… | |
… | |
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 = 2.21; |
51 | our $VERSION = 2.24; |
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 $MAX_RECURSE = 10; |
… | |
… | |
195 | C<$scheme> must be either missing or must be C<http> for HTTP. |
195 | C<$scheme> must be either missing or must be C<http> for HTTP. |
196 | |
196 | |
197 | If not specified, then the default proxy is used (see |
197 | If not specified, then the default proxy is used (see |
198 | C<AnyEvent::HTTP::set_proxy>). |
198 | C<AnyEvent::HTTP::set_proxy>). |
199 | |
199 | |
|
|
200 | Currently, if your proxy requires authorization, you have to specify an |
|
|
201 | appropriate "Proxy-Authorization" header in every request. |
|
|
202 | |
200 | =item body => $string |
203 | =item body => $string |
201 | |
204 | |
202 | The request body, usually empty. Will be sent as-is (future versions of |
205 | The request body, usually empty. Will be sent as-is (future versions of |
203 | this module might offer more options). |
206 | this module might offer more options). |
204 | |
207 | |
… | |
… | |
260 | In even rarer cases you want total control over how AnyEvent::HTTP |
263 | In even rarer cases you want total control over how AnyEvent::HTTP |
261 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
264 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
262 | to do this, but you can provide your own C<tcp_connect> function - |
265 | to do this, but you can provide your own C<tcp_connect> function - |
263 | obviously, it has to follow the same calling conventions, except that it |
266 | obviously, it has to follow the same calling conventions, except that it |
264 | may always return a connection guard object. |
267 | may always return a connection guard object. |
|
|
268 | |
|
|
269 | The connections made by this hook will be treated as equivalent to |
|
|
270 | connecitons made the built-in way, specifically, they will be put into |
|
|
271 | and taken from the persistent conneciton cache. If your C<$tcp_connect> |
|
|
272 | function is incompatible with this kind of re-use, consider switching off |
|
|
273 | C<persistent> connections and/or providing a C<session> identifier. |
265 | |
274 | |
266 | There are probably lots of weird uses for this function, starting from |
275 | There are probably lots of weird uses for this function, starting from |
267 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
276 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
268 | but fast) host => IP address caching or even socks protocol support. |
277 | but fast) host => IP address caching or even socks protocol support. |
269 | |
278 | |
… | |
… | |
339 | =item persistent => $boolean |
348 | =item persistent => $boolean |
340 | |
349 | |
341 | Try to create/reuse a persistent connection. When this flag is set |
350 | Try to create/reuse a persistent connection. When this flag is set |
342 | (default: true for idempotent requests, false for all others), then |
351 | (default: true for idempotent requests, false for all others), then |
343 | C<http_request> tries to re-use an existing (previously-created) |
352 | C<http_request> tries to re-use an existing (previously-created) |
344 | persistent connection to the host and, failing that, tries to create a new |
353 | persistent connection to same host (i.e. identical URL scheme, hostname, |
345 | one. |
354 | port and session) and, failing that, tries to create a new one. |
346 | |
355 | |
347 | Requests failing in certain ways will be automatically retried once, which |
356 | Requests failing in certain ways will be automatically retried once, which |
348 | is dangerous for non-idempotent requests, which is why it defaults to off |
357 | is dangerous for non-idempotent requests, which is why it defaults to off |
349 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
358 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
350 | made it impossible to distinguish between a fatal error and a normal |
359 | made it impossible to distinguish between a fatal error and a normal |
… | |
… | |
451 | |
460 | |
452 | # expire cookies |
461 | # expire cookies |
453 | sub cookie_jar_expire($;$) { |
462 | sub cookie_jar_expire($;$) { |
454 | my ($jar, $session_end) = @_; |
463 | my ($jar, $session_end) = @_; |
455 | |
464 | |
456 | %$jar = () if $jar->{version} != 1; |
465 | %$jar = () if $jar->{version} != 2; |
457 | |
466 | |
458 | my $anow = AE::now; |
467 | my $anow = AE::now; |
459 | |
468 | |
460 | while (my ($chost, $paths) = each %$jar) { |
469 | while (my ($chost, $paths) = each %$jar) { |
461 | next unless ref $paths; |
470 | next unless ref $paths; |
… | |
… | |
481 | |
490 | |
482 | # extract cookies from jar |
491 | # extract cookies from jar |
483 | sub cookie_jar_extract($$$$) { |
492 | sub cookie_jar_extract($$$$) { |
484 | my ($jar, $scheme, $host, $path) = @_; |
493 | my ($jar, $scheme, $host, $path) = @_; |
485 | |
494 | |
486 | %$jar = () if $jar->{version} != 1; |
495 | %$jar = () if $jar->{version} != 2; |
|
|
496 | |
|
|
497 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
498 | if $host =~ /[^\x00-\x7f]/; |
487 | |
499 | |
488 | my @cookies; |
500 | my @cookies; |
489 | |
501 | |
490 | while (my ($chost, $paths) = each %$jar) { |
502 | while (my ($chost, $paths) = each %$jar) { |
491 | next unless ref $paths; |
503 | next unless ref $paths; |
492 | |
504 | |
493 | if ($chost =~ /^\./) { |
505 | # exact match or suffix including . match |
494 | next unless $chost eq substr $host, -length $chost; |
506 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
495 | } elsif ($chost =~ /\./) { |
|
|
496 | next unless $chost eq $host; |
|
|
497 | } else { |
|
|
498 | next; |
507 | or next; |
499 | } |
|
|
500 | |
508 | |
501 | while (my ($cpath, $cookies) = each %$paths) { |
509 | while (my ($cpath, $cookies) = each %$paths) { |
502 | next unless $cpath eq substr $path, 0, length $cpath; |
510 | next unless $cpath eq substr $path, 0, length $cpath; |
503 | |
511 | |
504 | while (my ($cookie, $kv) = each %$cookies) { |
512 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
525 | } |
533 | } |
526 | |
534 | |
527 | # parse set_cookie header into jar |
535 | # parse set_cookie header into jar |
528 | sub cookie_jar_set_cookie($$$$) { |
536 | sub cookie_jar_set_cookie($$$$) { |
529 | my ($jar, $set_cookie, $host, $date) = @_; |
537 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
538 | |
|
|
539 | %$jar = () if $jar->{version} != 2; |
530 | |
540 | |
531 | my $anow = int AE::now; |
541 | my $anow = int AE::now; |
532 | my $snow; # server-now |
542 | my $snow; # server-now |
533 | |
543 | |
534 | for ($set_cookie) { |
544 | for ($set_cookie) { |
… | |
… | |
580 | |
590 | |
581 | my $cdom; |
591 | my $cdom; |
582 | my $cpath = (delete $kv{path}) || "/"; |
592 | my $cpath = (delete $kv{path}) || "/"; |
583 | |
593 | |
584 | if (exists $kv{domain}) { |
594 | if (exists $kv{domain}) { |
585 | $cdom = delete $kv{domain}; |
595 | $cdom = $kv{domain}; |
586 | |
596 | |
587 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
597 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
588 | |
598 | |
589 | next if $cdom =~ /\.$/; |
599 | next if $cdom =~ /\.$/; |
590 | |
600 | |
591 | # this is not rfc-like and not netscape-like. go figure. |
601 | # this is not rfc-like and not netscape-like. go figure. |
592 | my $ndots = $cdom =~ y/.//; |
602 | my $ndots = $cdom =~ y/.//; |
593 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
603 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
604 | |
|
|
605 | $cdom = substr $cdom, 1; # remove initial . |
594 | } else { |
606 | } else { |
595 | $cdom = $host; |
607 | $cdom = $host; |
596 | } |
608 | } |
597 | |
609 | |
598 | # store it |
610 | # store it |
599 | $jar->{version} = 1; |
611 | $jar->{version} = 2; |
600 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
612 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
601 | |
613 | |
602 | redo if /\G\s*,/gc; |
614 | redo if /\G\s*,/gc; |
603 | } |
615 | } |
604 | } |
616 | } |
… | |
… | |
770 | |
782 | |
771 | my $uport = $uscheme eq "http" ? 80 |
783 | my $uport = $uscheme eq "http" ? 80 |
772 | : $uscheme eq "https" ? 443 |
784 | : $uscheme eq "https" ? 443 |
773 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
785 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
774 | |
786 | |
775 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
787 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
776 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
788 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
777 | |
789 | |
778 | my $uhost = lc $1; |
790 | my $uhost = lc $1; |
779 | $uport = $2 if defined $2; |
791 | $uport = $2 if defined $2; |
780 | |
792 | |
… | |
… | |
892 | # we give our best and fall back to URI if available. |
904 | # we give our best and fall back to URI if available. |
893 | if (exists $hdr{location}) { |
905 | if (exists $hdr{location}) { |
894 | my $loc = $hdr{location}; |
906 | my $loc = $hdr{location}; |
895 | |
907 | |
896 | if ($loc =~ m%^//%) { # // |
908 | if ($loc =~ m%^//%) { # // |
897 | $loc = "$rscheme:$loc"; |
909 | $loc = "$uscheme:$loc"; |
898 | |
910 | |
899 | } elsif ($loc eq "") { |
911 | } elsif ($loc eq "") { |
900 | $loc = $url; |
912 | $loc = $url; |
901 | |
913 | |
902 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
914 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
903 | $loc =~ s/^\.\/+//; |
915 | $loc =~ s/^\.\/+//; |
904 | |
916 | |
905 | if ($loc !~ m%^[.?#]%) { |
917 | if ($loc !~ m%^[.?#]%) { |
906 | my $prefix = "$rscheme://$uhost:$uport"; |
918 | my $prefix = "$uscheme://$uauthority"; |
907 | |
919 | |
908 | unless ($loc =~ s/^\///) { |
920 | unless ($loc =~ s/^\///) { |
909 | $prefix .= $upath; |
921 | $prefix .= $upath; |
910 | $prefix =~ s/\/[^\/]*$//; |
922 | $prefix =~ s/\/[^\/]*$//; |
911 | } |
923 | } |
… | |
… | |
1028 | $finish->(delete $state{handle}); |
1040 | $finish->(delete $state{handle}); |
1029 | |
1041 | |
1030 | } elsif ($chunked) { |
1042 | } elsif ($chunked) { |
1031 | my $cl = 0; |
1043 | my $cl = 0; |
1032 | my $body = ""; |
1044 | my $body = ""; |
1033 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1045 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
1034 | |
1046 | |
1035 | $state{read_chunk} = sub { |
1047 | $state{read_chunk} = sub { |
1036 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1048 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1037 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1049 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1038 | |
1050 | |
… | |
… | |
1071 | } |
1083 | } |
1072 | }; |
1084 | }; |
1073 | |
1085 | |
1074 | $_[0]->push_read (line => $state{read_chunk}); |
1086 | $_[0]->push_read (line => $state{read_chunk}); |
1075 | |
1087 | |
1076 | } elsif ($arg{on_body}) { |
1088 | } elsif (!$redirect && $arg{on_body}) { |
1077 | if (defined $len) { |
1089 | if (defined $len) { |
1078 | $_[0]->on_read (sub { |
1090 | $_[0]->on_read (sub { |
1079 | $len -= length $_[0]{rbuf}; |
1091 | $len -= length $_[0]{rbuf}; |
1080 | |
1092 | |
1081 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1093 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
1120 | _destroy_state %state; |
1132 | _destroy_state %state; |
1121 | |
1133 | |
1122 | %state = (); |
1134 | %state = (); |
1123 | $state{recurse} = |
1135 | $state{recurse} = |
1124 | http_request ( |
1136 | http_request ( |
1125 | $method => $url, |
1137 | $method => $url, |
1126 | %arg, |
1138 | %arg, |
1127 | recurse => $recurse - 1, |
1139 | recurse => $recurse - 1, |
1128 | keepalive => 0, |
1140 | persistent => 0, |
1129 | sub { |
1141 | sub { |
1130 | %state = (); |
1142 | %state = (); |
1131 | &$cb |
1143 | &$cb |
1132 | } |
1144 | } |
1133 | ); |
1145 | ); |
… | |
… | |
1214 | # on a keepalive request (in theory, this should be a separate config option). |
1226 | # on a keepalive request (in theory, this should be a separate config option). |
1215 | if ($persistent && $KA_CACHE{$ka_key}) { |
1227 | if ($persistent && $KA_CACHE{$ka_key}) { |
1216 | $was_persistent = 1; |
1228 | $was_persistent = 1; |
1217 | |
1229 | |
1218 | $state{handle} = ka_fetch $ka_key; |
1230 | $state{handle} = ka_fetch $ka_key; |
1219 | $state{handle}->destroyed |
1231 | # $state{handle}->destroyed |
1220 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1232 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1221 | $prepare_handle->(); |
1233 | $prepare_handle->(); |
1222 | $state{handle}->destroyed |
1234 | # $state{handle}->destroyed |
1223 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1235 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1224 | $handle_actual_request->(); |
1236 | $handle_actual_request->(); |
1225 | |
1237 | |
1226 | } else { |
1238 | } else { |
1227 | my $tcp_connect = $arg{tcp_connect} |
1239 | my $tcp_connect = $arg{tcp_connect} |
1228 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1240 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1288 | function from time to time. |
1300 | function from time to time. |
1289 | |
1301 | |
1290 | A cookie jar is initially an empty hash-reference that is managed by this |
1302 | A cookie jar is initially an empty hash-reference that is managed by this |
1291 | module. Its format is subject to change, but currently it is as follows: |
1303 | module. Its format is subject to change, but currently it is as follows: |
1292 | |
1304 | |
1293 | The key C<version> has to contain C<1>, otherwise the hash gets |
1305 | The key C<version> has to contain C<2>, otherwise the hash gets |
1294 | emptied. All other keys are hostnames or IP addresses pointing to |
1306 | cleared. All other keys are hostnames or IP addresses pointing to |
1295 | hash-references. The key for these inner hash references is the |
1307 | hash-references. The key for these inner hash references is the |
1296 | server path for which this cookie is meant, and the values are again |
1308 | server path for which this cookie is meant, and the values are again |
1297 | hash-references. Each key of those hash-references is a cookie name, and |
1309 | hash-references. Each key of those hash-references is a cookie name, and |
1298 | the value, you guessed it, is another hash-reference, this time with the |
1310 | the value, you guessed it, is another hash-reference, this time with the |
1299 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1311 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
… | |
… | |
1303 | |
1315 | |
1304 | Here is an example of a cookie jar with a single cookie, so you have a |
1316 | Here is an example of a cookie jar with a single cookie, so you have a |
1305 | chance of understanding the above paragraph: |
1317 | chance of understanding the above paragraph: |
1306 | |
1318 | |
1307 | { |
1319 | { |
1308 | version => 1, |
1320 | version => 2, |
1309 | "10.0.0.1" => { |
1321 | "10.0.0.1" => { |
1310 | "/" => { |
1322 | "/" => { |
1311 | "mythweb_id" => { |
1323 | "mythweb_id" => { |
1312 | _expires => 1293917923, |
1324 | _expires => 1293917923, |
1313 | value => "ooRung9dThee3ooyXooM1Ohm", |
1325 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1458 | or die "$file: $!"; |
1470 | or die "$file: $!"; |
1459 | |
1471 | |
1460 | my %hdr; |
1472 | my %hdr; |
1461 | my $ofs = 0; |
1473 | my $ofs = 0; |
1462 | |
1474 | |
1463 | warn stat $fh; |
|
|
1464 | warn -s _; |
|
|
1465 | if (stat $fh and -s _) { |
1475 | if (stat $fh and -s _) { |
1466 | $ofs = -s _; |
1476 | $ofs = -s _; |
1467 | warn "-s is ", $ofs; |
1477 | warn "-s is ", $ofs; |
1468 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1478 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1469 | $hdr{"range"} = "bytes=$ofs-"; |
1479 | $hdr{"range"} = "bytes=$ofs-"; |
… | |
… | |
1497 | my (undef, $hdr) = @_; |
1507 | my (undef, $hdr) = @_; |
1498 | |
1508 | |
1499 | my $status = $hdr->{Status}; |
1509 | my $status = $hdr->{Status}; |
1500 | |
1510 | |
1501 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1511 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1502 | utime $fh, $time, $time; |
1512 | utime $time, $time, $fh; |
1503 | } |
1513 | } |
1504 | |
1514 | |
1505 | if ($status == 200 || $status == 206 || $status == 416) { |
1515 | if ($status == 200 || $status == 206 || $status == 416) { |
1506 | # download ok || resume ok || file already fully downloaded |
1516 | # download ok || resume ok || file already fully downloaded |
1507 | $cb->(1, $hdr); |
1517 | $cb->(1, $hdr); |