… | |
… | |
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 = '2.03'; |
51 | our $VERSION = 2.25; |
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 | |
|
|
162 | Only redirects to http and https URLs are supported. While most common |
|
|
163 | redirection forms are handled entirely within this module, some require |
|
|
164 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
165 | the request will fail with an error. |
161 | |
166 | |
162 | =item headers => hashref |
167 | =item headers => hashref |
163 | |
168 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
169 | 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 |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
… | |
… | |
169 | |
174 | |
170 | You really should provide your own C<User-Agent:> header value that is |
175 | 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 |
176 | appropriate for your program - I wouldn't be surprised if the default |
172 | AnyEvent string gets blocked by webservers sooner or later. |
177 | AnyEvent string gets blocked by webservers sooner or later. |
173 | |
178 | |
|
|
179 | Also, make sure that your headers names and values do not contain any |
|
|
180 | embedded newlines. |
|
|
181 | |
174 | =item timeout => $seconds |
182 | =item timeout => $seconds |
175 | |
183 | |
176 | The time-out to use for various stages - each connect attempt will reset |
184 | The time-out to use for various stages - each connect attempt will reset |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
185 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | timeout. |
186 | timeout. |
179 | |
187 | |
180 | Default timeout is 5 minutes. |
188 | Default timeout is 5 minutes. |
181 | |
189 | |
182 | =item proxy => [$host, $port[, $scheme]] or undef |
190 | =item proxy => [$host, $port[, $scheme]] or undef |
183 | |
191 | |
184 | Use the given http proxy for all requests. If not specified, then the |
192 | Use the given http proxy for all requests, or no proxy if C<undef> is |
185 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
193 | used. |
186 | |
194 | |
187 | 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 | |
|
|
197 | If not specified, then the default proxy is used (see |
|
|
198 | C<AnyEvent::HTTP::set_proxy>). |
|
|
199 | |
|
|
200 | Currently, if your proxy requires authorization, you have to specify an |
|
|
201 | appropriate "Proxy-Authorization" header in every request. |
|
|
202 | |
|
|
203 | Note that this module will prefer an existing persistent connection, |
|
|
204 | even if that connection was made using another proxy. If you need to |
|
|
205 | ensure that a new connection is made in this case, you can either force |
|
|
206 | C<persistent> to false or e.g. use the proxy address in your C<sessionid>. |
188 | |
207 | |
189 | =item body => $string |
208 | =item body => $string |
190 | |
209 | |
191 | The request body, usually empty. Will be sent as-is (future versions of |
210 | The request body, usually empty. Will be sent as-is (future versions of |
192 | this module might offer more options). |
211 | this module might offer more options). |
… | |
… | |
225 | The default for this option is C<low>, which could be interpreted as "give |
244 | The default for this option is C<low>, which could be interpreted as "give |
226 | me the page, no matter what". |
245 | me the page, no matter what". |
227 | |
246 | |
228 | See also the C<sessionid> parameter. |
247 | See also the C<sessionid> parameter. |
229 | |
248 | |
230 | =item session => $string |
249 | =item sessionid => $string |
231 | |
250 | |
232 | The module might reuse connections to the same host internally. Sometimes |
251 | The module might reuse connections to the same host internally (regardless |
233 | (e.g. when using TLS), you do not want to reuse connections from other |
252 | of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g. |
|
|
253 | when using TLS or a specfic proxy), you do not want to reuse connections |
234 | sessions. This can be achieved by setting this parameter to some unique |
254 | from other sessions. This can be achieved by setting this parameter to |
235 | ID (such as the address of an object storing your state data, or the TLS |
255 | some unique ID (such as the address of an object storing your state data |
236 | context) - only connections using the same unique ID will be reused. |
256 | or the TLS context, or the proxy IP) - only connections using the same |
|
|
257 | unique ID will be reused. |
237 | |
258 | |
238 | =item on_prepare => $callback->($fh) |
259 | =item on_prepare => $callback->($fh) |
239 | |
260 | |
240 | In rare cases you need to "tune" the socket before it is used to |
261 | In rare cases you need to "tune" the socket before it is used to |
241 | connect (for exmaple, to bind it on a given IP address). This parameter |
262 | connect (for example, to bind it on a given IP address). This parameter |
242 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
263 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
243 | and behaves exactly the same way (e.g. it has to provide a |
264 | and behaves exactly the same way (e.g. it has to provide a |
244 | timeout). See the description for the C<$prepare_cb> argument of |
265 | timeout). See the description for the C<$prepare_cb> argument of |
245 | C<AnyEvent::Socket::tcp_connect> for details. |
266 | C<AnyEvent::Socket::tcp_connect> for details. |
246 | |
267 | |
… | |
… | |
249 | In even rarer cases you want total control over how AnyEvent::HTTP |
270 | In even rarer cases you want total control over how AnyEvent::HTTP |
250 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
271 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
251 | to do this, but you can provide your own C<tcp_connect> function - |
272 | to do this, but you can provide your own C<tcp_connect> function - |
252 | obviously, it has to follow the same calling conventions, except that it |
273 | obviously, it has to follow the same calling conventions, except that it |
253 | may always return a connection guard object. |
274 | may always return a connection guard object. |
|
|
275 | |
|
|
276 | The connections made by this hook will be treated as equivalent to |
|
|
277 | connections made the built-in way, specifically, they will be put into |
|
|
278 | and taken from the persistent connection cache. If your C<$tcp_connect> |
|
|
279 | function is incompatible with this kind of re-use, consider switching off |
|
|
280 | C<persistent> connections and/or providing a C<sessionid> identifier. |
254 | |
281 | |
255 | There are probably lots of weird uses for this function, starting from |
282 | There are probably lots of weird uses for this function, starting from |
256 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
283 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
257 | but fast) host => IP address caching or even socks protocol support. |
284 | but fast) host => IP address caching or even socks protocol support. |
258 | |
285 | |
… | |
… | |
328 | =item persistent => $boolean |
355 | =item persistent => $boolean |
329 | |
356 | |
330 | Try to create/reuse a persistent connection. When this flag is set |
357 | Try to create/reuse a persistent connection. When this flag is set |
331 | (default: true for idempotent requests, false for all others), then |
358 | (default: true for idempotent requests, false for all others), then |
332 | C<http_request> tries to re-use an existing (previously-created) |
359 | C<http_request> tries to re-use an existing (previously-created) |
333 | persistent connection to the host and, failing that, tries to create a new |
360 | persistent connection to same host (i.e. identical URL scheme, hostname, |
334 | one. |
361 | port and sessionid) and, failing that, tries to create a new one. |
335 | |
362 | |
336 | Requests failing in certain ways will be automatically retried once, which |
363 | Requests failing in certain ways will be automatically retried once, which |
337 | is dangerous for non-idempotent requests, which is why it defaults to off |
364 | is dangerous for non-idempotent requests, which is why it defaults to off |
338 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
365 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
339 | made it impossible to distinguish between a fatal error and a normal |
366 | made it impossible to distinguish between a fatal error and a normal |
340 | connection timeout, so you never know whether there was a problem with |
367 | connection timeout, so you never know whether there was a problem with |
341 | your request or not. |
368 | your request or not. |
342 | |
369 | |
343 | When reusing an existent connection, many parameters (such as TLS context) |
370 | When reusing an existent connection, many parameters (such as TLS context) |
344 | will be ignored. See the C<session> parameter for a workaround. |
371 | will be ignored. See the C<sessionid> parameter for a workaround. |
345 | |
372 | |
346 | =item keepalive => $boolean |
373 | =item keepalive => $boolean |
347 | |
374 | |
348 | Only used when C<persistent> is also true. This parameter decides whether |
375 | Only used when C<persistent> is also true. This parameter decides whether |
349 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
376 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
… | |
… | |
378 | |
405 | |
379 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
406 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
380 | timeout of 30 seconds. |
407 | timeout of 30 seconds. |
381 | |
408 | |
382 | http_request |
409 | http_request |
383 | GET => "https://www.google.com", |
410 | HEAD => "https://www.google.com", |
384 | headers => { "user-agent" => "MySearchClient 1.0" }, |
411 | headers => { "user-agent" => "MySearchClient 1.0" }, |
385 | timeout => 30, |
412 | timeout => 30, |
386 | sub { |
413 | sub { |
387 | my ($body, $hdr) = @_; |
414 | my ($body, $hdr) = @_; |
388 | use Data::Dumper; |
415 | use Data::Dumper; |
… | |
… | |
440 | |
467 | |
441 | # expire cookies |
468 | # expire cookies |
442 | sub cookie_jar_expire($;$) { |
469 | sub cookie_jar_expire($;$) { |
443 | my ($jar, $session_end) = @_; |
470 | my ($jar, $session_end) = @_; |
444 | |
471 | |
445 | %$jar = () if $jar->{version} != 1; |
472 | %$jar = () if $jar->{version} != 2; |
446 | |
473 | |
447 | my $anow = AE::now; |
474 | my $anow = AE::now; |
448 | |
475 | |
449 | while (my ($chost, $paths) = each %$jar) { |
476 | while (my ($chost, $paths) = each %$jar) { |
450 | next unless ref $paths; |
477 | next unless ref $paths; |
… | |
… | |
470 | |
497 | |
471 | # extract cookies from jar |
498 | # extract cookies from jar |
472 | sub cookie_jar_extract($$$$) { |
499 | sub cookie_jar_extract($$$$) { |
473 | my ($jar, $scheme, $host, $path) = @_; |
500 | my ($jar, $scheme, $host, $path) = @_; |
474 | |
501 | |
475 | %$jar = () if $jar->{version} != 1; |
502 | %$jar = () if $jar->{version} != 2; |
|
|
503 | |
|
|
504 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
505 | if $host =~ /[^\x00-\x7f]/; |
476 | |
506 | |
477 | my @cookies; |
507 | my @cookies; |
478 | |
508 | |
479 | while (my ($chost, $paths) = each %$jar) { |
509 | while (my ($chost, $paths) = each %$jar) { |
480 | next unless ref $paths; |
510 | next unless ref $paths; |
481 | |
511 | |
482 | if ($chost =~ /^\./) { |
512 | # exact match or suffix including . match |
483 | next unless $chost eq substr $host, -length $chost; |
513 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
484 | } elsif ($chost =~ /\./) { |
|
|
485 | next unless $chost eq $host; |
|
|
486 | } else { |
|
|
487 | next; |
514 | or next; |
488 | } |
|
|
489 | |
515 | |
490 | while (my ($cpath, $cookies) = each %$paths) { |
516 | while (my ($cpath, $cookies) = each %$paths) { |
491 | next unless $cpath eq substr $path, 0, length $cpath; |
517 | next unless $cpath eq substr $path, 0, length $cpath; |
492 | |
518 | |
493 | while (my ($cookie, $kv) = each %$cookies) { |
519 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
514 | } |
540 | } |
515 | |
541 | |
516 | # parse set_cookie header into jar |
542 | # parse set_cookie header into jar |
517 | sub cookie_jar_set_cookie($$$$) { |
543 | sub cookie_jar_set_cookie($$$$) { |
518 | my ($jar, $set_cookie, $host, $date) = @_; |
544 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
545 | |
|
|
546 | %$jar = () if $jar->{version} != 2; |
519 | |
547 | |
520 | my $anow = int AE::now; |
548 | my $anow = int AE::now; |
521 | my $snow; # server-now |
549 | my $snow; # server-now |
522 | |
550 | |
523 | for ($set_cookie) { |
551 | for ($set_cookie) { |
… | |
… | |
529 | while ( |
557 | while ( |
530 | m{ |
558 | m{ |
531 | \G\s* |
559 | \G\s* |
532 | (?: |
560 | (?: |
533 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
561 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
534 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
562 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )? |
535 | ) |
563 | ) |
536 | }gcxsi |
564 | }gcxsi |
537 | ) { |
565 | ) { |
538 | my $name = $2; |
566 | my $name = $2; |
539 | my $value = $4; |
567 | my $value = $4; |
… | |
… | |
569 | |
597 | |
570 | my $cdom; |
598 | my $cdom; |
571 | my $cpath = (delete $kv{path}) || "/"; |
599 | my $cpath = (delete $kv{path}) || "/"; |
572 | |
600 | |
573 | if (exists $kv{domain}) { |
601 | if (exists $kv{domain}) { |
574 | $cdom = delete $kv{domain}; |
602 | $cdom = $kv{domain}; |
575 | |
603 | |
576 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
604 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
577 | |
605 | |
578 | next if $cdom =~ /\.$/; |
606 | next if $cdom =~ /\.$/; |
579 | |
607 | |
580 | # this is not rfc-like and not netscape-like. go figure. |
608 | # this is not rfc-like and not netscape-like. go figure. |
581 | my $ndots = $cdom =~ y/.//; |
609 | my $ndots = $cdom =~ y/.//; |
582 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
610 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
611 | |
|
|
612 | $cdom = substr $cdom, 1; # remove initial . |
583 | } else { |
613 | } else { |
584 | $cdom = $host; |
614 | $cdom = $host; |
585 | } |
615 | } |
586 | |
616 | |
587 | # store it |
617 | # store it |
588 | $jar->{version} = 1; |
618 | $jar->{version} = 2; |
589 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
619 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
590 | |
620 | |
591 | redo if /\G\s*,/gc; |
621 | redo if /\G\s*,/gc; |
592 | } |
622 | } |
593 | } |
623 | } |
… | |
… | |
683 | |
713 | |
684 | $cb->(undef, $hdr); |
714 | $cb->(undef, $hdr); |
685 | () |
715 | () |
686 | } |
716 | } |
687 | |
717 | |
|
|
718 | our %IDEMPOTENT = ( |
|
|
719 | DELETE => 1, |
|
|
720 | GET => 1, |
|
|
721 | QUERY => 1, |
|
|
722 | HEAD => 1, |
|
|
723 | OPTIONS => 1, |
|
|
724 | PUT => 1, |
|
|
725 | TRACE => 1, |
|
|
726 | |
|
|
727 | ACL => 1, |
|
|
728 | "BASELINE-CONTROL" => 1, |
|
|
729 | BIND => 1, |
|
|
730 | CHECKIN => 1, |
|
|
731 | CHECKOUT => 1, |
|
|
732 | COPY => 1, |
|
|
733 | LABEL => 1, |
|
|
734 | LINK => 1, |
|
|
735 | MERGE => 1, |
|
|
736 | MKACTIVITY => 1, |
|
|
737 | MKCALENDAR => 1, |
|
|
738 | MKCOL => 1, |
|
|
739 | MKREDIRECTREF => 1, |
|
|
740 | MKWORKSPACE => 1, |
|
|
741 | MOVE => 1, |
|
|
742 | ORDERPATCH => 1, |
|
|
743 | PROPFIND => 1, |
|
|
744 | PROPPATCH => 1, |
|
|
745 | REBIND => 1, |
|
|
746 | REPORT => 1, |
|
|
747 | SEARCH => 1, |
|
|
748 | UNBIND => 1, |
|
|
749 | UNCHECKOUT => 1, |
|
|
750 | UNLINK => 1, |
|
|
751 | UNLOCK => 1, |
|
|
752 | UPDATE => 1, |
|
|
753 | UPDATEREDIRECTREF => 1, |
|
|
754 | "VERSION-CONTROL" => 1, |
|
|
755 | ); |
|
|
756 | |
688 | sub http_request($$@) { |
757 | sub http_request($$@) { |
689 | my $cb = pop; |
758 | my $cb = pop; |
690 | my ($method, $url, %arg) = @_; |
759 | my ($method, $url, %arg) = @_; |
691 | |
760 | |
692 | my %hdr; |
761 | my %hdr; |
… | |
… | |
709 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
778 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
710 | |
779 | |
711 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
780 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
712 | if $recurse < 0; |
781 | if $recurse < 0; |
713 | |
782 | |
714 | my $proxy = $arg{proxy} || $PROXY; |
783 | my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY; |
715 | my $timeout = $arg{timeout} || $TIMEOUT; |
784 | my $timeout = $arg{timeout} || $TIMEOUT; |
716 | |
785 | |
717 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
786 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
718 | $url =~ m|^([^:/?#]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
787 | $url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
719 | |
788 | |
720 | $uscheme = lc $uscheme; |
789 | $uscheme = lc $uscheme; |
721 | |
790 | |
722 | my $uport = $uscheme eq "http" ? 80 |
791 | my $uport = $uscheme eq "http" ? 80 |
723 | : $uscheme eq "https" ? 443 |
792 | : $uscheme eq "https" ? 443 |
724 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
793 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
725 | |
794 | |
726 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
795 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
727 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
796 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
728 | |
797 | |
729 | my $uhost = lc $1; |
798 | my $uhost = lc $1; |
730 | $uport = $2 if defined $2; |
799 | $uport = $2 if defined $2; |
731 | |
800 | |
… | |
… | |
767 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
836 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
768 | |
837 | |
769 | $hdr{"content-length"} = length $arg{body} |
838 | $hdr{"content-length"} = length $arg{body} |
770 | if length $arg{body} || $method ne "GET"; |
839 | if length $arg{body} || $method ne "GET"; |
771 | |
840 | |
772 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
841 | my $idempotent = $IDEMPOTENT{$method}; |
773 | |
842 | |
774 | # default value for keepalive is true iff the request is for an idempotent method |
843 | # default value for keepalive is true iff the request is for an idempotent method |
775 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : $idempotent; |
844 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
776 | my $keepalive10 = exists $arg{keepalive10} ? $arg{keepalive10} : !$proxy; |
845 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
777 | my $keptalive; # true if this is actually a recycled connection |
846 | my $was_persistent; # true if this is actually a recycled connection |
778 | |
847 | |
779 | # the key to use in the keepalive cache |
848 | # the key to use in the keepalive cache |
780 | my $ka_key = "$uhost\x00$arg{sessionid}"; |
849 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
781 | |
850 | |
782 | $hdr{connection} = ($keepalive ? $keepalive10 ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
851 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
783 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
852 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
784 | |
853 | |
785 | my %state = (connect_guard => 1); |
854 | my %state = (connect_guard => 1); |
786 | |
855 | |
787 | my $ae_error = 595; # connecting |
856 | my $ae_error = 595; # connecting |
… | |
… | |
797 | # send request |
866 | # send request |
798 | $hdl->push_write ( |
867 | $hdl->push_write ( |
799 | "$method $rpath HTTP/1.1\015\012" |
868 | "$method $rpath HTTP/1.1\015\012" |
800 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
869 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
801 | . "\015\012" |
870 | . "\015\012" |
802 | . (delete $arg{body}) |
871 | . $arg{body} |
803 | ); |
872 | ); |
804 | |
873 | |
805 | # return if error occured during push_write() |
874 | # return if error occurred during push_write() |
806 | return unless %state; |
875 | return unless %state; |
807 | |
876 | |
808 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
877 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
809 | %hdr = (); |
878 | %hdr = (); |
810 | |
879 | |
… | |
… | |
837 | |
906 | |
838 | %hdr = (%$hdr, @pseudo); |
907 | %hdr = (%$hdr, @pseudo); |
839 | } |
908 | } |
840 | |
909 | |
841 | # redirect handling |
910 | # redirect handling |
842 | # microsoft and other shitheads don't give a shit for following standards, |
911 | # relative uri handling forced by microsoft and other shitheads. |
843 | # try to support some common forms of broken Location headers. |
912 | # we give our best and fall back to URI if available. |
844 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
913 | if (exists $hdr{location}) { |
|
|
914 | my $loc = $hdr{location}; |
|
|
915 | |
|
|
916 | if ($loc =~ m%^//%) { # // |
|
|
917 | $loc = "$uscheme:$loc"; |
|
|
918 | |
|
|
919 | } elsif ($loc eq "") { |
|
|
920 | $loc = $url; |
|
|
921 | |
|
|
922 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
845 | $hdr{location} =~ s/^\.\/+//; |
923 | $loc =~ s/^\.\/+//; |
846 | |
924 | |
847 | my $url = "$rscheme://$uhost:$uport"; |
925 | if ($loc !~ m%^[.?#]%) { |
|
|
926 | my $prefix = "$uscheme://$uauthority"; |
848 | |
927 | |
849 | unless ($hdr{location} =~ s/^\///) { |
928 | unless ($loc =~ s/^\///) { |
850 | $url .= $upath; |
929 | $prefix .= $upath; |
851 | $url =~ s/\/[^\/]*$//; |
930 | $prefix =~ s/\/[^\/]*$//; |
|
|
931 | } |
|
|
932 | |
|
|
933 | $loc = "$prefix/$loc"; |
|
|
934 | |
|
|
935 | } elsif (eval { require URI }) { # uri |
|
|
936 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
937 | |
|
|
938 | } else { |
|
|
939 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
940 | #$hdr{Status} = 599; |
|
|
941 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
942 | #$recurse = 0; |
|
|
943 | } |
852 | } |
944 | } |
853 | |
945 | |
854 | $hdr{location} = "$url/$hdr{location}"; |
946 | $hdr{location} = $loc; |
855 | } |
947 | } |
856 | |
948 | |
857 | my $redirect; |
949 | my $redirect; |
858 | |
950 | |
859 | if ($recurse) { |
951 | if ($recurse) { |
… | |
… | |
861 | |
953 | |
862 | # industry standard is to redirect POST as GET for |
954 | # industry standard is to redirect POST as GET for |
863 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
955 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
864 | # also, the UA should ask the user for 301 and 307 and POST, |
956 | # also, the UA should ask the user for 301 and 307 and POST, |
865 | # industry standard seems to be to simply follow. |
957 | # industry standard seems to be to simply follow. |
866 | # we go with the industry standard. |
958 | # we go with the industry standard. 308 is defined |
|
|
959 | # by rfc7538 |
867 | if ($status == 301 or $status == 302 or $status == 303) { |
960 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
961 | $redirect = 1; |
868 | # HTTP/1.1 is unclear on how to mutate the method |
962 | # HTTP/1.1 is unclear on how to mutate the method |
869 | $method = "GET" unless $method eq "HEAD"; |
963 | unless ($method eq "HEAD") { |
870 | $redirect = 1; |
964 | $method = "GET"; |
|
|
965 | delete $arg{body}; |
|
|
966 | } |
871 | } elsif ($status == 307) { |
967 | } elsif ($status == 307 or $status == 308) { |
872 | $redirect = 1; |
968 | $redirect = 1; |
873 | } |
969 | } |
874 | } |
970 | } |
875 | |
971 | |
876 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
972 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
877 | if ($state{handle}) { |
973 | if ($state{handle}) { |
878 | # handle keepalive |
974 | # handle keepalive |
879 | if ( |
975 | if ( |
880 | $keepalive |
976 | $persistent |
881 | && $_[3] |
977 | && $_[3] |
882 | && ($hdr{HTTPVersion} < 1.1 |
978 | && ($hdr{HTTPVersion} < 1.1 |
883 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
979 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
884 | : $hdr{connection} !~ /\bclose\b/i) |
980 | : $hdr{connection} !~ /\bclose\b/i) |
885 | ) { |
981 | ) { |
… | |
… | |
904 | |
1000 | |
905 | if ($redirect && exists $hdr{location}) { |
1001 | if ($redirect && exists $hdr{location}) { |
906 | # we ignore any errors, as it is very common to receive |
1002 | # we ignore any errors, as it is very common to receive |
907 | # Content-Length != 0 but no actual body |
1003 | # Content-Length != 0 but no actual body |
908 | # we also access %hdr, as $_[1] might be an erro |
1004 | # we also access %hdr, as $_[1] might be an erro |
|
|
1005 | $state{recurse} = |
909 | http_request ( |
1006 | http_request ( |
910 | $method => $hdr{location}, |
1007 | $method => $hdr{location}, |
911 | %arg, |
1008 | %arg, |
912 | recurse => $recurse - 1, |
1009 | recurse => $recurse - 1, |
913 | Redirect => [$_[0], \%hdr], |
1010 | Redirect => [$_[0], \%hdr], |
|
|
1011 | sub { |
|
|
1012 | %state = (); |
914 | $cb |
1013 | &$cb |
|
|
1014 | }, |
915 | ); |
1015 | ); |
916 | } else { |
1016 | } else { |
917 | $cb->($_[0], \%hdr); |
1017 | $cb->($_[0], \%hdr); |
918 | } |
1018 | } |
919 | }; |
1019 | }; |
920 | |
1020 | |
… | |
… | |
948 | $finish->(delete $state{handle}); |
1048 | $finish->(delete $state{handle}); |
949 | |
1049 | |
950 | } elsif ($chunked) { |
1050 | } elsif ($chunked) { |
951 | my $cl = 0; |
1051 | my $cl = 0; |
952 | my $body = ""; |
1052 | my $body = ""; |
953 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1053 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
954 | |
1054 | |
955 | $state{read_chunk} = sub { |
1055 | $state{read_chunk} = sub { |
956 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1056 | $_[1] =~ /^([0-9a-fA-F]+)/ |
957 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1057 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
958 | |
1058 | |
959 | my $len = hex $1; |
1059 | my $len = hex $1; |
960 | |
1060 | |
961 | if ($len) { |
1061 | if ($len) { |
962 | $cl += $len; |
1062 | $cl += $len; |
… | |
… | |
991 | } |
1091 | } |
992 | }; |
1092 | }; |
993 | |
1093 | |
994 | $_[0]->push_read (line => $state{read_chunk}); |
1094 | $_[0]->push_read (line => $state{read_chunk}); |
995 | |
1095 | |
996 | } elsif ($arg{on_body}) { |
1096 | } elsif (!$redirect && $arg{on_body}) { |
997 | if (defined $len) { |
1097 | if (defined $len) { |
998 | $_[0]->on_read (sub { |
1098 | $_[0]->on_read (sub { |
999 | $len -= length $_[0]{rbuf}; |
1099 | $len -= length $_[0]{rbuf}; |
1000 | |
1100 | |
1001 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1101 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
1032 | } |
1132 | } |
1033 | }; |
1133 | }; |
1034 | |
1134 | |
1035 | # if keepalive is enabled, then the server closing the connection |
1135 | # if keepalive is enabled, then the server closing the connection |
1036 | # before a response can happen legally - we retry on idempotent methods. |
1136 | # before a response can happen legally - we retry on idempotent methods. |
1037 | if ($keptalive && $idempotent) { |
1137 | if ($was_persistent && $idempotent) { |
1038 | my $old_eof = $hdl->{on_eof}; |
1138 | my $old_eof = $hdl->{on_eof}; |
1039 | $hdl->{on_eof} = sub { |
1139 | $hdl->{on_eof} = sub { |
1040 | _destroy_state %state; |
1140 | _destroy_state %state; |
1041 | |
1141 | |
|
|
1142 | %state = (); |
|
|
1143 | $state{recurse} = |
1042 | http_request ( |
1144 | http_request ( |
1043 | $method => $url, |
1145 | $method => $url, |
1044 | %arg, |
1146 | %arg, |
1045 | keepalive => 0, |
1147 | recurse => $recurse - 1, |
|
|
1148 | persistent => 0, |
|
|
1149 | sub { |
|
|
1150 | %state = (); |
1046 | $cb |
1151 | &$cb |
|
|
1152 | } |
1047 | ); |
1153 | ); |
1048 | }; |
1154 | }; |
1049 | $hdl->on_read (sub { |
1155 | $hdl->on_read (sub { |
1050 | return unless %state; |
1156 | return unless %state; |
1051 | |
1157 | |
1052 | # as soon as we receive something, a connection close |
1158 | # as soon as we receive something, a connection close |
… | |
… | |
1060 | }; |
1166 | }; |
1061 | |
1167 | |
1062 | my $prepare_handle = sub { |
1168 | my $prepare_handle = sub { |
1063 | my ($hdl) = $state{handle}; |
1169 | my ($hdl) = $state{handle}; |
1064 | |
1170 | |
1065 | $hdl->timeout ($timeout); |
|
|
1066 | $hdl->on_error (sub { |
1171 | $hdl->on_error (sub { |
1067 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1172 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
1068 | }); |
1173 | }); |
1069 | $hdl->on_eof (sub { |
1174 | $hdl->on_eof (sub { |
1070 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1175 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
1071 | }); |
1176 | }); |
|
|
1177 | $hdl->timeout_reset; |
|
|
1178 | $hdl->timeout ($timeout); |
1072 | }; |
1179 | }; |
1073 | |
1180 | |
1074 | # connected to proxy (or origin server) |
1181 | # connected to proxy (or origin server) |
1075 | my $connect_cb = sub { |
1182 | my $connect_cb = sub { |
1076 | my $fh = shift |
1183 | my $fh = shift |
… | |
… | |
1092 | |
1199 | |
1093 | # now handle proxy-CONNECT method |
1200 | # now handle proxy-CONNECT method |
1094 | if ($proxy && $uscheme eq "https") { |
1201 | if ($proxy && $uscheme eq "https") { |
1095 | # oh dear, we have to wrap it into a connect request |
1202 | # oh dear, we have to wrap it into a connect request |
1096 | |
1203 | |
|
|
1204 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1205 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1206 | : ""; |
|
|
1207 | |
1097 | # maybe re-use $uauthority with patched port? |
1208 | # maybe re-use $uauthority with patched port? |
1098 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1209 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
1099 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1210 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1100 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1211 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1101 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1212 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1102 | |
1213 | |
1103 | if ($2 == 200) { |
1214 | if ($2 == 200) { |
… | |
… | |
1106 | } else { |
1217 | } else { |
1107 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1218 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1108 | } |
1219 | } |
1109 | }); |
1220 | }); |
1110 | } else { |
1221 | } else { |
|
|
1222 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1223 | |
1111 | $handle_actual_request->(); |
1224 | $handle_actual_request->(); |
1112 | } |
1225 | } |
1113 | }; |
1226 | }; |
1114 | |
1227 | |
1115 | _get_slot $uhost, sub { |
1228 | _get_slot $uhost, sub { |
… | |
… | |
1117 | |
1230 | |
1118 | return unless $state{connect_guard}; |
1231 | return unless $state{connect_guard}; |
1119 | |
1232 | |
1120 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
1233 | # 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). |
1234 | # on a keepalive request (in theory, this should be a separate config option). |
1122 | if ($keepalive && $KA_CACHE{$ka_key}) { |
1235 | if ($persistent && $KA_CACHE{$ka_key}) { |
1123 | $keptalive = 1; |
1236 | $was_persistent = 1; |
|
|
1237 | |
1124 | $state{handle} = ka_fetch $ka_key; |
1238 | $state{handle} = ka_fetch $ka_key; |
|
|
1239 | # $state{handle}->destroyed |
|
|
1240 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1125 | $prepare_handle->(); |
1241 | $prepare_handle->(); |
|
|
1242 | # $state{handle}->destroyed |
|
|
1243 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
|
|
1244 | $rpath = $upath; |
1126 | $handle_actual_request->(); |
1245 | $handle_actual_request->(); |
1127 | |
1246 | |
1128 | } else { |
1247 | } else { |
1129 | my $tcp_connect = $arg{tcp_connect} |
1248 | my $tcp_connect = $arg{tcp_connect} |
1130 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1249 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1172 | Sets the default proxy server to use. The proxy-url must begin with a |
1291 | 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. |
1292 | string of the form C<http://host:port>, croaks otherwise. |
1174 | |
1293 | |
1175 | To clear an already-set proxy, use C<undef>. |
1294 | To clear an already-set proxy, use C<undef>. |
1176 | |
1295 | |
|
|
1296 | When AnyEvent::HTTP is loaded for the first time it will query the |
|
|
1297 | default proxy from the operating system, currently by looking at |
|
|
1298 | C<$ENV{http_proxy>}. |
|
|
1299 | |
1177 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1300 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1178 | |
1301 | |
1179 | Remove all cookies from the cookie jar that have been expired. If |
1302 | 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 |
1303 | C<$session_end> is given and true, then additionally remove all session |
1181 | cookies. |
1304 | cookies. |
1182 | |
1305 | |
1183 | You should call this function (with a true C<$session_end>) before you |
1306 | You should call this function (with a true C<$session_end>) before you |
1184 | save cookies to disk, and you should call this function after loading them |
1307 | save cookies to disk, and you should call this function after loading them |
1185 | again. If you have a long-running program you can additonally call this |
1308 | again. If you have a long-running program you can additionally call this |
1186 | function from time to time. |
1309 | function from time to time. |
1187 | |
1310 | |
1188 | A cookie jar is initially an empty hash-reference that is managed by this |
1311 | A cookie jar is initially an empty hash-reference that is managed by this |
1189 | module. It's format is subject to change, but currently it is like this: |
1312 | module. Its format is subject to change, but currently it is as follows: |
1190 | |
1313 | |
1191 | The key C<version> has to contain C<1>, otherwise the hash gets |
1314 | The key C<version> has to contain C<2>, otherwise the hash gets |
1192 | emptied. All other keys are hostnames or IP addresses pointing to |
1315 | cleared. All other keys are hostnames or IP addresses pointing to |
1193 | hash-references. The key for these inner hash references is the |
1316 | hash-references. The key for these inner hash references is the |
1194 | server path for which this cookie is meant, and the values are again |
1317 | server path for which this cookie is meant, and the values are again |
1195 | hash-references. The keys of those hash-references is the cookie name, and |
1318 | hash-references. Each key of those hash-references is a cookie name, and |
1196 | the value, you guessed it, is another hash-reference, this time with the |
1319 | the value, you guessed it, is another hash-reference, this time with the |
1197 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1320 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1198 | which have been replaced by a C<_expires> key that contains the cookie |
1321 | which have been replaced by a C<_expires> key that contains the cookie |
1199 | expiry timestamp. |
1322 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1323 | C<_expires> key. |
1200 | |
1324 | |
1201 | Here is an example of a cookie jar with a single cookie, so you have a |
1325 | Here is an example of a cookie jar with a single cookie, so you have a |
1202 | chance of understanding the above paragraph: |
1326 | chance of understanding the above paragraph: |
1203 | |
1327 | |
1204 | { |
1328 | { |
1205 | version => 1, |
1329 | version => 2, |
1206 | "10.0.0.1" => { |
1330 | "10.0.0.1" => { |
1207 | "/" => { |
1331 | "/" => { |
1208 | "mythweb_id" => { |
1332 | "mythweb_id" => { |
1209 | _expires => 1293917923, |
1333 | _expires => 1293917923, |
1210 | value => "ooRung9dThee3ooyXooM1Ohm", |
1334 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1228 | |
1352 | |
1229 | The default value for the C<recurse> request parameter (default: C<10>). |
1353 | The default value for the C<recurse> request parameter (default: C<10>). |
1230 | |
1354 | |
1231 | =item $AnyEvent::HTTP::TIMEOUT |
1355 | =item $AnyEvent::HTTP::TIMEOUT |
1232 | |
1356 | |
1233 | The default timeout for conenction operations (default: C<300>). |
1357 | The default timeout for connection operations (default: C<300>). |
1234 | |
1358 | |
1235 | =item $AnyEvent::HTTP::USERAGENT |
1359 | =item $AnyEvent::HTTP::USERAGENT |
1236 | |
1360 | |
1237 | The default value for the C<User-Agent> header (the default is |
1361 | The default value for the C<User-Agent> header (the default is |
1238 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1362 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1239 | |
1363 | |
1240 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1364 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1241 | |
1365 | |
1242 | The maximum number of concurrent connections to the same host (identified |
1366 | The maximum number of concurrent connections to the same host (identified |
1243 | by the hostname). If the limit is exceeded, then the additional requests |
1367 | by the hostname). If the limit is exceeded, then additional requests |
1244 | are queued until previous connections are closed. Both persistent and |
1368 | are queued until previous connections are closed. Both persistent and |
1245 | non-persistent connections are counted in this limit. |
1369 | non-persistent connections are counted in this limit. |
1246 | |
1370 | |
1247 | The default value for this is C<4>, and it is highly advisable to not |
1371 | The default value for this is C<4>, and it is highly advisable to not |
1248 | increase it much. |
1372 | increase it much. |
1249 | |
1373 | |
1250 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1374 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1251 | connections, older browsers used 2, newers (such as firefox 3) typically |
1375 | connections, older browsers used 2, newer ones (such as firefox 3) |
1252 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1376 | typically use 6, and Opera uses 8 because like, they have the fastest |
1253 | give a shit for everybody else on the planet. |
1377 | browser and give a shit for everybody else on the planet. |
1254 | |
1378 | |
1255 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1379 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1256 | |
1380 | |
1257 | The time after which idle persistent conenctions get closed by |
1381 | The time after which idle persistent connections get closed by |
1258 | AnyEvent::HTTP (default: C<3>). |
1382 | AnyEvent::HTTP (default: C<3>). |
1259 | |
1383 | |
1260 | =item $AnyEvent::HTTP::ACTIVE |
1384 | =item $AnyEvent::HTTP::ACTIVE |
1261 | |
1385 | |
1262 | The number of active connections. This is not the number of currently |
1386 | The number of active connections. This is not the number of currently |
… | |
… | |
1303 | # other formats fail in the loop below |
1427 | # other formats fail in the loop below |
1304 | |
1428 | |
1305 | for (0..11) { |
1429 | for (0..11) { |
1306 | if ($m eq $month[$_]) { |
1430 | if ($m eq $month[$_]) { |
1307 | require Time::Local; |
1431 | require Time::Local; |
1308 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1432 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1309 | } |
1433 | } |
1310 | } |
1434 | } |
1311 | |
1435 | |
1312 | undef |
1436 | undef |
1313 | } |
1437 | } |
… | |
… | |
1327 | set_proxy $ENV{http_proxy}; |
1451 | set_proxy $ENV{http_proxy}; |
1328 | }; |
1452 | }; |
1329 | |
1453 | |
1330 | =head2 SHOWCASE |
1454 | =head2 SHOWCASE |
1331 | |
1455 | |
1332 | This section contaisn some more elaborate "real-world" examples or code |
1456 | This section contains some more elaborate "real-world" examples or code |
1333 | snippets. |
1457 | snippets. |
1334 | |
1458 | |
1335 | =head2 HTTP/1.1 FILE DOWNLOAD |
1459 | =head2 HTTP/1.1 FILE DOWNLOAD |
1336 | |
1460 | |
1337 | Downloading files with HTTP can be quite tricky, especially when something |
1461 | Downloading files with HTTP can be quite tricky, especially when something |
… | |
… | |
1341 | last modified time to check for file content changes, and works with many |
1465 | 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 |
1466 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1343 | on older servers. |
1467 | on older servers. |
1344 | |
1468 | |
1345 | It calls the completion callback with either C<undef>, which means a |
1469 | It calls the completion callback with either C<undef>, which means a |
1346 | nonretryable error occured, C<0> when the download was partial and should |
1470 | nonretryable error occurred, C<0> when the download was partial and should |
1347 | be retried, and C<1> if it was successful. |
1471 | be retried, and C<1> if it was successful. |
1348 | |
1472 | |
1349 | use AnyEvent::HTTP; |
1473 | use AnyEvent::HTTP; |
1350 | |
1474 | |
1351 | sub download($$$) { |
1475 | sub download($$$) { |
… | |
… | |
1355 | or die "$file: $!"; |
1479 | or die "$file: $!"; |
1356 | |
1480 | |
1357 | my %hdr; |
1481 | my %hdr; |
1358 | my $ofs = 0; |
1482 | my $ofs = 0; |
1359 | |
1483 | |
1360 | warn stat $fh; |
|
|
1361 | warn -s _; |
|
|
1362 | if (stat $fh and -s _) { |
1484 | if (stat $fh and -s _) { |
1363 | $ofs = -s _; |
1485 | $ofs = -s _; |
1364 | warn "-s is ", $ofs;#d# |
1486 | warn "-s is ", $ofs; |
1365 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1487 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1366 | $hdr{"range"} = "bytes=$ofs-"; |
1488 | $hdr{"range"} = "bytes=$ofs-"; |
1367 | } |
1489 | } |
1368 | |
1490 | |
1369 | http_get $url, |
1491 | http_get $url, |
… | |
… | |
1394 | my (undef, $hdr) = @_; |
1516 | my (undef, $hdr) = @_; |
1395 | |
1517 | |
1396 | my $status = $hdr->{Status}; |
1518 | my $status = $hdr->{Status}; |
1397 | |
1519 | |
1398 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1520 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1399 | utime $fh, $time, $time; |
1521 | utime $time, $time, $fh; |
1400 | } |
1522 | } |
1401 | |
1523 | |
1402 | if ($status == 200 || $status == 206 || $status == 416) { |
1524 | if ($status == 200 || $status == 206 || $status == 416) { |
1403 | # download ok || resume ok || file already fully downloaded |
1525 | # download ok || resume ok || file already fully downloaded |
1404 | $cb->(1, $hdr); |
1526 | $cb->(1, $hdr); |