… | |
… | |
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 = '2.04'; |
51 | our $VERSION = '2.15'; |
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 | |
161 | |
162 | =item headers => hashref |
162 | =item headers => hashref |
163 | |
163 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
164 | 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 |
165 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
… | |
… | |
168 | they won't be sent at all). |
168 | they won't be sent at all). |
169 | |
169 | |
170 | You really should provide your own C<User-Agent:> header value that is |
170 | 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 |
171 | appropriate for your program - I wouldn't be surprised if the default |
172 | AnyEvent string gets blocked by webservers sooner or later. |
172 | AnyEvent string gets blocked by webservers sooner or later. |
|
|
173 | |
|
|
174 | Also, make sure that your headers names and values do not contain any |
|
|
175 | embedded newlines. |
173 | |
176 | |
174 | =item timeout => $seconds |
177 | =item timeout => $seconds |
175 | |
178 | |
176 | The time-out to use for various stages - each connect attempt will reset |
179 | 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 |
180 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
239 | context) - only connections using the same unique ID will be reused. |
242 | context) - only connections using the same unique ID will be reused. |
240 | |
243 | |
241 | =item on_prepare => $callback->($fh) |
244 | =item on_prepare => $callback->($fh) |
242 | |
245 | |
243 | In rare cases you need to "tune" the socket before it is used to |
246 | In rare cases you need to "tune" the socket before it is used to |
244 | connect (for exmaple, to bind it on a given IP address). This parameter |
247 | connect (for example, to bind it on a given IP address). This parameter |
245 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
248 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
246 | and behaves exactly the same way (e.g. it has to provide a |
249 | and behaves exactly the same way (e.g. it has to provide a |
247 | timeout). See the description for the C<$prepare_cb> argument of |
250 | timeout). See the description for the C<$prepare_cb> argument of |
248 | C<AnyEvent::Socket::tcp_connect> for details. |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
249 | |
252 | |
… | |
… | |
381 | |
384 | |
382 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
385 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
383 | timeout of 30 seconds. |
386 | timeout of 30 seconds. |
384 | |
387 | |
385 | http_request |
388 | http_request |
386 | GET => "https://www.google.com", |
389 | HEAD => "https://www.google.com", |
387 | headers => { "user-agent" => "MySearchClient 1.0" }, |
390 | headers => { "user-agent" => "MySearchClient 1.0" }, |
388 | timeout => 30, |
391 | timeout => 30, |
389 | sub { |
392 | sub { |
390 | my ($body, $hdr) = @_; |
393 | my ($body, $hdr) = @_; |
391 | use Data::Dumper; |
394 | use Data::Dumper; |
… | |
… | |
686 | |
689 | |
687 | $cb->(undef, $hdr); |
690 | $cb->(undef, $hdr); |
688 | () |
691 | () |
689 | } |
692 | } |
690 | |
693 | |
|
|
694 | our %IDEMPOTENT = ( |
|
|
695 | DELETE => 1, |
|
|
696 | GET => 1, |
|
|
697 | HEAD => 1, |
|
|
698 | OPTIONS => 1, |
|
|
699 | PUT => 1, |
|
|
700 | TRACE => 1, |
|
|
701 | |
|
|
702 | ACL => 1, |
|
|
703 | "BASELINE-CONTROL" => 1, |
|
|
704 | BIND => 1, |
|
|
705 | CHECKIN => 1, |
|
|
706 | CHECKOUT => 1, |
|
|
707 | COPY => 1, |
|
|
708 | LABEL => 1, |
|
|
709 | LINK => 1, |
|
|
710 | MERGE => 1, |
|
|
711 | MKACTIVITY => 1, |
|
|
712 | MKCALENDAR => 1, |
|
|
713 | MKCOL => 1, |
|
|
714 | MKREDIRECTREF => 1, |
|
|
715 | MKWORKSPACE => 1, |
|
|
716 | MOVE => 1, |
|
|
717 | ORDERPATCH => 1, |
|
|
718 | PROPFIND => 1, |
|
|
719 | PROPPATCH => 1, |
|
|
720 | REBIND => 1, |
|
|
721 | REPORT => 1, |
|
|
722 | SEARCH => 1, |
|
|
723 | UNBIND => 1, |
|
|
724 | UNCHECKOUT => 1, |
|
|
725 | UNLINK => 1, |
|
|
726 | UNLOCK => 1, |
|
|
727 | UPDATE => 1, |
|
|
728 | UPDATEREDIRECTREF => 1, |
|
|
729 | "VERSION-CONTROL" => 1, |
|
|
730 | ); |
|
|
731 | |
691 | sub http_request($$@) { |
732 | sub http_request($$@) { |
692 | my $cb = pop; |
733 | my $cb = pop; |
693 | my ($method, $url, %arg) = @_; |
734 | my ($method, $url, %arg) = @_; |
694 | |
735 | |
695 | my %hdr; |
736 | my %hdr; |
… | |
… | |
770 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
811 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
771 | |
812 | |
772 | $hdr{"content-length"} = length $arg{body} |
813 | $hdr{"content-length"} = length $arg{body} |
773 | if length $arg{body} || $method ne "GET"; |
814 | if length $arg{body} || $method ne "GET"; |
774 | |
815 | |
775 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
816 | my $idempotent = $IDEMPOTENT{$method}; |
776 | |
817 | |
777 | # default value for keepalive is true iff the request is for an idempotent method |
818 | # default value for keepalive is true iff the request is for an idempotent method |
778 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent; |
819 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
779 | my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy; |
820 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
780 | my $keptalive; # true if this is actually a recycled connection |
821 | my $was_persistent; # true if this is actually a recycled connection |
781 | |
822 | |
782 | # the key to use in the keepalive cache |
823 | # the key to use in the keepalive cache |
783 | my $ka_key = "$uhost\x00$arg{sessionid}"; |
824 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
784 | |
825 | |
785 | $hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
826 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
786 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
827 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
787 | |
828 | |
788 | my %state = (connect_guard => 1); |
829 | my %state = (connect_guard => 1); |
789 | |
830 | |
790 | my $ae_error = 595; # connecting |
831 | my $ae_error = 595; # connecting |
… | |
… | |
803 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
844 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
804 | . "\015\012" |
845 | . "\015\012" |
805 | . (delete $arg{body}) |
846 | . (delete $arg{body}) |
806 | ); |
847 | ); |
807 | |
848 | |
808 | # return if error occured during push_write() |
849 | # return if error occurred during push_write() |
809 | return unless %state; |
850 | return unless %state; |
810 | |
851 | |
811 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
852 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
812 | %hdr = (); |
853 | %hdr = (); |
813 | |
854 | |
… | |
… | |
874 | } elsif ($status == 307) { |
915 | } elsif ($status == 307) { |
875 | $redirect = 1; |
916 | $redirect = 1; |
876 | } |
917 | } |
877 | } |
918 | } |
878 | |
919 | |
879 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
920 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
880 | if ($state{handle}) { |
921 | if ($state{handle}) { |
881 | # handle keepalive |
922 | # handle keepalive |
882 | if ( |
923 | if ( |
883 | $keepalive |
924 | $persistent |
884 | && $_[3] |
925 | && $_[3] |
885 | && ($hdr{HTTPVersion} < 1.1 |
926 | && ($hdr{HTTPVersion} < 1.1 |
886 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
927 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
887 | : $hdr{connection} !~ /\bclose\b/i) |
928 | : $hdr{connection} !~ /\bclose\b/i) |
888 | ) { |
929 | ) { |
… | |
… | |
907 | |
948 | |
908 | if ($redirect && exists $hdr{location}) { |
949 | if ($redirect && exists $hdr{location}) { |
909 | # we ignore any errors, as it is very common to receive |
950 | # we ignore any errors, as it is very common to receive |
910 | # Content-Length != 0 but no actual body |
951 | # Content-Length != 0 but no actual body |
911 | # we also access %hdr, as $_[1] might be an erro |
952 | # we also access %hdr, as $_[1] might be an erro |
|
|
953 | $state{recurse} = |
912 | http_request ( |
954 | http_request ( |
913 | $method => $hdr{location}, |
955 | $method => $hdr{location}, |
914 | %arg, |
956 | %arg, |
915 | recurse => $recurse - 1, |
957 | recurse => $recurse - 1, |
916 | Redirect => [$_[0], \%hdr], |
958 | Redirect => [$_[0], \%hdr], |
|
|
959 | sub { |
|
|
960 | %state = (); |
917 | $cb |
961 | &$cb |
|
|
962 | }, |
918 | ); |
963 | ); |
919 | } else { |
964 | } else { |
920 | $cb->($_[0], \%hdr); |
965 | $cb->($_[0], \%hdr); |
921 | } |
966 | } |
922 | }; |
967 | }; |
923 | |
968 | |
… | |
… | |
955 | my $body = ""; |
1000 | my $body = ""; |
956 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1001 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
957 | |
1002 | |
958 | $state{read_chunk} = sub { |
1003 | $state{read_chunk} = sub { |
959 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1004 | $_[1] =~ /^([0-9a-fA-F]+)/ |
960 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1005 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
961 | |
1006 | |
962 | my $len = hex $1; |
1007 | my $len = hex $1; |
963 | |
1008 | |
964 | if ($len) { |
1009 | if ($len) { |
965 | $cl += $len; |
1010 | $cl += $len; |
… | |
… | |
1035 | } |
1080 | } |
1036 | }; |
1081 | }; |
1037 | |
1082 | |
1038 | # if keepalive is enabled, then the server closing the connection |
1083 | # if keepalive is enabled, then the server closing the connection |
1039 | # before a response can happen legally - we retry on idempotent methods. |
1084 | # before a response can happen legally - we retry on idempotent methods. |
1040 | if ($keptalive && $idempotent) { |
1085 | if ($was_persistent && $idempotent) { |
1041 | my $old_eof = $hdl->{on_eof}; |
1086 | my $old_eof = $hdl->{on_eof}; |
1042 | $hdl->{on_eof} = sub { |
1087 | $hdl->{on_eof} = sub { |
1043 | _destroy_state %state; |
1088 | _destroy_state %state; |
1044 | |
1089 | |
|
|
1090 | %state = (); |
|
|
1091 | $state{recurse} = |
1045 | http_request ( |
1092 | http_request ( |
1046 | $method => $url, |
1093 | $method => $url, |
1047 | %arg, |
1094 | %arg, |
|
|
1095 | recurse => $recurse - 1, |
1048 | keepalive => 0, |
1096 | keepalive => 0, |
|
|
1097 | sub { |
|
|
1098 | %state = (); |
1049 | $cb |
1099 | &$cb |
|
|
1100 | } |
1050 | ); |
1101 | ); |
1051 | }; |
1102 | }; |
1052 | $hdl->on_read (sub { |
1103 | $hdl->on_read (sub { |
1053 | return unless %state; |
1104 | return unless %state; |
1054 | |
1105 | |
1055 | # as soon as we receive something, a connection close |
1106 | # as soon as we receive something, a connection close |
… | |
… | |
1063 | }; |
1114 | }; |
1064 | |
1115 | |
1065 | my $prepare_handle = sub { |
1116 | my $prepare_handle = sub { |
1066 | my ($hdl) = $state{handle}; |
1117 | my ($hdl) = $state{handle}; |
1067 | |
1118 | |
1068 | $hdl->timeout ($timeout); |
|
|
1069 | $hdl->on_error (sub { |
1119 | $hdl->on_error (sub { |
1070 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1120 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1071 | }); |
1121 | }); |
1072 | $hdl->on_eof (sub { |
1122 | $hdl->on_eof (sub { |
1073 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1123 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1074 | }); |
1124 | }); |
|
|
1125 | $hdl->timeout_reset; |
|
|
1126 | $hdl->timeout ($timeout); |
1075 | }; |
1127 | }; |
1076 | |
1128 | |
1077 | # connected to proxy (or origin server) |
1129 | # connected to proxy (or origin server) |
1078 | my $connect_cb = sub { |
1130 | my $connect_cb = sub { |
1079 | my $fh = shift |
1131 | my $fh = shift |
… | |
… | |
1120 | |
1172 | |
1121 | return unless $state{connect_guard}; |
1173 | return unless $state{connect_guard}; |
1122 | |
1174 | |
1123 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1175 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1124 | # on a keepalive request (in theory, this should be a separate config option). |
1176 | # on a keepalive request (in theory, this should be a separate config option). |
1125 | if ($keepalive && $KA_CACHE{$ka_key}) { |
1177 | if ($persistent && $KA_CACHE{$ka_key}) { |
1126 | $keptalive = 1; |
1178 | $was_persistent = 1; |
|
|
1179 | |
1127 | $state{handle} = ka_fetch $ka_key; |
1180 | $state{handle} = ka_fetch $ka_key; |
|
|
1181 | $state{handle}->destroyed |
|
|
1182 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1128 | $prepare_handle->(); |
1183 | $prepare_handle->(); |
|
|
1184 | $state{handle}->destroyed |
|
|
1185 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1129 | $handle_actual_request->(); |
1186 | $handle_actual_request->(); |
1130 | |
1187 | |
1131 | } else { |
1188 | } else { |
1132 | my $tcp_connect = $arg{tcp_connect} |
1189 | my $tcp_connect = $arg{tcp_connect} |
1133 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1190 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1175 | Sets the default proxy server to use. The proxy-url must begin with a |
1232 | Sets the default proxy server to use. The proxy-url must begin with a |
1176 | string of the form C<http://host:port>, croaks otherwise. |
1233 | string of the form C<http://host:port>, croaks otherwise. |
1177 | |
1234 | |
1178 | To clear an already-set proxy, use C<undef>. |
1235 | To clear an already-set proxy, use C<undef>. |
1179 | |
1236 | |
1180 | When AnyEvent::HTTP is laoded for the first time it will query the |
1237 | When AnyEvent::HTTP is loaded for the first time it will query the |
1181 | default proxy from the operating system, currently by looking at |
1238 | default proxy from the operating system, currently by looking at |
1182 | C<$ENV{http_proxy>}. |
1239 | C<$ENV{http_proxy>}. |
1183 | |
1240 | |
1184 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1241 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1185 | |
1242 | |
… | |
… | |
1187 | C<$session_end> is given and true, then additionally remove all session |
1244 | C<$session_end> is given and true, then additionally remove all session |
1188 | cookies. |
1245 | cookies. |
1189 | |
1246 | |
1190 | You should call this function (with a true C<$session_end>) before you |
1247 | You should call this function (with a true C<$session_end>) before you |
1191 | save cookies to disk, and you should call this function after loading them |
1248 | save cookies to disk, and you should call this function after loading them |
1192 | again. If you have a long-running program you can additonally call this |
1249 | again. If you have a long-running program you can additionally call this |
1193 | function from time to time. |
1250 | function from time to time. |
1194 | |
1251 | |
1195 | A cookie jar is initially an empty hash-reference that is managed by this |
1252 | A cookie jar is initially an empty hash-reference that is managed by this |
1196 | module. It's format is subject to change, but currently it is like this: |
1253 | module. It's format is subject to change, but currently it is like this: |
1197 | |
1254 | |
1198 | The key C<version> has to contain C<1>, otherwise the hash gets |
1255 | The key C<version> has to contain C<1>, otherwise the hash gets |
1199 | emptied. All other keys are hostnames or IP addresses pointing to |
1256 | emptied. All other keys are hostnames or IP addresses pointing to |
1200 | hash-references. The key for these inner hash references is the |
1257 | hash-references. The key for these inner hash references is the |
1201 | server path for which this cookie is meant, and the values are again |
1258 | server path for which this cookie is meant, and the values are again |
1202 | hash-references. The keys of those hash-references is the cookie name, and |
1259 | hash-references. Each key of those hash-references is a cookie name, and |
1203 | the value, you guessed it, is another hash-reference, this time with the |
1260 | the value, you guessed it, is another hash-reference, this time with the |
1204 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1261 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1205 | which have been replaced by a C<_expires> key that contains the cookie |
1262 | which have been replaced by a C<_expires> key that contains the cookie |
1206 | expiry timestamp. |
1263 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1264 | C<_expires> key. |
1207 | |
1265 | |
1208 | Here is an example of a cookie jar with a single cookie, so you have a |
1266 | Here is an example of a cookie jar with a single cookie, so you have a |
1209 | chance of understanding the above paragraph: |
1267 | chance of understanding the above paragraph: |
1210 | |
1268 | |
1211 | { |
1269 | { |
… | |
… | |
1235 | |
1293 | |
1236 | The default value for the C<recurse> request parameter (default: C<10>). |
1294 | The default value for the C<recurse> request parameter (default: C<10>). |
1237 | |
1295 | |
1238 | =item $AnyEvent::HTTP::TIMEOUT |
1296 | =item $AnyEvent::HTTP::TIMEOUT |
1239 | |
1297 | |
1240 | The default timeout for conenction operations (default: C<300>). |
1298 | The default timeout for connection operations (default: C<300>). |
1241 | |
1299 | |
1242 | =item $AnyEvent::HTTP::USERAGENT |
1300 | =item $AnyEvent::HTTP::USERAGENT |
1243 | |
1301 | |
1244 | The default value for the C<User-Agent> header (the default is |
1302 | The default value for the C<User-Agent> header (the default is |
1245 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1303 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
… | |
… | |
1253 | |
1311 | |
1254 | The default value for this is C<4>, and it is highly advisable to not |
1312 | The default value for this is C<4>, and it is highly advisable to not |
1255 | increase it much. |
1313 | increase it much. |
1256 | |
1314 | |
1257 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1315 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1258 | connections, older browsers used 2, newers (such as firefox 3) typically |
1316 | connections, older browsers used 2, newer ones (such as firefox 3) |
1259 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1317 | typically use 6, and Opera uses 8 because like, they have the fastest |
1260 | give a shit for everybody else on the planet. |
1318 | browser and give a shit for everybody else on the planet. |
1261 | |
1319 | |
1262 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1320 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1263 | |
1321 | |
1264 | The time after which idle persistent conenctions get closed by |
1322 | The time after which idle persistent connections get closed by |
1265 | AnyEvent::HTTP (default: C<3>). |
1323 | AnyEvent::HTTP (default: C<3>). |
1266 | |
1324 | |
1267 | =item $AnyEvent::HTTP::ACTIVE |
1325 | =item $AnyEvent::HTTP::ACTIVE |
1268 | |
1326 | |
1269 | The number of active connections. This is not the number of currently |
1327 | The number of active connections. This is not the number of currently |
… | |
… | |
1310 | # other formats fail in the loop below |
1368 | # other formats fail in the loop below |
1311 | |
1369 | |
1312 | for (0..11) { |
1370 | for (0..11) { |
1313 | if ($m eq $month[$_]) { |
1371 | if ($m eq $month[$_]) { |
1314 | require Time::Local; |
1372 | require Time::Local; |
1315 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1373 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1316 | } |
1374 | } |
1317 | } |
1375 | } |
1318 | |
1376 | |
1319 | undef |
1377 | undef |
1320 | } |
1378 | } |
… | |
… | |
1334 | set_proxy $ENV{http_proxy}; |
1392 | set_proxy $ENV{http_proxy}; |
1335 | }; |
1393 | }; |
1336 | |
1394 | |
1337 | =head2 SHOWCASE |
1395 | =head2 SHOWCASE |
1338 | |
1396 | |
1339 | This section contaisn some more elaborate "real-world" examples or code |
1397 | This section contains some more elaborate "real-world" examples or code |
1340 | snippets. |
1398 | snippets. |
1341 | |
1399 | |
1342 | =head2 HTTP/1.1 FILE DOWNLOAD |
1400 | =head2 HTTP/1.1 FILE DOWNLOAD |
1343 | |
1401 | |
1344 | Downloading files with HTTP can be quite tricky, especially when something |
1402 | Downloading files with HTTP can be quite tricky, especially when something |
… | |
… | |
1348 | last modified time to check for file content changes, and works with many |
1406 | last modified time to check for file content changes, and works with many |
1349 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1407 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1350 | on older servers. |
1408 | on older servers. |
1351 | |
1409 | |
1352 | It calls the completion callback with either C<undef>, which means a |
1410 | It calls the completion callback with either C<undef>, which means a |
1353 | nonretryable error occured, C<0> when the download was partial and should |
1411 | nonretryable error occurred, C<0> when the download was partial and should |
1354 | be retried, and C<1> if it was successful. |
1412 | be retried, and C<1> if it was successful. |
1355 | |
1413 | |
1356 | use AnyEvent::HTTP; |
1414 | use AnyEvent::HTTP; |
1357 | |
1415 | |
1358 | sub download($$$) { |
1416 | sub download($$$) { |
… | |
… | |
1366 | |
1424 | |
1367 | warn stat $fh; |
1425 | warn stat $fh; |
1368 | warn -s _; |
1426 | warn -s _; |
1369 | if (stat $fh and -s _) { |
1427 | if (stat $fh and -s _) { |
1370 | $ofs = -s _; |
1428 | $ofs = -s _; |
1371 | warn "-s is ", $ofs;#d# |
1429 | warn "-s is ", $ofs; |
1372 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1430 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1373 | $hdr{"range"} = "bytes=$ofs-"; |
1431 | $hdr{"range"} = "bytes=$ofs-"; |
1374 | } |
1432 | } |
1375 | |
1433 | |
1376 | http_get $url, |
1434 | http_get $url, |