… | |
… | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Errno (); |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent 4.8 (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
|
|
49 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
50 | |
49 | |
51 | use base Exporter::; |
50 | use base Exporter::; |
52 | |
51 | |
53 | our $VERSION = '1.42'; |
52 | our $VERSION = '1.46'; |
54 | |
53 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
55 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
… | |
… | |
92 | must be an absolute http or https URL. |
91 | must be an absolute http or https URL. |
93 | |
92 | |
94 | When called in void context, nothing is returned. In other contexts, |
93 | When called in void context, nothing is returned. In other contexts, |
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
96 | object at least alive until the callback get called. If the object gets |
95 | object at least alive until the callback get called. If the object gets |
97 | destroyed before the callbakc is called, the request will be cancelled. |
96 | destroyed before the callback is called, the request will be cancelled. |
98 | |
97 | |
99 | The callback will be called with the response body data as first argument |
98 | The callback will be called with the response body data as first argument |
100 | (or C<undef> if an error occured), and a hash-ref with response headers as |
99 | (or C<undef> if an error occured), and a hash-ref with response headers as |
101 | second argument. |
100 | second argument. |
102 | |
101 | |
103 | All the headers in that hash are lowercased. In addition to the response |
102 | All the headers in that hash are lowercased. In addition to the response |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
|
|
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
105 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
106 | during the body phase of a request, then the original C<Status> and |
|
|
107 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
108 | C<OrigReason>. |
|
|
109 | |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
107 | requested URL when following redirects). |
111 | the requested URL when following redirects - for example, you might get |
|
|
112 | an error that your URL scheme is not supported even though your URL is a |
|
|
113 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
114 | look at the URL pseudo header). |
|
|
115 | |
|
|
116 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
117 | of an internal redirect. In that case it is an array reference with |
|
|
118 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
119 | response could in turn be the result of a redirect itself, and C<< |
|
|
120 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
121 | response, and so on. |
108 | |
122 | |
109 | If the server sends a header multiple times, then their contents will be |
123 | If the server sends a header multiple times, then their contents will be |
110 | joined together with a comma (C<,>), as per the HTTP spec. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
111 | |
125 | |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
… | |
… | |
145 | sent at all). |
159 | sent at all). |
146 | |
160 | |
147 | =item timeout => $seconds |
161 | =item timeout => $seconds |
148 | |
162 | |
149 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
150 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
165 | timeout. |
|
|
166 | |
|
|
167 | Default timeout is 5 minutes. |
151 | |
168 | |
152 | =item proxy => [$host, $port[, $scheme]] or undef |
169 | =item proxy => [$host, $port[, $scheme]] or undef |
153 | |
170 | |
154 | Use the given http proxy for all requests. If not specified, then the |
171 | Use the given http proxy for all requests. If not specified, then the |
155 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
172 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
… | |
… | |
187 | verification, highest compatibility) and high-security (CA and common-name |
204 | verification, highest compatibility) and high-security (CA and common-name |
188 | verification) TLS context. |
205 | verification) TLS context. |
189 | |
206 | |
190 | The default for this option is C<low>, which could be interpreted as "give |
207 | The default for this option is C<low>, which could be interpreted as "give |
191 | me the page, no matter what". |
208 | me the page, no matter what". |
|
|
209 | |
|
|
210 | =item on_prepare => $callback->($fh) |
|
|
211 | |
|
|
212 | In rare cases you need to "tune" the socket before it is used to |
|
|
213 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
214 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
215 | and behaves exactly the same way (e.g. it has to provide a |
|
|
216 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
217 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
218 | |
|
|
219 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
220 | |
|
|
221 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
222 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
223 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
224 | obviously, it has to follow the same calling conventions, except that it |
|
|
225 | may always return a connection guard object. |
|
|
226 | |
|
|
227 | There are probably lots of weird uses for this function, starting from |
|
|
228 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
229 | but fast) host => IP address caching or even socks protocol support. |
192 | |
230 | |
193 | =item on_header => $callback->($headers) |
231 | =item on_header => $callback->($headers) |
194 | |
232 | |
195 | When specified, this callback will be called with the header hash as soon |
233 | When specified, this callback will be called with the header hash as soon |
196 | as headers have been successfully received from the remote server (not on |
234 | as headers have been successfully received from the remote server (not on |
… | |
… | |
314 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
352 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
315 | |
353 | |
316 | _slot_schedule $_[0]; |
354 | _slot_schedule $_[0]; |
317 | } |
355 | } |
318 | |
356 | |
319 | our $qr_nl = qr{\015?\012}; |
|
|
320 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
357 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
321 | |
358 | |
322 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
359 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
323 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
360 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
324 | |
361 | |
… | |
… | |
337 | while (my ($k, $v) = each %$hdr) { |
374 | while (my ($k, $v) = each %$hdr) { |
338 | $hdr{lc $k} = $v; |
375 | $hdr{lc $k} = $v; |
339 | } |
376 | } |
340 | } |
377 | } |
341 | |
378 | |
|
|
379 | # pseudo headers for all subsequent responses |
|
|
380 | my @pseudo = (URL => $url); |
|
|
381 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
382 | |
342 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
383 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
343 | |
384 | |
344 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
385 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
345 | if $recurse < 0; |
386 | if $recurse < 0; |
346 | |
387 | |
347 | my $proxy = $arg{proxy} || $PROXY; |
388 | my $proxy = $arg{proxy} || $PROXY; |
348 | my $timeout = $arg{timeout} || $TIMEOUT; |
389 | my $timeout = $arg{timeout} || $TIMEOUT; |
349 | |
390 | |
350 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
391 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
351 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
392 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
352 | |
393 | |
353 | $uscheme = lc $uscheme; |
394 | $uscheme = lc $uscheme; |
354 | |
395 | |
355 | my $uport = $uscheme eq "http" ? 80 |
396 | my $uport = $uscheme eq "http" ? 80 |
356 | : $uscheme eq "https" ? 443 |
397 | : $uscheme eq "https" ? 443 |
357 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
398 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
358 | |
399 | |
359 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
400 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
360 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
401 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
361 | |
402 | |
362 | my $uhost = $1; |
403 | my $uhost = $1; |
363 | $uport = $2 if defined $2; |
404 | $uport = $2 if defined $2; |
364 | |
405 | |
365 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"; |
406 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
407 | unless exists $hdr{host}; |
366 | |
408 | |
367 | $uhost =~ s/^\[(.*)\]$/$1/; |
409 | $uhost =~ s/^\[(.*)\]$/$1/; |
368 | $upath .= "?$query" if length $query; |
410 | $upath .= $query if length $query; |
369 | |
411 | |
370 | $upath =~ s%^/?%/%; |
412 | $upath =~ s%^/?%/%; |
371 | |
413 | |
372 | # cookie processing |
414 | # cookie processing |
373 | if (my $jar = $arg{cookie_jar}) { |
415 | if (my $jar = $arg{cookie_jar}) { |
… | |
… | |
416 | |
458 | |
417 | # leave out fragment and query string, just a heuristic |
459 | # leave out fragment and query string, just a heuristic |
418 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
460 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
419 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
461 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
420 | |
462 | |
421 | $hdr{"content-length"} = length $arg{body}; |
463 | $hdr{"content-length"} = length $arg{body} |
|
|
464 | if length $arg{body} || $method ne "GET"; |
422 | |
465 | |
423 | my %state = (connect_guard => 1); |
466 | my %state = (connect_guard => 1); |
424 | |
467 | |
425 | _get_slot $uhost, sub { |
468 | _get_slot $uhost, sub { |
426 | $state{slot_guard} = shift; |
469 | $state{slot_guard} = shift; |
427 | |
470 | |
428 | return unless $state{connect_guard}; |
471 | return unless $state{connect_guard}; |
429 | |
472 | |
430 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
473 | my $connect_cb = sub { |
431 | $state{fh} = shift |
474 | $state{fh} = shift |
432 | or do { |
475 | or do { |
433 | my $err = "$!"; |
476 | my $err = "$!"; |
434 | %state = (); |
477 | %state = (); |
435 | return $cb->(undef, { Status => 599, Reason => $err, URL => $url }); |
478 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
436 | }; |
479 | }; |
437 | |
480 | |
438 | pop; # free memory, save a tree |
481 | pop; # free memory, save a tree |
439 | |
482 | |
440 | return unless delete $state{connect_guard}; |
483 | return unless delete $state{connect_guard}; |
441 | |
484 | |
442 | # get handle |
485 | # get handle |
443 | $state{handle} = new AnyEvent::Handle |
486 | $state{handle} = new AnyEvent::Handle |
444 | fh => $state{fh}, |
487 | fh => $state{fh}, |
|
|
488 | peername => $rhost, |
|
|
489 | tls_ctx => $arg{tls_ctx}, |
|
|
490 | # these need to be reconfigured on keepalive handles |
445 | timeout => $timeout, |
491 | timeout => $timeout, |
446 | peername => $rhost, |
492 | on_error => sub { |
447 | tls_ctx => $arg{tls_ctx}; |
493 | %state = (); |
|
|
494 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
|
|
495 | }, |
|
|
496 | on_eof => sub { |
|
|
497 | %state = (); |
|
|
498 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
|
|
499 | }, |
|
|
500 | ; |
448 | |
501 | |
449 | # limit the number of persistent connections |
502 | # limit the number of persistent connections |
450 | # keepalive not yet supported |
503 | # keepalive not yet supported |
451 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
504 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
452 | ++$KA_COUNT{$_[1]}; |
505 | # ++$KA_COUNT{$_[1]}; |
453 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
506 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
454 | --$KA_COUNT{$_[1]} |
507 | # --$KA_COUNT{$_[1]} |
455 | }; |
508 | # }; |
456 | $hdr{connection} = "keep-alive"; |
509 | # $hdr{connection} = "keep-alive"; |
457 | } else { |
510 | # } else { |
458 | delete $hdr{connection}; |
511 | delete $hdr{connection}; |
459 | } |
512 | # } |
460 | |
|
|
461 | # (re-)configure handle |
|
|
462 | $state{handle}->on_error (sub { |
|
|
463 | %state = (); |
|
|
464 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
465 | }); |
|
|
466 | $state{handle}->on_eof (sub { |
|
|
467 | %state = (); |
|
|
468 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
|
|
469 | }); |
|
|
470 | |
513 | |
471 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
514 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
472 | |
515 | |
473 | # handle actual, non-tunneled, request |
516 | # handle actual, non-tunneled, request |
474 | my $handle_actual_request = sub { |
517 | my $handle_actual_request = sub { |
… | |
… | |
480 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
523 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
481 | . "\015\012" |
524 | . "\015\012" |
482 | . (delete $arg{body}) |
525 | . (delete $arg{body}) |
483 | ); |
526 | ); |
484 | |
527 | |
|
|
528 | # return if error occured during push_write() |
|
|
529 | return unless %state; |
|
|
530 | |
485 | %hdr = (); # reduce memory usage, save a kitten |
531 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
486 | |
532 | |
487 | # status line |
533 | # status line and headers |
488 | $state{handle}->push_read (line => $qr_nl, sub { |
534 | $state{handle}->push_read (line => $qr_nlnl, sub { |
489 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
535 | my $keepalive = pop; |
490 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
491 | |
536 | |
492 | my %hdr = ( # response headers |
|
|
493 | HTTPVersion => ",$1", |
|
|
494 | Status => ",$2", |
|
|
495 | Reason => ",$3", |
|
|
496 | URL => ",$url" |
|
|
497 | ); |
|
|
498 | |
|
|
499 | # headers, could be optimized a bit |
|
|
500 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
|
|
501 | for ("$_[1]") { |
537 | for ("$_[1]") { |
502 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
538 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
503 | |
539 | |
|
|
540 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
|
|
541 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
542 | |
|
|
543 | push @pseudo, |
|
|
544 | HTTPVersion => $1, |
|
|
545 | Status => $2, |
|
|
546 | Reason => $3, |
|
|
547 | ; |
|
|
548 | |
504 | # things seen, not parsed: |
549 | # things seen, not parsed: |
505 | # p3pP="NON CUR OTPi OUR NOR UNI" |
550 | # p3pP="NON CUR OTPi OUR NOR UNI" |
506 | |
551 | |
507 | $hdr{lc $1} .= ",$2" |
552 | $hdr{lc $1} .= ",$2" |
508 | while /\G |
553 | while /\G |
509 | ([^:\000-\037]*): |
554 | ([^:\000-\037]*): |
510 | [\011\040]* |
555 | [\011\040]* |
511 | ((?: [^\012]+ | \012[\011\040] )*) |
556 | ((?: [^\012]+ | \012[\011\040] )*) |
512 | \012 |
557 | \012 |
513 | /gxc; |
558 | /gxc; |
514 | |
559 | |
515 | /\G$/ |
560 | /\G$/ |
516 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
561 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
562 | } |
|
|
563 | |
|
|
564 | # remove the "," prefix we added to all headers above |
|
|
565 | substr $_, 0, 1, "" |
|
|
566 | for values %hdr; |
|
|
567 | |
|
|
568 | # patch in all pseudo headers |
|
|
569 | %hdr = (%hdr, @pseudo); |
|
|
570 | |
|
|
571 | # redirect handling |
|
|
572 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
573 | # try to support some common forms of broken Location headers. |
|
|
574 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
575 | $hdr{location} =~ s/^\.\/+//; |
|
|
576 | |
|
|
577 | my $url = "$rscheme://$uhost:$uport"; |
|
|
578 | |
|
|
579 | unless ($hdr{location} =~ s/^\///) { |
|
|
580 | $url .= $upath; |
|
|
581 | $url =~ s/\/[^\/]*$//; |
517 | } |
582 | } |
518 | |
583 | |
519 | substr $_, 0, 1, "" |
|
|
520 | for values %hdr; |
|
|
521 | |
|
|
522 | # redirect handling |
|
|
523 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
524 | # try to support some common forms of broken Location headers. |
|
|
525 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
526 | $hdr{location} =~ s/^\.\/+//; |
|
|
527 | |
|
|
528 | my $url = "$rscheme://$uhost:$uport"; |
|
|
529 | |
|
|
530 | unless ($hdr{location} =~ s/^\///) { |
|
|
531 | $url .= $upath; |
|
|
532 | $url =~ s/\/[^\/]*$//; |
|
|
533 | } |
|
|
534 | |
|
|
535 | $hdr{location} = "$url/$hdr{location}"; |
584 | $hdr{location} = "$url/$hdr{location}"; |
|
|
585 | } |
|
|
586 | |
|
|
587 | my $redirect; |
|
|
588 | |
|
|
589 | if ($recurse) { |
|
|
590 | my $status = $hdr{Status}; |
|
|
591 | |
|
|
592 | # industry standard is to redirect POST as GET for |
|
|
593 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
594 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
595 | # industry standard seems to be to simply follow. |
|
|
596 | # we go with the industry standard. |
|
|
597 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
598 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
599 | $method = "GET" unless $method eq "HEAD"; |
|
|
600 | $redirect = 1; |
|
|
601 | } elsif ($status == 307) { |
|
|
602 | $redirect = 1; |
536 | } |
603 | } |
|
|
604 | } |
537 | |
605 | |
538 | my $redirect; |
606 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
607 | $state{handle}->destroy if $state{handle}; |
|
|
608 | %state = (); |
539 | |
609 | |
|
|
610 | if (defined $_[1]) { |
|
|
611 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
612 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
613 | } |
|
|
614 | |
|
|
615 | # set-cookie processing |
540 | if ($recurse) { |
616 | if ($arg{cookie_jar}) { |
541 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
617 | for ($hdr{"set-cookie"}) { |
542 | # apparently, mozilla et al. just change POST to GET here |
618 | # parse NAME=VALUE |
543 | # more research is needed before we do the same |
619 | my @kv; |
|
|
620 | |
|
|
621 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
544 | $redirect = 1; |
622 | my $name = $1; |
545 | } elsif ($hdr{Status} == 303) { |
623 | my $value = $3; |
546 | # even http/1.1 is unclear on how to mutate the method |
624 | |
547 | $method = "GET" unless $method eq "HEAD"; |
625 | unless ($value) { |
|
|
626 | $value = $2; |
|
|
627 | $value =~ s/\\(.)/$1/gs; |
|
|
628 | } |
|
|
629 | |
|
|
630 | push @kv, $name => $value; |
|
|
631 | |
|
|
632 | last unless /\G\s*;/gc; |
|
|
633 | } |
|
|
634 | |
|
|
635 | last unless @kv; |
|
|
636 | |
|
|
637 | my $name = shift @kv; |
|
|
638 | my %kv = (value => shift @kv, @kv); |
|
|
639 | |
|
|
640 | my $cdom; |
|
|
641 | my $cpath = (delete $kv{path}) || "/"; |
|
|
642 | |
|
|
643 | if (exists $kv{domain}) { |
|
|
644 | $cdom = delete $kv{domain}; |
|
|
645 | |
|
|
646 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
647 | |
|
|
648 | next if $cdom =~ /\.$/; |
|
|
649 | |
|
|
650 | # this is not rfc-like and not netscape-like. go figure. |
|
|
651 | my $ndots = $cdom =~ y/.//; |
|
|
652 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
653 | } else { |
|
|
654 | $cdom = $uhost; |
|
|
655 | } |
|
|
656 | |
548 | $redirect = 1; |
657 | # store it |
549 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
658 | $arg{cookie_jar}{version} = 1; |
550 | $redirect = 1; |
659 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
660 | |
|
|
661 | redo if /\G\s*,/gc; |
551 | } |
662 | } |
552 | } |
663 | } |
553 | |
664 | |
554 | my $finish = sub { |
665 | if ($redirect && exists $hdr{location}) { |
555 | $state{handle}->destroy if $state{handle}; |
666 | # we ignore any errors, as it is very common to receive |
556 | %state = (); |
667 | # Content-Length != 0 but no actual body |
557 | |
668 | # we also access %hdr, as $_[1] might be an erro |
558 | # set-cookie processing |
669 | http_request ( |
559 | if ($arg{cookie_jar}) { |
670 | $method => $hdr{location}, |
560 | for ($_[1]{"set-cookie"}) { |
|
|
561 | # parse NAME=VALUE |
|
|
562 | my @kv; |
|
|
563 | |
|
|
564 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
565 | my $name = $1; |
|
|
566 | my $value = $3; |
|
|
567 | |
|
|
568 | unless ($value) { |
|
|
569 | $value = $2; |
|
|
570 | $value =~ s/\\(.)/$1/gs; |
|
|
571 | } |
671 | %arg, |
|
|
672 | recurse => $recurse - 1, |
|
|
673 | Redirect => [$_[0], \%hdr], |
|
|
674 | $cb); |
|
|
675 | } else { |
|
|
676 | $cb->($_[0], \%hdr); |
|
|
677 | } |
|
|
678 | }; |
572 | |
679 | |
573 | push @kv, $name => $value; |
680 | my $len = $hdr{"content-length"}; |
574 | |
681 | |
575 | last unless /\G\s*;/gc; |
682 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
683 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
684 | } elsif ( |
|
|
685 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
686 | or $method eq "HEAD" |
|
|
687 | or (defined $len && !$len) |
|
|
688 | ) { |
|
|
689 | # no body |
|
|
690 | $finish->("", undef, undef, 1); |
|
|
691 | } else { |
|
|
692 | # body handling, four different code paths |
|
|
693 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
694 | # we might read too much here, but it does not matter yet (no pipelining) |
|
|
695 | if (!$redirect && $arg{want_body_handle}) { |
|
|
696 | $_[0]->on_eof (undef); |
|
|
697 | $_[0]->on_error (undef); |
|
|
698 | $_[0]->on_read (undef); |
|
|
699 | |
|
|
700 | $finish->(delete $state{handle}); |
|
|
701 | |
|
|
702 | } elsif ($arg{on_body}) { |
|
|
703 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
704 | if ($len) { |
|
|
705 | $_[0]->on_read (sub { |
|
|
706 | $len -= length $_[0]{rbuf}; |
|
|
707 | |
|
|
708 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
709 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
710 | |
576 | } |
711 | $len > 0 |
577 | |
712 | or $finish->("", undef, undef, 1); |
578 | last unless @kv; |
|
|
579 | |
|
|
580 | my $name = shift @kv; |
|
|
581 | my %kv = (value => shift @kv, @kv); |
|
|
582 | |
|
|
583 | my $cdom; |
|
|
584 | my $cpath = (delete $kv{path}) || "/"; |
|
|
585 | |
|
|
586 | if (exists $kv{domain}) { |
|
|
587 | $cdom = delete $kv{domain}; |
|
|
588 | |
|
|
589 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
590 | |
|
|
591 | next if $cdom =~ /\.$/; |
|
|
592 | |
|
|
593 | # this is not rfc-like and not netscape-like. go figure. |
|
|
594 | my $ndots = $cdom =~ y/.//; |
|
|
595 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
596 | } else { |
|
|
597 | $cdom = $uhost; |
|
|
598 | } |
|
|
599 | |
|
|
600 | # store it |
|
|
601 | $arg{cookie_jar}{version} = 1; |
|
|
602 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
603 | |
|
|
604 | redo if /\G\s*,/gc; |
|
|
605 | } |
713 | }); |
|
|
714 | } else { |
|
|
715 | $_[0]->on_eof (sub { |
|
|
716 | $finish->(""); |
|
|
717 | }); |
|
|
718 | $_[0]->on_read (sub { |
|
|
719 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
720 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
721 | }); |
606 | } |
722 | } |
|
|
723 | } else { |
|
|
724 | $_[0]->on_eof (undef); |
607 | |
725 | |
608 | if ($redirect && exists $hdr{location}) { |
726 | if ($len) { |
609 | # we ignore any errors, as it is very common to receive |
727 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
610 | # Content-Length != 0 but no actual body |
728 | $_[0]->on_read (sub { |
611 | # we also access %hdr, as $_[1] might be an erro |
729 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
612 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
730 | if $len <= length $_[0]{rbuf}; |
|
|
731 | }); |
613 | } else { |
732 | } else { |
614 | $cb->($_[0], $_[1]); |
|
|
615 | } |
|
|
616 | }; |
|
|
617 | |
|
|
618 | my $len = $hdr{"content-length"}; |
|
|
619 | |
|
|
620 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
621 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
|
|
622 | } elsif ( |
|
|
623 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
624 | or $method eq "HEAD" |
|
|
625 | or (defined $len && !$len) |
|
|
626 | ) { |
|
|
627 | # no body |
|
|
628 | $finish->("", \%hdr); |
|
|
629 | } else { |
|
|
630 | # body handling, four different code paths |
|
|
631 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
632 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
633 | if (!$redirect && $arg{want_body_handle}) { |
|
|
634 | $_[0]->on_eof (undef); |
|
|
635 | $_[0]->on_error (undef); |
|
|
636 | $_[0]->on_read (undef); |
|
|
637 | |
|
|
638 | $finish->(delete $state{handle}, \%hdr); |
|
|
639 | |
|
|
640 | } elsif ($arg{on_body}) { |
|
|
641 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
642 | if ($len) { |
|
|
643 | $_[0]->on_eof (undef); |
|
|
644 | $_[0]->on_read (sub { |
|
|
645 | $len -= length $_[0]{rbuf}; |
|
|
646 | |
|
|
647 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
648 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
649 | |
|
|
650 | $len > 0 |
|
|
651 | or $finish->("", \%hdr); |
|
|
652 | }); |
|
|
653 | } else { |
|
|
654 | $_[0]->on_eof (sub { |
|
|
655 | $finish->("", \%hdr); |
|
|
656 | }); |
|
|
657 | $_[0]->on_read (sub { |
|
|
658 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
659 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
660 | }); |
|
|
661 | } |
|
|
662 | } else { |
|
|
663 | $_[0]->on_eof (undef); |
|
|
664 | |
|
|
665 | if ($len) { |
|
|
666 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
667 | $_[0]->on_read (sub { |
|
|
668 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
669 | if $len <= length $_[0]{rbuf}; |
|
|
670 | }); |
|
|
671 | } else { |
|
|
672 | $_[0]->on_error (sub { |
733 | $_[0]->on_error (sub { |
673 | $! == Errno::EPIPE || !$! |
734 | ($! == Errno::EPIPE || !$!) |
674 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
735 | ? $finish->(delete $_[0]{rbuf}) |
675 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
736 | : $finish->(undef, 599 => $_[2]); |
676 | }); |
737 | }); |
677 | $_[0]->on_read (sub { }); |
738 | $_[0]->on_read (sub { }); |
678 | } |
|
|
679 | } |
739 | } |
680 | } |
740 | } |
681 | }); |
741 | } |
682 | }); |
742 | }); |
683 | }; |
743 | }; |
684 | |
744 | |
685 | # now handle proxy-CONNECT method |
745 | # now handle proxy-CONNECT method |
686 | if ($proxy && $uscheme eq "https") { |
746 | if ($proxy && $uscheme eq "https") { |
… | |
… | |
688 | |
748 | |
689 | # maybe re-use $uauthority with patched port? |
749 | # maybe re-use $uauthority with patched port? |
690 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
750 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
691 | $state{handle}->push_read (line => $qr_nlnl, sub { |
751 | $state{handle}->push_read (line => $qr_nlnl, sub { |
692 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
752 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
693 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
753 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
694 | |
754 | |
695 | if ($2 == 200) { |
755 | if ($2 == 200) { |
696 | $rpath = $upath; |
756 | $rpath = $upath; |
697 | &$handle_actual_request; |
757 | &$handle_actual_request; |
698 | } else { |
758 | } else { |
699 | %state = (); |
759 | %state = (); |
700 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
760 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
701 | } |
761 | } |
702 | }); |
762 | }); |
703 | } else { |
763 | } else { |
704 | &$handle_actual_request; |
764 | &$handle_actual_request; |
705 | } |
765 | } |
|
|
766 | }; |
706 | |
767 | |
707 | }, $arg{on_prepare} || sub { $timeout }; |
768 | my $tcp_connect = $arg{tcp_connect} |
|
|
769 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
770 | |
|
|
771 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
772 | |
708 | }; |
773 | }; |
709 | |
774 | |
710 | defined wantarray && AnyEvent::Util::guard { %state = () } |
775 | defined wantarray && AnyEvent::Util::guard { %state = () } |
711 | } |
776 | } |
712 | |
777 | |
… | |
… | |
726 | &http_request |
791 | &http_request |
727 | } |
792 | } |
728 | |
793 | |
729 | =back |
794 | =back |
730 | |
795 | |
|
|
796 | =head2 DNS CACHING |
|
|
797 | |
|
|
798 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
799 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
800 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
801 | on its own. If you want DNS caching, you currently have to provide |
|
|
802 | your own default resolver (by storing a suitable resolver object in |
|
|
803 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
804 | |
731 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
805 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
732 | |
806 | |
733 | =over 4 |
807 | =over 4 |
734 | |
808 | |
735 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
809 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
736 | |
810 | |
737 | Sets the default proxy server to use. The proxy-url must begin with a |
811 | Sets the default proxy server to use. The proxy-url must begin with a |
738 | string of the form C<http://host:port> (optionally C<https:...>). |
812 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
813 | otherwise. |
|
|
814 | |
|
|
815 | To clear an already-set proxy, use C<undef>. |
|
|
816 | |
|
|
817 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
818 | |
|
|
819 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
820 | Date (RFC 2616). |
|
|
821 | |
|
|
822 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
823 | |
|
|
824 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
|
|
825 | timestamp, or C<undef> if the date cannot be parsed. |
739 | |
826 | |
740 | =item $AnyEvent::HTTP::MAX_RECURSE |
827 | =item $AnyEvent::HTTP::MAX_RECURSE |
741 | |
828 | |
742 | The default value for the C<recurse> request parameter (default: C<10>). |
829 | The default value for the C<recurse> request parameter (default: C<10>). |
743 | |
830 | |
… | |
… | |
763 | |
850 | |
764 | =back |
851 | =back |
765 | |
852 | |
766 | =cut |
853 | =cut |
767 | |
854 | |
|
|
855 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
856 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
857 | |
|
|
858 | sub format_date($) { |
|
|
859 | my ($time) = @_; |
|
|
860 | |
|
|
861 | # RFC 822/1123 format |
|
|
862 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
863 | |
|
|
864 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
865 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
866 | $H, $M, $S; |
|
|
867 | } |
|
|
868 | |
|
|
869 | sub parse_date($) { |
|
|
870 | my ($date) = @_; |
|
|
871 | |
|
|
872 | my ($d, $m, $y, $H, $M, $S); |
|
|
873 | |
|
|
874 | if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
|
|
875 | # RFC 822/1123, required by RFC 2616 |
|
|
876 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
877 | |
|
|
878 | } elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
|
|
879 | # RFC 850 |
|
|
880 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
881 | |
|
|
882 | } elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) { |
|
|
883 | # ISO C's asctime |
|
|
884 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
885 | } |
|
|
886 | # other formats fail in the loop below |
|
|
887 | |
|
|
888 | for (0..11) { |
|
|
889 | if ($m eq $month[$_]) { |
|
|
890 | require Time::Local; |
|
|
891 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
892 | } |
|
|
893 | } |
|
|
894 | |
|
|
895 | undef |
|
|
896 | } |
|
|
897 | |
768 | sub set_proxy($) { |
898 | sub set_proxy($) { |
|
|
899 | if (length $_[0]) { |
769 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
900 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
901 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
902 | $PROXY = [$2, $3 || 3128, $1] |
|
|
903 | } else { |
|
|
904 | undef $PROXY; |
|
|
905 | } |
770 | } |
906 | } |
771 | |
907 | |
772 | # initialise proxy from environment |
908 | # initialise proxy from environment |
|
|
909 | eval { |
773 | set_proxy $ENV{http_proxy}; |
910 | set_proxy $ENV{http_proxy}; |
|
|
911 | }; |
|
|
912 | |
|
|
913 | =head2 SOCKS PROXIES |
|
|
914 | |
|
|
915 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
916 | compile your perl to support socks, or use an external program such as |
|
|
917 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
918 | transparently. |
|
|
919 | |
|
|
920 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
921 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
922 | that works with socks4a proxies: |
|
|
923 | |
|
|
924 | use Errno; |
|
|
925 | use AnyEvent::Util; |
|
|
926 | use AnyEvent::Socket; |
|
|
927 | use AnyEvent::Handle; |
|
|
928 | |
|
|
929 | # host, port and username of/for your socks4a proxy |
|
|
930 | my $socks_host = "10.0.0.23"; |
|
|
931 | my $socks_port = 9050; |
|
|
932 | my $socks_user = ""; |
|
|
933 | |
|
|
934 | sub socks4a_connect { |
|
|
935 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
936 | |
|
|
937 | my $hdl = new AnyEvent::Handle |
|
|
938 | connect => [$socks_host, $socks_port], |
|
|
939 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
940 | on_error => sub { $connect_cb->() }, |
|
|
941 | ; |
|
|
942 | |
|
|
943 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
944 | |
|
|
945 | $hdl->push_read (chunk => 8, sub { |
|
|
946 | my ($hdl, $chunk) = @_; |
|
|
947 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
948 | |
|
|
949 | if ($status == 0x5a) { |
|
|
950 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
951 | } else { |
|
|
952 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
953 | } |
|
|
954 | }); |
|
|
955 | |
|
|
956 | $hdl |
|
|
957 | } |
|
|
958 | |
|
|
959 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
960 | possibly after switching off other proxy types: |
|
|
961 | |
|
|
962 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
963 | |
|
|
964 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
965 | my ($data, $headers) = @_; |
|
|
966 | ... |
|
|
967 | }; |
774 | |
968 | |
775 | =head1 SEE ALSO |
969 | =head1 SEE ALSO |
776 | |
970 | |
777 | L<AnyEvent>. |
971 | L<AnyEvent>. |
778 | |
972 | |