… | |
… | |
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 = '2.02'; |
51 | our $VERSION = 2.21; |
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 | |
… | |
… | |
154 | |
154 | |
155 | =over 4 |
155 | =over 4 |
156 | |
156 | |
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 |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
160 | retries and so on, and how often to do so. |
160 | other retries and so on, and how often to do so. |
|
|
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. |
161 | |
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 |
… | |
… | |
169 | |
174 | |
170 | You really should provide your own C<User-Agent:> header value that is |
175 | You really should provide your own C<User-Agent:> header value that is |
171 | appropriate for your program - I wouldn't be surprised if the default |
176 | appropriate for your program - I wouldn't be surprised if the default |
172 | AnyEvent string gets blocked by webservers sooner or later. |
177 | AnyEvent string gets blocked by webservers sooner or later. |
173 | |
178 | |
|
|
179 | Also, make sure that your headers names and values do not contain any |
|
|
180 | embedded newlines. |
|
|
181 | |
174 | =item timeout => $seconds |
182 | =item timeout => $seconds |
175 | |
183 | |
176 | The time-out to use for various stages - each connect attempt will reset |
184 | The time-out to use for various stages - each connect attempt will reset |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
185 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | timeout. |
186 | timeout. |
179 | |
187 | |
180 | Default timeout is 5 minutes. |
188 | Default timeout is 5 minutes. |
181 | |
189 | |
182 | =item proxy => [$host, $port[, $scheme]] or undef |
190 | =item proxy => [$host, $port[, $scheme]] or undef |
183 | |
191 | |
184 | Use the given http proxy for all requests. If not specified, then the |
192 | Use the given http proxy for all requests, or no proxy if C<undef> is |
185 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
193 | used. |
186 | |
194 | |
187 | 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. |
|
|
196 | |
|
|
197 | If not specified, then the default proxy is used (see |
|
|
198 | C<AnyEvent::HTTP::set_proxy>). |
188 | |
199 | |
189 | =item body => $string |
200 | =item body => $string |
190 | |
201 | |
191 | The request body, usually empty. Will be sent as-is (future versions of |
202 | The request body, usually empty. Will be sent as-is (future versions of |
192 | this module might offer more options). |
203 | this module might offer more options). |
… | |
… | |
236 | context) - only connections using the same unique ID will be reused. |
247 | context) - only connections using the same unique ID will be reused. |
237 | |
248 | |
238 | =item on_prepare => $callback->($fh) |
249 | =item on_prepare => $callback->($fh) |
239 | |
250 | |
240 | In rare cases you need to "tune" the socket before it is used to |
251 | In rare cases you need to "tune" the socket before it is used to |
241 | connect (for exmaple, to bind it on a given IP address). This parameter |
252 | connect (for example, to bind it on a given IP address). This parameter |
242 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
253 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
243 | and behaves exactly the same way (e.g. it has to provide a |
254 | and behaves exactly the same way (e.g. it has to provide a |
244 | timeout). See the description for the C<$prepare_cb> argument of |
255 | timeout). See the description for the C<$prepare_cb> argument of |
245 | C<AnyEvent::Socket::tcp_connect> for details. |
256 | C<AnyEvent::Socket::tcp_connect> for details. |
246 | |
257 | |
… | |
… | |
378 | |
389 | |
379 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
390 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
380 | timeout of 30 seconds. |
391 | timeout of 30 seconds. |
381 | |
392 | |
382 | http_request |
393 | http_request |
383 | GET => "https://www.google.com", |
394 | HEAD => "https://www.google.com", |
384 | headers => { "user-agent" => "MySearchClient 1.0" }, |
395 | headers => { "user-agent" => "MySearchClient 1.0" }, |
385 | timeout => 30, |
396 | timeout => 30, |
386 | sub { |
397 | sub { |
387 | my ($body, $hdr) = @_; |
398 | my ($body, $hdr) = @_; |
388 | use Data::Dumper; |
399 | use Data::Dumper; |
… | |
… | |
529 | while ( |
540 | while ( |
530 | m{ |
541 | m{ |
531 | \G\s* |
542 | \G\s* |
532 | (?: |
543 | (?: |
533 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
544 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
534 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
545 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )? |
535 | ) |
546 | ) |
536 | }gcxsi |
547 | }gcxsi |
537 | ) { |
548 | ) { |
538 | my $name = $2; |
549 | my $name = $2; |
539 | my $value = $4; |
550 | my $value = $4; |
… | |
… | |
683 | |
694 | |
684 | $cb->(undef, $hdr); |
695 | $cb->(undef, $hdr); |
685 | () |
696 | () |
686 | } |
697 | } |
687 | |
698 | |
|
|
699 | our %IDEMPOTENT = ( |
|
|
700 | DELETE => 1, |
|
|
701 | GET => 1, |
|
|
702 | HEAD => 1, |
|
|
703 | OPTIONS => 1, |
|
|
704 | PUT => 1, |
|
|
705 | TRACE => 1, |
|
|
706 | |
|
|
707 | ACL => 1, |
|
|
708 | "BASELINE-CONTROL" => 1, |
|
|
709 | BIND => 1, |
|
|
710 | CHECKIN => 1, |
|
|
711 | CHECKOUT => 1, |
|
|
712 | COPY => 1, |
|
|
713 | LABEL => 1, |
|
|
714 | LINK => 1, |
|
|
715 | MERGE => 1, |
|
|
716 | MKACTIVITY => 1, |
|
|
717 | MKCALENDAR => 1, |
|
|
718 | MKCOL => 1, |
|
|
719 | MKREDIRECTREF => 1, |
|
|
720 | MKWORKSPACE => 1, |
|
|
721 | MOVE => 1, |
|
|
722 | ORDERPATCH => 1, |
|
|
723 | PROPFIND => 1, |
|
|
724 | PROPPATCH => 1, |
|
|
725 | REBIND => 1, |
|
|
726 | REPORT => 1, |
|
|
727 | SEARCH => 1, |
|
|
728 | UNBIND => 1, |
|
|
729 | UNCHECKOUT => 1, |
|
|
730 | UNLINK => 1, |
|
|
731 | UNLOCK => 1, |
|
|
732 | UPDATE => 1, |
|
|
733 | UPDATEREDIRECTREF => 1, |
|
|
734 | "VERSION-CONTROL" => 1, |
|
|
735 | ); |
|
|
736 | |
688 | sub http_request($$@) { |
737 | sub http_request($$@) { |
689 | my $cb = pop; |
738 | my $cb = pop; |
690 | my ($method, $url, %arg) = @_; |
739 | my ($method, $url, %arg) = @_; |
691 | |
740 | |
692 | my %hdr; |
741 | my %hdr; |
… | |
… | |
709 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
758 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
710 | |
759 | |
711 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
760 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
712 | if $recurse < 0; |
761 | if $recurse < 0; |
713 | |
762 | |
714 | my $proxy = $arg{proxy} || $PROXY; |
763 | my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY; |
715 | my $timeout = $arg{timeout} || $TIMEOUT; |
764 | my $timeout = $arg{timeout} || $TIMEOUT; |
716 | |
765 | |
717 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
766 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
718 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
767 | $url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
719 | |
768 | |
720 | $uscheme = lc $uscheme; |
769 | $uscheme = lc $uscheme; |
721 | |
770 | |
722 | my $uport = $uscheme eq "http" ? 80 |
771 | my $uport = $uscheme eq "http" ? 80 |
723 | : $uscheme eq "https" ? 443 |
772 | : $uscheme eq "https" ? 443 |
… | |
… | |
767 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
816 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
768 | |
817 | |
769 | $hdr{"content-length"} = length $arg{body} |
818 | $hdr{"content-length"} = length $arg{body} |
770 | if length $arg{body} || $method ne "GET"; |
819 | if length $arg{body} || $method ne "GET"; |
771 | |
820 | |
772 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
821 | my $idempotent = $IDEMPOTENT{$method}; |
773 | |
822 | |
774 | # default value for keepalive is true iff the request is for an idempotent method |
823 | # default value for keepalive is true iff the request is for an idempotent method |
775 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent; |
824 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
776 | my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy; |
825 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
777 | my $keptalive; # true if this is actually a recycled connection |
826 | my $was_persistent; # true if this is actually a recycled connection |
778 | |
827 | |
779 | # the key to use in the keepalive cache |
828 | # the key to use in the keepalive cache |
780 | my $ka_key = "$uhost\x00$arg{sessionid}"; |
829 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
781 | |
830 | |
782 | $hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
831 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
783 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
832 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
784 | |
833 | |
785 | my %state = (connect_guard => 1); |
834 | my %state = (connect_guard => 1); |
786 | |
835 | |
787 | my $ae_error = 595; # connecting |
836 | my $ae_error = 595; # connecting |
… | |
… | |
797 | # send request |
846 | # send request |
798 | $hdl->push_write ( |
847 | $hdl->push_write ( |
799 | "$method $rpath HTTP/1.1\015\012" |
848 | "$method $rpath HTTP/1.1\015\012" |
800 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
849 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
801 | . "\015\012" |
850 | . "\015\012" |
802 | . (delete $arg{body}) |
851 | . $arg{body} |
803 | ); |
852 | ); |
804 | |
853 | |
805 | # return if error occured during push_write() |
854 | # return if error occurred during push_write() |
806 | return unless %state; |
855 | return unless %state; |
807 | |
856 | |
808 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
857 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
809 | %hdr = (); |
858 | %hdr = (); |
810 | |
859 | |
… | |
… | |
837 | |
886 | |
838 | %hdr = (%$hdr, @pseudo); |
887 | %hdr = (%$hdr, @pseudo); |
839 | } |
888 | } |
840 | |
889 | |
841 | # redirect handling |
890 | # redirect handling |
842 | # microsoft and other shitheads don't give a shit for following standards, |
891 | # relative uri handling forced by microsoft and other shitheads. |
843 | # try to support some common forms of broken Location headers. |
892 | # we give our best and fall back to URI if available. |
844 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
893 | if (exists $hdr{location}) { |
|
|
894 | my $loc = $hdr{location}; |
|
|
895 | |
|
|
896 | if ($loc =~ m%^//%) { # // |
|
|
897 | $loc = "$rscheme:$loc"; |
|
|
898 | |
|
|
899 | } elsif ($loc eq "") { |
|
|
900 | $loc = $url; |
|
|
901 | |
|
|
902 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
845 | $hdr{location} =~ s/^\.\/+//; |
903 | $loc =~ s/^\.\/+//; |
846 | |
904 | |
|
|
905 | if ($loc !~ m%^[.?#]%) { |
847 | my $url = "$rscheme://$uhost:$uport"; |
906 | my $prefix = "$rscheme://$uhost:$uport"; |
848 | |
907 | |
849 | unless ($hdr{location} =~ s/^\///) { |
908 | unless ($loc =~ s/^\///) { |
850 | $url .= $upath; |
909 | $prefix .= $upath; |
851 | $url =~ s/\/[^\/]*$//; |
910 | $prefix =~ s/\/[^\/]*$//; |
|
|
911 | } |
|
|
912 | |
|
|
913 | $loc = "$prefix/$loc"; |
|
|
914 | |
|
|
915 | } elsif (eval { require URI }) { # uri |
|
|
916 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
917 | |
|
|
918 | } else { |
|
|
919 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
920 | #$hdr{Status} = 599; |
|
|
921 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
922 | #$recurse = 0; |
|
|
923 | } |
852 | } |
924 | } |
853 | |
925 | |
854 | $hdr{location} = "$url/$hdr{location}"; |
926 | $hdr{location} = $loc; |
855 | } |
927 | } |
856 | |
928 | |
857 | my $redirect; |
929 | my $redirect; |
858 | |
930 | |
859 | if ($recurse) { |
931 | if ($recurse) { |
… | |
… | |
861 | |
933 | |
862 | # industry standard is to redirect POST as GET for |
934 | # industry standard is to redirect POST as GET for |
863 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
935 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
864 | # also, the UA should ask the user for 301 and 307 and POST, |
936 | # also, the UA should ask the user for 301 and 307 and POST, |
865 | # industry standard seems to be to simply follow. |
937 | # industry standard seems to be to simply follow. |
866 | # we go with the industry standard. |
938 | # we go with the industry standard. 308 is defined |
|
|
939 | # by rfc7538 |
867 | if ($status == 301 or $status == 302 or $status == 303) { |
940 | if ($status == 301 or $status == 302 or $status == 303) { |
868 | # HTTP/1.1 is unclear on how to mutate the method |
941 | # HTTP/1.1 is unclear on how to mutate the method |
869 | $method = "GET" unless $method eq "HEAD"; |
942 | $method = "GET" unless $method eq "HEAD"; |
870 | $redirect = 1; |
943 | $redirect = 1; |
871 | } elsif ($status == 307) { |
944 | } elsif ($status == 307 or $status == 308) { |
872 | $redirect = 1; |
945 | $redirect = 1; |
873 | } |
946 | } |
874 | } |
947 | } |
875 | |
948 | |
876 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
949 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
877 | if ($state{handle}) { |
950 | if ($state{handle}) { |
878 | # handle keepalive |
951 | # handle keepalive |
879 | if ( |
952 | if ( |
880 | $keepalive |
953 | $persistent |
881 | && $_[3] |
954 | && $_[3] |
882 | && ($hdr{HTTPVersion} < 1.1 |
955 | && ($hdr{HTTPVersion} < 1.1 |
883 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
956 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
884 | : $hdr{connection} !~ /\bclose\b/i) |
957 | : $hdr{connection} !~ /\bclose\b/i) |
885 | ) { |
958 | ) { |
… | |
… | |
904 | |
977 | |
905 | if ($redirect && exists $hdr{location}) { |
978 | if ($redirect && exists $hdr{location}) { |
906 | # we ignore any errors, as it is very common to receive |
979 | # we ignore any errors, as it is very common to receive |
907 | # Content-Length != 0 but no actual body |
980 | # Content-Length != 0 but no actual body |
908 | # we also access %hdr, as $_[1] might be an erro |
981 | # we also access %hdr, as $_[1] might be an erro |
|
|
982 | $state{recurse} = |
909 | http_request ( |
983 | http_request ( |
910 | $method => $hdr{location}, |
984 | $method => $hdr{location}, |
911 | %arg, |
985 | %arg, |
912 | recurse => $recurse - 1, |
986 | recurse => $recurse - 1, |
913 | Redirect => [$_[0], \%hdr], |
987 | Redirect => [$_[0], \%hdr], |
|
|
988 | sub { |
|
|
989 | %state = (); |
914 | $cb |
990 | &$cb |
|
|
991 | }, |
915 | ); |
992 | ); |
916 | } else { |
993 | } else { |
917 | $cb->($_[0], \%hdr); |
994 | $cb->($_[0], \%hdr); |
918 | } |
995 | } |
919 | }; |
996 | }; |
920 | |
997 | |
… | |
… | |
952 | my $body = ""; |
1029 | my $body = ""; |
953 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1030 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
954 | |
1031 | |
955 | $state{read_chunk} = sub { |
1032 | $state{read_chunk} = sub { |
956 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1033 | $_[1] =~ /^([0-9a-fA-F]+)/ |
957 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1034 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
958 | |
1035 | |
959 | my $len = hex $1; |
1036 | my $len = hex $1; |
960 | |
1037 | |
961 | if ($len) { |
1038 | if ($len) { |
962 | $cl += $len; |
1039 | $cl += $len; |
… | |
… | |
1032 | } |
1109 | } |
1033 | }; |
1110 | }; |
1034 | |
1111 | |
1035 | # if keepalive is enabled, then the server closing the connection |
1112 | # if keepalive is enabled, then the server closing the connection |
1036 | # before a response can happen legally - we retry on idempotent methods. |
1113 | # before a response can happen legally - we retry on idempotent methods. |
1037 | if ($keptalive && $idempotent) { |
1114 | if ($was_persistent && $idempotent) { |
1038 | my $old_eof = $hdl->{on_eof}; |
1115 | my $old_eof = $hdl->{on_eof}; |
1039 | $hdl->{on_eof} = sub { |
1116 | $hdl->{on_eof} = sub { |
1040 | _destroy_state %state; |
1117 | _destroy_state %state; |
1041 | |
1118 | |
|
|
1119 | %state = (); |
|
|
1120 | $state{recurse} = |
1042 | http_request ( |
1121 | http_request ( |
1043 | $method => $url, |
1122 | $method => $url, |
1044 | %arg, |
1123 | %arg, |
|
|
1124 | recurse => $recurse - 1, |
1045 | keepalive => 0, |
1125 | keepalive => 0, |
|
|
1126 | sub { |
|
|
1127 | %state = (); |
1046 | $cb |
1128 | &$cb |
|
|
1129 | } |
1047 | ); |
1130 | ); |
1048 | }; |
1131 | }; |
1049 | $hdl->on_read (sub { |
1132 | $hdl->on_read (sub { |
1050 | return unless %state; |
1133 | return unless %state; |
1051 | |
1134 | |
1052 | # as soon as we receive something, a connection close |
1135 | # as soon as we receive something, a connection close |
… | |
… | |
1060 | }; |
1143 | }; |
1061 | |
1144 | |
1062 | my $prepare_handle = sub { |
1145 | my $prepare_handle = sub { |
1063 | my ($hdl) = $state{handle}; |
1146 | my ($hdl) = $state{handle}; |
1064 | |
1147 | |
1065 | $hdl->timeout ($timeout); |
|
|
1066 | $hdl->on_error (sub { |
1148 | $hdl->on_error (sub { |
1067 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1149 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1068 | }); |
1150 | }); |
1069 | $hdl->on_eof (sub { |
1151 | $hdl->on_eof (sub { |
1070 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1152 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1071 | }); |
1153 | }); |
|
|
1154 | $hdl->timeout_reset; |
|
|
1155 | $hdl->timeout ($timeout); |
1072 | }; |
1156 | }; |
1073 | |
1157 | |
1074 | # connected to proxy (or origin server) |
1158 | # connected to proxy (or origin server) |
1075 | my $connect_cb = sub { |
1159 | my $connect_cb = sub { |
1076 | my $fh = shift |
1160 | my $fh = shift |
… | |
… | |
1117 | |
1201 | |
1118 | return unless $state{connect_guard}; |
1202 | return unless $state{connect_guard}; |
1119 | |
1203 | |
1120 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1204 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1121 | # on a keepalive request (in theory, this should be a separate config option). |
1205 | # on a keepalive request (in theory, this should be a separate config option). |
1122 | if ($keepalive && $KA_CACHE{$ka_key}) { |
1206 | if ($persistent && $KA_CACHE{$ka_key}) { |
1123 | $keptalive = 1; |
1207 | $was_persistent = 1; |
|
|
1208 | |
1124 | $state{handle} = ka_fetch $ka_key; |
1209 | $state{handle} = ka_fetch $ka_key; |
|
|
1210 | $state{handle}->destroyed |
|
|
1211 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1125 | $prepare_handle->(); |
1212 | $prepare_handle->(); |
|
|
1213 | $state{handle}->destroyed |
|
|
1214 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1126 | $handle_actual_request->(); |
1215 | $handle_actual_request->(); |
1127 | |
1216 | |
1128 | } else { |
1217 | } else { |
1129 | my $tcp_connect = $arg{tcp_connect} |
1218 | my $tcp_connect = $arg{tcp_connect} |
1130 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1219 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1172 | Sets the default proxy server to use. The proxy-url must begin with a |
1261 | Sets the default proxy server to use. The proxy-url must begin with a |
1173 | string of the form C<http://host:port>, croaks otherwise. |
1262 | string of the form C<http://host:port>, croaks otherwise. |
1174 | |
1263 | |
1175 | To clear an already-set proxy, use C<undef>. |
1264 | To clear an already-set proxy, use C<undef>. |
1176 | |
1265 | |
|
|
1266 | When AnyEvent::HTTP is loaded for the first time it will query the |
|
|
1267 | default proxy from the operating system, currently by looking at |
|
|
1268 | C<$ENV{http_proxy>}. |
|
|
1269 | |
1177 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1270 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1178 | |
1271 | |
1179 | Remove all cookies from the cookie jar that have been expired. If |
1272 | Remove all cookies from the cookie jar that have been expired. If |
1180 | C<$session_end> is given and true, then additionally remove all session |
1273 | C<$session_end> is given and true, then additionally remove all session |
1181 | cookies. |
1274 | cookies. |
1182 | |
1275 | |
1183 | You should call this function (with a true C<$session_end>) before you |
1276 | You should call this function (with a true C<$session_end>) before you |
1184 | save cookies to disk, and you should call this function after loading them |
1277 | save cookies to disk, and you should call this function after loading them |
1185 | again. If you have a long-running program you can additonally call this |
1278 | again. If you have a long-running program you can additionally call this |
1186 | function from time to time. |
1279 | function from time to time. |
1187 | |
1280 | |
1188 | A cookie jar is initially an empty hash-reference that is managed by this |
1281 | A cookie jar is initially an empty hash-reference that is managed by this |
1189 | module. It's format is subject to change, but currently it is like this: |
1282 | module. Its format is subject to change, but currently it is as follows: |
1190 | |
1283 | |
1191 | The key C<version> has to contain C<1>, otherwise the hash gets |
1284 | The key C<version> has to contain C<1>, otherwise the hash gets |
1192 | emptied. All other keys are hostnames or IP addresses pointing to |
1285 | emptied. All other keys are hostnames or IP addresses pointing to |
1193 | hash-references. The key for these inner hash references is the |
1286 | hash-references. The key for these inner hash references is the |
1194 | server path for which this cookie is meant, and the values are again |
1287 | server path for which this cookie is meant, and the values are again |
1195 | hash-references. The keys of those hash-references is the cookie name, and |
1288 | hash-references. Each key of those hash-references is a cookie name, and |
1196 | the value, you guessed it, is another hash-reference, this time with the |
1289 | the value, you guessed it, is another hash-reference, this time with the |
1197 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1290 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1198 | which have been replaced by a C<_expires> key that contains the cookie |
1291 | which have been replaced by a C<_expires> key that contains the cookie |
1199 | expiry timestamp. |
1292 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1293 | C<_expires> key. |
1200 | |
1294 | |
1201 | Here is an example of a cookie jar with a single cookie, so you have a |
1295 | Here is an example of a cookie jar with a single cookie, so you have a |
1202 | chance of understanding the above paragraph: |
1296 | chance of understanding the above paragraph: |
1203 | |
1297 | |
1204 | { |
1298 | { |
… | |
… | |
1228 | |
1322 | |
1229 | The default value for the C<recurse> request parameter (default: C<10>). |
1323 | The default value for the C<recurse> request parameter (default: C<10>). |
1230 | |
1324 | |
1231 | =item $AnyEvent::HTTP::TIMEOUT |
1325 | =item $AnyEvent::HTTP::TIMEOUT |
1232 | |
1326 | |
1233 | The default timeout for conenction operations (default: C<300>). |
1327 | The default timeout for connection operations (default: C<300>). |
1234 | |
1328 | |
1235 | =item $AnyEvent::HTTP::USERAGENT |
1329 | =item $AnyEvent::HTTP::USERAGENT |
1236 | |
1330 | |
1237 | The default value for the C<User-Agent> header (the default is |
1331 | The default value for the C<User-Agent> header (the default is |
1238 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1332 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1239 | |
1333 | |
1240 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1334 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1241 | |
1335 | |
1242 | The maximum number of concurrent connections to the same host (identified |
1336 | The maximum number of concurrent connections to the same host (identified |
1243 | by the hostname). If the limit is exceeded, then the additional requests |
1337 | by the hostname). If the limit is exceeded, then additional requests |
1244 | are queued until previous connections are closed. Both persistent and |
1338 | are queued until previous connections are closed. Both persistent and |
1245 | non-persistent connections are counted in this limit. |
1339 | non-persistent connections are counted in this limit. |
1246 | |
1340 | |
1247 | The default value for this is C<4>, and it is highly advisable to not |
1341 | The default value for this is C<4>, and it is highly advisable to not |
1248 | increase it much. |
1342 | increase it much. |
1249 | |
1343 | |
1250 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1344 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1251 | connections, older browsers used 2, newers (such as firefox 3) typically |
1345 | connections, older browsers used 2, newer ones (such as firefox 3) |
1252 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1346 | typically use 6, and Opera uses 8 because like, they have the fastest |
1253 | give a shit for everybody else on the planet. |
1347 | browser and give a shit for everybody else on the planet. |
1254 | |
1348 | |
1255 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1349 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1256 | |
1350 | |
1257 | The time after which idle persistent conenctions get closed by |
1351 | The time after which idle persistent connections get closed by |
1258 | AnyEvent::HTTP (default: C<3>). |
1352 | AnyEvent::HTTP (default: C<3>). |
1259 | |
1353 | |
1260 | =item $AnyEvent::HTTP::ACTIVE |
1354 | =item $AnyEvent::HTTP::ACTIVE |
1261 | |
1355 | |
1262 | The number of active connections. This is not the number of currently |
1356 | The number of active connections. This is not the number of currently |
… | |
… | |
1303 | # other formats fail in the loop below |
1397 | # other formats fail in the loop below |
1304 | |
1398 | |
1305 | for (0..11) { |
1399 | for (0..11) { |
1306 | if ($m eq $month[$_]) { |
1400 | if ($m eq $month[$_]) { |
1307 | require Time::Local; |
1401 | require Time::Local; |
1308 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1402 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1309 | } |
1403 | } |
1310 | } |
1404 | } |
1311 | |
1405 | |
1312 | undef |
1406 | undef |
1313 | } |
1407 | } |
… | |
… | |
1327 | set_proxy $ENV{http_proxy}; |
1421 | set_proxy $ENV{http_proxy}; |
1328 | }; |
1422 | }; |
1329 | |
1423 | |
1330 | =head2 SHOWCASE |
1424 | =head2 SHOWCASE |
1331 | |
1425 | |
1332 | This section contaisn some more elaborate "real-world" examples or code |
1426 | This section contains some more elaborate "real-world" examples or code |
1333 | snippets. |
1427 | snippets. |
1334 | |
1428 | |
1335 | =head2 HTTP/1.1 FILE DOWNLOAD |
1429 | =head2 HTTP/1.1 FILE DOWNLOAD |
1336 | |
1430 | |
1337 | Downloading files with HTTP can be quite tricky, especially when something |
1431 | Downloading files with HTTP can be quite tricky, especially when something |
1338 | goes wrong and you want tor esume. |
1432 | goes wrong and you want to resume. |
1339 | |
1433 | |
1340 | Here is a function that initiates and resumes a download. It uses the |
1434 | Here is a function that initiates and resumes a download. It uses the |
1341 | last modified time to check for file content changes, and works with many |
1435 | last modified time to check for file content changes, and works with many |
1342 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1436 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1343 | on older servers. |
1437 | on older servers. |
1344 | |
1438 | |
1345 | It calls the completion callback with either C<undef>, which means a |
1439 | It calls the completion callback with either C<undef>, which means a |
1346 | nonretryable error occured, C<0> when the download was partial and should |
1440 | nonretryable error occurred, C<0> when the download was partial and should |
1347 | be retried, and C<1> if it was successful. |
1441 | be retried, and C<1> if it was successful. |
1348 | |
1442 | |
1349 | use AnyEvent::HTTP; |
1443 | use AnyEvent::HTTP; |
1350 | |
1444 | |
1351 | sub download($$$) { |
1445 | sub download($$$) { |
… | |
… | |
1359 | |
1453 | |
1360 | warn stat $fh; |
1454 | warn stat $fh; |
1361 | warn -s _; |
1455 | warn -s _; |
1362 | if (stat $fh and -s _) { |
1456 | if (stat $fh and -s _) { |
1363 | $ofs = -s _; |
1457 | $ofs = -s _; |
1364 | warn "-s is ", $ofs;#d# |
1458 | warn "-s is ", $ofs; |
1365 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1459 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1366 | $hdr{"range"} = "bytes=$ofs-"; |
1460 | $hdr{"range"} = "bytes=$ofs-"; |
1367 | } |
1461 | } |
1368 | |
1462 | |
1369 | http_get $url, |
1463 | http_get $url, |