… | |
… | |
152 | |
152 | |
153 | =item headers => hashref |
153 | =item headers => hashref |
154 | |
154 | |
155 | The request headers to use. Currently, C<http_request> may provide its own |
155 | The request headers to use. Currently, C<http_request> may provide its own |
156 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
156 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
157 | will provide defaults for C<TE:>, C<Referer:> and C<User-Agent:> (this can |
157 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
158 | be suppressed by using C<undef> for these headers in which case they won't |
158 | (this can be suppressed by using C<undef> for these headers in which case |
159 | be sent at all). |
159 | they won't be sent at all). |
160 | |
160 | |
161 | =item timeout => $seconds |
161 | =item timeout => $seconds |
162 | |
162 | |
163 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
183 | |
183 | |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
185 | based on the original netscape specification. |
185 | based on the original netscape specification. |
186 | |
186 | |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
188 | get updated automatically. It is possible to save the cookie_jar to |
188 | get updated automatically. It is possible to save the cookie jar to |
189 | persistent storage with something like JSON or Storable, but this is not |
189 | persistent storage with something like JSON or Storable, but this is not |
190 | recommended, as expiry times are currently being ignored. |
190 | recommended, as session-only cookies might survive longer than expected. |
191 | |
191 | |
192 | Note that this cookie implementation is not of very high quality, nor |
192 | Note that this cookie implementation is not meant to be complete. If |
193 | meant to be complete. If you want complete cookie management you have to |
193 | you want complete cookie management you have to do that on your |
194 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
194 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
195 | cookie-using sites working. Cookies are a privacy disaster, do not use |
195 | working. Cookies are a privacy disaster, do not use them unless required |
196 | them unless required to. |
196 | to. |
|
|
197 | |
|
|
198 | 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 |
|
|
200 | left untouched. |
197 | |
201 | |
198 | =item tls_ctx => $scheme | $tls_ctx |
202 | =item tls_ctx => $scheme | $tls_ctx |
199 | |
203 | |
200 | Specifies the AnyEvent::TLS context to be used for https connections. This |
204 | Specifies the AnyEvent::TLS context to be used for https connections. This |
201 | parameter follows the same rules as the C<tls_ctx> parameter to |
205 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
360 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
364 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
361 | |
365 | |
362 | _slot_schedule $_[0]; |
366 | _slot_schedule $_[0]; |
363 | } |
367 | } |
364 | |
368 | |
|
|
369 | sub cookie_jar_extract($$$$) { |
|
|
370 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
371 | |
|
|
372 | %$jar = () if $jar->{version} != 1; |
|
|
373 | |
|
|
374 | my @cookies; |
|
|
375 | |
|
|
376 | while (my ($chost, $paths) = each %$jar) { |
|
|
377 | next unless ref $paths; |
|
|
378 | |
|
|
379 | if ($chost =~ /^\./) { |
|
|
380 | next unless $chost eq substr $uhost, -length $chost; |
|
|
381 | } elsif ($chost =~ /\./) { |
|
|
382 | next unless $chost eq $uhost; |
|
|
383 | } else { |
|
|
384 | next; |
|
|
385 | } |
|
|
386 | |
|
|
387 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
388 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
389 | |
|
|
390 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
391 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
392 | |
|
|
393 | if (exists $kv->{expires}) { |
|
|
394 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
395 | delete $cookies->{$cookie}; |
|
|
396 | next; |
|
|
397 | } |
|
|
398 | } |
|
|
399 | |
|
|
400 | my $value = $kv->{value}; |
|
|
401 | |
|
|
402 | if ($value =~ /[=;,[:space:]]/) { |
|
|
403 | $value =~ s/([\\"])/\\$1/g; |
|
|
404 | $value = "\"$value\""; |
|
|
405 | } |
|
|
406 | |
|
|
407 | push @cookies, "$cookie=$value"; |
|
|
408 | } |
|
|
409 | } |
|
|
410 | } |
|
|
411 | |
|
|
412 | \@cookies |
|
|
413 | } |
|
|
414 | |
365 | # continue to parse $_ for headers and place them into the arg |
415 | # continue to parse $_ for headers and place them into the arg |
366 | sub parse_hdr() { |
416 | sub parse_hdr() { |
367 | my %hdr; |
417 | my %hdr; |
368 | |
418 | |
369 | # things seen, not parsed: |
419 | # things seen, not parsed: |
… | |
… | |
444 | |
494 | |
445 | $upath =~ s%^/?%/%; |
495 | $upath =~ s%^/?%/%; |
446 | |
496 | |
447 | # cookie processing |
497 | # cookie processing |
448 | if (my $jar = $arg{cookie_jar}) { |
498 | if (my $jar = $arg{cookie_jar}) { |
449 | %$jar = () if $jar->{version} != 1; |
499 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
450 | |
500 | |
451 | my @cookie; |
|
|
452 | |
|
|
453 | while (my ($chost, $v) = each %$jar) { |
|
|
454 | if ($chost =~ /^\./) { |
|
|
455 | next unless $chost eq substr $uhost, -length $chost; |
|
|
456 | } elsif ($chost =~ /\./) { |
|
|
457 | next unless $chost eq $uhost; |
|
|
458 | } else { |
|
|
459 | next; |
|
|
460 | } |
|
|
461 | |
|
|
462 | while (my ($cpath, $v) = each %$v) { |
|
|
463 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
464 | |
|
|
465 | while (my ($k, $v) = each %$v) { |
|
|
466 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
467 | my $value = $v->{value}; |
|
|
468 | $value =~ s/([\\"])/\\$1/g; |
|
|
469 | push @cookie, "$k=\"$value\""; |
|
|
470 | } |
|
|
471 | } |
|
|
472 | } |
|
|
473 | |
|
|
474 | $hdr{cookie} = join "; ", @cookie |
501 | $hdr{cookie} = join "; ", @$cookies |
475 | if @cookie; |
502 | if @$cookies; |
476 | } |
503 | } |
477 | |
504 | |
478 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
505 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
479 | |
506 | |
480 | if ($proxy) { |
507 | if ($proxy) { |
… | |
… | |
642 | if ($arg{cookie_jar}) { |
669 | if ($arg{cookie_jar}) { |
643 | for ($hdr{"set-cookie"}) { |
670 | for ($hdr{"set-cookie"}) { |
644 | # parse NAME=VALUE |
671 | # parse NAME=VALUE |
645 | my @kv; |
672 | my @kv; |
646 | |
673 | |
|
|
674 | while ( |
|
|
675 | m{ |
|
|
676 | \G\s* |
|
|
677 | (?: |
|
|
678 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
647 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
679 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
|
|
680 | ) |
|
|
681 | }gcxsi |
|
|
682 | ) { |
648 | my $name = $1; |
683 | my $name = $2; |
649 | my $value = $3; |
684 | my $value = $4; |
650 | |
685 | |
651 | unless ($value) { |
686 | unless (defined $name) { |
|
|
687 | # expires |
|
|
688 | $name = "expires"; |
652 | $value = $2; |
689 | $value = $1; |
|
|
690 | } elsif (!defined $value) { |
|
|
691 | # quoted |
|
|
692 | $value = $3; |
653 | $value =~ s/\\(.)/$1/gs; |
693 | $value =~ s/\\(.)/$1/gs; |
654 | } |
694 | } |
655 | |
695 | |
656 | push @kv, $name => $value; |
696 | push @kv, lc $name, $value; |
657 | |
697 | |
658 | last unless /\G\s*;/gc; |
698 | last unless /\G\s*;/gc; |
659 | } |
699 | } |
660 | |
700 | |
661 | last unless @kv; |
701 | last unless @kv; |
662 | |
702 | |
663 | my $name = shift @kv; |
703 | my $name = shift @kv; |
664 | my %kv = (value => shift @kv, @kv); |
704 | my %kv = (value => shift @kv, @kv); |
|
|
705 | |
|
|
706 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
707 | if exists $kv{"max-age"}; |
665 | |
708 | |
666 | my $cdom; |
709 | my $cdom; |
667 | my $cpath = (delete $kv{path}) || "/"; |
710 | my $cpath = (delete $kv{path}) || "/"; |
668 | |
711 | |
669 | if (exists $kv{domain}) { |
712 | if (exists $kv{domain}) { |
… | |
… | |
899 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
942 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
900 | Date (RFC 2616). |
943 | Date (RFC 2616). |
901 | |
944 | |
902 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
945 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
903 | |
946 | |
904 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
947 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
905 | timestamp, or C<undef> if the date cannot be parsed. |
948 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
|
|
949 | be parsed. |
906 | |
950 | |
907 | =item $AnyEvent::HTTP::MAX_RECURSE |
951 | =item $AnyEvent::HTTP::MAX_RECURSE |
908 | |
952 | |
909 | The default value for the C<recurse> request parameter (default: C<10>). |
953 | The default value for the C<recurse> request parameter (default: C<10>). |
910 | |
954 | |
… | |
… | |
949 | sub parse_date($) { |
993 | sub parse_date($) { |
950 | my ($date) = @_; |
994 | my ($date) = @_; |
951 | |
995 | |
952 | my ($d, $m, $y, $H, $M, $S); |
996 | my ($d, $m, $y, $H, $M, $S); |
953 | |
997 | |
954 | if ($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$/) { |
998 | if ($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$/) { |
955 | # RFC 822/1123, required by RFC 2616 |
999 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1000 | # cookie dates (with "-") |
|
|
1001 | |
956 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1002 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
957 | |
1003 | |
958 | } elsif ($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$/) { |
1004 | } elsif ($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$/) { |
959 | # RFC 850 |
1005 | # RFC 850 |
960 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1006 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |