… | |
… | |
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 = 2.25; |
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 $MAX_RECURSE = 10; |
… | |
… | |
264 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
264 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
265 | to do this, but you can provide your own C<tcp_connect> function - |
265 | to do this, but you can provide your own C<tcp_connect> function - |
266 | obviously, it has to follow the same calling conventions, except that it |
266 | obviously, it has to follow the same calling conventions, except that it |
267 | may always return a connection guard object. |
267 | may always return a connection guard object. |
268 | |
268 | |
|
|
269 | The connections made by this hook will be treated as equivalent to |
|
|
270 | connecitons made the built-in way, specifically, they will be put into |
|
|
271 | and taken from the persistent conneciton cache. If your C<$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. |
|
|
274 | |
269 | 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 |
270 | 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 |
271 | but fast) host => IP address caching or even socks protocol support. |
277 | but fast) host => IP address caching or even socks protocol support. |
272 | |
278 | |
273 | =item on_header => $callback->($headers) |
279 | =item on_header => $callback->($headers) |
… | |
… | |
342 | =item persistent => $boolean |
348 | =item persistent => $boolean |
343 | |
349 | |
344 | Try to create/reuse a persistent connection. When this flag is set |
350 | Try to create/reuse a persistent connection. When this flag is set |
345 | (default: true for idempotent requests, false for all others), then |
351 | (default: true for idempotent requests, false for all others), then |
346 | C<http_request> tries to re-use an existing (previously-created) |
352 | C<http_request> tries to re-use an existing (previously-created) |
347 | persistent connection to the host and, failing that, tries to create a new |
353 | persistent connection to same host (i.e. identical URL scheme, hostname, |
348 | one. |
354 | port and session) and, failing that, tries to create a new one. |
349 | |
355 | |
350 | Requests failing in certain ways will be automatically retried once, which |
356 | Requests failing in certain ways will be automatically retried once, which |
351 | is dangerous for non-idempotent requests, which is why it defaults to off |
357 | is dangerous for non-idempotent requests, which is why it defaults to off |
352 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
358 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
353 | made it impossible to distinguish between a fatal error and a normal |
359 | made it impossible to distinguish between a fatal error and a normal |
… | |
… | |
454 | |
460 | |
455 | # expire cookies |
461 | # expire cookies |
456 | sub cookie_jar_expire($;$) { |
462 | sub cookie_jar_expire($;$) { |
457 | my ($jar, $session_end) = @_; |
463 | my ($jar, $session_end) = @_; |
458 | |
464 | |
459 | %$jar = () if $jar->{version} != 1; |
465 | %$jar = () if $jar->{version} != 2; |
460 | |
466 | |
461 | my $anow = AE::now; |
467 | my $anow = AE::now; |
462 | |
468 | |
463 | while (my ($chost, $paths) = each %$jar) { |
469 | while (my ($chost, $paths) = each %$jar) { |
464 | next unless ref $paths; |
470 | next unless ref $paths; |
… | |
… | |
484 | |
490 | |
485 | # extract cookies from jar |
491 | # extract cookies from jar |
486 | sub cookie_jar_extract($$$$) { |
492 | sub cookie_jar_extract($$$$) { |
487 | my ($jar, $scheme, $host, $path) = @_; |
493 | my ($jar, $scheme, $host, $path) = @_; |
488 | |
494 | |
489 | %$jar = () if $jar->{version} != 1; |
495 | %$jar = () if $jar->{version} != 2; |
|
|
496 | |
|
|
497 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
498 | if $host =~ /[^\x00-\x7f]/; |
490 | |
499 | |
491 | my @cookies; |
500 | my @cookies; |
492 | |
501 | |
493 | while (my ($chost, $paths) = each %$jar) { |
502 | while (my ($chost, $paths) = each %$jar) { |
494 | next unless ref $paths; |
503 | next unless ref $paths; |
495 | |
504 | |
496 | if ($chost =~ /^\./) { |
505 | # exact match or suffix including . match |
497 | next unless $chost eq substr $host, -length $chost; |
506 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
498 | } elsif ($chost =~ /\./) { |
|
|
499 | next unless $chost eq $host; |
|
|
500 | } else { |
|
|
501 | next; |
507 | or next; |
502 | } |
|
|
503 | |
508 | |
504 | while (my ($cpath, $cookies) = each %$paths) { |
509 | while (my ($cpath, $cookies) = each %$paths) { |
505 | next unless $cpath eq substr $path, 0, length $cpath; |
510 | next unless $cpath eq substr $path, 0, length $cpath; |
506 | |
511 | |
507 | while (my ($cookie, $kv) = each %$cookies) { |
512 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
528 | } |
533 | } |
529 | |
534 | |
530 | # parse set_cookie header into jar |
535 | # parse set_cookie header into jar |
531 | sub cookie_jar_set_cookie($$$$) { |
536 | sub cookie_jar_set_cookie($$$$) { |
532 | my ($jar, $set_cookie, $host, $date) = @_; |
537 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
538 | |
|
|
539 | %$jar = () if $jar->{version} != 2; |
533 | |
540 | |
534 | my $anow = int AE::now; |
541 | my $anow = int AE::now; |
535 | my $snow; # server-now |
542 | my $snow; # server-now |
536 | |
543 | |
537 | for ($set_cookie) { |
544 | for ($set_cookie) { |
… | |
… | |
583 | |
590 | |
584 | my $cdom; |
591 | my $cdom; |
585 | my $cpath = (delete $kv{path}) || "/"; |
592 | my $cpath = (delete $kv{path}) || "/"; |
586 | |
593 | |
587 | if (exists $kv{domain}) { |
594 | if (exists $kv{domain}) { |
588 | $cdom = delete $kv{domain}; |
595 | $cdom = $kv{domain}; |
589 | |
596 | |
590 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
597 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
591 | |
598 | |
592 | next if $cdom =~ /\.$/; |
599 | next if $cdom =~ /\.$/; |
593 | |
600 | |
594 | # this is not rfc-like and not netscape-like. go figure. |
601 | # this is not rfc-like and not netscape-like. go figure. |
595 | my $ndots = $cdom =~ y/.//; |
602 | my $ndots = $cdom =~ y/.//; |
596 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
603 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
604 | |
|
|
605 | $cdom = substr $cdom, 1; # remove initial . |
597 | } else { |
606 | } else { |
598 | $cdom = $host; |
607 | $cdom = $host; |
599 | } |
608 | } |
600 | |
609 | |
601 | # store it |
610 | # store it |
602 | $jar->{version} = 1; |
611 | $jar->{version} = 2; |
603 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
612 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
604 | |
613 | |
605 | redo if /\G\s*,/gc; |
614 | redo if /\G\s*,/gc; |
606 | } |
615 | } |
607 | } |
616 | } |
… | |
… | |
1291 | function from time to time. |
1300 | function from time to time. |
1292 | |
1301 | |
1293 | 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 |
1294 | 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: |
1295 | |
1304 | |
1296 | 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 |
1297 | emptied. All other keys are hostnames or IP addresses pointing to |
1306 | cleared. All other keys are hostnames or IP addresses pointing to |
1298 | hash-references. The key for these inner hash references is the |
1307 | hash-references. The key for these inner hash references is the |
1299 | 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 |
1300 | 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 |
1301 | 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 |
1302 | 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>, |
… | |
… | |
1306 | |
1315 | |
1307 | 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 |
1308 | chance of understanding the above paragraph: |
1317 | chance of understanding the above paragraph: |
1309 | |
1318 | |
1310 | { |
1319 | { |
1311 | version => 1, |
1320 | version => 2, |
1312 | "10.0.0.1" => { |
1321 | "10.0.0.1" => { |
1313 | "/" => { |
1322 | "/" => { |
1314 | "mythweb_id" => { |
1323 | "mythweb_id" => { |
1315 | _expires => 1293917923, |
1324 | _expires => 1293917923, |
1316 | value => "ooRung9dThee3ooyXooM1Ohm", |
1325 | value => "ooRung9dThee3ooyXooM1Ohm", |