… | |
… | |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
16 | run a supported event loop. |
16 | run a supported event loop. |
17 | |
17 | |
18 | This module implements a simple, stateless and non-blocking HTTP |
18 | This module implements a simple, stateless and non-blocking HTTP |
19 | client. It supports GET, POST and other request methods, cookies and more, |
19 | client. It supports GET, POST and other request methods, cookies and more, |
20 | all on a very low level. It can follow redirects supports proxies and |
20 | all on a very low level. It can follow redirects, supports proxies, and |
21 | automatically limits the number of connections to the values specified in |
21 | automatically limits the number of connections to the values specified in |
22 | the RFC. |
22 | the RFC. |
23 | |
23 | |
24 | It should generally be a "good client" that is enough for most HTTP |
24 | It should generally be a "good client" that is enough for most HTTP |
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
… | |
… | |
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 = '2.01'; |
51 | our $VERSION = '2.11'; |
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; |
… | |
… | |
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 | |
173 | |
|
|
174 | Also, make sure that your headers names and values do not contain any |
|
|
175 | embedded newlines. |
|
|
176 | |
174 | =item timeout => $seconds |
177 | =item timeout => $seconds |
175 | |
178 | |
176 | The time-out to use for various stages - each connect attempt will reset |
179 | The time-out to use for various stages - each connect attempt will reset |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
180 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | timeout. |
181 | timeout. |
179 | |
182 | |
180 | Default timeout is 5 minutes. |
183 | Default timeout is 5 minutes. |
181 | |
184 | |
182 | =item proxy => [$host, $port[, $scheme]] or undef |
185 | =item proxy => [$host, $port[, $scheme]] or undef |
183 | |
186 | |
184 | Use the given http proxy for all requests. If not specified, then the |
187 | Use the given http proxy for all requests, or no proxy if C<undef> is |
185 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
188 | used. |
186 | |
189 | |
187 | C<$scheme> must be either missing or must be C<http> for HTTP. |
190 | C<$scheme> must be either missing or must be C<http> for HTTP. |
|
|
191 | |
|
|
192 | If not specified, then the default proxy is used (see |
|
|
193 | C<AnyEvent::HTTP::set_proxy>). |
188 | |
194 | |
189 | =item body => $string |
195 | =item body => $string |
190 | |
196 | |
191 | The request body, usually empty. Will be sent as-is (future versions of |
197 | The request body, usually empty. Will be sent as-is (future versions of |
192 | this module might offer more options). |
198 | this module might offer more options). |
… | |
… | |
529 | while ( |
535 | while ( |
530 | m{ |
536 | m{ |
531 | \G\s* |
537 | \G\s* |
532 | (?: |
538 | (?: |
533 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
539 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
534 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
540 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )? |
535 | ) |
541 | ) |
536 | }gcxsi |
542 | }gcxsi |
537 | ) { |
543 | ) { |
538 | my $name = $2; |
544 | my $name = $2; |
539 | my $value = $4; |
545 | my $value = $4; |
… | |
… | |
546 | # quoted |
552 | # quoted |
547 | $value = $3; |
553 | $value = $3; |
548 | $value =~ s/\\(.)/$1/gs; |
554 | $value =~ s/\\(.)/$1/gs; |
549 | } |
555 | } |
550 | |
556 | |
551 | push @kv, lc $name, $value; |
557 | push @kv, @kv ? lc $name : $name, $value; |
552 | |
558 | |
553 | last unless /\G\s*;/gc; |
559 | last unless /\G\s*;/gc; |
554 | } |
560 | } |
555 | |
561 | |
556 | last unless @kv; |
562 | last unless @kv; |
… | |
… | |
709 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
715 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
710 | |
716 | |
711 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
717 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
712 | if $recurse < 0; |
718 | if $recurse < 0; |
713 | |
719 | |
714 | my $proxy = $arg{proxy} || $PROXY; |
720 | my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY; |
715 | my $timeout = $arg{timeout} || $TIMEOUT; |
721 | my $timeout = $arg{timeout} || $TIMEOUT; |
716 | |
722 | |
717 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
723 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
718 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
724 | $url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
719 | |
725 | |
720 | $uscheme = lc $uscheme; |
726 | $uscheme = lc $uscheme; |
721 | |
727 | |
722 | my $uport = $uscheme eq "http" ? 80 |
728 | my $uport = $uscheme eq "http" ? 80 |
723 | : $uscheme eq "https" ? 443 |
729 | : $uscheme eq "https" ? 443 |
… | |
… | |
770 | if length $arg{body} || $method ne "GET"; |
776 | if length $arg{body} || $method ne "GET"; |
771 | |
777 | |
772 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
778 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
773 | |
779 | |
774 | # default value for keepalive is true iff the request is for an idempotent method |
780 | # default value for keepalive is true iff the request is for an idempotent method |
775 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent; |
781 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
776 | my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy; |
782 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
777 | my $keptalive; # true if this is actually a recycled connection |
783 | my $was_persistent; # true if this is actually a recycled connection |
778 | |
784 | |
779 | # the key to use in the keepalive cache |
785 | # the key to use in the keepalive cache |
780 | my $ka_key = "$uhost\x00$arg{sessionid}"; |
786 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
781 | |
787 | |
782 | $hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
788 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
783 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
789 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
784 | |
790 | |
785 | my %state = (connect_guard => 1); |
791 | my %state = (connect_guard => 1); |
786 | |
792 | |
787 | my $ae_error = 595; # connecting |
793 | my $ae_error = 595; # connecting |
… | |
… | |
871 | } elsif ($status == 307) { |
877 | } elsif ($status == 307) { |
872 | $redirect = 1; |
878 | $redirect = 1; |
873 | } |
879 | } |
874 | } |
880 | } |
875 | |
881 | |
876 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
882 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
877 | if ($state{handle}) { |
883 | if ($state{handle}) { |
878 | # handle keepalive |
884 | # handle keepalive |
879 | if ( |
885 | if ( |
880 | $keepalive |
886 | $persistent |
881 | && $_[3] |
887 | && $_[3] |
882 | && ($hdr{HTTPVersion} < 1.1 |
888 | && ($hdr{HTTPVersion} < 1.1 |
883 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
889 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
884 | : $hdr{connection} !~ /\bclose\b/i) |
890 | : $hdr{connection} !~ /\bclose\b/i) |
885 | ) { |
891 | ) { |
… | |
… | |
904 | |
910 | |
905 | if ($redirect && exists $hdr{location}) { |
911 | if ($redirect && exists $hdr{location}) { |
906 | # we ignore any errors, as it is very common to receive |
912 | # we ignore any errors, as it is very common to receive |
907 | # Content-Length != 0 but no actual body |
913 | # Content-Length != 0 but no actual body |
908 | # we also access %hdr, as $_[1] might be an erro |
914 | # we also access %hdr, as $_[1] might be an erro |
|
|
915 | $state{recurse} = |
909 | http_request ( |
916 | http_request ( |
910 | $method => $hdr{location}, |
917 | $method => $hdr{location}, |
911 | %arg, |
918 | %arg, |
912 | recurse => $recurse - 1, |
919 | recurse => $recurse - 1, |
913 | Redirect => [$_[0], \%hdr], |
920 | Redirect => [$_[0], \%hdr], |
|
|
921 | sub { |
|
|
922 | %state = (); |
914 | $cb |
923 | &$cb |
|
|
924 | }, |
915 | ); |
925 | ); |
916 | } else { |
926 | } else { |
917 | $cb->($_[0], \%hdr); |
927 | $cb->($_[0], \%hdr); |
918 | } |
928 | } |
919 | }; |
929 | }; |
920 | |
930 | |
… | |
… | |
1032 | } |
1042 | } |
1033 | }; |
1043 | }; |
1034 | |
1044 | |
1035 | # if keepalive is enabled, then the server closing the connection |
1045 | # if keepalive is enabled, then the server closing the connection |
1036 | # before a response can happen legally - we retry on idempotent methods. |
1046 | # before a response can happen legally - we retry on idempotent methods. |
1037 | if ($keptalive && $idempotent) { |
1047 | if ($was_persistent && $idempotent) { |
1038 | my $old_eof = $hdl->{on_eof}; |
1048 | my $old_eof = $hdl->{on_eof}; |
1039 | $hdl->{on_eof} = sub { |
1049 | $hdl->{on_eof} = sub { |
1040 | _destroy_state %state; |
1050 | _destroy_state %state; |
1041 | |
1051 | |
|
|
1052 | %state = (); |
|
|
1053 | $state{recurse} = |
1042 | http_request ( |
1054 | http_request ( |
1043 | $method => $url, |
1055 | $method => $url, |
1044 | %arg, |
1056 | %arg, |
1045 | keepalive => 0, |
1057 | keepalive => 0, |
|
|
1058 | sub { |
|
|
1059 | %state = (); |
1046 | $cb |
1060 | &$cb |
|
|
1061 | } |
1047 | ); |
1062 | ); |
1048 | }; |
1063 | }; |
1049 | $hdl->on_read (sub { |
1064 | $hdl->on_read (sub { |
1050 | return unless %state; |
1065 | return unless %state; |
1051 | |
1066 | |
1052 | # as soon as we receive something, a connection close |
1067 | # as soon as we receive something, a connection close |
… | |
… | |
1060 | }; |
1075 | }; |
1061 | |
1076 | |
1062 | my $prepare_handle = sub { |
1077 | my $prepare_handle = sub { |
1063 | my ($hdl) = $state{handle}; |
1078 | my ($hdl) = $state{handle}; |
1064 | |
1079 | |
1065 | $hdl->timeout ($timeout); |
|
|
1066 | $hdl->on_error (sub { |
1080 | $hdl->on_error (sub { |
1067 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1081 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1068 | }); |
1082 | }); |
1069 | $hdl->on_eof (sub { |
1083 | $hdl->on_eof (sub { |
1070 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1084 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1071 | }); |
1085 | }); |
|
|
1086 | $hdl->timeout_reset; |
|
|
1087 | $hdl->timeout ($timeout); |
1072 | }; |
1088 | }; |
1073 | |
1089 | |
1074 | # connected to proxy (or origin server) |
1090 | # connected to proxy (or origin server) |
1075 | my $connect_cb = sub { |
1091 | my $connect_cb = sub { |
1076 | my $fh = shift |
1092 | my $fh = shift |
… | |
… | |
1117 | |
1133 | |
1118 | return unless $state{connect_guard}; |
1134 | return unless $state{connect_guard}; |
1119 | |
1135 | |
1120 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1136 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1121 | # on a keepalive request (in theory, this should be a separate config option). |
1137 | # on a keepalive request (in theory, this should be a separate config option). |
1122 | if ($keepalive && $KA_CACHE{$ka_key}) { |
1138 | if ($persistent && $KA_CACHE{$ka_key}) { |
1123 | $keptalive = 1; |
1139 | $was_persistent = 1; |
|
|
1140 | |
1124 | $state{handle} = ka_fetch $ka_key; |
1141 | $state{handle} = ka_fetch $ka_key; |
|
|
1142 | $state{handle}->destroyed |
|
|
1143 | and die "got a destructed habndle. pah\n";#d# |
1125 | $prepare_handle->(); |
1144 | $prepare_handle->(); |
|
|
1145 | $state{handle}->destroyed |
|
|
1146 | and die "got a destructed habndle. pa2\n";#d# |
1126 | $handle_actual_request->(); |
1147 | $handle_actual_request->(); |
|
|
1148 | $state{handle}->destroyed |
|
|
1149 | and die "got a destructed habndle. pa3\n";#d# |
1127 | |
1150 | |
1128 | } else { |
1151 | } else { |
1129 | my $tcp_connect = $arg{tcp_connect} |
1152 | my $tcp_connect = $arg{tcp_connect} |
1130 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1153 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1131 | |
1154 | |
… | |
… | |
1171 | |
1194 | |
1172 | Sets the default proxy server to use. The proxy-url must begin with a |
1195 | Sets the default proxy server to use. The proxy-url must begin with a |
1173 | string of the form C<http://host:port>, croaks otherwise. |
1196 | string of the form C<http://host:port>, croaks otherwise. |
1174 | |
1197 | |
1175 | To clear an already-set proxy, use C<undef>. |
1198 | To clear an already-set proxy, use C<undef>. |
|
|
1199 | |
|
|
1200 | When AnyEvent::HTTP is laoded for the first time it will query the |
|
|
1201 | default proxy from the operating system, currently by looking at |
|
|
1202 | C<$ENV{http_proxy>}. |
1176 | |
1203 | |
1177 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1204 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1178 | |
1205 | |
1179 | Remove all cookies from the cookie jar that have been expired. If |
1206 | Remove all cookies from the cookie jar that have been expired. If |
1180 | C<$session_end> is given and true, then additionally remove all session |
1207 | C<$session_end> is given and true, then additionally remove all session |
… | |
… | |
1332 | This section contaisn some more elaborate "real-world" examples or code |
1359 | This section contaisn some more elaborate "real-world" examples or code |
1333 | snippets. |
1360 | snippets. |
1334 | |
1361 | |
1335 | =head2 HTTP/1.1 FILE DOWNLOAD |
1362 | =head2 HTTP/1.1 FILE DOWNLOAD |
1336 | |
1363 | |
1337 | Downloading files with HTTP cna be quite tricky, especially when something |
1364 | Downloading files with HTTP can be quite tricky, especially when something |
1338 | goes wrong and you want tor esume. |
1365 | goes wrong and you want to resume. |
1339 | |
1366 | |
1340 | Here is a function that initiates and resumes a download. It uses the |
1367 | 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 |
1368 | 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 |
1369 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1343 | on older servers. |
1370 | on older servers. |