… | |
… | |
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 = '2.1'; |
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; |
… | |
… | |
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 => $seconds |
175 | |
178 | |
176 | The time-out to use for various stages - each connect attempt will reset |
179 | The time-out to use for various stages - each connect attempt will reset |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
180 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
381 | |
384 | |
382 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
385 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
383 | timeout of 30 seconds. |
386 | timeout of 30 seconds. |
384 | |
387 | |
385 | http_request |
388 | http_request |
386 | GET => "https://www.google.com", |
389 | HEAD => "https://www.google.com", |
387 | headers => { "user-agent" => "MySearchClient 1.0" }, |
390 | headers => { "user-agent" => "MySearchClient 1.0" }, |
388 | timeout => 30, |
391 | timeout => 30, |
389 | sub { |
392 | sub { |
390 | my ($body, $hdr) = @_; |
393 | my ($body, $hdr) = @_; |
391 | use Data::Dumper; |
394 | use Data::Dumper; |
… | |
… | |
778 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
781 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
779 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
782 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
780 | my $was_persistent; # true if this is actually a recycled connection |
783 | my $was_persistent; # true if this is actually a recycled connection |
781 | |
784 | |
782 | # the key to use in the keepalive cache |
785 | # the key to use in the keepalive cache |
783 | my $ka_key = "$uhost\x00$arg{sessionid}"; |
786 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
784 | |
787 | |
785 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
788 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
786 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
789 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
787 | |
790 | |
788 | my %state = (connect_guard => 1); |
791 | my %state = (connect_guard => 1); |
… | |
… | |
959 | my $body = ""; |
962 | my $body = ""; |
960 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
963 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
961 | |
964 | |
962 | $state{read_chunk} = sub { |
965 | $state{read_chunk} = sub { |
963 | $_[1] =~ /^([0-9a-fA-F]+)/ |
966 | $_[1] =~ /^([0-9a-fA-F]+)/ |
964 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
967 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
965 | |
968 | |
966 | my $len = hex $1; |
969 | my $len = hex $1; |
967 | |
970 | |
968 | if ($len) { |
971 | if ($len) { |
969 | $cl += $len; |
972 | $cl += $len; |
… | |
… | |
1047 | _destroy_state %state; |
1050 | _destroy_state %state; |
1048 | |
1051 | |
1049 | %state = (); |
1052 | %state = (); |
1050 | $state{recurse} = |
1053 | $state{recurse} = |
1051 | http_request ( |
1054 | http_request ( |
1052 | $method => $url, |
1055 | $method => $url, |
1053 | %arg, |
1056 | %arg, |
|
|
1057 | recurse => $recurse - 1, |
1054 | keepalive => 0, |
1058 | keepalive => 0, |
1055 | sub { |
1059 | sub { |
1056 | %state = (); |
1060 | %state = (); |
1057 | &$cb |
1061 | &$cb |
1058 | } |
1062 | } |
… | |
… | |
1135 | if ($persistent && $KA_CACHE{$ka_key}) { |
1139 | if ($persistent && $KA_CACHE{$ka_key}) { |
1136 | $was_persistent = 1; |
1140 | $was_persistent = 1; |
1137 | |
1141 | |
1138 | $state{handle} = ka_fetch $ka_key; |
1142 | $state{handle} = ka_fetch $ka_key; |
1139 | $state{handle}->destroyed |
1143 | $state{handle}->destroyed |
1140 | and die "got a destructed habndle. pah\n";#d# |
1144 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1141 | $prepare_handle->(); |
1145 | $prepare_handle->(); |
1142 | $state{handle}->destroyed |
1146 | $state{handle}->destroyed |
1143 | and die "got a destructed habndle. pa2\n";#d# |
1147 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1144 | $handle_actual_request->(); |
1148 | $handle_actual_request->(); |
1145 | $state{handle}->destroyed |
|
|
1146 | and die "got a destructed habndle. pa3\n";#d# |
|
|
1147 | |
1149 | |
1148 | } else { |
1150 | } else { |
1149 | my $tcp_connect = $arg{tcp_connect} |
1151 | my $tcp_connect = $arg{tcp_connect} |
1150 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1152 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1151 | |
1153 | |
… | |
… | |
1192 | Sets the default proxy server to use. The proxy-url must begin with a |
1194 | Sets the default proxy server to use. The proxy-url must begin with a |
1193 | string of the form C<http://host:port>, croaks otherwise. |
1195 | string of the form C<http://host:port>, croaks otherwise. |
1194 | |
1196 | |
1195 | To clear an already-set proxy, use C<undef>. |
1197 | To clear an already-set proxy, use C<undef>. |
1196 | |
1198 | |
1197 | When AnyEvent::HTTP is laoded for the first time it will query the |
1199 | When AnyEvent::HTTP is loaded for the first time it will query the |
1198 | default proxy from the operating system, currently by looking at |
1200 | default proxy from the operating system, currently by looking at |
1199 | C<$ENV{http_proxy>}. |
1201 | C<$ENV{http_proxy>}. |
1200 | |
1202 | |
1201 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1203 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1202 | |
1204 | |
… | |
… | |
1214 | |
1216 | |
1215 | The key C<version> has to contain C<1>, otherwise the hash gets |
1217 | The key C<version> has to contain C<1>, otherwise the hash gets |
1216 | emptied. All other keys are hostnames or IP addresses pointing to |
1218 | emptied. All other keys are hostnames or IP addresses pointing to |
1217 | hash-references. The key for these inner hash references is the |
1219 | hash-references. The key for these inner hash references is the |
1218 | server path for which this cookie is meant, and the values are again |
1220 | server path for which this cookie is meant, and the values are again |
1219 | hash-references. The keys of those hash-references is the cookie name, and |
1221 | hash-references. Each key of those hash-references is a cookie name, and |
1220 | the value, you guessed it, is another hash-reference, this time with the |
1222 | the value, you guessed it, is another hash-reference, this time with the |
1221 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1223 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1222 | which have been replaced by a C<_expires> key that contains the cookie |
1224 | which have been replaced by a C<_expires> key that contains the cookie |
1223 | expiry timestamp. |
1225 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1226 | C<_expires> key. |
1224 | |
1227 | |
1225 | Here is an example of a cookie jar with a single cookie, so you have a |
1228 | Here is an example of a cookie jar with a single cookie, so you have a |
1226 | chance of understanding the above paragraph: |
1229 | chance of understanding the above paragraph: |
1227 | |
1230 | |
1228 | { |
1231 | { |
… | |
… | |
1252 | |
1255 | |
1253 | The default value for the C<recurse> request parameter (default: C<10>). |
1256 | The default value for the C<recurse> request parameter (default: C<10>). |
1254 | |
1257 | |
1255 | =item $AnyEvent::HTTP::TIMEOUT |
1258 | =item $AnyEvent::HTTP::TIMEOUT |
1256 | |
1259 | |
1257 | The default timeout for conenction operations (default: C<300>). |
1260 | The default timeout for connection operations (default: C<300>). |
1258 | |
1261 | |
1259 | =item $AnyEvent::HTTP::USERAGENT |
1262 | =item $AnyEvent::HTTP::USERAGENT |
1260 | |
1263 | |
1261 | The default value for the C<User-Agent> header (the default is |
1264 | The default value for the C<User-Agent> header (the default is |
1262 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1265 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
… | |
… | |
1327 | # other formats fail in the loop below |
1330 | # other formats fail in the loop below |
1328 | |
1331 | |
1329 | for (0..11) { |
1332 | for (0..11) { |
1330 | if ($m eq $month[$_]) { |
1333 | if ($m eq $month[$_]) { |
1331 | require Time::Local; |
1334 | require Time::Local; |
1332 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1335 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1333 | } |
1336 | } |
1334 | } |
1337 | } |
1335 | |
1338 | |
1336 | undef |
1339 | undef |
1337 | } |
1340 | } |
… | |
… | |
1383 | |
1386 | |
1384 | warn stat $fh; |
1387 | warn stat $fh; |
1385 | warn -s _; |
1388 | warn -s _; |
1386 | if (stat $fh and -s _) { |
1389 | if (stat $fh and -s _) { |
1387 | $ofs = -s _; |
1390 | $ofs = -s _; |
1388 | warn "-s is ", $ofs;#d# |
1391 | warn "-s is ", $ofs; |
1389 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1392 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1390 | $hdr{"range"} = "bytes=$ofs-"; |
1393 | $hdr{"range"} = "bytes=$ofs-"; |
1391 | } |
1394 | } |
1392 | |
1395 | |
1393 | http_get $url, |
1396 | http_get $url, |