… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::HTTP; |
7 | use AnyEvent::HTTP; |
8 | |
8 | |
9 | http_get "http://www.nethype.de/", sub { print $_[1] }; |
9 | http_get "http://www.nethype.de/", sub { |
|
|
10 | my ($body, $hdr) = @_; |
|
|
11 | print "$hdr->{URL} Status: $hdr->{Status}\n"; |
|
|
12 | print $body; |
|
|
13 | }; |
10 | |
14 | |
11 | # ... do something else here |
15 | # ... do something else here |
12 | |
16 | |
13 | =head1 DESCRIPTION |
17 | =head1 DESCRIPTION |
14 | |
18 | |
… | |
… | |
46 | use AnyEvent::Util (); |
50 | use AnyEvent::Util (); |
47 | use AnyEvent::Handle (); |
51 | use AnyEvent::Handle (); |
48 | |
52 | |
49 | use base Exporter::; |
53 | use base Exporter::; |
50 | |
54 | |
51 | our $VERSION = '2.15'; |
55 | our $VERSION = 2.25; |
52 | |
56 | |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
57 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | |
58 | |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
59 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $MAX_RECURSE = 10; |
60 | our $MAX_RECURSE = 10; |
… | |
… | |
157 | =item recurse => $count (default: $MAX_RECURSE) |
161 | =item recurse => $count (default: $MAX_RECURSE) |
158 | |
162 | |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
163 | Whether to recurse requests or not, e.g. on redirects, authentication and |
160 | other retries and so on, and how often to do so. |
164 | other retries and so on, and how often to do so. |
161 | |
165 | |
|
|
166 | Only redirects to http and https URLs are supported. While most common |
|
|
167 | redirection forms are handled entirely within this module, some require |
|
|
168 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
169 | the request will fail with an error. |
|
|
170 | |
162 | =item headers => hashref |
171 | =item headers => hashref |
163 | |
172 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
173 | The request headers to use. Currently, C<http_request> may provide its own |
165 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
174 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
166 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
175 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
… | |
… | |
189 | |
198 | |
190 | C<$scheme> must be either missing or must be C<http> for HTTP. |
199 | C<$scheme> must be either missing or must be C<http> for HTTP. |
191 | |
200 | |
192 | If not specified, then the default proxy is used (see |
201 | If not specified, then the default proxy is used (see |
193 | C<AnyEvent::HTTP::set_proxy>). |
202 | C<AnyEvent::HTTP::set_proxy>). |
|
|
203 | |
|
|
204 | Currently, if your proxy requires authorization, you have to specify an |
|
|
205 | appropriate "Proxy-Authorization" header in every request. |
|
|
206 | |
|
|
207 | Note that this module will prefer an existing persistent connection, |
|
|
208 | even if that connection was made using another proxy. If you need to |
|
|
209 | ensure that a new connection is made in this case, you can either force |
|
|
210 | C<persistent> to false or e.g. use the proxy address in your C<sessionid>. |
194 | |
211 | |
195 | =item body => $string |
212 | =item body => $string |
196 | |
213 | |
197 | The request body, usually empty. Will be sent as-is (future versions of |
214 | The request body, usually empty. Will be sent as-is (future versions of |
198 | this module might offer more options). |
215 | this module might offer more options). |
… | |
… | |
231 | The default for this option is C<low>, which could be interpreted as "give |
248 | The default for this option is C<low>, which could be interpreted as "give |
232 | me the page, no matter what". |
249 | me the page, no matter what". |
233 | |
250 | |
234 | See also the C<sessionid> parameter. |
251 | See also the C<sessionid> parameter. |
235 | |
252 | |
236 | =item session => $string |
253 | =item sessionid => $string |
237 | |
254 | |
238 | The module might reuse connections to the same host internally. Sometimes |
255 | 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 |
256 | of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g. |
|
|
257 | 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 |
258 | 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 |
259 | 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. |
260 | or the TLS context, or the proxy IP) - only connections using the same |
|
|
261 | unique ID will be reused. |
243 | |
262 | |
244 | =item on_prepare => $callback->($fh) |
263 | =item on_prepare => $callback->($fh) |
245 | |
264 | |
246 | In rare cases you need to "tune" the socket before it is used to |
265 | In rare cases you need to "tune" the socket before it is used to |
247 | connect (for example, to bind it on a given IP address). This parameter |
266 | connect (for example, to bind it on a given IP address). This parameter |
… | |
… | |
255 | In even rarer cases you want total control over how AnyEvent::HTTP |
274 | In even rarer cases you want total control over how AnyEvent::HTTP |
256 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
275 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
257 | to do this, but you can provide your own C<tcp_connect> function - |
276 | 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 |
277 | obviously, it has to follow the same calling conventions, except that it |
259 | may always return a connection guard object. |
278 | may always return a connection guard object. |
|
|
279 | |
|
|
280 | The connections made by this hook will be treated as equivalent to |
|
|
281 | connections made the built-in way, specifically, they will be put into |
|
|
282 | and taken from the persistent connection cache. If your C<$tcp_connect> |
|
|
283 | function is incompatible with this kind of re-use, consider switching off |
|
|
284 | C<persistent> connections and/or providing a C<sessionid> identifier. |
260 | |
285 | |
261 | There are probably lots of weird uses for this function, starting from |
286 | 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 |
287 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
263 | but fast) host => IP address caching or even socks protocol support. |
288 | but fast) host => IP address caching or even socks protocol support. |
264 | |
289 | |
… | |
… | |
334 | =item persistent => $boolean |
359 | =item persistent => $boolean |
335 | |
360 | |
336 | Try to create/reuse a persistent connection. When this flag is set |
361 | Try to create/reuse a persistent connection. When this flag is set |
337 | (default: true for idempotent requests, false for all others), then |
362 | (default: true for idempotent requests, false for all others), then |
338 | C<http_request> tries to re-use an existing (previously-created) |
363 | 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 |
364 | persistent connection to same host (i.e. identical URL scheme, hostname, |
340 | one. |
365 | port and sessionid) and, failing that, tries to create a new one. |
341 | |
366 | |
342 | Requests failing in certain ways will be automatically retried once, which |
367 | 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 |
368 | 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 |
369 | 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 |
370 | 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 |
371 | connection timeout, so you never know whether there was a problem with |
347 | your request or not. |
372 | your request or not. |
348 | |
373 | |
349 | When reusing an existent connection, many parameters (such as TLS context) |
374 | When reusing an existent connection, many parameters (such as TLS context) |
350 | will be ignored. See the C<session> parameter for a workaround. |
375 | will be ignored. See the C<sessionid> parameter for a workaround. |
351 | |
376 | |
352 | =item keepalive => $boolean |
377 | =item keepalive => $boolean |
353 | |
378 | |
354 | Only used when C<persistent> is also true. This parameter decides whether |
379 | Only used when C<persistent> is also true. This parameter decides whether |
355 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
380 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
… | |
… | |
446 | |
471 | |
447 | # expire cookies |
472 | # expire cookies |
448 | sub cookie_jar_expire($;$) { |
473 | sub cookie_jar_expire($;$) { |
449 | my ($jar, $session_end) = @_; |
474 | my ($jar, $session_end) = @_; |
450 | |
475 | |
451 | %$jar = () if $jar->{version} != 1; |
476 | %$jar = () if $jar->{version} != 2; |
452 | |
477 | |
453 | my $anow = AE::now; |
478 | my $anow = AE::now; |
454 | |
479 | |
455 | while (my ($chost, $paths) = each %$jar) { |
480 | while (my ($chost, $paths) = each %$jar) { |
456 | next unless ref $paths; |
481 | next unless ref $paths; |
… | |
… | |
476 | |
501 | |
477 | # extract cookies from jar |
502 | # extract cookies from jar |
478 | sub cookie_jar_extract($$$$) { |
503 | sub cookie_jar_extract($$$$) { |
479 | my ($jar, $scheme, $host, $path) = @_; |
504 | my ($jar, $scheme, $host, $path) = @_; |
480 | |
505 | |
481 | %$jar = () if $jar->{version} != 1; |
506 | %$jar = () if $jar->{version} != 2; |
|
|
507 | |
|
|
508 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
509 | if $host =~ /[^\x00-\x7f]/; |
482 | |
510 | |
483 | my @cookies; |
511 | my @cookies; |
484 | |
512 | |
485 | while (my ($chost, $paths) = each %$jar) { |
513 | while (my ($chost, $paths) = each %$jar) { |
486 | next unless ref $paths; |
514 | next unless ref $paths; |
487 | |
515 | |
488 | if ($chost =~ /^\./) { |
516 | # exact match or suffix including . match |
489 | next unless $chost eq substr $host, -length $chost; |
517 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
490 | } elsif ($chost =~ /\./) { |
|
|
491 | next unless $chost eq $host; |
|
|
492 | } else { |
|
|
493 | next; |
518 | or next; |
494 | } |
|
|
495 | |
519 | |
496 | while (my ($cpath, $cookies) = each %$paths) { |
520 | while (my ($cpath, $cookies) = each %$paths) { |
497 | next unless $cpath eq substr $path, 0, length $cpath; |
521 | next unless $cpath eq substr $path, 0, length $cpath; |
498 | |
522 | |
499 | while (my ($cookie, $kv) = each %$cookies) { |
523 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
520 | } |
544 | } |
521 | |
545 | |
522 | # parse set_cookie header into jar |
546 | # parse set_cookie header into jar |
523 | sub cookie_jar_set_cookie($$$$) { |
547 | sub cookie_jar_set_cookie($$$$) { |
524 | my ($jar, $set_cookie, $host, $date) = @_; |
548 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
549 | |
|
|
550 | %$jar = () if $jar->{version} != 2; |
525 | |
551 | |
526 | my $anow = int AE::now; |
552 | my $anow = int AE::now; |
527 | my $snow; # server-now |
553 | my $snow; # server-now |
528 | |
554 | |
529 | for ($set_cookie) { |
555 | for ($set_cookie) { |
… | |
… | |
575 | |
601 | |
576 | my $cdom; |
602 | my $cdom; |
577 | my $cpath = (delete $kv{path}) || "/"; |
603 | my $cpath = (delete $kv{path}) || "/"; |
578 | |
604 | |
579 | if (exists $kv{domain}) { |
605 | if (exists $kv{domain}) { |
580 | $cdom = delete $kv{domain}; |
606 | $cdom = $kv{domain}; |
581 | |
607 | |
582 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
608 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
583 | |
609 | |
584 | next if $cdom =~ /\.$/; |
610 | next if $cdom =~ /\.$/; |
585 | |
611 | |
586 | # this is not rfc-like and not netscape-like. go figure. |
612 | # this is not rfc-like and not netscape-like. go figure. |
587 | my $ndots = $cdom =~ y/.//; |
613 | my $ndots = $cdom =~ y/.//; |
588 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
614 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
615 | |
|
|
616 | $cdom = substr $cdom, 1; # remove initial . |
589 | } else { |
617 | } else { |
590 | $cdom = $host; |
618 | $cdom = $host; |
591 | } |
619 | } |
592 | |
620 | |
593 | # store it |
621 | # store it |
594 | $jar->{version} = 1; |
622 | $jar->{version} = 2; |
595 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
623 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
596 | |
624 | |
597 | redo if /\G\s*,/gc; |
625 | redo if /\G\s*,/gc; |
598 | } |
626 | } |
599 | } |
627 | } |
… | |
… | |
692 | } |
720 | } |
693 | |
721 | |
694 | our %IDEMPOTENT = ( |
722 | our %IDEMPOTENT = ( |
695 | DELETE => 1, |
723 | DELETE => 1, |
696 | GET => 1, |
724 | GET => 1, |
|
|
725 | QUERY => 1, |
697 | HEAD => 1, |
726 | HEAD => 1, |
698 | OPTIONS => 1, |
727 | OPTIONS => 1, |
699 | PUT => 1, |
728 | PUT => 1, |
700 | TRACE => 1, |
729 | TRACE => 1, |
701 | |
730 | |
… | |
… | |
713 | MKCOL => 1, |
742 | MKCOL => 1, |
714 | MKREDIRECTREF => 1, |
743 | MKREDIRECTREF => 1, |
715 | MKWORKSPACE => 1, |
744 | MKWORKSPACE => 1, |
716 | MOVE => 1, |
745 | MOVE => 1, |
717 | ORDERPATCH => 1, |
746 | ORDERPATCH => 1, |
|
|
747 | PRI => 1, |
718 | PROPFIND => 1, |
748 | PROPFIND => 1, |
719 | PROPPATCH => 1, |
749 | PROPPATCH => 1, |
720 | REBIND => 1, |
750 | REBIND => 1, |
721 | REPORT => 1, |
751 | REPORT => 1, |
722 | SEARCH => 1, |
752 | SEARCH => 1, |
… | |
… | |
765 | |
795 | |
766 | my $uport = $uscheme eq "http" ? 80 |
796 | my $uport = $uscheme eq "http" ? 80 |
767 | : $uscheme eq "https" ? 443 |
797 | : $uscheme eq "https" ? 443 |
768 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
798 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
769 | |
799 | |
770 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
800 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
771 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
801 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
772 | |
802 | |
773 | my $uhost = lc $1; |
803 | my $uhost = lc $1; |
774 | $uport = $2 if defined $2; |
804 | $uport = $2 if defined $2; |
775 | |
805 | |
… | |
… | |
821 | my $was_persistent; # true if this is actually a recycled connection |
851 | my $was_persistent; # true if this is actually a recycled connection |
822 | |
852 | |
823 | # the key to use in the keepalive cache |
853 | # the key to use in the keepalive cache |
824 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
854 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
825 | |
855 | |
826 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
856 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
827 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
857 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
828 | |
858 | |
829 | my %state = (connect_guard => 1); |
859 | my %state = (connect_guard => 1); |
830 | |
860 | |
831 | my $ae_error = 595; # connecting |
861 | my $ae_error = 595; # connecting |
… | |
… | |
841 | # send request |
871 | # send request |
842 | $hdl->push_write ( |
872 | $hdl->push_write ( |
843 | "$method $rpath HTTP/1.1\015\012" |
873 | "$method $rpath HTTP/1.1\015\012" |
844 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
874 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
845 | . "\015\012" |
875 | . "\015\012" |
846 | . (delete $arg{body}) |
876 | . $arg{body} |
847 | ); |
877 | ); |
848 | |
878 | |
849 | # return if error occurred during push_write() |
879 | # return if error occurred during push_write() |
850 | return unless %state; |
880 | return unless %state; |
851 | |
881 | |
… | |
… | |
881 | |
911 | |
882 | %hdr = (%$hdr, @pseudo); |
912 | %hdr = (%$hdr, @pseudo); |
883 | } |
913 | } |
884 | |
914 | |
885 | # redirect handling |
915 | # redirect handling |
886 | # microsoft and other shitheads don't give a shit for following standards, |
916 | # relative uri handling forced by microsoft and other shitheads. |
887 | # try to support some common forms of broken Location headers. |
917 | # we give our best and fall back to URI if available. |
888 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
918 | if (exists $hdr{location}) { |
|
|
919 | my $loc = $hdr{location}; |
|
|
920 | |
|
|
921 | if ($loc =~ m%^//%) { # // |
|
|
922 | $loc = "$uscheme:$loc"; |
|
|
923 | |
|
|
924 | } elsif ($loc eq "") { |
|
|
925 | $loc = $url; |
|
|
926 | |
|
|
927 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
889 | $hdr{location} =~ s/^\.\/+//; |
928 | $loc =~ s/^\.\/+//; |
890 | |
929 | |
891 | my $url = "$rscheme://$uhost:$uport"; |
930 | if ($loc !~ m%^[.?#]%) { |
|
|
931 | my $prefix = "$uscheme://$uauthority"; |
892 | |
932 | |
893 | unless ($hdr{location} =~ s/^\///) { |
933 | unless ($loc =~ s/^\///) { |
894 | $url .= $upath; |
934 | $prefix .= $upath; |
895 | $url =~ s/\/[^\/]*$//; |
935 | $prefix =~ s/\/[^\/]*$//; |
|
|
936 | } |
|
|
937 | |
|
|
938 | $loc = "$prefix/$loc"; |
|
|
939 | |
|
|
940 | } elsif (eval { require URI }) { # uri |
|
|
941 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
942 | |
|
|
943 | } else { |
|
|
944 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
945 | #$hdr{Status} = 599; |
|
|
946 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
947 | #$recurse = 0; |
|
|
948 | } |
896 | } |
949 | } |
897 | |
950 | |
898 | $hdr{location} = "$url/$hdr{location}"; |
951 | $hdr{location} = $loc; |
899 | } |
952 | } |
900 | |
953 | |
901 | my $redirect; |
954 | my $redirect; |
902 | |
955 | |
903 | if ($recurse) { |
956 | if ($recurse) { |
… | |
… | |
905 | |
958 | |
906 | # industry standard is to redirect POST as GET for |
959 | # industry standard is to redirect POST as GET for |
907 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
960 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
908 | # also, the UA should ask the user for 301 and 307 and POST, |
961 | # also, the UA should ask the user for 301 and 307 and POST, |
909 | # industry standard seems to be to simply follow. |
962 | # industry standard seems to be to simply follow. |
910 | # we go with the industry standard. |
963 | # we go with the industry standard. 308 is defined |
|
|
964 | # by rfc7538 |
911 | if ($status == 301 or $status == 302 or $status == 303) { |
965 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
966 | $redirect = 1; |
912 | # HTTP/1.1 is unclear on how to mutate the method |
967 | # HTTP/1.1 is unclear on how to mutate the method |
913 | $method = "GET" unless $method eq "HEAD"; |
968 | unless ($method eq "HEAD") { |
914 | $redirect = 1; |
969 | $method = "GET"; |
|
|
970 | delete $arg{body}; |
|
|
971 | } |
915 | } elsif ($status == 307) { |
972 | } elsif ($status == 307 or $status == 308) { |
916 | $redirect = 1; |
973 | $redirect = 1; |
917 | } |
974 | } |
918 | } |
975 | } |
919 | |
976 | |
920 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
977 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
… | |
… | |
996 | $finish->(delete $state{handle}); |
1053 | $finish->(delete $state{handle}); |
997 | |
1054 | |
998 | } elsif ($chunked) { |
1055 | } elsif ($chunked) { |
999 | my $cl = 0; |
1056 | my $cl = 0; |
1000 | my $body = ""; |
1057 | my $body = ""; |
1001 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1058 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
1002 | |
1059 | |
1003 | $state{read_chunk} = sub { |
1060 | $state{read_chunk} = sub { |
1004 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1061 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1005 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1062 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1006 | |
1063 | |
… | |
… | |
1039 | } |
1096 | } |
1040 | }; |
1097 | }; |
1041 | |
1098 | |
1042 | $_[0]->push_read (line => $state{read_chunk}); |
1099 | $_[0]->push_read (line => $state{read_chunk}); |
1043 | |
1100 | |
1044 | } elsif ($arg{on_body}) { |
1101 | } elsif (!$redirect && $arg{on_body}) { |
1045 | if (defined $len) { |
1102 | if (defined $len) { |
1046 | $_[0]->on_read (sub { |
1103 | $_[0]->on_read (sub { |
1047 | $len -= length $_[0]{rbuf}; |
1104 | $len -= length $_[0]{rbuf}; |
1048 | |
1105 | |
1049 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1106 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
1088 | _destroy_state %state; |
1145 | _destroy_state %state; |
1089 | |
1146 | |
1090 | %state = (); |
1147 | %state = (); |
1091 | $state{recurse} = |
1148 | $state{recurse} = |
1092 | http_request ( |
1149 | http_request ( |
1093 | $method => $url, |
1150 | $method => $url, |
1094 | %arg, |
1151 | %arg, |
1095 | recurse => $recurse - 1, |
1152 | recurse => $recurse - 1, |
1096 | keepalive => 0, |
1153 | persistent => 0, |
1097 | sub { |
1154 | sub { |
1098 | %state = (); |
1155 | %state = (); |
1099 | &$cb |
1156 | &$cb |
1100 | } |
1157 | } |
1101 | ); |
1158 | ); |
… | |
… | |
1147 | |
1204 | |
1148 | # now handle proxy-CONNECT method |
1205 | # now handle proxy-CONNECT method |
1149 | if ($proxy && $uscheme eq "https") { |
1206 | if ($proxy && $uscheme eq "https") { |
1150 | # oh dear, we have to wrap it into a connect request |
1207 | # oh dear, we have to wrap it into a connect request |
1151 | |
1208 | |
|
|
1209 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1210 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1211 | : ""; |
|
|
1212 | |
1152 | # maybe re-use $uauthority with patched port? |
1213 | # maybe re-use $uauthority with patched port? |
1153 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1214 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
1154 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1215 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1155 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1216 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1156 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1217 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1157 | |
1218 | |
1158 | if ($2 == 200) { |
1219 | if ($2 == 200) { |
… | |
… | |
1161 | } else { |
1222 | } else { |
1162 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1223 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1163 | } |
1224 | } |
1164 | }); |
1225 | }); |
1165 | } else { |
1226 | } else { |
|
|
1227 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1228 | |
1166 | $handle_actual_request->(); |
1229 | $handle_actual_request->(); |
1167 | } |
1230 | } |
1168 | }; |
1231 | }; |
1169 | |
1232 | |
1170 | _get_slot $uhost, sub { |
1233 | _get_slot $uhost, sub { |
… | |
… | |
1176 | # on a keepalive request (in theory, this should be a separate config option). |
1239 | # on a keepalive request (in theory, this should be a separate config option). |
1177 | if ($persistent && $KA_CACHE{$ka_key}) { |
1240 | if ($persistent && $KA_CACHE{$ka_key}) { |
1178 | $was_persistent = 1; |
1241 | $was_persistent = 1; |
1179 | |
1242 | |
1180 | $state{handle} = ka_fetch $ka_key; |
1243 | $state{handle} = ka_fetch $ka_key; |
1181 | $state{handle}->destroyed |
1244 | # $state{handle}->destroyed |
1182 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1245 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1183 | $prepare_handle->(); |
1246 | $prepare_handle->(); |
1184 | $state{handle}->destroyed |
1247 | # $state{handle}->destroyed |
1185 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1248 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
|
|
1249 | $rpath = $upath; |
1186 | $handle_actual_request->(); |
1250 | $handle_actual_request->(); |
1187 | |
1251 | |
1188 | } else { |
1252 | } else { |
1189 | my $tcp_connect = $arg{tcp_connect} |
1253 | my $tcp_connect = $arg{tcp_connect} |
1190 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1254 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1248 | save cookies to disk, and you should call this function after loading them |
1312 | save cookies to disk, and you should call this function after loading them |
1249 | again. If you have a long-running program you can additionally call this |
1313 | again. If you have a long-running program you can additionally call this |
1250 | function from time to time. |
1314 | function from time to time. |
1251 | |
1315 | |
1252 | A cookie jar is initially an empty hash-reference that is managed by this |
1316 | A cookie jar is initially an empty hash-reference that is managed by this |
1253 | module. It's format is subject to change, but currently it is like this: |
1317 | module. Its format is subject to change, but currently it is as follows: |
1254 | |
1318 | |
1255 | The key C<version> has to contain C<1>, otherwise the hash gets |
1319 | The key C<version> has to contain C<2>, otherwise the hash gets |
1256 | emptied. All other keys are hostnames or IP addresses pointing to |
1320 | cleared. All other keys are hostnames or IP addresses pointing to |
1257 | hash-references. The key for these inner hash references is the |
1321 | hash-references. The key for these inner hash references is the |
1258 | server path for which this cookie is meant, and the values are again |
1322 | server path for which this cookie is meant, and the values are again |
1259 | hash-references. Each key of those hash-references is a cookie name, and |
1323 | hash-references. Each key of those hash-references is a cookie name, and |
1260 | the value, you guessed it, is another hash-reference, this time with the |
1324 | the value, you guessed it, is another hash-reference, this time with the |
1261 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1325 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
… | |
… | |
1265 | |
1329 | |
1266 | Here is an example of a cookie jar with a single cookie, so you have a |
1330 | Here is an example of a cookie jar with a single cookie, so you have a |
1267 | chance of understanding the above paragraph: |
1331 | chance of understanding the above paragraph: |
1268 | |
1332 | |
1269 | { |
1333 | { |
1270 | version => 1, |
1334 | version => 2, |
1271 | "10.0.0.1" => { |
1335 | "10.0.0.1" => { |
1272 | "/" => { |
1336 | "/" => { |
1273 | "mythweb_id" => { |
1337 | "mythweb_id" => { |
1274 | _expires => 1293917923, |
1338 | _expires => 1293917923, |
1275 | value => "ooRung9dThee3ooyXooM1Ohm", |
1339 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1303 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1367 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1304 | |
1368 | |
1305 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1369 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1306 | |
1370 | |
1307 | The maximum number of concurrent connections to the same host (identified |
1371 | The maximum number of concurrent connections to the same host (identified |
1308 | by the hostname). If the limit is exceeded, then the additional requests |
1372 | by the hostname). If the limit is exceeded, then additional requests |
1309 | are queued until previous connections are closed. Both persistent and |
1373 | are queued until previous connections are closed. Both persistent and |
1310 | non-persistent connections are counted in this limit. |
1374 | non-persistent connections are counted in this limit. |
1311 | |
1375 | |
1312 | The default value for this is C<4>, and it is highly advisable to not |
1376 | The default value for this is C<4>, and it is highly advisable to not |
1313 | increase it much. |
1377 | increase it much. |
… | |
… | |
1420 | or die "$file: $!"; |
1484 | or die "$file: $!"; |
1421 | |
1485 | |
1422 | my %hdr; |
1486 | my %hdr; |
1423 | my $ofs = 0; |
1487 | my $ofs = 0; |
1424 | |
1488 | |
1425 | warn stat $fh; |
|
|
1426 | warn -s _; |
|
|
1427 | if (stat $fh and -s _) { |
1489 | if (stat $fh and -s _) { |
1428 | $ofs = -s _; |
1490 | $ofs = -s _; |
1429 | warn "-s is ", $ofs; |
1491 | warn "-s is ", $ofs; |
1430 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1492 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1431 | $hdr{"range"} = "bytes=$ofs-"; |
1493 | $hdr{"range"} = "bytes=$ofs-"; |
… | |
… | |
1459 | my (undef, $hdr) = @_; |
1521 | my (undef, $hdr) = @_; |
1460 | |
1522 | |
1461 | my $status = $hdr->{Status}; |
1523 | my $status = $hdr->{Status}; |
1462 | |
1524 | |
1463 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1525 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1464 | utime $fh, $time, $time; |
1526 | utime $time, $time, $fh; |
1465 | } |
1527 | } |
1466 | |
1528 | |
1467 | if ($status == 200 || $status == 206 || $status == 416) { |
1529 | if ($status == 200 || $status == 206 || $status == 416) { |
1468 | # download ok || resume ok || file already fully downloaded |
1530 | # download ok || resume ok || file already fully downloaded |
1469 | $cb->(1, $hdr); |
1531 | $cb->(1, $hdr); |