… | |
… | |
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 $PERSISTENT_TIMEOUT = 2; |
… | |
… | |
89 | The callback will be called with the response data as first argument |
93 | The callback will be called with the response data as first argument |
90 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
91 | response headers as second argument. |
95 | response headers as second argument. |
92 | |
96 | |
93 | All the headers in that hash are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
94 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
95 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
|
|
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
101 | requested URL when following redirects). |
|
|
102 | |
96 | name. If the server sends a header multiple lines, then their contents |
103 | If the server sends a header multiple lines, then their contents will be |
97 | will be joined together with C<\x00>. |
104 | joined together with C<\x00>. |
98 | |
105 | |
99 | If an internal error occurs, such as not being able to resolve a hostname, |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
100 | then C<$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> |
101 | and the C<Reason> pseudo-header will contain an error message. |
108 | and the C<Reason> pseudo-header will contain an error message. |
102 | |
109 | |
… | |
… | |
214 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
215 | |
222 | |
216 | _slot_schedule $_[0]; |
223 | _slot_schedule $_[0]; |
217 | } |
224 | } |
218 | |
225 | |
219 | sub http_request($$$;@) { |
226 | sub http_request($$@) { |
220 | my $cb = pop; |
227 | my $cb = pop; |
221 | my ($method, $url, %arg) = @_; |
228 | my ($method, $url, %arg) = @_; |
222 | |
229 | |
223 | my %hdr; |
230 | my %hdr; |
224 | |
231 | |
… | |
… | |
230 | } |
237 | } |
231 | } |
238 | } |
232 | |
239 | |
233 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
240 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
234 | |
241 | |
235 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
236 | if $recurse < 0; |
243 | if $recurse < 0; |
237 | |
244 | |
238 | my $proxy = $arg{proxy} || $PROXY; |
245 | my $proxy = $arg{proxy} || $PROXY; |
239 | my $timeout = $arg{timeout} || $TIMEOUT; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
240 | |
247 | |
… | |
… | |
245 | |
252 | |
246 | $scheme = lc $scheme; |
253 | $scheme = lc $scheme; |
247 | |
254 | |
248 | my $uport = $scheme eq "http" ? 80 |
255 | my $uport = $scheme eq "http" ? 80 |
249 | : $scheme eq "https" ? 443 |
256 | : $scheme eq "https" ? 443 |
250 | : 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 }); |
251 | |
258 | |
252 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
259 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
253 | |
260 | |
254 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
255 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); |
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
256 | |
263 | |
257 | my $uhost = $1; |
264 | my $uhost = $1; |
258 | $uport = $2 if defined $2; |
265 | $uport = $2 if defined $2; |
259 | |
266 | |
260 | $uhost =~ s/^\[(.*)\]$/$1/; |
267 | $uhost =~ s/^\[(.*)\]$/$1/; |
… | |
… | |
305 | |
312 | |
306 | return unless $state{connect_guard}; |
313 | return unless $state{connect_guard}; |
307 | |
314 | |
308 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
309 | $state{fh} = shift |
316 | $state{fh} = shift |
310 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
311 | |
318 | |
312 | delete $state{connect_guard}; # reduce memory usage, save a tree |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
313 | |
320 | |
314 | # get handle |
321 | # get handle |
315 | $state{handle} = new AnyEvent::Handle |
322 | $state{handle} = new AnyEvent::Handle |
… | |
… | |
329 | # (re-)configure handle |
336 | # (re-)configure handle |
330 | $state{handle}->timeout ($timeout); |
337 | $state{handle}->timeout ($timeout); |
331 | $state{handle}->on_error (sub { |
338 | $state{handle}->on_error (sub { |
332 | my $errno = "$!"; |
339 | my $errno = "$!"; |
333 | %state = (); |
340 | %state = (); |
334 | $cb->(undef, { Status => 599, Reason => $errno }); |
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
335 | }); |
342 | }); |
336 | $state{handle}->on_eof (sub { |
343 | $state{handle}->on_eof (sub { |
337 | %state = (); |
344 | %state = (); |
338 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
339 | }); |
346 | }); |
340 | |
347 | |
341 | # send request |
348 | # send request |
342 | $state{handle}->push_write ( |
349 | $state{handle}->push_write ( |
343 | "$method $rpath HTTP/1.0\015\012" |
350 | "$method $rpath HTTP/1.0\015\012" |
… | |
… | |
349 | %hdr = (); # reduce memory usage, save a kitten |
356 | %hdr = (); # reduce memory usage, save a kitten |
350 | |
357 | |
351 | # status line |
358 | # status line |
352 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
359 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
353 | $_[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 |
354 | 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 })); |
355 | |
362 | |
356 | my %hdr = ( # response headers |
363 | my %hdr = ( # response headers |
357 | HTTPVersion => "\x00$1", |
364 | HTTPVersion => "\x00$1", |
358 | Status => "\x00$2", |
365 | Status => "\x00$2", |
359 | Reason => "\x00$3", |
366 | Reason => "\x00$3", |
|
|
367 | URL => "\x00$url" |
360 | ); |
368 | ); |
361 | |
369 | |
362 | # headers, could be optimized a bit |
370 | # headers, could be optimized a bit |
363 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
364 | for ("$_[1]\012") { |
372 | for ("$_[1]\012") { |
… | |
… | |
371 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
372 | \015?\012 |
380 | \015?\012 |
373 | /gxc; |
381 | /gxc; |
374 | |
382 | |
375 | /\G$/ |
383 | /\G$/ |
376 | 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 })); |
377 | } |
385 | } |
378 | |
386 | |
379 | substr $_, 0, 1, "" |
387 | substr $_, 0, 1, "" |
380 | for values %hdr; |
388 | for values %hdr; |
381 | |
389 | |
… | |
… | |
447 | }; |
455 | }; |
448 | |
456 | |
449 | defined wantarray && AnyEvent::Util::guard { %state = () } |
457 | defined wantarray && AnyEvent::Util::guard { %state = () } |
450 | } |
458 | } |
451 | |
459 | |
452 | sub http_get($$;@) { |
460 | sub http_get($@) { |
453 | unshift @_, "GET"; |
461 | unshift @_, "GET"; |
454 | &http_request |
462 | &http_request |
455 | } |
463 | } |
456 | |
464 | |
457 | sub http_head($$;@) { |
465 | sub http_head($@) { |
458 | unshift @_, "HEAD"; |
466 | unshift @_, "HEAD"; |
459 | &http_request |
467 | &http_request |
460 | } |
468 | } |
461 | |
469 | |
462 | sub http_post($$$;@) { |
470 | sub http_post($$@) { |
|
|
471 | my $url = shift; |
463 | unshift @_, "POST", "body"; |
472 | unshift @_, "POST", $url, "body"; |
464 | &http_request |
473 | &http_request |
465 | } |
474 | } |
466 | |
475 | |
467 | =back |
476 | =back |
468 | |
477 | |
… | |
… | |
517 | |
526 | |
518 | L<AnyEvent>. |
527 | L<AnyEvent>. |
519 | |
528 | |
520 | =head1 AUTHOR |
529 | =head1 AUTHOR |
521 | |
530 | |
522 | Marc Lehmann <schmorp@schmorp.de> |
531 | Marc Lehmann <schmorp@schmorp.de> |
523 | http://home.schmorp.de/ |
532 | http://home.schmorp.de/ |
524 | |
533 | |
525 | =cut |
534 | =cut |
526 | |
535 | |
527 | 1 |
536 | 1 |
528 | |
537 | |