… | |
… | |
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 = '2.15'; |
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 |
… | |
… | |
242 | context) - only connections using the same unique ID will be reused. |
242 | context) - only connections using the same unique ID will be reused. |
243 | |
243 | |
244 | =item on_prepare => $callback->($fh) |
244 | =item on_prepare => $callback->($fh) |
245 | |
245 | |
246 | 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 |
247 | 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 |
248 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
248 | 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 |
249 | and behaves exactly the same way (e.g. it has to provide a |
250 | timeout). See the description for the C<$prepare_cb> argument of |
250 | timeout). See the description for the C<$prepare_cb> argument of |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
252 | |
252 | |
… | |
… | |
384 | |
384 | |
385 | 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 |
386 | timeout of 30 seconds. |
386 | timeout of 30 seconds. |
387 | |
387 | |
388 | http_request |
388 | http_request |
389 | GET => "https://www.google.com", |
389 | HEAD => "https://www.google.com", |
390 | headers => { "user-agent" => "MySearchClient 1.0" }, |
390 | headers => { "user-agent" => "MySearchClient 1.0" }, |
391 | timeout => 30, |
391 | timeout => 30, |
392 | sub { |
392 | sub { |
393 | my ($body, $hdr) = @_; |
393 | my ($body, $hdr) = @_; |
394 | use Data::Dumper; |
394 | use Data::Dumper; |
… | |
… | |
689 | |
689 | |
690 | $cb->(undef, $hdr); |
690 | $cb->(undef, $hdr); |
691 | () |
691 | () |
692 | } |
692 | } |
693 | |
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 | |
694 | sub http_request($$@) { |
732 | sub http_request($$@) { |
695 | my $cb = pop; |
733 | my $cb = pop; |
696 | my ($method, $url, %arg) = @_; |
734 | my ($method, $url, %arg) = @_; |
697 | |
735 | |
698 | my %hdr; |
736 | my %hdr; |
… | |
… | |
773 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
811 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
774 | |
812 | |
775 | $hdr{"content-length"} = length $arg{body} |
813 | $hdr{"content-length"} = length $arg{body} |
776 | if length $arg{body} || $method ne "GET"; |
814 | if length $arg{body} || $method ne "GET"; |
777 | |
815 | |
778 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
816 | my $idempotent = $IDEMPOTENT{$method}; |
779 | |
817 | |
780 | # 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 |
781 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
819 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
782 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
820 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
783 | my $was_persistent; # true if this is actually a recycled connection |
821 | my $was_persistent; # true if this is actually a recycled connection |
784 | |
822 | |
785 | # the key to use in the keepalive cache |
823 | # the key to use in the keepalive cache |
786 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
824 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
787 | |
825 | |
788 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
826 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
789 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
827 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
790 | |
828 | |
791 | my %state = (connect_guard => 1); |
829 | my %state = (connect_guard => 1); |
792 | |
830 | |
793 | my $ae_error = 595; # connecting |
831 | my $ae_error = 595; # connecting |
… | |
… | |
806 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
844 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
807 | . "\015\012" |
845 | . "\015\012" |
808 | . (delete $arg{body}) |
846 | . (delete $arg{body}) |
809 | ); |
847 | ); |
810 | |
848 | |
811 | # return if error occured during push_write() |
849 | # return if error occurred during push_write() |
812 | return unless %state; |
850 | return unless %state; |
813 | |
851 | |
814 | # 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. |
815 | %hdr = (); |
853 | %hdr = (); |
816 | |
854 | |
… | |
… | |
962 | my $body = ""; |
1000 | my $body = ""; |
963 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1001 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
964 | |
1002 | |
965 | $state{read_chunk} = sub { |
1003 | $state{read_chunk} = sub { |
966 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1004 | $_[1] =~ /^([0-9a-fA-F]+)/ |
967 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1005 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
968 | |
1006 | |
969 | my $len = hex $1; |
1007 | my $len = hex $1; |
970 | |
1008 | |
971 | if ($len) { |
1009 | if ($len) { |
972 | $cl += $len; |
1010 | $cl += $len; |
… | |
… | |
1050 | _destroy_state %state; |
1088 | _destroy_state %state; |
1051 | |
1089 | |
1052 | %state = (); |
1090 | %state = (); |
1053 | $state{recurse} = |
1091 | $state{recurse} = |
1054 | http_request ( |
1092 | http_request ( |
1055 | $method => $url, |
1093 | $method => $url, |
1056 | %arg, |
1094 | %arg, |
|
|
1095 | recurse => $recurse - 1, |
1057 | keepalive => 0, |
1096 | keepalive => 0, |
1058 | sub { |
1097 | sub { |
1059 | %state = (); |
1098 | %state = (); |
1060 | &$cb |
1099 | &$cb |
1061 | } |
1100 | } |
… | |
… | |
1138 | if ($persistent && $KA_CACHE{$ka_key}) { |
1177 | if ($persistent && $KA_CACHE{$ka_key}) { |
1139 | $was_persistent = 1; |
1178 | $was_persistent = 1; |
1140 | |
1179 | |
1141 | $state{handle} = ka_fetch $ka_key; |
1180 | $state{handle} = ka_fetch $ka_key; |
1142 | $state{handle}->destroyed |
1181 | $state{handle}->destroyed |
1143 | and die "got a destructed habndle. pah\n";#d# |
1182 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1144 | $prepare_handle->(); |
1183 | $prepare_handle->(); |
1145 | $state{handle}->destroyed |
1184 | $state{handle}->destroyed |
1146 | and die "got a destructed habndle. pa2\n";#d# |
1185 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1147 | $handle_actual_request->(); |
1186 | $handle_actual_request->(); |
1148 | $state{handle}->destroyed |
|
|
1149 | and die "got a destructed habndle. pa3\n";#d# |
|
|
1150 | |
1187 | |
1151 | } else { |
1188 | } else { |
1152 | my $tcp_connect = $arg{tcp_connect} |
1189 | my $tcp_connect = $arg{tcp_connect} |
1153 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1190 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1154 | |
1191 | |
… | |
… | |
1195 | Sets the default proxy server to use. The proxy-url must begin with a |
1232 | Sets the default proxy server to use. The proxy-url must begin with a |
1196 | string of the form C<http://host:port>, croaks otherwise. |
1233 | string of the form C<http://host:port>, croaks otherwise. |
1197 | |
1234 | |
1198 | To clear an already-set proxy, use C<undef>. |
1235 | To clear an already-set proxy, use C<undef>. |
1199 | |
1236 | |
1200 | When AnyEvent::HTTP is laoded for the first time it will query the |
1237 | When AnyEvent::HTTP is loaded for the first time it will query the |
1201 | default proxy from the operating system, currently by looking at |
1238 | default proxy from the operating system, currently by looking at |
1202 | C<$ENV{http_proxy>}. |
1239 | C<$ENV{http_proxy>}. |
1203 | |
1240 | |
1204 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1241 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1205 | |
1242 | |
… | |
… | |
1207 | C<$session_end> is given and true, then additionally remove all session |
1244 | C<$session_end> is given and true, then additionally remove all session |
1208 | cookies. |
1245 | cookies. |
1209 | |
1246 | |
1210 | You should call this function (with a true C<$session_end>) before you |
1247 | You should call this function (with a true C<$session_end>) before you |
1211 | 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 |
1212 | 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 |
1213 | function from time to time. |
1250 | function from time to time. |
1214 | |
1251 | |
1215 | 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 |
1216 | 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: |
1217 | |
1254 | |
1218 | 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 |
1219 | emptied. All other keys are hostnames or IP addresses pointing to |
1256 | emptied. All other keys are hostnames or IP addresses pointing to |
1220 | hash-references. The key for these inner hash references is the |
1257 | 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 |
1258 | 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 |
1259 | 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 |
1260 | 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>, |
1261 | 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 |
1262 | which have been replaced by a C<_expires> key that contains the cookie |
1226 | expiry timestamp. |
1263 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1264 | C<_expires> key. |
1227 | |
1265 | |
1228 | 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 |
1229 | chance of understanding the above paragraph: |
1267 | chance of understanding the above paragraph: |
1230 | |
1268 | |
1231 | { |
1269 | { |
… | |
… | |
1255 | |
1293 | |
1256 | 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>). |
1257 | |
1295 | |
1258 | =item $AnyEvent::HTTP::TIMEOUT |
1296 | =item $AnyEvent::HTTP::TIMEOUT |
1259 | |
1297 | |
1260 | The default timeout for conenction operations (default: C<300>). |
1298 | The default timeout for connection operations (default: C<300>). |
1261 | |
1299 | |
1262 | =item $AnyEvent::HTTP::USERAGENT |
1300 | =item $AnyEvent::HTTP::USERAGENT |
1263 | |
1301 | |
1264 | The default value for the C<User-Agent> header (the default is |
1302 | The default value for the C<User-Agent> header (the default is |
1265 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1303 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
… | |
… | |
1273 | |
1311 | |
1274 | 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 |
1275 | increase it much. |
1313 | increase it much. |
1276 | |
1314 | |
1277 | 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 |
1278 | connections, older browsers used 2, newers (such as firefox 3) typically |
1316 | 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 |
1317 | typically use 6, and Opera uses 8 because like, they have the fastest |
1280 | give a shit for everybody else on the planet. |
1318 | browser and give a shit for everybody else on the planet. |
1281 | |
1319 | |
1282 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1320 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1283 | |
1321 | |
1284 | The time after which idle persistent conenctions get closed by |
1322 | The time after which idle persistent connections get closed by |
1285 | AnyEvent::HTTP (default: C<3>). |
1323 | AnyEvent::HTTP (default: C<3>). |
1286 | |
1324 | |
1287 | =item $AnyEvent::HTTP::ACTIVE |
1325 | =item $AnyEvent::HTTP::ACTIVE |
1288 | |
1326 | |
1289 | The number of active connections. This is not the number of currently |
1327 | The number of active connections. This is not the number of currently |
… | |
… | |
1330 | # other formats fail in the loop below |
1368 | # other formats fail in the loop below |
1331 | |
1369 | |
1332 | for (0..11) { |
1370 | for (0..11) { |
1333 | if ($m eq $month[$_]) { |
1371 | if ($m eq $month[$_]) { |
1334 | require Time::Local; |
1372 | require Time::Local; |
1335 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1373 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1336 | } |
1374 | } |
1337 | } |
1375 | } |
1338 | |
1376 | |
1339 | undef |
1377 | undef |
1340 | } |
1378 | } |
… | |
… | |
1354 | set_proxy $ENV{http_proxy}; |
1392 | set_proxy $ENV{http_proxy}; |
1355 | }; |
1393 | }; |
1356 | |
1394 | |
1357 | =head2 SHOWCASE |
1395 | =head2 SHOWCASE |
1358 | |
1396 | |
1359 | This section contaisn some more elaborate "real-world" examples or code |
1397 | This section contains some more elaborate "real-world" examples or code |
1360 | snippets. |
1398 | snippets. |
1361 | |
1399 | |
1362 | =head2 HTTP/1.1 FILE DOWNLOAD |
1400 | =head2 HTTP/1.1 FILE DOWNLOAD |
1363 | |
1401 | |
1364 | Downloading files with HTTP can be quite tricky, especially when something |
1402 | 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 |
1406 | 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 |
1407 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1370 | on older servers. |
1408 | on older servers. |
1371 | |
1409 | |
1372 | 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 |
1373 | 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 |
1374 | be retried, and C<1> if it was successful. |
1412 | be retried, and C<1> if it was successful. |
1375 | |
1413 | |
1376 | use AnyEvent::HTTP; |
1414 | use AnyEvent::HTTP; |
1377 | |
1415 | |
1378 | sub download($$$) { |
1416 | sub download($$$) { |
… | |
… | |
1386 | |
1424 | |
1387 | warn stat $fh; |
1425 | warn stat $fh; |
1388 | warn -s _; |
1426 | warn -s _; |
1389 | if (stat $fh and -s _) { |
1427 | if (stat $fh and -s _) { |
1390 | $ofs = -s _; |
1428 | $ofs = -s _; |
1391 | warn "-s is ", $ofs;#d# |
1429 | warn "-s is ", $ofs; |
1392 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1430 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1393 | $hdr{"range"} = "bytes=$ofs-"; |
1431 | $hdr{"range"} = "bytes=$ofs-"; |
1394 | } |
1432 | } |
1395 | |
1433 | |
1396 | http_get $url, |
1434 | http_get $url, |