… | |
… | |
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 = '2.11'; |
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 |
… | |
… | |
242 | context) - only connections using the same unique ID will be reused. |
247 | context) - only connections using the same unique ID will be reused. |
243 | |
248 | |
244 | =item on_prepare => $callback->($fh) |
249 | =item on_prepare => $callback->($fh) |
245 | |
250 | |
246 | 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 |
247 | 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 |
248 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
253 | 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 |
254 | and behaves exactly the same way (e.g. it has to provide a |
250 | timeout). See the description for the C<$prepare_cb> argument of |
255 | timeout). See the description for the C<$prepare_cb> argument of |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
256 | C<AnyEvent::Socket::tcp_connect> for details. |
252 | |
257 | |
… | |
… | |
384 | |
389 | |
385 | 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 |
386 | timeout of 30 seconds. |
391 | timeout of 30 seconds. |
387 | |
392 | |
388 | http_request |
393 | http_request |
389 | GET => "https://www.google.com", |
394 | HEAD => "https://www.google.com", |
390 | headers => { "user-agent" => "MySearchClient 1.0" }, |
395 | headers => { "user-agent" => "MySearchClient 1.0" }, |
391 | timeout => 30, |
396 | timeout => 30, |
392 | sub { |
397 | sub { |
393 | my ($body, $hdr) = @_; |
398 | my ($body, $hdr) = @_; |
394 | use Data::Dumper; |
399 | use Data::Dumper; |
… | |
… | |
689 | |
694 | |
690 | $cb->(undef, $hdr); |
695 | $cb->(undef, $hdr); |
691 | () |
696 | () |
692 | } |
697 | } |
693 | |
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 | |
694 | sub http_request($$@) { |
737 | sub http_request($$@) { |
695 | my $cb = pop; |
738 | my $cb = pop; |
696 | my ($method, $url, %arg) = @_; |
739 | my ($method, $url, %arg) = @_; |
697 | |
740 | |
698 | my %hdr; |
741 | my %hdr; |
… | |
… | |
773 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
816 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
774 | |
817 | |
775 | $hdr{"content-length"} = length $arg{body} |
818 | $hdr{"content-length"} = length $arg{body} |
776 | if length $arg{body} || $method ne "GET"; |
819 | if length $arg{body} || $method ne "GET"; |
777 | |
820 | |
778 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
821 | my $idempotent = $IDEMPOTENT{$method}; |
779 | |
822 | |
780 | # 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 |
781 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
824 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
782 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
825 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
783 | my $was_persistent; # true if this is actually a recycled connection |
826 | my $was_persistent; # true if this is actually a recycled connection |
784 | |
827 | |
785 | # the key to use in the keepalive cache |
828 | # the key to use in the keepalive cache |
786 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
829 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
787 | |
830 | |
788 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
831 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
789 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
832 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
790 | |
833 | |
791 | my %state = (connect_guard => 1); |
834 | my %state = (connect_guard => 1); |
792 | |
835 | |
793 | my $ae_error = 595; # connecting |
836 | my $ae_error = 595; # connecting |
… | |
… | |
803 | # send request |
846 | # send request |
804 | $hdl->push_write ( |
847 | $hdl->push_write ( |
805 | "$method $rpath HTTP/1.1\015\012" |
848 | "$method $rpath HTTP/1.1\015\012" |
806 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
849 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
807 | . "\015\012" |
850 | . "\015\012" |
808 | . (delete $arg{body}) |
851 | . $arg{body} |
809 | ); |
852 | ); |
810 | |
853 | |
811 | # return if error occured during push_write() |
854 | # return if error occurred during push_write() |
812 | return unless %state; |
855 | return unless %state; |
813 | |
856 | |
814 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
857 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
815 | %hdr = (); |
858 | %hdr = (); |
816 | |
859 | |
… | |
… | |
843 | |
886 | |
844 | %hdr = (%$hdr, @pseudo); |
887 | %hdr = (%$hdr, @pseudo); |
845 | } |
888 | } |
846 | |
889 | |
847 | # redirect handling |
890 | # redirect handling |
848 | # microsoft and other shitheads don't give a shit for following standards, |
891 | # relative uri handling forced by microsoft and other shitheads. |
849 | # try to support some common forms of broken Location headers. |
892 | # we give our best and fall back to URI if available. |
850 | if ($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" |
851 | $hdr{location} =~ s/^\.\/+//; |
903 | $loc =~ s/^\.\/+//; |
852 | |
904 | |
|
|
905 | if ($loc !~ m%^[.?#]%) { |
853 | my $url = "$rscheme://$uhost:$uport"; |
906 | my $prefix = "$rscheme://$uhost:$uport"; |
854 | |
907 | |
855 | unless ($hdr{location} =~ s/^\///) { |
908 | unless ($loc =~ s/^\///) { |
856 | $url .= $upath; |
909 | $prefix .= $upath; |
857 | $url =~ s/\/[^\/]*$//; |
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 | } |
858 | } |
924 | } |
859 | |
925 | |
860 | $hdr{location} = "$url/$hdr{location}"; |
926 | $hdr{location} = $loc; |
861 | } |
927 | } |
862 | |
928 | |
863 | my $redirect; |
929 | my $redirect; |
864 | |
930 | |
865 | if ($recurse) { |
931 | if ($recurse) { |
… | |
… | |
867 | |
933 | |
868 | # industry standard is to redirect POST as GET for |
934 | # industry standard is to redirect POST as GET for |
869 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
935 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
870 | # also, the UA should ask the user for 301 and 307 and POST, |
936 | # also, the UA should ask the user for 301 and 307 and POST, |
871 | # industry standard seems to be to simply follow. |
937 | # industry standard seems to be to simply follow. |
872 | # we go with the industry standard. |
938 | # we go with the industry standard. 308 is defined |
|
|
939 | # by rfc7538 |
873 | if ($status == 301 or $status == 302 or $status == 303) { |
940 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
941 | $redirect = 1; |
874 | # HTTP/1.1 is unclear on how to mutate the method |
942 | # HTTP/1.1 is unclear on how to mutate the method |
875 | $method = "GET" unless $method eq "HEAD"; |
943 | unless ($method eq "HEAD") { |
876 | $redirect = 1; |
944 | $method = "GET"; |
|
|
945 | delete $arg{body}; |
|
|
946 | } |
877 | } elsif ($status == 307) { |
947 | } elsif ($status == 307 or $status == 308) { |
878 | $redirect = 1; |
948 | $redirect = 1; |
879 | } |
949 | } |
880 | } |
950 | } |
881 | |
951 | |
882 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
952 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
… | |
… | |
962 | my $body = ""; |
1032 | my $body = ""; |
963 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1033 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
964 | |
1034 | |
965 | $state{read_chunk} = sub { |
1035 | $state{read_chunk} = sub { |
966 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1036 | $_[1] =~ /^([0-9a-fA-F]+)/ |
967 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1037 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
968 | |
1038 | |
969 | my $len = hex $1; |
1039 | my $len = hex $1; |
970 | |
1040 | |
971 | if ($len) { |
1041 | if ($len) { |
972 | $cl += $len; |
1042 | $cl += $len; |
… | |
… | |
1050 | _destroy_state %state; |
1120 | _destroy_state %state; |
1051 | |
1121 | |
1052 | %state = (); |
1122 | %state = (); |
1053 | $state{recurse} = |
1123 | $state{recurse} = |
1054 | http_request ( |
1124 | http_request ( |
1055 | $method => $url, |
1125 | $method => $url, |
1056 | %arg, |
1126 | %arg, |
|
|
1127 | recurse => $recurse - 1, |
1057 | keepalive => 0, |
1128 | keepalive => 0, |
1058 | sub { |
1129 | sub { |
1059 | %state = (); |
1130 | %state = (); |
1060 | &$cb |
1131 | &$cb |
1061 | } |
1132 | } |
… | |
… | |
1108 | |
1179 | |
1109 | # now handle proxy-CONNECT method |
1180 | # now handle proxy-CONNECT method |
1110 | if ($proxy && $uscheme eq "https") { |
1181 | if ($proxy && $uscheme eq "https") { |
1111 | # oh dear, we have to wrap it into a connect request |
1182 | # oh dear, we have to wrap it into a connect request |
1112 | |
1183 | |
|
|
1184 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1185 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1186 | : ""; |
|
|
1187 | |
1113 | # maybe re-use $uauthority with patched port? |
1188 | # maybe re-use $uauthority with patched port? |
1114 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1189 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
1115 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1190 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1116 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1191 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1117 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1192 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1118 | |
1193 | |
1119 | if ($2 == 200) { |
1194 | if ($2 == 200) { |
… | |
… | |
1122 | } else { |
1197 | } else { |
1123 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1198 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1124 | } |
1199 | } |
1125 | }); |
1200 | }); |
1126 | } else { |
1201 | } else { |
|
|
1202 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1203 | |
1127 | $handle_actual_request->(); |
1204 | $handle_actual_request->(); |
1128 | } |
1205 | } |
1129 | }; |
1206 | }; |
1130 | |
1207 | |
1131 | _get_slot $uhost, sub { |
1208 | _get_slot $uhost, sub { |
… | |
… | |
1138 | if ($persistent && $KA_CACHE{$ka_key}) { |
1215 | if ($persistent && $KA_CACHE{$ka_key}) { |
1139 | $was_persistent = 1; |
1216 | $was_persistent = 1; |
1140 | |
1217 | |
1141 | $state{handle} = ka_fetch $ka_key; |
1218 | $state{handle} = ka_fetch $ka_key; |
1142 | $state{handle}->destroyed |
1219 | $state{handle}->destroyed |
1143 | and die "got a destructed handle. pah\n";#d# |
1220 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1144 | $prepare_handle->(); |
1221 | $prepare_handle->(); |
1145 | $state{handle}->destroyed |
1222 | $state{handle}->destroyed |
1146 | and die "got a destructed handle. pa2\n";#d# |
1223 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1147 | $handle_actual_request->(); |
1224 | $handle_actual_request->(); |
1148 | $state{handle}->destroyed |
|
|
1149 | and die "got a destructed handle. pa3\n";#d# |
|
|
1150 | |
1225 | |
1151 | } else { |
1226 | } else { |
1152 | my $tcp_connect = $arg{tcp_connect} |
1227 | my $tcp_connect = $arg{tcp_connect} |
1153 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1228 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1154 | |
1229 | |
… | |
… | |
1195 | Sets the default proxy server to use. The proxy-url must begin with a |
1270 | Sets the default proxy server to use. The proxy-url must begin with a |
1196 | string of the form C<http://host:port>, croaks otherwise. |
1271 | string of the form C<http://host:port>, croaks otherwise. |
1197 | |
1272 | |
1198 | To clear an already-set proxy, use C<undef>. |
1273 | To clear an already-set proxy, use C<undef>. |
1199 | |
1274 | |
1200 | When AnyEvent::HTTP is laoded for the first time it will query the |
1275 | When AnyEvent::HTTP is loaded for the first time it will query the |
1201 | default proxy from the operating system, currently by looking at |
1276 | default proxy from the operating system, currently by looking at |
1202 | C<$ENV{http_proxy>}. |
1277 | C<$ENV{http_proxy>}. |
1203 | |
1278 | |
1204 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1279 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1205 | |
1280 | |
… | |
… | |
1207 | C<$session_end> is given and true, then additionally remove all session |
1282 | C<$session_end> is given and true, then additionally remove all session |
1208 | cookies. |
1283 | cookies. |
1209 | |
1284 | |
1210 | You should call this function (with a true C<$session_end>) before you |
1285 | You should call this function (with a true C<$session_end>) before you |
1211 | save cookies to disk, and you should call this function after loading them |
1286 | save cookies to disk, and you should call this function after loading them |
1212 | again. If you have a long-running program you can additonally call this |
1287 | again. If you have a long-running program you can additionally call this |
1213 | function from time to time. |
1288 | function from time to time. |
1214 | |
1289 | |
1215 | A cookie jar is initially an empty hash-reference that is managed by this |
1290 | A cookie jar is initially an empty hash-reference that is managed by this |
1216 | module. It's format is subject to change, but currently it is like this: |
1291 | module. Its format is subject to change, but currently it is as follows: |
1217 | |
1292 | |
1218 | The key C<version> has to contain C<1>, otherwise the hash gets |
1293 | The key C<version> has to contain C<1>, otherwise the hash gets |
1219 | emptied. All other keys are hostnames or IP addresses pointing to |
1294 | emptied. All other keys are hostnames or IP addresses pointing to |
1220 | hash-references. The key for these inner hash references is the |
1295 | hash-references. The key for these inner hash references is the |
1221 | server path for which this cookie is meant, and the values are again |
1296 | server path for which this cookie is meant, and the values are again |
1222 | hash-references. The keys of those hash-references is the cookie name, and |
1297 | hash-references. Each key of those hash-references is a cookie name, and |
1223 | the value, you guessed it, is another hash-reference, this time with the |
1298 | the value, you guessed it, is another hash-reference, this time with the |
1224 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1299 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1225 | which have been replaced by a C<_expires> key that contains the cookie |
1300 | which have been replaced by a C<_expires> key that contains the cookie |
1226 | expiry timestamp. |
1301 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1302 | C<_expires> key. |
1227 | |
1303 | |
1228 | Here is an example of a cookie jar with a single cookie, so you have a |
1304 | Here is an example of a cookie jar with a single cookie, so you have a |
1229 | chance of understanding the above paragraph: |
1305 | chance of understanding the above paragraph: |
1230 | |
1306 | |
1231 | { |
1307 | { |
… | |
… | |
1255 | |
1331 | |
1256 | The default value for the C<recurse> request parameter (default: C<10>). |
1332 | The default value for the C<recurse> request parameter (default: C<10>). |
1257 | |
1333 | |
1258 | =item $AnyEvent::HTTP::TIMEOUT |
1334 | =item $AnyEvent::HTTP::TIMEOUT |
1259 | |
1335 | |
1260 | The default timeout for conenction operations (default: C<300>). |
1336 | The default timeout for connection operations (default: C<300>). |
1261 | |
1337 | |
1262 | =item $AnyEvent::HTTP::USERAGENT |
1338 | =item $AnyEvent::HTTP::USERAGENT |
1263 | |
1339 | |
1264 | The default value for the C<User-Agent> header (the default is |
1340 | The default value for the C<User-Agent> header (the default is |
1265 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1341 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1266 | |
1342 | |
1267 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1343 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1268 | |
1344 | |
1269 | The maximum number of concurrent connections to the same host (identified |
1345 | The maximum number of concurrent connections to the same host (identified |
1270 | by the hostname). If the limit is exceeded, then the additional requests |
1346 | by the hostname). If the limit is exceeded, then additional requests |
1271 | are queued until previous connections are closed. Both persistent and |
1347 | are queued until previous connections are closed. Both persistent and |
1272 | non-persistent connections are counted in this limit. |
1348 | non-persistent connections are counted in this limit. |
1273 | |
1349 | |
1274 | The default value for this is C<4>, and it is highly advisable to not |
1350 | The default value for this is C<4>, and it is highly advisable to not |
1275 | increase it much. |
1351 | increase it much. |
1276 | |
1352 | |
1277 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1353 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1278 | connections, older browsers used 2, newers (such as firefox 3) typically |
1354 | connections, older browsers used 2, newer ones (such as firefox 3) |
1279 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1355 | typically use 6, and Opera uses 8 because like, they have the fastest |
1280 | give a shit for everybody else on the planet. |
1356 | browser and give a shit for everybody else on the planet. |
1281 | |
1357 | |
1282 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1358 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1283 | |
1359 | |
1284 | The time after which idle persistent conenctions get closed by |
1360 | The time after which idle persistent connections get closed by |
1285 | AnyEvent::HTTP (default: C<3>). |
1361 | AnyEvent::HTTP (default: C<3>). |
1286 | |
1362 | |
1287 | =item $AnyEvent::HTTP::ACTIVE |
1363 | =item $AnyEvent::HTTP::ACTIVE |
1288 | |
1364 | |
1289 | The number of active connections. This is not the number of currently |
1365 | The number of active connections. This is not the number of currently |
… | |
… | |
1330 | # other formats fail in the loop below |
1406 | # other formats fail in the loop below |
1331 | |
1407 | |
1332 | for (0..11) { |
1408 | for (0..11) { |
1333 | if ($m eq $month[$_]) { |
1409 | if ($m eq $month[$_]) { |
1334 | require Time::Local; |
1410 | require Time::Local; |
1335 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1411 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1336 | } |
1412 | } |
1337 | } |
1413 | } |
1338 | |
1414 | |
1339 | undef |
1415 | undef |
1340 | } |
1416 | } |
… | |
… | |
1354 | set_proxy $ENV{http_proxy}; |
1430 | set_proxy $ENV{http_proxy}; |
1355 | }; |
1431 | }; |
1356 | |
1432 | |
1357 | =head2 SHOWCASE |
1433 | =head2 SHOWCASE |
1358 | |
1434 | |
1359 | This section contaisn some more elaborate "real-world" examples or code |
1435 | This section contains some more elaborate "real-world" examples or code |
1360 | snippets. |
1436 | snippets. |
1361 | |
1437 | |
1362 | =head2 HTTP/1.1 FILE DOWNLOAD |
1438 | =head2 HTTP/1.1 FILE DOWNLOAD |
1363 | |
1439 | |
1364 | Downloading files with HTTP can be quite tricky, especially when something |
1440 | Downloading files with HTTP can be quite tricky, especially when something |
… | |
… | |
1368 | last modified time to check for file content changes, and works with many |
1444 | last modified time to check for file content changes, and works with many |
1369 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1445 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1370 | on older servers. |
1446 | on older servers. |
1371 | |
1447 | |
1372 | It calls the completion callback with either C<undef>, which means a |
1448 | It calls the completion callback with either C<undef>, which means a |
1373 | nonretryable error occured, C<0> when the download was partial and should |
1449 | nonretryable error occurred, C<0> when the download was partial and should |
1374 | be retried, and C<1> if it was successful. |
1450 | be retried, and C<1> if it was successful. |
1375 | |
1451 | |
1376 | use AnyEvent::HTTP; |
1452 | use AnyEvent::HTTP; |
1377 | |
1453 | |
1378 | sub download($$$) { |
1454 | sub download($$$) { |
… | |
… | |
1386 | |
1462 | |
1387 | warn stat $fh; |
1463 | warn stat $fh; |
1388 | warn -s _; |
1464 | warn -s _; |
1389 | if (stat $fh and -s _) { |
1465 | if (stat $fh and -s _) { |
1390 | $ofs = -s _; |
1466 | $ofs = -s _; |
1391 | warn "-s is ", $ofs;#d# |
1467 | warn "-s is ", $ofs; |
1392 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1468 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1393 | $hdr{"range"} = "bytes=$ofs-"; |
1469 | $hdr{"range"} = "bytes=$ofs-"; |
1394 | } |
1470 | } |
1395 | |
1471 | |
1396 | http_get $url, |
1472 | http_get $url, |