 |
256 | : $scheme eq "https" ? 443 |
247 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); |
257 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
|
|
258 | |
|
|
259 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
248 | |
260 | |
249 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
250 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); |
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
251 | |
263 | |
252 | my $uhost = $1; |
264 | my $uhost = $1; |
253 | $uport = $2 if defined $2; |
265 | $uport = $2 if defined $2; |
254 | |
266 | |
255 | $uhost =~ s/^\[(.*)\]$/$1/; |
267 | $uhost =~ s/^\[(.*)\]$/$1/; |
256 | $upath .= "?$query" if length $query; |
268 | $upath .= "?$query" if length $query; |
257 | |
269 | |
258 | $upath =~ s%^/?%/%; |
270 | $upath =~ s%^/?%/%; |
259 | |
|
|
260 | $hdr{referer} ||= "$scheme://$authority$upath"; |
|
|
261 | |
271 | |
262 | # cookie processing |
272 | # cookie processing |
263 | if (my $jar = $arg{cookie_jar}) { |
273 | if (my $jar = $arg{cookie_jar}) { |
264 | %$jar = () if $jar->{version} < 1; |
274 | %$jar = () if $jar->{version} < 1; |
265 | |
275 | |
… | |
… | |
302 | |
312 | |
303 | return unless $state{connect_guard}; |
313 | return unless $state{connect_guard}; |
304 | |
314 | |
305 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
306 | $state{fh} = shift |
316 | $state{fh} = shift |
307 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
308 | |
318 | |
309 | delete $state{connect_guard}; # reduce memory usage, save a tree |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
310 | |
320 | |
311 | # get handle |
321 | # get handle |
312 | $state{handle} = new AnyEvent::Handle |
322 | $state{handle} = new AnyEvent::Handle |
… | |
… | |
324 | } |
334 | } |
325 | |
335 | |
326 | # (re-)configure handle |
336 | # (re-)configure handle |
327 | $state{handle}->timeout ($timeout); |
337 | $state{handle}->timeout ($timeout); |
328 | $state{handle}->on_error (sub { |
338 | $state{handle}->on_error (sub { |
|
|
339 | my $errno = "$!"; |
329 | %state = (); |
340 | %state = (); |
330 | $cb->(undef, { Status => 599, Reason => "$!" }); |
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
331 | }); |
342 | }); |
332 | $state{handle}->on_eof (sub { |
343 | $state{handle}->on_eof (sub { |
333 | %state = (); |
344 | %state = (); |
334 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
335 | }); |
346 | }); |
336 | |
347 | |
337 | # send request |
348 | # send request |
338 | $state{handle}->push_write ( |
349 | $state{handle}->push_write ( |
339 | "$method $rpath HTTP/1.0\015\012" |
350 | "$method $rpath HTTP/1.0\015\012" |
… | |
… | |
345 | %hdr = (); # reduce memory usage, save a kitten |
356 | %hdr = (); # reduce memory usage, save a kitten |
346 | |
357 | |
347 | # status line |
358 | # status line |
348 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
359 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
349 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
360 | $_[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])" })); |
361 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
351 | |
362 | |
352 | my %hdr = ( # response headers |
363 | my %hdr = ( # response headers |
353 | HTTPVersion => "\x00$1", |
364 | HTTPVersion => "\x00$1", |
354 | Status => "\x00$2", |
365 | Status => "\x00$2", |
355 | Reason => "\x00$3", |
366 | Reason => "\x00$3", |
|
|
367 | URL => "\x00$url" |
356 | ); |
368 | ); |
357 | |
369 | |
358 | # headers, could be optimized a bit |
370 | # headers, could be optimized a bit |
359 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
360 | for ("$_[1]\012") { |
372 | for ("$_[1]\012") { |
… | |
… | |
367 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
368 | \015?\012 |
380 | \015?\012 |
369 | /gxc; |
381 | /gxc; |
370 | |
382 | |
371 | /\G$/ |
383 | /\G$/ |
372 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); |
384 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
373 | } |
385 | } |
374 | |
386 | |
375 | substr $_, 0, 1, "" |
387 | substr $_, 0, 1, "" |
376 | for values %hdr; |
388 | for values %hdr; |
377 | |
389 | |
… | |
… | |
400 | $arg{cookie_jar}{version} = 1; |
412 | $arg{cookie_jar}{version} = 1; |
401 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
413 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
402 | } |
414 | } |
403 | } |
415 | } |
404 | |
416 | |
405 | if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) { |
417 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
406 | # microsoft and other assholes don't give a shit for following standards, |
418 | # microsoft and other assholes don't give a shit for following standards, |
407 | # try to support a common form of broken Location header. |
419 | # try to support a common form of broken Location header. |
408 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
420 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
409 | |
421 | |
|
|
422 | # apparently, mozilla et al. just change POST to GET here |
|
|
423 | # more research is needed before we do the same |
|
|
424 | |
410 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
425 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
426 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
427 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
|
|
428 | |
|
|
429 | http_request (GET => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
411 | } else { |
430 | } else { |
412 | $cb->($_[0], $_[1]); |
431 | $cb->($_[0], $_[1]); |
413 | } |
432 | } |
414 | }; |
433 | }; |
415 | |
434 | |
… | |
… | |
443 | }; |
462 | }; |
444 | |
463 | |
445 | defined wantarray && AnyEvent::Util::guard { %state = () } |
464 | defined wantarray && AnyEvent::Util::guard { %state = () } |
446 | } |
465 | } |
447 | |
466 | |
448 | sub http_get($$;@) { |
467 | sub http_get($@) { |
449 | unshift @_, "GET"; |
468 | unshift @_, "GET"; |
450 | &http_request |
469 | &http_request |
451 | } |
470 | } |
452 | |
471 | |
453 | sub http_head($$;@) { |
472 | sub http_head($@) { |
454 | unshift @_, "HEAD"; |
473 | unshift @_, "HEAD"; |
455 | &http_request |
474 | &http_request |
456 | } |
475 | } |
457 | |
476 | |
458 | sub http_post($$$;@) { |
477 | sub http_post($$@) { |
|
|
478 | my $url = shift; |
459 | unshift @_, "POST", "body"; |
479 | unshift @_, "POST", $url, "body"; |
460 | &http_request |
480 | &http_request |
461 | } |
481 | } |
462 | |
482 | |
463 | =back |
483 | =back |
464 | |
484 | |
… | |
… | |
490 | |
510 | |
491 | The maximum time to cache a persistent connection, in seconds (default: 2). |
511 | The maximum time to cache a persistent connection, in seconds (default: 2). |
492 | |
512 | |
493 | Not implemented currently. |
513 | Not implemented currently. |
494 | |
514 | |
|
|
515 | =item $AnyEvent::HTTP::ACTIVE |
|
|
516 | |
|
|
517 | The number of active connections. This is not the number of currently |
|
|
518 | running requests, but the number of currently open and non-idle TCP |
|
|
519 | connections. This number of can be useful for load-leveling. |
|
|
520 | |
495 | =back |
521 | =back |
496 | |
522 | |
497 | =cut |
523 | =cut |
498 | |
524 | |
499 | sub set_proxy($) { |
525 | sub set_proxy($) { |
… | |
… | |
507 | |
533 | |
508 | L<AnyEvent>. |
534 | L<AnyEvent>. |
509 | |
535 | |
510 | =head1 AUTHOR |
536 | =head1 AUTHOR |
511 | |
537 | |
512 | Marc Lehmann <schmorp@schmorp.de> |
538 | Marc Lehmann <schmorp@schmorp.de> |
513 | http://home.schmorp.de/ |
539 | http://home.schmorp.de/ |
514 | |
540 | |
515 | =cut |
541 | =cut |
516 | |
542 | |
517 | 1 |
543 | 1 |
518 | |
544 | |