… | |
… | |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
49 | |
49 | |
50 | use base Exporter::; |
50 | use base Exporter::; |
51 | |
51 | |
52 | our $VERSION = '1.46'; |
52 | our $VERSION = '1.5'; |
53 | |
53 | |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | |
55 | |
56 | 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)"; |
57 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
… | |
… | |
100 | second argument. |
100 | second argument. |
101 | |
101 | |
102 | 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 |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
105 | three parts of the HTTP Status-Line of the same name. |
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>. |
106 | |
109 | |
107 | The pseudo-header C<URL> contains the actual URL (which can differ from |
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
108 | the requested URL when following redirects - for example, you might get |
111 | the requested URL when following redirects - for example, you might get |
109 | an error that your URL scheme is not supported even though your URL is a |
112 | an error that your URL scheme is not supported even though your URL is a |
110 | valid http URL because it redirected to an ftp URL, in which case you can |
113 | valid http URL because it redirected to an ftp URL, in which case you can |
… | |
… | |
216 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
219 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
217 | |
220 | |
218 | In even rarer cases you want total control over how AnyEvent::HTTP |
221 | In even rarer cases you want total control over how AnyEvent::HTTP |
219 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
222 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
220 | to do this, but you can provide your own C<tcp_connect> function - |
223 | to do this, but you can provide your own C<tcp_connect> function - |
221 | obviously, it has to follow the same calling conventions. |
224 | obviously, it has to follow the same calling conventions, except that it |
|
|
225 | may always return a connection guard object. |
222 | |
226 | |
223 | There are probably lots of weird uses for this function, starting from |
227 | There are probably lots of weird uses for this function, starting from |
224 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
228 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
225 | but fast) host => IP address caching or even socks protocol support. |
229 | but fast) host => IP address caching or even socks protocol support. |
226 | |
230 | |
… | |
… | |
348 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
352 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
349 | |
353 | |
350 | _slot_schedule $_[0]; |
354 | _slot_schedule $_[0]; |
351 | } |
355 | } |
352 | |
356 | |
|
|
357 | # continue to parse $_ for headers and place them into the arg |
|
|
358 | sub parse_hdr() { |
|
|
359 | my %hdr; |
|
|
360 | |
|
|
361 | # things seen, not parsed: |
|
|
362 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
363 | |
|
|
364 | $hdr{lc $1} .= ",$2" |
|
|
365 | while /\G |
|
|
366 | ([^:\000-\037]*): |
|
|
367 | [\011\040]* |
|
|
368 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
369 | \012 |
|
|
370 | /gxc; |
|
|
371 | |
|
|
372 | /\G$/ |
|
|
373 | or return; |
|
|
374 | |
|
|
375 | # remove the "," prefix we added to all headers above |
|
|
376 | substr $_, 0, 1, "" |
|
|
377 | for values %hdr; |
|
|
378 | |
|
|
379 | \%hdr |
|
|
380 | } |
|
|
381 | |
353 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
382 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
354 | |
383 | |
355 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
384 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
356 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
385 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
357 | |
386 | |
… | |
… | |
376 | my @pseudo = (URL => $url); |
405 | my @pseudo = (URL => $url); |
377 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
406 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
378 | |
407 | |
379 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
408 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
380 | |
409 | |
381 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo }) |
410 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
382 | if $recurse < 0; |
411 | if $recurse < 0; |
383 | |
412 | |
384 | my $proxy = $arg{proxy} || $PROXY; |
413 | my $proxy = $arg{proxy} || $PROXY; |
385 | my $timeout = $arg{timeout} || $TIMEOUT; |
414 | my $timeout = $arg{timeout} || $TIMEOUT; |
386 | |
415 | |
… | |
… | |
389 | |
418 | |
390 | $uscheme = lc $uscheme; |
419 | $uscheme = lc $uscheme; |
391 | |
420 | |
392 | my $uport = $uscheme eq "http" ? 80 |
421 | my $uport = $uscheme eq "http" ? 80 |
393 | : $uscheme eq "https" ? 443 |
422 | : $uscheme eq "https" ? 443 |
394 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo }); |
423 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
395 | |
424 | |
396 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
425 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
397 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo }); |
426 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
398 | |
427 | |
399 | my $uhost = $1; |
428 | my $uhost = $1; |
400 | $uport = $2 if defined $2; |
429 | $uport = $2 if defined $2; |
401 | |
430 | |
402 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
431 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
… | |
… | |
451 | } else { |
480 | } else { |
452 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
481 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
453 | } |
482 | } |
454 | |
483 | |
455 | # leave out fragment and query string, just a heuristic |
484 | # leave out fragment and query string, just a heuristic |
456 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
485 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
457 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
486 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
458 | |
487 | |
459 | $hdr{"content-length"} = length $arg{body} |
488 | $hdr{"content-length"} = length $arg{body} |
460 | if length $arg{body} || $method ne "GET"; |
489 | if length $arg{body} || $method ne "GET"; |
461 | |
490 | |
|
|
491 | $hdr{connection} = "close TE"; |
|
|
492 | $hdr{te} = "trailers" unless exists $hdr{te}; |
|
|
493 | |
462 | my %state = (connect_guard => 1); |
494 | my %state = (connect_guard => 1); |
463 | |
495 | |
464 | _get_slot $uhost, sub { |
496 | _get_slot $uhost, sub { |
465 | $state{slot_guard} = shift; |
497 | $state{slot_guard} = shift; |
466 | |
498 | |
467 | return unless $state{connect_guard}; |
499 | return unless $state{connect_guard}; |
468 | |
500 | |
469 | my $tcp_connect = $arg{tcp_connect} |
501 | my $connect_cb = sub { |
470 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
471 | |
|
|
472 | $state{connect_guard} = $tcp_connect->( |
|
|
473 | $rhost, |
|
|
474 | $rport, |
|
|
475 | sub { |
|
|
476 | $state{fh} = shift |
502 | $state{fh} = shift |
477 | or do { |
503 | or do { |
478 | my $err = "$!"; |
504 | my $err = "$!"; |
479 | %state = (); |
505 | %state = (); |
480 | return $cb->(undef, { Status => 599, Reason => $err, @pseudo }); |
506 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
481 | }; |
507 | }; |
482 | |
508 | |
483 | pop; # free memory, save a tree |
509 | pop; # free memory, save a tree |
484 | |
510 | |
485 | return unless delete $state{connect_guard}; |
511 | return unless delete $state{connect_guard}; |
486 | |
512 | |
487 | # get handle |
513 | # get handle |
488 | $state{handle} = new AnyEvent::Handle |
514 | $state{handle} = new AnyEvent::Handle |
489 | fh => $state{fh}, |
515 | fh => $state{fh}, |
490 | peername => $rhost, |
516 | peername => $rhost, |
491 | tls_ctx => $arg{tls_ctx}, |
517 | tls_ctx => $arg{tls_ctx}, |
492 | # these need to be reconfigured on keepalive handles |
518 | # these need to be reconfigured on keepalive handles |
493 | timeout => $timeout, |
519 | timeout => $timeout, |
494 | on_error => sub { |
520 | on_error => sub { |
495 | %state = (); |
521 | %state = (); |
496 | $cb->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
522 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
497 | }, |
523 | }, |
498 | on_eof => sub { |
524 | on_eof => sub { |
499 | %state = (); |
525 | %state = (); |
500 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo }); |
526 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
501 | }, |
527 | }, |
502 | ; |
528 | ; |
503 | |
529 | |
504 | # limit the number of persistent connections |
530 | # limit the number of persistent connections |
505 | # keepalive not yet supported |
531 | # keepalive not yet supported |
506 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
532 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
507 | # ++$KA_COUNT{$_[1]}; |
533 | # ++$KA_COUNT{$_[1]}; |
508 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
534 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
509 | # --$KA_COUNT{$_[1]} |
535 | # --$KA_COUNT{$_[1]} |
510 | # }; |
536 | # }; |
511 | # $hdr{connection} = "keep-alive"; |
537 | # $hdr{connection} = "keep-alive"; |
512 | # } else { |
538 | # } else { |
513 | delete $hdr{connection}; |
539 | # delete $hdr{connection}; |
514 | # } |
540 | # } |
515 | |
541 | |
516 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
542 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
517 | |
543 | |
518 | # handle actual, non-tunneled, request |
544 | # handle actual, non-tunneled, request |
519 | my $handle_actual_request = sub { |
545 | my $handle_actual_request = sub { |
520 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
546 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
521 | |
547 | |
522 | # send request |
548 | # send request |
523 | $state{handle}->push_write ( |
549 | $state{handle}->push_write ( |
524 | "$method $rpath HTTP/1.0\015\012" |
550 | "$method $rpath HTTP/1.1\015\012" |
525 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
551 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
526 | . "\015\012" |
552 | . "\015\012" |
527 | . (delete $arg{body}) |
553 | . (delete $arg{body}) |
528 | ); |
554 | ); |
529 | |
555 | |
530 | # return if error occured during push_write() |
556 | # return if error occured during push_write() |
531 | return unless %state; |
557 | return unless %state; |
532 | |
558 | |
533 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
559 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
534 | |
560 | |
535 | # status line and headers |
561 | # status line and headers |
536 | $state{handle}->push_read (line => $qr_nlnl, sub { |
562 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
563 | my $keepalive = pop; |
|
|
564 | |
537 | for ("$_[1]") { |
565 | for ("$_[1]") { |
538 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
566 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
539 | |
567 | |
540 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
568 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
541 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo })); |
569 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
542 | |
570 | |
543 | push @pseudo, |
571 | push @pseudo, |
544 | HTTPVersion => $1, |
572 | HTTPVersion => $1, |
545 | Status => $2, |
573 | Status => $2, |
546 | Reason => $3, |
574 | Reason => $3, |
547 | ; |
575 | ; |
548 | |
576 | |
549 | # things seen, not parsed: |
577 | my $hdr = parse_hdr |
550 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
551 | |
|
|
552 | $hdr{lc $1} .= ",$2" |
|
|
553 | while /\G |
|
|
554 | ([^:\000-\037]*): |
|
|
555 | [\011\040]* |
|
|
556 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
557 | \012 |
|
|
558 | /gxc; |
|
|
559 | |
|
|
560 | /\G$/ |
|
|
561 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo })); |
578 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
579 | |
|
|
580 | %hdr = (%$hdr, @pseudo); |
|
|
581 | } |
|
|
582 | |
|
|
583 | # redirect handling |
|
|
584 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
585 | # try to support some common forms of broken Location headers. |
|
|
586 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
587 | $hdr{location} =~ s/^\.\/+//; |
|
|
588 | |
|
|
589 | my $url = "$rscheme://$uhost:$uport"; |
|
|
590 | |
|
|
591 | unless ($hdr{location} =~ s/^\///) { |
|
|
592 | $url .= $upath; |
|
|
593 | $url =~ s/\/[^\/]*$//; |
562 | } |
594 | } |
563 | |
595 | |
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 | $url =~ s/\/[^\/]*$//; |
|
|
582 | } |
|
|
583 | |
|
|
584 | $hdr{location} = "$url/$hdr{location}"; |
596 | $hdr{location} = "$url/$hdr{location}"; |
|
|
597 | } |
|
|
598 | |
|
|
599 | my $redirect; |
|
|
600 | |
|
|
601 | if ($recurse) { |
|
|
602 | my $status = $hdr{Status}; |
|
|
603 | |
|
|
604 | # industry standard is to redirect POST as GET for |
|
|
605 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
606 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
607 | # industry standard seems to be to simply follow. |
|
|
608 | # we go with the industry standard. |
|
|
609 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
610 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
611 | $method = "GET" unless $method eq "HEAD"; |
|
|
612 | $redirect = 1; |
|
|
613 | } elsif ($status == 307) { |
|
|
614 | $redirect = 1; |
585 | } |
615 | } |
|
|
616 | } |
586 | |
617 | |
587 | my $redirect; |
618 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
619 | $state{handle}->destroy if $state{handle}; |
|
|
620 | %state = (); |
588 | |
621 | |
|
|
622 | if (defined $_[1]) { |
|
|
623 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
624 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
625 | } |
|
|
626 | |
|
|
627 | # set-cookie processing |
589 | if ($recurse) { |
628 | if ($arg{cookie_jar}) { |
590 | my $status = $hdr{Status}; |
629 | for ($hdr{"set-cookie"}) { |
|
|
630 | # parse NAME=VALUE |
|
|
631 | my @kv; |
591 | |
632 | |
592 | # industry standard is to redirect POST as GET for |
633 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
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; |
634 | my $name = $1; |
601 | } elsif ($status == 307) { |
635 | my $value = $3; |
|
|
636 | |
|
|
637 | unless ($value) { |
|
|
638 | $value = $2; |
|
|
639 | $value =~ s/\\(.)/$1/gs; |
|
|
640 | } |
|
|
641 | |
|
|
642 | push @kv, $name => $value; |
|
|
643 | |
|
|
644 | last unless /\G\s*;/gc; |
|
|
645 | } |
|
|
646 | |
|
|
647 | last unless @kv; |
|
|
648 | |
|
|
649 | my $name = shift @kv; |
|
|
650 | my %kv = (value => shift @kv, @kv); |
|
|
651 | |
|
|
652 | my $cdom; |
|
|
653 | my $cpath = (delete $kv{path}) || "/"; |
|
|
654 | |
|
|
655 | if (exists $kv{domain}) { |
|
|
656 | $cdom = delete $kv{domain}; |
|
|
657 | |
|
|
658 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
659 | |
|
|
660 | next if $cdom =~ /\.$/; |
|
|
661 | |
|
|
662 | # this is not rfc-like and not netscape-like. go figure. |
|
|
663 | my $ndots = $cdom =~ y/.//; |
|
|
664 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
665 | } else { |
|
|
666 | $cdom = $uhost; |
|
|
667 | } |
|
|
668 | |
602 | $redirect = 1; |
669 | # store it |
|
|
670 | $arg{cookie_jar}{version} = 1; |
|
|
671 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
672 | |
|
|
673 | redo if /\G\s*,/gc; |
603 | } |
674 | } |
604 | } |
675 | } |
605 | |
676 | |
606 | my $finish = sub { |
|
|
607 | $state{handle}->destroy if $state{handle}; |
|
|
608 | %state = (); |
|
|
609 | |
|
|
610 | # set-cookie processing |
|
|
611 | if ($arg{cookie_jar}) { |
|
|
612 | for ($_[1]{"set-cookie"}) { |
|
|
613 | # parse NAME=VALUE |
|
|
614 | my @kv; |
|
|
615 | |
|
|
616 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
617 | my $name = $1; |
|
|
618 | my $value = $3; |
|
|
619 | |
|
|
620 | unless ($value) { |
|
|
621 | $value = $2; |
|
|
622 | $value =~ s/\\(.)/$1/gs; |
|
|
623 | } |
|
|
624 | |
|
|
625 | push @kv, $name => $value; |
|
|
626 | |
|
|
627 | last unless /\G\s*;/gc; |
|
|
628 | } |
|
|
629 | |
|
|
630 | last unless @kv; |
|
|
631 | |
|
|
632 | my $name = shift @kv; |
|
|
633 | my %kv = (value => shift @kv, @kv); |
|
|
634 | |
|
|
635 | my $cdom; |
|
|
636 | my $cpath = (delete $kv{path}) || "/"; |
|
|
637 | |
|
|
638 | if (exists $kv{domain}) { |
|
|
639 | $cdom = delete $kv{domain}; |
|
|
640 | |
|
|
641 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
642 | |
|
|
643 | next if $cdom =~ /\.$/; |
|
|
644 | |
|
|
645 | # this is not rfc-like and not netscape-like. go figure. |
|
|
646 | my $ndots = $cdom =~ y/.//; |
|
|
647 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
648 | } else { |
|
|
649 | $cdom = $uhost; |
|
|
650 | } |
|
|
651 | |
|
|
652 | # store it |
|
|
653 | $arg{cookie_jar}{version} = 1; |
|
|
654 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
655 | |
|
|
656 | redo if /\G\s*,/gc; |
|
|
657 | } |
|
|
658 | } |
|
|
659 | |
|
|
660 | if ($redirect && exists $hdr{location}) { |
677 | if ($redirect && exists $hdr{location}) { |
661 | # we ignore any errors, as it is very common to receive |
678 | # we ignore any errors, as it is very common to receive |
662 | # Content-Length != 0 but no actual body |
679 | # Content-Length != 0 but no actual body |
663 | # we also access %hdr, as $_[1] might be an erro |
680 | # we also access %hdr, as $_[1] might be an erro |
664 | http_request ( |
681 | http_request ( |
665 | $method => $hdr{location}, |
682 | $method => $hdr{location}, |
666 | %arg, |
683 | %arg, |
667 | recurse => $recurse - 1, |
684 | recurse => $recurse - 1, |
668 | Redirect => \@_, |
685 | Redirect => [$_[0], \%hdr], |
669 | $cb); |
686 | $cb); |
670 | } else { |
|
|
671 | $cb->($_[0], $_[1]); |
|
|
672 | } |
|
|
673 | }; |
|
|
674 | |
|
|
675 | my $len = $hdr{"content-length"}; |
|
|
676 | |
|
|
677 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
678 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo }); |
|
|
679 | } elsif ( |
|
|
680 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
681 | or $method eq "HEAD" |
|
|
682 | or (defined $len && !$len) |
|
|
683 | ) { |
|
|
684 | # no body |
|
|
685 | $finish->("", \%hdr); |
|
|
686 | } else { |
687 | } else { |
|
|
688 | $cb->($_[0], \%hdr); |
|
|
689 | } |
|
|
690 | }; |
|
|
691 | |
|
|
692 | my $len = $hdr{"content-length"}; |
|
|
693 | |
|
|
694 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
695 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
696 | } elsif ( |
|
|
697 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
698 | or $method eq "HEAD" |
|
|
699 | or (defined $len && !$len) |
|
|
700 | ) { |
|
|
701 | # no body |
|
|
702 | $finish->("", undef, undef, 1); |
|
|
703 | } else { |
687 | # body handling, four different code paths |
704 | # body handling, many different code paths |
688 | # for want_body_handle, on_body (2x), normal (2x) |
705 | # - no body expected |
689 | # we might read too much here, but it does not matter yet (no pers. connections) |
706 | # - want_body_handle |
|
|
707 | # - te chunked |
|
|
708 | # - 2x length known (with or without on_body) |
|
|
709 | # - 2x length not known (with or without on_body) |
690 | if (!$redirect && $arg{want_body_handle}) { |
710 | if (!$redirect && $arg{want_body_handle}) { |
691 | $_[0]->on_eof (undef); |
711 | $_[0]->on_eof (undef); |
692 | $_[0]->on_error (undef); |
712 | $_[0]->on_error (undef); |
693 | $_[0]->on_read (undef); |
713 | $_[0]->on_read (undef); |
694 | |
714 | |
695 | $finish->(delete $state{handle}, \%hdr); |
715 | $finish->(delete $state{handle}); |
696 | |
716 | |
697 | } elsif ($arg{on_body}) { |
717 | } elsif ($hdr{"transfer-encoding"} =~ /chunked/) { |
|
|
718 | my $body = undef; |
|
|
719 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
720 | |
698 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
721 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
722 | |
|
|
723 | my $read_chunk; $read_chunk = sub { |
|
|
724 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
725 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
726 | |
|
|
727 | my $len = hex $1; |
|
|
728 | |
699 | if ($len) { |
729 | if ($len) { |
700 | $_[0]->on_eof (undef); |
730 | $_[0]->push_read (chunk => hex $1, sub { |
|
|
731 | $on_body->($_[1], \%hdr) |
|
|
732 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
733 | |
701 | $_[0]->on_read (sub { |
734 | $_[0]->push_read (line => sub { |
702 | $len -= length $_[0]{rbuf}; |
735 | length $_[1] |
703 | |
736 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
704 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
737 | $_[0]->push_read (line => $read_chunk); |
705 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
706 | |
|
|
707 | $len > 0 |
738 | }); |
708 | or $finish->("", \%hdr); |
|
|
709 | }); |
739 | }); |
710 | } else { |
740 | } else { |
711 | $_[0]->on_eof (sub { |
741 | $_[0]->push_read (line => $qr_nlnl, sub { |
712 | $finish->("", \%hdr); |
742 | if (length $_[1]) { |
|
|
743 | for ("$_[1]") { |
|
|
744 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
745 | |
|
|
746 | my $hdr = parse_hdr |
|
|
747 | or return $finish->(undef, 599 => "Garbled response trailers"); |
|
|
748 | |
|
|
749 | %hdr = (%hdr, %$hdr); |
|
|
750 | } |
713 | }); |
751 | } |
714 | $_[0]->on_read (sub { |
752 | |
715 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
753 | $finish->($body, undef, undef, 1); |
716 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
717 | }); |
754 | }); |
718 | } |
755 | } |
|
|
756 | }; |
|
|
757 | |
|
|
758 | $_[0]->push_read (line => $read_chunk); |
|
|
759 | |
|
|
760 | } elsif ($arg{on_body}) { |
|
|
761 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
762 | |
|
|
763 | if ($len) { |
|
|
764 | $_[0]->on_read (sub { |
|
|
765 | $len -= length $_[0]{rbuf}; |
|
|
766 | |
|
|
767 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
768 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
769 | |
|
|
770 | $len > 0 |
|
|
771 | or $finish->("", undef, undef, 1); |
|
|
772 | }); |
719 | } else { |
773 | } else { |
720 | $_[0]->on_eof (undef); |
774 | $_[0]->on_eof (sub { |
721 | |
775 | $finish->(""); |
722 | if ($len) { |
776 | }); |
723 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
|
|
724 | $_[0]->on_read (sub { |
777 | $_[0]->on_read (sub { |
|
|
778 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
779 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
780 | }); |
|
|
781 | } |
|
|
782 | } else { |
|
|
783 | $_[0]->on_eof (undef); |
|
|
784 | |
|
|
785 | if ($len) { |
|
|
786 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
787 | $_[0]->on_read (sub { |
725 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
788 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
726 | if $len <= length $_[0]{rbuf}; |
789 | if $len <= length $_[0]{rbuf}; |
727 | }); |
790 | }); |
728 | } else { |
791 | } else { |
729 | $_[0]->on_error (sub { |
792 | $_[0]->on_error (sub { |
730 | ($! == Errno::EPIPE || !$!) |
793 | ($! == Errno::EPIPE || !$!) |
731 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
794 | ? $finish->(delete $_[0]{rbuf}) |
732 | : $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
795 | : $finish->(undef, 599 => $_[2]); |
733 | }); |
796 | }); |
734 | $_[0]->on_read (sub { }); |
797 | $_[0]->on_read (sub { }); |
735 | } |
|
|
736 | } |
798 | } |
737 | } |
799 | } |
738 | }); |
800 | } |
739 | }; |
801 | }); |
|
|
802 | }; |
740 | |
803 | |
741 | # now handle proxy-CONNECT method |
804 | # now handle proxy-CONNECT method |
742 | if ($proxy && $uscheme eq "https") { |
805 | if ($proxy && $uscheme eq "https") { |
743 | # oh dear, we have to wrap it into a connect request |
806 | # oh dear, we have to wrap it into a connect request |
744 | |
807 | |
745 | # maybe re-use $uauthority with patched port? |
808 | # maybe re-use $uauthority with patched port? |
746 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
809 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
747 | $state{handle}->push_read (line => $qr_nlnl, sub { |
810 | $state{handle}->push_read (line => $qr_nlnl, sub { |
748 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
811 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
749 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo })); |
812 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
750 | |
813 | |
751 | if ($2 == 200) { |
814 | if ($2 == 200) { |
752 | $rpath = $upath; |
815 | $rpath = $upath; |
753 | &$handle_actual_request; |
816 | &$handle_actual_request; |
754 | } else { |
817 | } else { |
755 | %state = (); |
818 | %state = (); |
756 | $cb->(undef, { Status => $2, Reason => $3, @pseudo }); |
819 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
757 | } |
|
|
758 | }); |
820 | } |
|
|
821 | }); |
759 | } else { |
822 | } else { |
760 | &$handle_actual_request; |
823 | &$handle_actual_request; |
761 | } |
|
|
762 | |
|
|
763 | }, |
824 | } |
764 | $arg{on_prepare} || sub { $timeout } |
|
|
765 | ); |
825 | }; |
|
|
826 | |
|
|
827 | my $tcp_connect = $arg{tcp_connect} |
|
|
828 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
829 | |
|
|
830 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
831 | |
766 | }; |
832 | }; |
767 | |
833 | |
768 | defined wantarray && AnyEvent::Util::guard { %state = () } |
834 | defined wantarray && AnyEvent::Util::guard { %state = () } |
769 | } |
835 | } |
770 | |
836 | |
… | |
… | |
805 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
871 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
806 | otherwise. |
872 | otherwise. |
807 | |
873 | |
808 | To clear an already-set proxy, use C<undef>. |
874 | To clear an already-set proxy, use C<undef>. |
809 | |
875 | |
|
|
876 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
877 | |
|
|
878 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
879 | Date (RFC 2616). |
|
|
880 | |
|
|
881 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
882 | |
|
|
883 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
|
|
884 | timestamp, or C<undef> if the date cannot be parsed. |
|
|
885 | |
810 | =item $AnyEvent::HTTP::MAX_RECURSE |
886 | =item $AnyEvent::HTTP::MAX_RECURSE |
811 | |
887 | |
812 | The default value for the C<recurse> request parameter (default: C<10>). |
888 | The default value for the C<recurse> request parameter (default: C<10>). |
813 | |
889 | |
814 | =item $AnyEvent::HTTP::USERAGENT |
890 | =item $AnyEvent::HTTP::USERAGENT |
… | |
… | |
832 | connections. This number of can be useful for load-leveling. |
908 | connections. This number of can be useful for load-leveling. |
833 | |
909 | |
834 | =back |
910 | =back |
835 | |
911 | |
836 | =cut |
912 | =cut |
|
|
913 | |
|
|
914 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
915 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
916 | |
|
|
917 | sub format_date($) { |
|
|
918 | my ($time) = @_; |
|
|
919 | |
|
|
920 | # RFC 822/1123 format |
|
|
921 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
922 | |
|
|
923 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
924 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
925 | $H, $M, $S; |
|
|
926 | } |
|
|
927 | |
|
|
928 | sub parse_date($) { |
|
|
929 | my ($date) = @_; |
|
|
930 | |
|
|
931 | my ($d, $m, $y, $H, $M, $S); |
|
|
932 | |
|
|
933 | if ($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$/) { |
|
|
934 | # RFC 822/1123, required by RFC 2616 |
|
|
935 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
936 | |
|
|
937 | } elsif ($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$/) { |
|
|
938 | # RFC 850 |
|
|
939 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
940 | |
|
|
941 | } elsif ($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])$/) { |
|
|
942 | # ISO C's asctime |
|
|
943 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
944 | } |
|
|
945 | # other formats fail in the loop below |
|
|
946 | |
|
|
947 | for (0..11) { |
|
|
948 | if ($m eq $month[$_]) { |
|
|
949 | require Time::Local; |
|
|
950 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
951 | } |
|
|
952 | } |
|
|
953 | |
|
|
954 | undef |
|
|
955 | } |
837 | |
956 | |
838 | sub set_proxy($) { |
957 | sub set_proxy($) { |
839 | if (length $_[0]) { |
958 | if (length $_[0]) { |
840 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
959 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
841 | or Carp::croak "$_[0]: invalid proxy URL"; |
960 | or Carp::croak "$_[0]: invalid proxy URL"; |
… | |
… | |
848 | # initialise proxy from environment |
967 | # initialise proxy from environment |
849 | eval { |
968 | eval { |
850 | set_proxy $ENV{http_proxy}; |
969 | set_proxy $ENV{http_proxy}; |
851 | }; |
970 | }; |
852 | |
971 | |
|
|
972 | =head2 SOCKS PROXIES |
|
|
973 | |
|
|
974 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
975 | compile your perl to support socks, or use an external program such as |
|
|
976 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
977 | transparently. |
|
|
978 | |
|
|
979 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
980 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
981 | that works with socks4a proxies: |
|
|
982 | |
|
|
983 | use Errno; |
|
|
984 | use AnyEvent::Util; |
|
|
985 | use AnyEvent::Socket; |
|
|
986 | use AnyEvent::Handle; |
|
|
987 | |
|
|
988 | # host, port and username of/for your socks4a proxy |
|
|
989 | my $socks_host = "10.0.0.23"; |
|
|
990 | my $socks_port = 9050; |
|
|
991 | my $socks_user = ""; |
|
|
992 | |
|
|
993 | sub socks4a_connect { |
|
|
994 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
995 | |
|
|
996 | my $hdl = new AnyEvent::Handle |
|
|
997 | connect => [$socks_host, $socks_port], |
|
|
998 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
999 | on_error => sub { $connect_cb->() }, |
|
|
1000 | ; |
|
|
1001 | |
|
|
1002 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1003 | |
|
|
1004 | $hdl->push_read (chunk => 8, sub { |
|
|
1005 | my ($hdl, $chunk) = @_; |
|
|
1006 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1007 | |
|
|
1008 | if ($status == 0x5a) { |
|
|
1009 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1010 | } else { |
|
|
1011 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1012 | } |
|
|
1013 | }); |
|
|
1014 | |
|
|
1015 | $hdl |
|
|
1016 | } |
|
|
1017 | |
|
|
1018 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1019 | possibly after switching off other proxy types: |
|
|
1020 | |
|
|
1021 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1022 | |
|
|
1023 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1024 | my ($data, $headers) = @_; |
|
|
1025 | ... |
|
|
1026 | }; |
|
|
1027 | |
853 | =head1 SEE ALSO |
1028 | =head1 SEE ALSO |
854 | |
1029 | |
855 | L<AnyEvent>. |
1030 | L<AnyEvent>. |
856 | |
1031 | |
857 | =head1 AUTHOR |
1032 | =head1 AUTHOR |