… | |
… | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Errno (); |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent 4.8 (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
49 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
50 | |
50 | |
51 | use base Exporter::; |
51 | use base Exporter::; |
52 | |
52 | |
53 | our $VERSION = '1.4'; |
53 | our $VERSION = '1.43'; |
54 | |
54 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
56 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
… | |
… | |
138 | |
138 | |
139 | =item headers => hashref |
139 | =item headers => hashref |
140 | |
140 | |
141 | The request headers to use. Currently, C<http_request> may provide its |
141 | The request headers to use. Currently, C<http_request> may provide its |
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
143 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
143 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
|
|
144 | suppressed by using C<undef> for these headers in which case they won't be |
|
|
145 | sent at all). |
144 | |
146 | |
145 | =item timeout => $seconds |
147 | =item timeout => $seconds |
146 | |
148 | |
147 | The time-out to use for various stages - each connect attempt will reset |
149 | The time-out to use for various stages - each connect attempt will reset |
148 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
150 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
151 | timeout. |
|
|
152 | |
|
|
153 | Default timeout is 5 minutes. |
149 | |
154 | |
150 | =item proxy => [$host, $port[, $scheme]] or undef |
155 | =item proxy => [$host, $port[, $scheme]] or undef |
151 | |
156 | |
152 | Use the given http proxy for all requests. If not specified, then the |
157 | Use the given http proxy for all requests. If not specified, then the |
153 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
158 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
154 | |
159 | |
155 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
160 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
156 | HTTPS. |
161 | HTTPS. |
157 | |
162 | |
158 | =item body => $string |
163 | =item body => $string |
159 | |
164 | |
160 | The request body, usually empty. Will be-sent as-is (future versions of |
165 | The request body, usually empty. Will be-sent as-is (future versions of |
… | |
… | |
185 | verification, highest compatibility) and high-security (CA and common-name |
190 | verification, highest compatibility) and high-security (CA and common-name |
186 | verification) TLS context. |
191 | verification) TLS context. |
187 | |
192 | |
188 | The default for this option is C<low>, which could be interpreted as "give |
193 | The default for this option is C<low>, which could be interpreted as "give |
189 | me the page, no matter what". |
194 | me the page, no matter what". |
|
|
195 | |
|
|
196 | =item on_prepare => $callback->($fh) |
|
|
197 | |
|
|
198 | In rare cases you need to "tune" the socket before it is used to |
|
|
199 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
200 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
201 | and behaves exactly the same way (e.g. it has to provide a |
|
|
202 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
203 | C<AnyEvent::Socket::tcp_connect> for details. |
190 | |
204 | |
191 | =item on_header => $callback->($headers) |
205 | =item on_header => $callback->($headers) |
192 | |
206 | |
193 | When specified, this callback will be called with the header hash as soon |
207 | When specified, this callback will be called with the header hash as soon |
194 | as headers have been successfully received from the remote server (not on |
208 | as headers have been successfully received from the remote server (not on |
… | |
… | |
312 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
326 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
313 | |
327 | |
314 | _slot_schedule $_[0]; |
328 | _slot_schedule $_[0]; |
315 | } |
329 | } |
316 | |
330 | |
317 | our $qr_nl = qr<\015?\012>; |
331 | our $qr_nl = qr{\015?\012}; |
318 | our $qr_nlnl = qr<\015?\012\015?\012>; |
332 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
319 | |
333 | |
320 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
334 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
321 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
335 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
322 | |
336 | |
323 | sub http_request($$@) { |
337 | sub http_request($$@) { |
… | |
… | |
401 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
415 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
402 | |
416 | |
403 | if ($proxy) { |
417 | if ($proxy) { |
404 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
418 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
405 | |
419 | |
|
|
420 | $rscheme = "http" unless defined $rscheme; |
|
|
421 | |
406 | # don't support https requests over https-proxy transport, |
422 | # don't support https requests over https-proxy transport, |
407 | # can't be done with tls as spec'ed, unless you double-encrypt. |
423 | # can't be done with tls as spec'ed, unless you double-encrypt. |
408 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
424 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
409 | } else { |
425 | } else { |
410 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
426 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
411 | } |
427 | } |
412 | |
428 | |
413 | $hdr{"user-agent"} ||= $USERAGENT; |
429 | # leave out fragment and query string, just a heuristic |
414 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
430 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
431 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
415 | |
432 | |
416 | $hdr{"content-length"} = length $arg{body}; |
433 | $hdr{"content-length"} = length $arg{body}; |
417 | |
434 | |
418 | my %state = (connect_guard => 1); |
435 | my %state = (connect_guard => 1); |
419 | |
436 | |
… | |
… | |
470 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
487 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
471 | |
488 | |
472 | # send request |
489 | # send request |
473 | $state{handle}->push_write ( |
490 | $state{handle}->push_write ( |
474 | "$method $rpath HTTP/1.0\015\012" |
491 | "$method $rpath HTTP/1.0\015\012" |
475 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
492 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
476 | . "\015\012" |
493 | . "\015\012" |
477 | . (delete $arg{body}) |
494 | . (delete $arg{body}) |
478 | ); |
495 | ); |
479 | |
496 | |
480 | %hdr = (); # reduce memory usage, save a kitten |
497 | %hdr = (); # reduce memory usage, save a kitten |
… | |
… | |
491 | URL => ",$url" |
508 | URL => ",$url" |
492 | ); |
509 | ); |
493 | |
510 | |
494 | # headers, could be optimized a bit |
511 | # headers, could be optimized a bit |
495 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
512 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
496 | for ("$_[1]\012") { |
513 | for ("$_[1]") { |
497 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
514 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
498 | |
515 | |
499 | # things seen, not parsed: |
516 | # things seen, not parsed: |
500 | # p3pP="NON CUR OTPi OUR NOR UNI" |
517 | # p3pP="NON CUR OTPi OUR NOR UNI" |
501 | |
518 | |
… | |
… | |
598 | |
615 | |
599 | redo if /\G\s*,/gc; |
616 | redo if /\G\s*,/gc; |
600 | } |
617 | } |
601 | } |
618 | } |
602 | |
619 | |
603 | if ($redirect) { |
620 | if ($redirect && exists $hdr{location}) { |
604 | # we ignore any errors, as it is very common to receive |
621 | # we ignore any errors, as it is very common to receive |
605 | # Content-Length != 0 but no actual body |
622 | # Content-Length != 0 but no actual body |
606 | # we also access %hdr, as $_[1] might be an erro |
623 | # we also access %hdr, as $_[1] might be an erro |
607 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
624 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
608 | } else { |
625 | } else { |
… | |
… | |
697 | }); |
714 | }); |
698 | } else { |
715 | } else { |
699 | &$handle_actual_request; |
716 | &$handle_actual_request; |
700 | } |
717 | } |
701 | |
718 | |
702 | }, sub { |
719 | }, $arg{on_prepare} || sub { $timeout }; |
703 | $timeout |
|
|
704 | }; |
|
|
705 | }; |
720 | }; |
706 | |
721 | |
707 | defined wantarray && AnyEvent::Util::guard { %state = () } |
722 | defined wantarray && AnyEvent::Util::guard { %state = () } |
708 | } |
723 | } |
709 | |
724 | |
… | |
… | |
743 | The default value for the C<User-Agent> header (the default is |
758 | The default value for the C<User-Agent> header (the default is |
744 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
759 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
745 | |
760 | |
746 | =item $AnyEvent::HTTP::MAX_PER_HOST |
761 | =item $AnyEvent::HTTP::MAX_PER_HOST |
747 | |
762 | |
748 | The maximum number of concurrent conenctions to the same host (identified |
763 | The maximum number of concurrent connections to the same host (identified |
749 | by the hostname). If the limit is exceeded, then the additional requests |
764 | by the hostname). If the limit is exceeded, then the additional requests |
750 | are queued until previous connections are closed. |
765 | are queued until previous connections are closed. |
751 | |
766 | |
752 | The default value for this is C<4>, and it is highly advisable to not |
767 | The default value for this is C<4>, and it is highly advisable to not |
753 | increase it. |
768 | increase it. |