… | |
… | |
122 | |
122 | |
123 | 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 |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
125 | |
125 | |
126 | 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, |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
128 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
128 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
129 | message. |
129 | message. Currently the following status codes are used: |
|
|
130 | |
|
|
131 | =over 4 |
|
|
132 | |
|
|
133 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
134 | |
|
|
135 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
136 | |
|
|
137 | =item 597 - errors during body receiving or processing. |
|
|
138 | |
|
|
139 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
140 | |
|
|
141 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
142 | |
|
|
143 | =back |
130 | |
144 | |
131 | A typical callback might look like this: |
145 | A typical callback might look like this: |
132 | |
146 | |
133 | sub { |
147 | sub { |
134 | my ($body, $hdr) = @_; |
148 | my ($body, $hdr) = @_; |
… | |
… | |
182 | =item cookie_jar => $hash_ref |
196 | =item cookie_jar => $hash_ref |
183 | |
197 | |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
198 | Passing this parameter enables (simplified) cookie-processing, loosely |
185 | based on the original netscape specification. |
199 | based on the original netscape specification. |
186 | |
200 | |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
201 | The C<$hash_ref> must be an (initially empty) hash reference which |
188 | get updated automatically. It is possible to save the cookie jar to |
202 | will get updated automatically. It is possible to save the cookie jar |
189 | persistent storage with something like JSON or Storable, but this is not |
203 | to persistent storage with something like JSON or Storable - see the |
190 | recommended, as session-only cookies might survive longer than expected. |
204 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
205 | expired or session-only cookies, and also for documentation on the format |
|
|
206 | of the cookie jar. |
191 | |
207 | |
192 | Note that this cookie implementation is not meant to be complete. If |
208 | Note that this cookie implementation is not meant to be complete. If |
193 | you want complete cookie management you have to do that on your |
209 | you want complete cookie management you have to do that on your |
194 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
210 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
195 | working. Cookies are a privacy disaster, do not use them unless required |
211 | working. Cookies are a privacy disaster, do not use them unless required |
196 | to. |
212 | to. |
197 | |
213 | |
198 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
214 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
199 | headers will be set and handled by this module, otherwise they will be |
215 | headers will be set and handled by this module, otherwise they will be |
… | |
… | |
364 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
380 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
365 | |
381 | |
366 | _slot_schedule $_[0]; |
382 | _slot_schedule $_[0]; |
367 | } |
383 | } |
368 | |
384 | |
|
|
385 | ############################################################################# |
|
|
386 | |
|
|
387 | # expire cookies |
|
|
388 | sub cookie_jar_expire($;$) { |
|
|
389 | my ($jar, $session_end) = @_; |
|
|
390 | |
|
|
391 | %$jar = () if $jar->{version} != 1; |
|
|
392 | |
|
|
393 | my $anow = AE::now; |
|
|
394 | |
|
|
395 | while (my ($chost, $paths) = each %$jar) { |
|
|
396 | next unless ref $paths; |
|
|
397 | |
|
|
398 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
399 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
400 | if (exists $kv->{_expires}) { |
|
|
401 | delete $cookies->{$cookie} |
|
|
402 | if $anow > $kv->{_expires}; |
|
|
403 | } elsif ($session_end) { |
|
|
404 | delete $cookies->{$cookie}; |
|
|
405 | } |
|
|
406 | } |
|
|
407 | |
|
|
408 | delete $paths->{$cpath} |
|
|
409 | unless %$cookies; |
|
|
410 | } |
|
|
411 | |
|
|
412 | delete $jar->{$chost} |
|
|
413 | unless %$paths; |
|
|
414 | } |
|
|
415 | } |
|
|
416 | |
369 | # extract cookies from jar |
417 | # extract cookies from jar |
370 | sub cookie_jar_extract($$$$) { |
418 | sub cookie_jar_extract($$$$) { |
371 | my ($jar, $uscheme, $uhost, $upath) = @_; |
419 | my ($jar, $uscheme, $uhost, $upath) = @_; |
372 | |
420 | |
373 | %$jar = () if $jar->{version} != 1; |
421 | %$jar = () if $jar->{version} != 1; |
… | |
… | |
389 | next unless $cpath eq substr $upath, 0, length $cpath; |
437 | next unless $cpath eq substr $upath, 0, length $cpath; |
390 | |
438 | |
391 | while (my ($cookie, $kv) = each %$cookies) { |
439 | while (my ($cookie, $kv) = each %$cookies) { |
392 | next if $uscheme ne "https" && exists $kv->{secure}; |
440 | next if $uscheme ne "https" && exists $kv->{secure}; |
393 | |
441 | |
394 | if (exists $kv->{expires}) { |
442 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
395 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
396 | delete $cookies->{$cookie}; |
443 | delete $cookies->{$cookie}; |
397 | next; |
444 | next; |
398 | } |
|
|
399 | } |
445 | } |
400 | |
446 | |
401 | my $value = $kv->{value}; |
447 | my $value = $kv->{value}; |
402 | |
448 | |
403 | if ($value =~ /[=;,[:space:]]/) { |
449 | if ($value =~ /[=;,[:space:]]/) { |
… | |
… | |
412 | |
458 | |
413 | \@cookies |
459 | \@cookies |
414 | } |
460 | } |
415 | |
461 | |
416 | # parse set_cookie header into jar |
462 | # parse set_cookie header into jar |
417 | sub cookie_jar_set_cookie($$$) { |
463 | sub cookie_jar_set_cookie($$$$) { |
418 | my ($jar, $set_cookie, $uhost) = @_; |
464 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
465 | |
|
|
466 | my $anow = int AE::now; |
|
|
467 | my $snow; # server-now |
419 | |
468 | |
420 | for ($set_cookie) { |
469 | for ($set_cookie) { |
421 | # parse NAME=VALUE |
470 | # parse NAME=VALUE |
422 | my @kv; |
471 | my @kv; |
423 | |
472 | |
|
|
473 | # expires is not http-compliant in the original cookie-spec, |
|
|
474 | # we support the official date format and some extensions |
424 | while ( |
475 | while ( |
425 | m{ |
476 | m{ |
426 | \G\s* |
477 | \G\s* |
427 | (?: |
478 | (?: |
428 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
479 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
429 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
480 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
430 | ) |
481 | ) |
431 | }gcxsi |
482 | }gcxsi |
432 | ) { |
483 | ) { |
433 | my $name = $2; |
484 | my $name = $2; |
… | |
… | |
451 | last unless @kv; |
502 | last unless @kv; |
452 | |
503 | |
453 | my $name = shift @kv; |
504 | my $name = shift @kv; |
454 | my %kv = (value => shift @kv, @kv); |
505 | my %kv = (value => shift @kv, @kv); |
455 | |
506 | |
456 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
457 | if exists $kv{"max-age"}; |
507 | if (exists $kv{"max-age"}) { |
|
|
508 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
509 | } elsif (exists $kv{expires}) { |
|
|
510 | $snow ||= parse_date ($date) || $anow; |
|
|
511 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
512 | } else { |
|
|
513 | delete $kv{_expires}; |
|
|
514 | } |
458 | |
515 | |
459 | my $cdom; |
516 | my $cdom; |
460 | my $cpath = (delete $kv{path}) || "/"; |
517 | my $cpath = (delete $kv{path}) || "/"; |
461 | |
518 | |
462 | if (exists $kv{domain}) { |
519 | if (exists $kv{domain}) { |
… | |
… | |
600 | _get_slot $uhost, sub { |
657 | _get_slot $uhost, sub { |
601 | $state{slot_guard} = shift; |
658 | $state{slot_guard} = shift; |
602 | |
659 | |
603 | return unless $state{connect_guard}; |
660 | return unless $state{connect_guard}; |
604 | |
661 | |
|
|
662 | my $ae_error = 595; # connecting |
|
|
663 | |
605 | my $connect_cb = sub { |
664 | my $connect_cb = sub { |
606 | $state{fh} = shift |
665 | $state{fh} = shift |
607 | or do { |
666 | or do { |
608 | my $err = "$!"; |
667 | my $err = "$!"; |
609 | %state = (); |
668 | %state = (); |
610 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
669 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
611 | }; |
670 | }; |
612 | |
|
|
613 | pop; # free memory, save a tree |
|
|
614 | |
671 | |
615 | return unless delete $state{connect_guard}; |
672 | return unless delete $state{connect_guard}; |
616 | |
673 | |
617 | # get handle |
674 | # get handle |
618 | $state{handle} = new AnyEvent::Handle |
675 | $state{handle} = new AnyEvent::Handle |
… | |
… | |
621 | tls_ctx => $arg{tls_ctx}, |
678 | tls_ctx => $arg{tls_ctx}, |
622 | # these need to be reconfigured on keepalive handles |
679 | # these need to be reconfigured on keepalive handles |
623 | timeout => $timeout, |
680 | timeout => $timeout, |
624 | on_error => sub { |
681 | on_error => sub { |
625 | %state = (); |
682 | %state = (); |
626 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
683 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
627 | }, |
684 | }, |
628 | on_eof => sub { |
685 | on_eof => sub { |
629 | %state = (); |
686 | %state = (); |
630 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
687 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
631 | }, |
688 | }, |
632 | ; |
689 | ; |
633 | |
690 | |
634 | # limit the number of persistent connections |
691 | # limit the number of persistent connections |
635 | # keepalive not yet supported |
692 | # keepalive not yet supported |
… | |
… | |
643 | |
700 | |
644 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
701 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
645 | |
702 | |
646 | # handle actual, non-tunneled, request |
703 | # handle actual, non-tunneled, request |
647 | my $handle_actual_request = sub { |
704 | my $handle_actual_request = sub { |
|
|
705 | $ae_error = 596; # request phase |
|
|
706 | |
648 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
707 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
649 | |
708 | |
650 | # send request |
709 | # send request |
651 | $state{handle}->push_write ( |
710 | $state{handle}->push_write ( |
652 | "$method $rpath HTTP/1.1\015\012" |
711 | "$method $rpath HTTP/1.1\015\012" |
… | |
… | |
663 | # status line and headers |
722 | # status line and headers |
664 | $state{read_response} = sub { |
723 | $state{read_response} = sub { |
665 | for ("$_[1]") { |
724 | for ("$_[1]") { |
666 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
725 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
667 | |
726 | |
668 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
727 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
669 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
728 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
670 | |
729 | |
671 | # 100 Continue handling |
730 | # 100 Continue handling |
672 | # should not happen as we don't send expect: 100-continue, |
731 | # should not happen as we don't send expect: 100-continue, |
673 | # but we handle it just in case. |
732 | # but we handle it just in case. |
… | |
… | |
708 | |
767 | |
709 | if ($recurse) { |
768 | if ($recurse) { |
710 | my $status = $hdr{Status}; |
769 | my $status = $hdr{Status}; |
711 | |
770 | |
712 | # industry standard is to redirect POST as GET for |
771 | # industry standard is to redirect POST as GET for |
713 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
772 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
714 | # also, the UA should ask the user for 301 and 307 and POST, |
773 | # also, the UA should ask the user for 301 and 307 and POST, |
715 | # industry standard seems to be to simply follow. |
774 | # industry standard seems to be to simply follow. |
716 | # we go with the industry standard. |
775 | # we go with the industry standard. |
717 | if ($status == 301 or $status == 302 or $status == 303) { |
776 | if ($status == 301 or $status == 302 or $status == 303) { |
718 | # HTTP/1.1 is unclear on how to mutate the method |
777 | # HTTP/1.1 is unclear on how to mutate the method |
… | |
… | |
734 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
793 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
735 | } |
794 | } |
736 | |
795 | |
737 | # set-cookie processing |
796 | # set-cookie processing |
738 | if ($arg{cookie_jar}) { |
797 | if ($arg{cookie_jar}) { |
739 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost; |
798 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
740 | } |
799 | } |
741 | |
800 | |
742 | if ($redirect && exists $hdr{location}) { |
801 | if ($redirect && exists $hdr{location}) { |
743 | # we ignore any errors, as it is very common to receive |
802 | # we ignore any errors, as it is very common to receive |
744 | # Content-Length != 0 but no actual body |
803 | # Content-Length != 0 but no actual body |
… | |
… | |
751 | $cb); |
810 | $cb); |
752 | } else { |
811 | } else { |
753 | $cb->($_[0], \%hdr); |
812 | $cb->($_[0], \%hdr); |
754 | } |
813 | } |
755 | }; |
814 | }; |
|
|
815 | |
|
|
816 | $ae_error = 597; # body phase |
756 | |
817 | |
757 | my $len = $hdr{"content-length"}; |
818 | my $len = $hdr{"content-length"}; |
758 | |
819 | |
759 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
820 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
760 | $finish->(undef, 598 => "Request cancelled by on_header"); |
821 | $finish->(undef, 598 => "Request cancelled by on_header"); |
… | |
… | |
782 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
843 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
783 | my $cl = 0; |
844 | my $cl = 0; |
784 | my $body = undef; |
845 | my $body = undef; |
785 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
846 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
786 | |
847 | |
787 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
788 | |
|
|
789 | my $read_chunk; $read_chunk = sub { |
848 | $state{read_chunk} = sub { |
790 | $_[1] =~ /^([0-9a-fA-F]+)/ |
849 | $_[1] =~ /^([0-9a-fA-F]+)/ |
791 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
850 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
792 | |
851 | |
793 | my $len = hex $1; |
852 | my $len = hex $1; |
794 | |
853 | |
795 | if ($len) { |
854 | if ($len) { |
796 | $cl += $len; |
855 | $cl += $len; |
… | |
… | |
799 | $on_body->($_[1], \%hdr) |
858 | $on_body->($_[1], \%hdr) |
800 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
859 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
801 | |
860 | |
802 | $_[0]->push_read (line => sub { |
861 | $_[0]->push_read (line => sub { |
803 | length $_[1] |
862 | length $_[1] |
804 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
863 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
805 | $_[0]->push_read (line => $read_chunk); |
864 | $_[0]->push_read (line => $state{read_chunk}); |
806 | }); |
865 | }); |
807 | }); |
866 | }); |
808 | } else { |
867 | } else { |
809 | $hdr{"content-length"} ||= $cl; |
868 | $hdr{"content-length"} ||= $cl; |
810 | |
869 | |
… | |
… | |
812 | if (length $_[1]) { |
871 | if (length $_[1]) { |
813 | for ("$_[1]") { |
872 | for ("$_[1]") { |
814 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
873 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
815 | |
874 | |
816 | my $hdr = parse_hdr |
875 | my $hdr = parse_hdr |
817 | or return $finish->(undef, 599 => "Garbled response trailers"); |
876 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
818 | |
877 | |
819 | %hdr = (%hdr, %$hdr); |
878 | %hdr = (%hdr, %$hdr); |
820 | } |
879 | } |
821 | } |
880 | } |
822 | |
881 | |
823 | $finish->($body, undef, undef, 1); |
882 | $finish->($body, undef, undef, 1); |
824 | }); |
883 | }); |
825 | } |
884 | } |
826 | }; |
885 | }; |
827 | |
886 | |
828 | $_[0]->push_read (line => $read_chunk); |
887 | $_[0]->push_read (line => $state{read_chunk}); |
829 | |
888 | |
830 | } elsif ($arg{on_body}) { |
889 | } elsif ($arg{on_body}) { |
831 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
832 | |
|
|
833 | if ($len) { |
890 | if ($len) { |
834 | $_[0]->on_read (sub { |
891 | $_[0]->on_read (sub { |
835 | $len -= length $_[0]{rbuf}; |
892 | $len -= length $_[0]{rbuf}; |
836 | |
893 | |
837 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
894 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
851 | } |
908 | } |
852 | } else { |
909 | } else { |
853 | $_[0]->on_eof (undef); |
910 | $_[0]->on_eof (undef); |
854 | |
911 | |
855 | if ($len) { |
912 | if ($len) { |
856 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
857 | $_[0]->on_read (sub { |
913 | $_[0]->on_read (sub { |
858 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
914 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
859 | if $len <= length $_[0]{rbuf}; |
915 | if $len <= length $_[0]{rbuf}; |
860 | }); |
916 | }); |
861 | } else { |
917 | } else { |
862 | $_[0]->on_error (sub { |
918 | $_[0]->on_error (sub { |
863 | ($! == Errno::EPIPE || !$!) |
919 | ($! == Errno::EPIPE || !$!) |
864 | ? $finish->(delete $_[0]{rbuf}) |
920 | ? $finish->(delete $_[0]{rbuf}) |
865 | : $finish->(undef, 599 => $_[2]); |
921 | : $finish->(undef, $ae_error => $_[2]); |
866 | }); |
922 | }); |
867 | $_[0]->on_read (sub { }); |
923 | $_[0]->on_read (sub { }); |
868 | } |
924 | } |
869 | } |
925 | } |
870 | } |
926 | } |
… | |
… | |
883 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
939 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
884 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
940 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
885 | |
941 | |
886 | if ($2 == 200) { |
942 | if ($2 == 200) { |
887 | $rpath = $upath; |
943 | $rpath = $upath; |
888 | &$handle_actual_request; |
944 | $handle_actual_request->(); |
889 | } else { |
945 | } else { |
890 | %state = (); |
946 | %state = (); |
891 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
947 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
892 | } |
948 | } |
893 | }); |
949 | }); |
894 | } else { |
950 | } else { |
895 | &$handle_actual_request; |
951 | $handle_actual_request->(); |
896 | } |
952 | } |
897 | }; |
953 | }; |
898 | |
954 | |
899 | my $tcp_connect = $arg{tcp_connect} |
955 | my $tcp_connect = $arg{tcp_connect} |
900 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
956 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
943 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
999 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
944 | otherwise. |
1000 | otherwise. |
945 | |
1001 | |
946 | To clear an already-set proxy, use C<undef>. |
1002 | To clear an already-set proxy, use C<undef>. |
947 | |
1003 | |
|
|
1004 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1005 | |
|
|
1006 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1007 | C<$session_end> is given and true, then additionally remove all session |
|
|
1008 | cookies. |
|
|
1009 | |
|
|
1010 | You should call this function (with a true C<$session_end>) before you |
|
|
1011 | save cookies to disk, and you should call this function after loading them |
|
|
1012 | again. If you have a long-running program you can additonally call this |
|
|
1013 | function from time to time. |
|
|
1014 | |
|
|
1015 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1016 | module. It's format is subject to change, but currently it is like this: |
|
|
1017 | |
|
|
1018 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1019 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1020 | hash-references. The key for these inner hash references is the |
|
|
1021 | server path for which this cookie is meant, and the values are again |
|
|
1022 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1023 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1024 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1025 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1026 | expiry timestamp. |
|
|
1027 | |
|
|
1028 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1029 | chance of understanding the above paragraph: |
|
|
1030 | |
|
|
1031 | { |
|
|
1032 | version => 1, |
|
|
1033 | "10.0.0.1" => { |
|
|
1034 | "/" => { |
|
|
1035 | "mythweb_id" => { |
|
|
1036 | _expires => 1293917923, |
|
|
1037 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1038 | }, |
|
|
1039 | }, |
|
|
1040 | }, |
|
|
1041 | } |
|
|
1042 | |
948 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1043 | =item $date = AnyEvent::HTTP::format_date $timestamp |
949 | |
1044 | |
950 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1045 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
951 | Date (RFC 2616). |
1046 | Date (RFC 2616). |
952 | |
1047 | |
953 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1048 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
954 | |
1049 | |
955 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
1050 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
956 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
1051 | bunch of minor variations of those, and returns the corresponding POSIX |
957 | be parsed. |
1052 | timestamp, or C<undef> if the date cannot be parsed. |
958 | |
1053 | |
959 | =item $AnyEvent::HTTP::MAX_RECURSE |
1054 | =item $AnyEvent::HTTP::MAX_RECURSE |
960 | |
1055 | |
961 | The default value for the C<recurse> request parameter (default: C<10>). |
1056 | The default value for the C<recurse> request parameter (default: C<10>). |
962 | |
1057 | |
… | |
… | |
1001 | sub parse_date($) { |
1096 | sub parse_date($) { |
1002 | my ($date) = @_; |
1097 | my ($date) = @_; |
1003 | |
1098 | |
1004 | my ($d, $m, $y, $H, $M, $S); |
1099 | my ($d, $m, $y, $H, $M, $S); |
1005 | |
1100 | |
1006 | if ($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$/) { |
1101 | if ($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$/) { |
1007 | # RFC 822/1123, required by RFC 2616 (with " ") |
1102 | # RFC 822/1123, required by RFC 2616 (with " ") |
1008 | # cookie dates (with "-") |
1103 | # cookie dates (with "-") |
1009 | |
1104 | |
1010 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1105 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1011 | |
1106 | |
1012 | } elsif ($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$/) { |
1107 | } elsif ($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]?) GMT$/) { |
1013 | # RFC 850 |
1108 | # RFC 850 |
1014 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1109 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1015 | |
1110 | |
1016 | } elsif ($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])$/) { |
1111 | } elsif ($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])$/) { |
1017 | # ISO C's asctime |
1112 | # ISO C's asctime |
1018 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1113 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1019 | } |
1114 | } |
1020 | # other formats fail in the loop below |
1115 | # other formats fail in the loop below |
1021 | |
1116 | |