… | |
… | |
46 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
47 | use AnyEvent::Handle (); |
47 | use AnyEvent::Handle (); |
48 | |
48 | |
49 | use base Exporter::; |
49 | use base Exporter::; |
50 | |
50 | |
51 | our $VERSION = '2.15'; |
51 | our $VERSION = 2.24; |
52 | |
52 | |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | |
54 | |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $MAX_RECURSE = 10; |
56 | our $MAX_RECURSE = 10; |
… | |
… | |
89 | C<http_request> returns a "cancellation guard" - you have to keep the |
89 | C<http_request> returns a "cancellation guard" - you have to keep the |
90 | object at least alive until the callback get called. If the object gets |
90 | object at least alive until the callback get called. If the object gets |
91 | destroyed before the callback is called, the request will be cancelled. |
91 | destroyed before the callback is called, the request will be cancelled. |
92 | |
92 | |
93 | The callback will be called with the response body data as first argument |
93 | The callback will be called with the response body data as first argument |
94 | (or C<undef> if an error occured), and a hash-ref with response headers |
94 | (or C<undef> if an error occurred), and a hash-ref with response headers |
95 | (and trailers) as second argument. |
95 | (and trailers) as second argument. |
96 | |
96 | |
97 | All the headers in that hash are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
98 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
98 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
99 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
99 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
… | |
… | |
123 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
123 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
124 | message. Currently the following status codes are used: |
124 | message. Currently the following status codes are used: |
125 | |
125 | |
126 | =over 4 |
126 | =over 4 |
127 | |
127 | |
128 | =item 595 - errors during connection etsbalishment, proxy handshake. |
128 | =item 595 - errors during connection establishment, proxy handshake. |
129 | |
129 | |
130 | =item 596 - errors during TLS negotiation, request sending and header processing. |
130 | =item 596 - errors during TLS negotiation, request sending and header processing. |
131 | |
131 | |
132 | =item 597 - errors during body receiving or processing. |
132 | =item 597 - errors during body receiving or processing. |
133 | |
133 | |
… | |
… | |
157 | =item recurse => $count (default: $MAX_RECURSE) |
157 | =item recurse => $count (default: $MAX_RECURSE) |
158 | |
158 | |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
160 | other retries and so on, and how often to do so. |
160 | other retries and so on, and how often to do so. |
161 | |
161 | |
|
|
162 | Only redirects to http and https URLs are supported. While most common |
|
|
163 | redirection forms are handled entirely within this module, some require |
|
|
164 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
165 | the request will fail with an error. |
|
|
166 | |
162 | =item headers => hashref |
167 | =item headers => hashref |
163 | |
168 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
169 | The request headers to use. Currently, C<http_request> may provide its own |
165 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
166 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
… | |
… | |
189 | |
194 | |
190 | C<$scheme> must be either missing or must be C<http> for HTTP. |
195 | C<$scheme> must be either missing or must be C<http> for HTTP. |
191 | |
196 | |
192 | If not specified, then the default proxy is used (see |
197 | If not specified, then the default proxy is used (see |
193 | C<AnyEvent::HTTP::set_proxy>). |
198 | C<AnyEvent::HTTP::set_proxy>). |
|
|
199 | |
|
|
200 | Currently, if your proxy requires authorization, you have to specify an |
|
|
201 | appropriate "Proxy-Authorization" header in every request. |
|
|
202 | |
|
|
203 | Note that this module will prefer an existing persistent connection, |
|
|
204 | even if that connection was made using another proxy. If you need to |
|
|
205 | ensure that a new conneciton is made in this case, you can either force |
|
|
206 | C<persistent> to false or e.g. use the proxy address in your C<sessionid>. |
194 | |
207 | |
195 | =item body => $string |
208 | =item body => $string |
196 | |
209 | |
197 | The request body, usually empty. Will be sent as-is (future versions of |
210 | The request body, usually empty. Will be sent as-is (future versions of |
198 | this module might offer more options). |
211 | this module might offer more options). |
… | |
… | |
231 | The default for this option is C<low>, which could be interpreted as "give |
244 | The default for this option is C<low>, which could be interpreted as "give |
232 | me the page, no matter what". |
245 | me the page, no matter what". |
233 | |
246 | |
234 | See also the C<sessionid> parameter. |
247 | See also the C<sessionid> parameter. |
235 | |
248 | |
236 | =item session => $string |
249 | =item sessionid => $string |
237 | |
250 | |
238 | The module might reuse connections to the same host internally. Sometimes |
251 | The module might reuse connections to the same host internally (regardless |
239 | (e.g. when using TLS), you do not want to reuse connections from other |
252 | of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g. |
|
|
253 | when using TLS or a specfic proxy), you do not want to reuse connections |
240 | sessions. This can be achieved by setting this parameter to some unique |
254 | from other sessions. This can be achieved by setting this parameter to |
241 | ID (such as the address of an object storing your state data, or the TLS |
255 | some unique ID (such as the address of an object storing your state data |
242 | context) - only connections using the same unique ID will be reused. |
256 | or the TLS context, or the proxy IP) - only connections using the same |
|
|
257 | unique ID will be reused. |
243 | |
258 | |
244 | =item on_prepare => $callback->($fh) |
259 | =item on_prepare => $callback->($fh) |
245 | |
260 | |
246 | In rare cases you need to "tune" the socket before it is used to |
261 | In rare cases you need to "tune" the socket before it is used to |
247 | connect (for exmaple, to bind it on a given IP address). This parameter |
262 | connect (for example, to bind it on a given IP address). This parameter |
248 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
263 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
249 | and behaves exactly the same way (e.g. it has to provide a |
264 | and behaves exactly the same way (e.g. it has to provide a |
250 | timeout). See the description for the C<$prepare_cb> argument of |
265 | timeout). See the description for the C<$prepare_cb> argument of |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
266 | C<AnyEvent::Socket::tcp_connect> for details. |
252 | |
267 | |
… | |
… | |
255 | In even rarer cases you want total control over how AnyEvent::HTTP |
270 | In even rarer cases you want total control over how AnyEvent::HTTP |
256 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
271 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
257 | to do this, but you can provide your own C<tcp_connect> function - |
272 | to do this, but you can provide your own C<tcp_connect> function - |
258 | obviously, it has to follow the same calling conventions, except that it |
273 | obviously, it has to follow the same calling conventions, except that it |
259 | may always return a connection guard object. |
274 | may always return a connection guard object. |
|
|
275 | |
|
|
276 | The connections made by this hook will be treated as equivalent to |
|
|
277 | connecitons made the built-in way, specifically, they will be put into |
|
|
278 | and taken from the persistent conneciton cache. If your C<$tcp_connect> |
|
|
279 | function is incompatible with this kind of re-use, consider switching off |
|
|
280 | C<persistent> connections and/or providing a C<sessionid> identifier. |
260 | |
281 | |
261 | There are probably lots of weird uses for this function, starting from |
282 | There are probably lots of weird uses for this function, starting from |
262 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
283 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
263 | but fast) host => IP address caching or even socks protocol support. |
284 | but fast) host => IP address caching or even socks protocol support. |
264 | |
285 | |
… | |
… | |
334 | =item persistent => $boolean |
355 | =item persistent => $boolean |
335 | |
356 | |
336 | Try to create/reuse a persistent connection. When this flag is set |
357 | Try to create/reuse a persistent connection. When this flag is set |
337 | (default: true for idempotent requests, false for all others), then |
358 | (default: true for idempotent requests, false for all others), then |
338 | C<http_request> tries to re-use an existing (previously-created) |
359 | C<http_request> tries to re-use an existing (previously-created) |
339 | persistent connection to the host and, failing that, tries to create a new |
360 | persistent connection to same host (i.e. identical URL scheme, hostname, |
340 | one. |
361 | port and sessionid) and, failing that, tries to create a new one. |
341 | |
362 | |
342 | Requests failing in certain ways will be automatically retried once, which |
363 | Requests failing in certain ways will be automatically retried once, which |
343 | is dangerous for non-idempotent requests, which is why it defaults to off |
364 | is dangerous for non-idempotent requests, which is why it defaults to off |
344 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
365 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
345 | made it impossible to distinguish between a fatal error and a normal |
366 | made it impossible to distinguish between a fatal error and a normal |
346 | connection timeout, so you never know whether there was a problem with |
367 | connection timeout, so you never know whether there was a problem with |
347 | your request or not. |
368 | your request or not. |
348 | |
369 | |
349 | When reusing an existent connection, many parameters (such as TLS context) |
370 | When reusing an existent connection, many parameters (such as TLS context) |
350 | will be ignored. See the C<session> parameter for a workaround. |
371 | will be ignored. See the C<sessionid> parameter for a workaround. |
351 | |
372 | |
352 | =item keepalive => $boolean |
373 | =item keepalive => $boolean |
353 | |
374 | |
354 | Only used when C<persistent> is also true. This parameter decides whether |
375 | Only used when C<persistent> is also true. This parameter decides whether |
355 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
376 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
… | |
… | |
446 | |
467 | |
447 | # expire cookies |
468 | # expire cookies |
448 | sub cookie_jar_expire($;$) { |
469 | sub cookie_jar_expire($;$) { |
449 | my ($jar, $session_end) = @_; |
470 | my ($jar, $session_end) = @_; |
450 | |
471 | |
451 | %$jar = () if $jar->{version} != 1; |
472 | %$jar = () if $jar->{version} != 2; |
452 | |
473 | |
453 | my $anow = AE::now; |
474 | my $anow = AE::now; |
454 | |
475 | |
455 | while (my ($chost, $paths) = each %$jar) { |
476 | while (my ($chost, $paths) = each %$jar) { |
456 | next unless ref $paths; |
477 | next unless ref $paths; |
… | |
… | |
476 | |
497 | |
477 | # extract cookies from jar |
498 | # extract cookies from jar |
478 | sub cookie_jar_extract($$$$) { |
499 | sub cookie_jar_extract($$$$) { |
479 | my ($jar, $scheme, $host, $path) = @_; |
500 | my ($jar, $scheme, $host, $path) = @_; |
480 | |
501 | |
481 | %$jar = () if $jar->{version} != 1; |
502 | %$jar = () if $jar->{version} != 2; |
|
|
503 | |
|
|
504 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
505 | if $host =~ /[^\x00-\x7f]/; |
482 | |
506 | |
483 | my @cookies; |
507 | my @cookies; |
484 | |
508 | |
485 | while (my ($chost, $paths) = each %$jar) { |
509 | while (my ($chost, $paths) = each %$jar) { |
486 | next unless ref $paths; |
510 | next unless ref $paths; |
487 | |
511 | |
488 | if ($chost =~ /^\./) { |
512 | # exact match or suffix including . match |
489 | next unless $chost eq substr $host, -length $chost; |
513 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
490 | } elsif ($chost =~ /\./) { |
|
|
491 | next unless $chost eq $host; |
|
|
492 | } else { |
|
|
493 | next; |
514 | or next; |
494 | } |
|
|
495 | |
515 | |
496 | while (my ($cpath, $cookies) = each %$paths) { |
516 | while (my ($cpath, $cookies) = each %$paths) { |
497 | next unless $cpath eq substr $path, 0, length $cpath; |
517 | next unless $cpath eq substr $path, 0, length $cpath; |
498 | |
518 | |
499 | while (my ($cookie, $kv) = each %$cookies) { |
519 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
520 | } |
540 | } |
521 | |
541 | |
522 | # parse set_cookie header into jar |
542 | # parse set_cookie header into jar |
523 | sub cookie_jar_set_cookie($$$$) { |
543 | sub cookie_jar_set_cookie($$$$) { |
524 | my ($jar, $set_cookie, $host, $date) = @_; |
544 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
545 | |
|
|
546 | %$jar = () if $jar->{version} != 2; |
525 | |
547 | |
526 | my $anow = int AE::now; |
548 | my $anow = int AE::now; |
527 | my $snow; # server-now |
549 | my $snow; # server-now |
528 | |
550 | |
529 | for ($set_cookie) { |
551 | for ($set_cookie) { |
… | |
… | |
575 | |
597 | |
576 | my $cdom; |
598 | my $cdom; |
577 | my $cpath = (delete $kv{path}) || "/"; |
599 | my $cpath = (delete $kv{path}) || "/"; |
578 | |
600 | |
579 | if (exists $kv{domain}) { |
601 | if (exists $kv{domain}) { |
580 | $cdom = delete $kv{domain}; |
602 | $cdom = $kv{domain}; |
581 | |
603 | |
582 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
604 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
583 | |
605 | |
584 | next if $cdom =~ /\.$/; |
606 | next if $cdom =~ /\.$/; |
585 | |
607 | |
586 | # this is not rfc-like and not netscape-like. go figure. |
608 | # this is not rfc-like and not netscape-like. go figure. |
587 | my $ndots = $cdom =~ y/.//; |
609 | my $ndots = $cdom =~ y/.//; |
588 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
610 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
611 | |
|
|
612 | $cdom = substr $cdom, 1; # remove initial . |
589 | } else { |
613 | } else { |
590 | $cdom = $host; |
614 | $cdom = $host; |
591 | } |
615 | } |
592 | |
616 | |
593 | # store it |
617 | # store it |
594 | $jar->{version} = 1; |
618 | $jar->{version} = 2; |
595 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
619 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
596 | |
620 | |
597 | redo if /\G\s*,/gc; |
621 | redo if /\G\s*,/gc; |
598 | } |
622 | } |
599 | } |
623 | } |
… | |
… | |
689 | |
713 | |
690 | $cb->(undef, $hdr); |
714 | $cb->(undef, $hdr); |
691 | () |
715 | () |
692 | } |
716 | } |
693 | |
717 | |
|
|
718 | our %IDEMPOTENT = ( |
|
|
719 | DELETE => 1, |
|
|
720 | GET => 1, |
|
|
721 | HEAD => 1, |
|
|
722 | OPTIONS => 1, |
|
|
723 | PUT => 1, |
|
|
724 | TRACE => 1, |
|
|
725 | |
|
|
726 | ACL => 1, |
|
|
727 | "BASELINE-CONTROL" => 1, |
|
|
728 | BIND => 1, |
|
|
729 | CHECKIN => 1, |
|
|
730 | CHECKOUT => 1, |
|
|
731 | COPY => 1, |
|
|
732 | LABEL => 1, |
|
|
733 | LINK => 1, |
|
|
734 | MERGE => 1, |
|
|
735 | MKACTIVITY => 1, |
|
|
736 | MKCALENDAR => 1, |
|
|
737 | MKCOL => 1, |
|
|
738 | MKREDIRECTREF => 1, |
|
|
739 | MKWORKSPACE => 1, |
|
|
740 | MOVE => 1, |
|
|
741 | ORDERPATCH => 1, |
|
|
742 | PROPFIND => 1, |
|
|
743 | PROPPATCH => 1, |
|
|
744 | REBIND => 1, |
|
|
745 | REPORT => 1, |
|
|
746 | SEARCH => 1, |
|
|
747 | UNBIND => 1, |
|
|
748 | UNCHECKOUT => 1, |
|
|
749 | UNLINK => 1, |
|
|
750 | UNLOCK => 1, |
|
|
751 | UPDATE => 1, |
|
|
752 | UPDATEREDIRECTREF => 1, |
|
|
753 | "VERSION-CONTROL" => 1, |
|
|
754 | ); |
|
|
755 | |
694 | sub http_request($$@) { |
756 | sub http_request($$@) { |
695 | my $cb = pop; |
757 | my $cb = pop; |
696 | my ($method, $url, %arg) = @_; |
758 | my ($method, $url, %arg) = @_; |
697 | |
759 | |
698 | my %hdr; |
760 | my %hdr; |
… | |
… | |
727 | |
789 | |
728 | my $uport = $uscheme eq "http" ? 80 |
790 | my $uport = $uscheme eq "http" ? 80 |
729 | : $uscheme eq "https" ? 443 |
791 | : $uscheme eq "https" ? 443 |
730 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
792 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
731 | |
793 | |
732 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
794 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
733 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
795 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
734 | |
796 | |
735 | my $uhost = lc $1; |
797 | my $uhost = lc $1; |
736 | $uport = $2 if defined $2; |
798 | $uport = $2 if defined $2; |
737 | |
799 | |
… | |
… | |
773 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
835 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
774 | |
836 | |
775 | $hdr{"content-length"} = length $arg{body} |
837 | $hdr{"content-length"} = length $arg{body} |
776 | if length $arg{body} || $method ne "GET"; |
838 | if length $arg{body} || $method ne "GET"; |
777 | |
839 | |
778 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
840 | my $idempotent = $IDEMPOTENT{$method}; |
779 | |
841 | |
780 | # default value for keepalive is true iff the request is for an idempotent method |
842 | # default value for keepalive is true iff the request is for an idempotent method |
781 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
843 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
782 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
844 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
783 | my $was_persistent; # true if this is actually a recycled connection |
845 | my $was_persistent; # true if this is actually a recycled connection |
784 | |
846 | |
785 | # the key to use in the keepalive cache |
847 | # the key to use in the keepalive cache |
786 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
848 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
787 | |
849 | |
788 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
850 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
789 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
851 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
790 | |
852 | |
791 | my %state = (connect_guard => 1); |
853 | my %state = (connect_guard => 1); |
792 | |
854 | |
793 | my $ae_error = 595; # connecting |
855 | my $ae_error = 595; # connecting |
… | |
… | |
803 | # send request |
865 | # send request |
804 | $hdl->push_write ( |
866 | $hdl->push_write ( |
805 | "$method $rpath HTTP/1.1\015\012" |
867 | "$method $rpath HTTP/1.1\015\012" |
806 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
868 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
807 | . "\015\012" |
869 | . "\015\012" |
808 | . (delete $arg{body}) |
870 | . $arg{body} |
809 | ); |
871 | ); |
810 | |
872 | |
811 | # return if error occured during push_write() |
873 | # return if error occurred during push_write() |
812 | return unless %state; |
874 | return unless %state; |
813 | |
875 | |
814 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
876 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
815 | %hdr = (); |
877 | %hdr = (); |
816 | |
878 | |
… | |
… | |
843 | |
905 | |
844 | %hdr = (%$hdr, @pseudo); |
906 | %hdr = (%$hdr, @pseudo); |
845 | } |
907 | } |
846 | |
908 | |
847 | # redirect handling |
909 | # redirect handling |
848 | # microsoft and other shitheads don't give a shit for following standards, |
910 | # relative uri handling forced by microsoft and other shitheads. |
849 | # try to support some common forms of broken Location headers. |
911 | # we give our best and fall back to URI if available. |
850 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
912 | if (exists $hdr{location}) { |
|
|
913 | my $loc = $hdr{location}; |
|
|
914 | |
|
|
915 | if ($loc =~ m%^//%) { # // |
|
|
916 | $loc = "$uscheme:$loc"; |
|
|
917 | |
|
|
918 | } elsif ($loc eq "") { |
|
|
919 | $loc = $url; |
|
|
920 | |
|
|
921 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
851 | $hdr{location} =~ s/^\.\/+//; |
922 | $loc =~ s/^\.\/+//; |
852 | |
923 | |
853 | my $url = "$rscheme://$uhost:$uport"; |
924 | if ($loc !~ m%^[.?#]%) { |
|
|
925 | my $prefix = "$uscheme://$uauthority"; |
854 | |
926 | |
855 | unless ($hdr{location} =~ s/^\///) { |
927 | unless ($loc =~ s/^\///) { |
856 | $url .= $upath; |
928 | $prefix .= $upath; |
857 | $url =~ s/\/[^\/]*$//; |
929 | $prefix =~ s/\/[^\/]*$//; |
|
|
930 | } |
|
|
931 | |
|
|
932 | $loc = "$prefix/$loc"; |
|
|
933 | |
|
|
934 | } elsif (eval { require URI }) { # uri |
|
|
935 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
936 | |
|
|
937 | } else { |
|
|
938 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
939 | #$hdr{Status} = 599; |
|
|
940 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
941 | #$recurse = 0; |
|
|
942 | } |
858 | } |
943 | } |
859 | |
944 | |
860 | $hdr{location} = "$url/$hdr{location}"; |
945 | $hdr{location} = $loc; |
861 | } |
946 | } |
862 | |
947 | |
863 | my $redirect; |
948 | my $redirect; |
864 | |
949 | |
865 | if ($recurse) { |
950 | if ($recurse) { |
… | |
… | |
867 | |
952 | |
868 | # industry standard is to redirect POST as GET for |
953 | # industry standard is to redirect POST as GET for |
869 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
954 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
870 | # also, the UA should ask the user for 301 and 307 and POST, |
955 | # also, the UA should ask the user for 301 and 307 and POST, |
871 | # industry standard seems to be to simply follow. |
956 | # industry standard seems to be to simply follow. |
872 | # we go with the industry standard. |
957 | # we go with the industry standard. 308 is defined |
|
|
958 | # by rfc7538 |
873 | if ($status == 301 or $status == 302 or $status == 303) { |
959 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
960 | $redirect = 1; |
874 | # HTTP/1.1 is unclear on how to mutate the method |
961 | # HTTP/1.1 is unclear on how to mutate the method |
875 | $method = "GET" unless $method eq "HEAD"; |
962 | unless ($method eq "HEAD") { |
876 | $redirect = 1; |
963 | $method = "GET"; |
|
|
964 | delete $arg{body}; |
|
|
965 | } |
877 | } elsif ($status == 307) { |
966 | } elsif ($status == 307 or $status == 308) { |
878 | $redirect = 1; |
967 | $redirect = 1; |
879 | } |
968 | } |
880 | } |
969 | } |
881 | |
970 | |
882 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
971 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
… | |
… | |
958 | $finish->(delete $state{handle}); |
1047 | $finish->(delete $state{handle}); |
959 | |
1048 | |
960 | } elsif ($chunked) { |
1049 | } elsif ($chunked) { |
961 | my $cl = 0; |
1050 | my $cl = 0; |
962 | my $body = ""; |
1051 | my $body = ""; |
963 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1052 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
964 | |
1053 | |
965 | $state{read_chunk} = sub { |
1054 | $state{read_chunk} = sub { |
966 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1055 | $_[1] =~ /^([0-9a-fA-F]+)/ |
967 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1056 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
968 | |
1057 | |
… | |
… | |
1001 | } |
1090 | } |
1002 | }; |
1091 | }; |
1003 | |
1092 | |
1004 | $_[0]->push_read (line => $state{read_chunk}); |
1093 | $_[0]->push_read (line => $state{read_chunk}); |
1005 | |
1094 | |
1006 | } elsif ($arg{on_body}) { |
1095 | } elsif (!$redirect && $arg{on_body}) { |
1007 | if (defined $len) { |
1096 | if (defined $len) { |
1008 | $_[0]->on_read (sub { |
1097 | $_[0]->on_read (sub { |
1009 | $len -= length $_[0]{rbuf}; |
1098 | $len -= length $_[0]{rbuf}; |
1010 | |
1099 | |
1011 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1100 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
1050 | _destroy_state %state; |
1139 | _destroy_state %state; |
1051 | |
1140 | |
1052 | %state = (); |
1141 | %state = (); |
1053 | $state{recurse} = |
1142 | $state{recurse} = |
1054 | http_request ( |
1143 | http_request ( |
1055 | $method => $url, |
1144 | $method => $url, |
1056 | %arg, |
1145 | %arg, |
1057 | recurse => $recurse - 1, |
1146 | recurse => $recurse - 1, |
1058 | keepalive => 0, |
1147 | persistent => 0, |
1059 | sub { |
1148 | sub { |
1060 | %state = (); |
1149 | %state = (); |
1061 | &$cb |
1150 | &$cb |
1062 | } |
1151 | } |
1063 | ); |
1152 | ); |
… | |
… | |
1109 | |
1198 | |
1110 | # now handle proxy-CONNECT method |
1199 | # now handle proxy-CONNECT method |
1111 | if ($proxy && $uscheme eq "https") { |
1200 | if ($proxy && $uscheme eq "https") { |
1112 | # oh dear, we have to wrap it into a connect request |
1201 | # oh dear, we have to wrap it into a connect request |
1113 | |
1202 | |
|
|
1203 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1204 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1205 | : ""; |
|
|
1206 | |
1114 | # maybe re-use $uauthority with patched port? |
1207 | # maybe re-use $uauthority with patched port? |
1115 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1208 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
1116 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1209 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1117 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1210 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1118 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1211 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1119 | |
1212 | |
1120 | if ($2 == 200) { |
1213 | if ($2 == 200) { |
… | |
… | |
1123 | } else { |
1216 | } else { |
1124 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1217 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1125 | } |
1218 | } |
1126 | }); |
1219 | }); |
1127 | } else { |
1220 | } else { |
|
|
1221 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1222 | |
1128 | $handle_actual_request->(); |
1223 | $handle_actual_request->(); |
1129 | } |
1224 | } |
1130 | }; |
1225 | }; |
1131 | |
1226 | |
1132 | _get_slot $uhost, sub { |
1227 | _get_slot $uhost, sub { |
… | |
… | |
1138 | # on a keepalive request (in theory, this should be a separate config option). |
1233 | # on a keepalive request (in theory, this should be a separate config option). |
1139 | if ($persistent && $KA_CACHE{$ka_key}) { |
1234 | if ($persistent && $KA_CACHE{$ka_key}) { |
1140 | $was_persistent = 1; |
1235 | $was_persistent = 1; |
1141 | |
1236 | |
1142 | $state{handle} = ka_fetch $ka_key; |
1237 | $state{handle} = ka_fetch $ka_key; |
1143 | $state{handle}->destroyed |
1238 | # $state{handle}->destroyed |
1144 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1239 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1145 | $prepare_handle->(); |
1240 | $prepare_handle->(); |
1146 | $state{handle}->destroyed |
1241 | # $state{handle}->destroyed |
1147 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1242 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1148 | $handle_actual_request->(); |
1243 | $handle_actual_request->(); |
1149 | |
1244 | |
1150 | } else { |
1245 | } else { |
1151 | my $tcp_connect = $arg{tcp_connect} |
1246 | my $tcp_connect = $arg{tcp_connect} |
1152 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1247 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1194 | Sets the default proxy server to use. The proxy-url must begin with a |
1289 | Sets the default proxy server to use. The proxy-url must begin with a |
1195 | string of the form C<http://host:port>, croaks otherwise. |
1290 | string of the form C<http://host:port>, croaks otherwise. |
1196 | |
1291 | |
1197 | To clear an already-set proxy, use C<undef>. |
1292 | To clear an already-set proxy, use C<undef>. |
1198 | |
1293 | |
1199 | When AnyEvent::HTTP is laoded for the first time it will query the |
1294 | When AnyEvent::HTTP is loaded for the first time it will query the |
1200 | default proxy from the operating system, currently by looking at |
1295 | default proxy from the operating system, currently by looking at |
1201 | C<$ENV{http_proxy>}. |
1296 | C<$ENV{http_proxy>}. |
1202 | |
1297 | |
1203 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1298 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1204 | |
1299 | |
… | |
… | |
1206 | C<$session_end> is given and true, then additionally remove all session |
1301 | C<$session_end> is given and true, then additionally remove all session |
1207 | cookies. |
1302 | cookies. |
1208 | |
1303 | |
1209 | You should call this function (with a true C<$session_end>) before you |
1304 | You should call this function (with a true C<$session_end>) before you |
1210 | save cookies to disk, and you should call this function after loading them |
1305 | save cookies to disk, and you should call this function after loading them |
1211 | again. If you have a long-running program you can additonally call this |
1306 | again. If you have a long-running program you can additionally call this |
1212 | function from time to time. |
1307 | function from time to time. |
1213 | |
1308 | |
1214 | A cookie jar is initially an empty hash-reference that is managed by this |
1309 | A cookie jar is initially an empty hash-reference that is managed by this |
1215 | module. It's format is subject to change, but currently it is like this: |
1310 | module. Its format is subject to change, but currently it is as follows: |
1216 | |
1311 | |
1217 | The key C<version> has to contain C<1>, otherwise the hash gets |
1312 | The key C<version> has to contain C<2>, otherwise the hash gets |
1218 | emptied. All other keys are hostnames or IP addresses pointing to |
1313 | cleared. All other keys are hostnames or IP addresses pointing to |
1219 | hash-references. The key for these inner hash references is the |
1314 | hash-references. The key for these inner hash references is the |
1220 | server path for which this cookie is meant, and the values are again |
1315 | server path for which this cookie is meant, and the values are again |
1221 | hash-references. The keys of those hash-references is the cookie name, and |
1316 | hash-references. Each key of those hash-references is a cookie name, and |
1222 | the value, you guessed it, is another hash-reference, this time with the |
1317 | the value, you guessed it, is another hash-reference, this time with the |
1223 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1318 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1224 | which have been replaced by a C<_expires> key that contains the cookie |
1319 | which have been replaced by a C<_expires> key that contains the cookie |
1225 | expiry timestamp. |
1320 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1321 | C<_expires> key. |
1226 | |
1322 | |
1227 | Here is an example of a cookie jar with a single cookie, so you have a |
1323 | Here is an example of a cookie jar with a single cookie, so you have a |
1228 | chance of understanding the above paragraph: |
1324 | chance of understanding the above paragraph: |
1229 | |
1325 | |
1230 | { |
1326 | { |
1231 | version => 1, |
1327 | version => 2, |
1232 | "10.0.0.1" => { |
1328 | "10.0.0.1" => { |
1233 | "/" => { |
1329 | "/" => { |
1234 | "mythweb_id" => { |
1330 | "mythweb_id" => { |
1235 | _expires => 1293917923, |
1331 | _expires => 1293917923, |
1236 | value => "ooRung9dThee3ooyXooM1Ohm", |
1332 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1264 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1360 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1265 | |
1361 | |
1266 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1362 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1267 | |
1363 | |
1268 | The maximum number of concurrent connections to the same host (identified |
1364 | The maximum number of concurrent connections to the same host (identified |
1269 | by the hostname). If the limit is exceeded, then the additional requests |
1365 | by the hostname). If the limit is exceeded, then additional requests |
1270 | are queued until previous connections are closed. Both persistent and |
1366 | are queued until previous connections are closed. Both persistent and |
1271 | non-persistent connections are counted in this limit. |
1367 | non-persistent connections are counted in this limit. |
1272 | |
1368 | |
1273 | The default value for this is C<4>, and it is highly advisable to not |
1369 | The default value for this is C<4>, and it is highly advisable to not |
1274 | increase it much. |
1370 | increase it much. |
1275 | |
1371 | |
1276 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1372 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1277 | connections, older browsers used 2, newers (such as firefox 3) typically |
1373 | connections, older browsers used 2, newer ones (such as firefox 3) |
1278 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1374 | typically use 6, and Opera uses 8 because like, they have the fastest |
1279 | give a shit for everybody else on the planet. |
1375 | browser and give a shit for everybody else on the planet. |
1280 | |
1376 | |
1281 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1377 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1282 | |
1378 | |
1283 | The time after which idle persistent conenctions get closed by |
1379 | The time after which idle persistent connections get closed by |
1284 | AnyEvent::HTTP (default: C<3>). |
1380 | AnyEvent::HTTP (default: C<3>). |
1285 | |
1381 | |
1286 | =item $AnyEvent::HTTP::ACTIVE |
1382 | =item $AnyEvent::HTTP::ACTIVE |
1287 | |
1383 | |
1288 | The number of active connections. This is not the number of currently |
1384 | The number of active connections. This is not the number of currently |
… | |
… | |
1353 | set_proxy $ENV{http_proxy}; |
1449 | set_proxy $ENV{http_proxy}; |
1354 | }; |
1450 | }; |
1355 | |
1451 | |
1356 | =head2 SHOWCASE |
1452 | =head2 SHOWCASE |
1357 | |
1453 | |
1358 | This section contaisn some more elaborate "real-world" examples or code |
1454 | This section contains some more elaborate "real-world" examples or code |
1359 | snippets. |
1455 | snippets. |
1360 | |
1456 | |
1361 | =head2 HTTP/1.1 FILE DOWNLOAD |
1457 | =head2 HTTP/1.1 FILE DOWNLOAD |
1362 | |
1458 | |
1363 | Downloading files with HTTP can be quite tricky, especially when something |
1459 | Downloading files with HTTP can be quite tricky, especially when something |
… | |
… | |
1367 | last modified time to check for file content changes, and works with many |
1463 | last modified time to check for file content changes, and works with many |
1368 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1464 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1369 | on older servers. |
1465 | on older servers. |
1370 | |
1466 | |
1371 | It calls the completion callback with either C<undef>, which means a |
1467 | It calls the completion callback with either C<undef>, which means a |
1372 | nonretryable error occured, C<0> when the download was partial and should |
1468 | nonretryable error occurred, C<0> when the download was partial and should |
1373 | be retried, and C<1> if it was successful. |
1469 | be retried, and C<1> if it was successful. |
1374 | |
1470 | |
1375 | use AnyEvent::HTTP; |
1471 | use AnyEvent::HTTP; |
1376 | |
1472 | |
1377 | sub download($$$) { |
1473 | sub download($$$) { |
… | |
… | |
1381 | or die "$file: $!"; |
1477 | or die "$file: $!"; |
1382 | |
1478 | |
1383 | my %hdr; |
1479 | my %hdr; |
1384 | my $ofs = 0; |
1480 | my $ofs = 0; |
1385 | |
1481 | |
1386 | warn stat $fh; |
|
|
1387 | warn -s _; |
|
|
1388 | if (stat $fh and -s _) { |
1482 | if (stat $fh and -s _) { |
1389 | $ofs = -s _; |
1483 | $ofs = -s _; |
1390 | warn "-s is ", $ofs; |
1484 | warn "-s is ", $ofs; |
1391 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1485 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1392 | $hdr{"range"} = "bytes=$ofs-"; |
1486 | $hdr{"range"} = "bytes=$ofs-"; |
… | |
… | |
1420 | my (undef, $hdr) = @_; |
1514 | my (undef, $hdr) = @_; |
1421 | |
1515 | |
1422 | my $status = $hdr->{Status}; |
1516 | my $status = $hdr->{Status}; |
1423 | |
1517 | |
1424 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1518 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1425 | utime $fh, $time, $time; |
1519 | utime $time, $time, $fh; |
1426 | } |
1520 | } |
1427 | |
1521 | |
1428 | if ($status == 200 || $status == 206 || $status == 416) { |
1522 | if ($status == 200 || $status == 206 || $status == 416) { |
1429 | # download ok || resume ok || file already fully downloaded |
1523 | # download ok || resume ok || file already fully downloaded |
1430 | $cb->(1, $hdr); |
1524 | $cb->(1, $hdr); |