… | |
… | |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
49 | |
49 | |
50 | use base Exporter::; |
50 | use base Exporter::; |
51 | |
51 | |
52 | our $VERSION = '1.46'; |
52 | our $VERSION = '1.5'; |
53 | |
53 | |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | |
55 | |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
… | |
… | |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
95 | object at least alive until the callback get called. If the object gets |
95 | object at least alive until the callback get called. If the object gets |
96 | destroyed before the callback is called, the request will be cancelled. |
96 | destroyed before the callback is called, the request will be cancelled. |
97 | |
97 | |
98 | The callback will be called with the response body data as first argument |
98 | The callback will be called with the response body data as first argument |
99 | (or C<undef> if an error occured), and a hash-ref with response headers as |
99 | (or C<undef> if an error occured), and a hash-ref with response headers |
100 | second argument. |
100 | (and trailers) as second argument. |
101 | |
101 | |
102 | All the headers in that hash are lowercased. In addition to the response |
102 | All the headers in that hash are lowercased. In addition to the response |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
105 | three parts of the HTTP Status-Line of the same name. |
105 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
106 | during the body phase of a request, then the original C<Status> and |
|
|
107 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
108 | C<OrigReason>. |
106 | |
109 | |
107 | The pseudo-header C<URL> contains the actual URL (which can differ from |
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
108 | the requested URL when following redirects - for example, you might get |
111 | the requested URL when following redirects - for example, you might get |
109 | an error that your URL scheme is not supported even though your URL is a |
112 | an error that your URL scheme is not supported even though your URL is a |
110 | valid http URL because it redirected to an ftp URL, in which case you can |
113 | valid http URL because it redirected to an ftp URL, in which case you can |
… | |
… | |
147 | Whether to recurse requests or not, e.g. on redirects, authentication |
150 | Whether to recurse requests or not, e.g. on redirects, authentication |
148 | retries and so on, and how often to do so. |
151 | retries and so on, and how often to do so. |
149 | |
152 | |
150 | =item headers => hashref |
153 | =item headers => hashref |
151 | |
154 | |
152 | The request headers to use. Currently, C<http_request> may provide its |
155 | The request headers to use. Currently, C<http_request> may provide its own |
153 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
156 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
154 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
157 | will provide defaults for C<TE:>, C<Referer:> and C<User-Agent:> (this can |
155 | suppressed by using C<undef> for these headers in which case they won't be |
158 | be suppressed by using C<undef> for these headers in which case they won't |
156 | sent at all). |
159 | be sent at all). |
157 | |
160 | |
158 | =item timeout => $seconds |
161 | =item timeout => $seconds |
159 | |
162 | |
160 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
161 | the timeout, as will read or write activity, i.e. this is not an overall |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
171 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
174 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
172 | HTTPS. |
175 | HTTPS. |
173 | |
176 | |
174 | =item body => $string |
177 | =item body => $string |
175 | |
178 | |
176 | The request body, usually empty. Will be-sent as-is (future versions of |
179 | The request body, usually empty. Will be sent as-is (future versions of |
177 | this module might offer more options). |
180 | this module might offer more options). |
178 | |
181 | |
179 | =item cookie_jar => $hash_ref |
182 | =item cookie_jar => $hash_ref |
180 | |
183 | |
181 | Passing this parameter enables (simplified) cookie-processing, loosely |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
… | |
… | |
237 | |
240 | |
238 | This callback is useful, among other things, to quickly reject unwanted |
241 | This callback is useful, among other things, to quickly reject unwanted |
239 | content, which, if it is supposed to be rare, can be faster than first |
242 | content, which, if it is supposed to be rare, can be faster than first |
240 | doing a C<HEAD> request. |
243 | doing a C<HEAD> request. |
241 | |
244 | |
|
|
245 | The downside is that cancelling the request makes it impossible to re-use |
|
|
246 | the connection. Also, the C<on_header> callback will not receive any |
|
|
247 | trailer (headers sent after the response body). |
|
|
248 | |
242 | Example: cancel the request unless the content-type is "text/html". |
249 | Example: cancel the request unless the content-type is "text/html". |
243 | |
250 | |
244 | on_header => sub { |
251 | on_header => sub { |
245 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
252 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
246 | }, |
253 | }, |
… | |
… | |
252 | string instead of the body data. |
259 | string instead of the body data. |
253 | |
260 | |
254 | It has to return either true (in which case AnyEvent::HTTP will continue), |
261 | It has to return either true (in which case AnyEvent::HTTP will continue), |
255 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
262 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
256 | the completion callback with an error code of C<598>). |
263 | the completion callback with an error code of C<598>). |
|
|
264 | |
|
|
265 | The downside to cancelling the request is that it makes it impossible to |
|
|
266 | re-use the connection. |
257 | |
267 | |
258 | This callback is useful when the data is too large to be held in memory |
268 | This callback is useful when the data is too large to be held in memory |
259 | (so the callback writes it to a file) or when only some information should |
269 | (so the callback writes it to a file) or when only some information should |
260 | be extracted, or when the body should be processed incrementally. |
270 | be extracted, or when the body should be processed incrementally. |
261 | |
271 | |
… | |
… | |
287 | If you think you need this, first have a look at C<on_body>, to see if |
297 | If you think you need this, first have a look at C<on_body>, to see if |
288 | that doesn't solve your problem in a better way. |
298 | that doesn't solve your problem in a better way. |
289 | |
299 | |
290 | =back |
300 | =back |
291 | |
301 | |
292 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
302 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
303 | the response body. |
293 | |
304 | |
294 | http_request GET => "http://www.nethype.de/", sub { |
305 | http_request GET => "http://www.nethype.de/", sub { |
295 | my ($body, $hdr) = @_; |
306 | my ($body, $hdr) = @_; |
296 | print "$body\n"; |
307 | print "$body\n"; |
297 | }; |
308 | }; |
298 | |
309 | |
299 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
310 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
300 | timeout of 30 seconds. |
311 | timeout of 30 seconds. |
301 | |
312 | |
302 | http_request |
313 | http_request |
303 | GET => "https://www.google.com", |
314 | GET => "https://www.google.com", |
304 | timeout => 30, |
315 | timeout => 30, |
… | |
… | |
307 | use Data::Dumper; |
318 | use Data::Dumper; |
308 | print Dumper $hdr; |
319 | print Dumper $hdr; |
309 | } |
320 | } |
310 | ; |
321 | ; |
311 | |
322 | |
312 | Example: make another simple HTTP GET request, but immediately try to |
323 | Example: do another simple HTTP GET request, but immediately try to |
313 | cancel it. |
324 | cancel it. |
314 | |
325 | |
315 | my $request = http_request GET => "http://www.nethype.de/", sub { |
326 | my $request = http_request GET => "http://www.nethype.de/", sub { |
316 | my ($body, $hdr) = @_; |
327 | my ($body, $hdr) = @_; |
317 | print "$body\n"; |
328 | print "$body\n"; |
… | |
… | |
349 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
360 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
350 | |
361 | |
351 | _slot_schedule $_[0]; |
362 | _slot_schedule $_[0]; |
352 | } |
363 | } |
353 | |
364 | |
|
|
365 | # continue to parse $_ for headers and place them into the arg |
|
|
366 | sub parse_hdr() { |
|
|
367 | my %hdr; |
|
|
368 | |
|
|
369 | # things seen, not parsed: |
|
|
370 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
371 | |
|
|
372 | $hdr{lc $1} .= ",$2" |
|
|
373 | while /\G |
|
|
374 | ([^:\000-\037]*): |
|
|
375 | [\011\040]* |
|
|
376 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
377 | \012 |
|
|
378 | /gxc; |
|
|
379 | |
|
|
380 | /\G$/ |
|
|
381 | or return; |
|
|
382 | |
|
|
383 | # remove the "," prefix we added to all headers above |
|
|
384 | substr $_, 0, 1, "" |
|
|
385 | for values %hdr; |
|
|
386 | |
|
|
387 | \%hdr |
|
|
388 | } |
|
|
389 | |
354 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
390 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
355 | |
391 | |
356 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
392 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
357 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
393 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
358 | |
394 | |
… | |
… | |
377 | my @pseudo = (URL => $url); |
413 | my @pseudo = (URL => $url); |
378 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
414 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
379 | |
415 | |
380 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
416 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
381 | |
417 | |
382 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo }) |
418 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
383 | if $recurse < 0; |
419 | if $recurse < 0; |
384 | |
420 | |
385 | my $proxy = $arg{proxy} || $PROXY; |
421 | my $proxy = $arg{proxy} || $PROXY; |
386 | my $timeout = $arg{timeout} || $TIMEOUT; |
422 | my $timeout = $arg{timeout} || $TIMEOUT; |
387 | |
423 | |
… | |
… | |
390 | |
426 | |
391 | $uscheme = lc $uscheme; |
427 | $uscheme = lc $uscheme; |
392 | |
428 | |
393 | my $uport = $uscheme eq "http" ? 80 |
429 | my $uport = $uscheme eq "http" ? 80 |
394 | : $uscheme eq "https" ? 443 |
430 | : $uscheme eq "https" ? 443 |
395 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo }); |
431 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
396 | |
432 | |
397 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
433 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
398 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo }); |
434 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
399 | |
435 | |
400 | my $uhost = $1; |
436 | my $uhost = $1; |
401 | $uport = $2 if defined $2; |
437 | $uport = $2 if defined $2; |
402 | |
438 | |
403 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
439 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
… | |
… | |
452 | } else { |
488 | } else { |
453 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
489 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
454 | } |
490 | } |
455 | |
491 | |
456 | # leave out fragment and query string, just a heuristic |
492 | # leave out fragment and query string, just a heuristic |
457 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
493 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
458 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
494 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
459 | |
495 | |
460 | $hdr{"content-length"} = length $arg{body} |
496 | $hdr{"content-length"} = length $arg{body} |
461 | if length $arg{body} || $method ne "GET"; |
497 | if length $arg{body} || $method ne "GET"; |
462 | |
498 | |
|
|
499 | $hdr{connection} = "close TE"; #1.1 |
|
|
500 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
|
|
501 | |
463 | my %state = (connect_guard => 1); |
502 | my %state = (connect_guard => 1); |
464 | |
503 | |
465 | _get_slot $uhost, sub { |
504 | _get_slot $uhost, sub { |
466 | $state{slot_guard} = shift; |
505 | $state{slot_guard} = shift; |
467 | |
506 | |
468 | return unless $state{connect_guard}; |
507 | return unless $state{connect_guard}; |
469 | |
508 | |
470 | my $tcp_connect = $arg{tcp_connect} |
509 | my $connect_cb = sub { |
471 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
472 | |
|
|
473 | $state{connect_guard} = $tcp_connect->( |
|
|
474 | $rhost, |
|
|
475 | $rport, |
|
|
476 | sub { |
|
|
477 | $state{fh} = shift |
510 | $state{fh} = shift |
478 | or do { |
511 | or do { |
479 | my $err = "$!"; |
512 | my $err = "$!"; |
480 | %state = (); |
513 | %state = (); |
481 | return $cb->(undef, { Status => 599, Reason => $err, @pseudo }); |
514 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
482 | }; |
515 | }; |
483 | |
516 | |
484 | pop; # free memory, save a tree |
517 | pop; # free memory, save a tree |
485 | |
518 | |
486 | return unless delete $state{connect_guard}; |
519 | return unless delete $state{connect_guard}; |
487 | |
520 | |
488 | # get handle |
521 | # get handle |
489 | $state{handle} = new AnyEvent::Handle |
522 | $state{handle} = new AnyEvent::Handle |
490 | fh => $state{fh}, |
523 | fh => $state{fh}, |
491 | peername => $rhost, |
524 | peername => $rhost, |
492 | tls_ctx => $arg{tls_ctx}, |
525 | tls_ctx => $arg{tls_ctx}, |
493 | # these need to be reconfigured on keepalive handles |
526 | # these need to be reconfigured on keepalive handles |
494 | timeout => $timeout, |
527 | timeout => $timeout, |
495 | on_error => sub { |
528 | on_error => sub { |
496 | %state = (); |
529 | %state = (); |
497 | $cb->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
530 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
498 | }, |
531 | }, |
499 | on_eof => sub { |
532 | on_eof => sub { |
500 | %state = (); |
533 | %state = (); |
501 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo }); |
534 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
502 | }, |
535 | }, |
503 | ; |
536 | ; |
504 | |
537 | |
505 | # limit the number of persistent connections |
538 | # limit the number of persistent connections |
506 | # keepalive not yet supported |
539 | # keepalive not yet supported |
507 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
540 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
508 | # ++$KA_COUNT{$_[1]}; |
541 | # ++$KA_COUNT{$_[1]}; |
509 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
542 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
510 | # --$KA_COUNT{$_[1]} |
543 | # --$KA_COUNT{$_[1]} |
511 | # }; |
544 | # }; |
512 | # $hdr{connection} = "keep-alive"; |
545 | # $hdr{connection} = "keep-alive"; |
513 | # } else { |
|
|
514 | delete $hdr{connection}; |
|
|
515 | # } |
546 | # } |
516 | |
547 | |
517 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
548 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
518 | |
549 | |
519 | # handle actual, non-tunneled, request |
550 | # handle actual, non-tunneled, request |
520 | my $handle_actual_request = sub { |
551 | my $handle_actual_request = sub { |
521 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
552 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
522 | |
553 | |
523 | # send request |
554 | # send request |
524 | $state{handle}->push_write ( |
555 | $state{handle}->push_write ( |
525 | "$method $rpath HTTP/1.0\015\012" |
556 | "$method $rpath HTTP/1.1\015\012" |
526 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
557 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
527 | . "\015\012" |
558 | . "\015\012" |
528 | . (delete $arg{body}) |
559 | . (delete $arg{body}) |
529 | ); |
560 | ); |
530 | |
561 | |
531 | # return if error occured during push_write() |
562 | # return if error occured during push_write() |
532 | return unless %state; |
563 | return unless %state; |
533 | |
564 | |
534 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
565 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
535 | |
566 | |
536 | # status line and headers |
567 | # status line and headers |
537 | $state{handle}->push_read (line => $qr_nlnl, sub { |
568 | $state{read_response} = sub { |
538 | for ("$_[1]") { |
569 | for ("$_[1]") { |
539 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
570 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
540 | |
571 | |
541 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
572 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
542 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo })); |
573 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
543 | |
574 | |
|
|
575 | # 100 Continue handling |
|
|
576 | # should not happen as we don't send expect: 100-continue, |
|
|
577 | # but we handle it just in case. |
|
|
578 | # since we send the request body regardless, if we get an error |
|
|
579 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
580 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
581 | if $2 eq 100; |
|
|
582 | |
544 | push @pseudo, |
583 | push @pseudo, |
545 | HTTPVersion => $1, |
584 | HTTPVersion => $1, |
546 | Status => $2, |
585 | Status => $2, |
547 | Reason => $3, |
586 | Reason => $3, |
548 | ; |
587 | ; |
549 | |
588 | |
550 | # things seen, not parsed: |
589 | my $hdr = parse_hdr |
551 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
552 | |
|
|
553 | $hdr{lc $1} .= ",$2" |
|
|
554 | while /\G |
|
|
555 | ([^:\000-\037]*): |
|
|
556 | [\011\040]* |
|
|
557 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
558 | \012 |
|
|
559 | /gxc; |
|
|
560 | |
|
|
561 | /\G$/ |
|
|
562 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo })); |
590 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
591 | |
|
|
592 | %hdr = (%$hdr, @pseudo); |
|
|
593 | } |
|
|
594 | |
|
|
595 | # redirect handling |
|
|
596 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
597 | # try to support some common forms of broken Location headers. |
|
|
598 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
599 | $hdr{location} =~ s/^\.\/+//; |
|
|
600 | |
|
|
601 | my $url = "$rscheme://$uhost:$uport"; |
|
|
602 | |
|
|
603 | unless ($hdr{location} =~ s/^\///) { |
|
|
604 | $url .= $upath; |
|
|
605 | $url =~ s/\/[^\/]*$//; |
563 | } |
606 | } |
564 | |
607 | |
565 | # remove the "," prefix we added to all headers above |
|
|
566 | substr $_, 0, 1, "" |
|
|
567 | for values %hdr; |
|
|
568 | |
|
|
569 | # patch in all pseudo headers |
|
|
570 | %hdr = (%hdr, @pseudo); |
|
|
571 | |
|
|
572 | # redirect handling |
|
|
573 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
574 | # try to support some common forms of broken Location headers. |
|
|
575 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
576 | $hdr{location} =~ s/^\.\/+//; |
|
|
577 | |
|
|
578 | my $url = "$rscheme://$uhost:$uport"; |
|
|
579 | |
|
|
580 | unless ($hdr{location} =~ s/^\///) { |
|
|
581 | $url .= $upath; |
|
|
582 | $url =~ s/\/[^\/]*$//; |
|
|
583 | } |
|
|
584 | |
|
|
585 | $hdr{location} = "$url/$hdr{location}"; |
608 | $hdr{location} = "$url/$hdr{location}"; |
|
|
609 | } |
|
|
610 | |
|
|
611 | my $redirect; |
|
|
612 | |
|
|
613 | if ($recurse) { |
|
|
614 | my $status = $hdr{Status}; |
|
|
615 | |
|
|
616 | # industry standard is to redirect POST as GET for |
|
|
617 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
618 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
619 | # industry standard seems to be to simply follow. |
|
|
620 | # we go with the industry standard. |
|
|
621 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
622 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
623 | $method = "GET" unless $method eq "HEAD"; |
|
|
624 | $redirect = 1; |
|
|
625 | } elsif ($status == 307) { |
|
|
626 | $redirect = 1; |
586 | } |
627 | } |
|
|
628 | } |
587 | |
629 | |
|
|
630 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
588 | my $redirect; |
631 | my $keepalive = pop; |
589 | |
632 | |
|
|
633 | $state{handle}->destroy if $state{handle}; |
|
|
634 | %state = (); |
|
|
635 | |
|
|
636 | if (defined $_[1]) { |
|
|
637 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
638 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
639 | } |
|
|
640 | |
|
|
641 | # set-cookie processing |
590 | if ($recurse) { |
642 | if ($arg{cookie_jar}) { |
591 | my $status = $hdr{Status}; |
643 | for ($hdr{"set-cookie"}) { |
|
|
644 | # parse NAME=VALUE |
|
|
645 | my @kv; |
592 | |
646 | |
593 | # industry standard is to redirect POST as GET for |
647 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
594 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
595 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
596 | # industry standard seems to be to simply follow. |
|
|
597 | # we go with the industry standard. |
|
|
598 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
599 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
600 | $method = "GET" unless $method eq "HEAD"; |
|
|
601 | $redirect = 1; |
648 | my $name = $1; |
602 | } elsif ($status == 307) { |
649 | my $value = $3; |
|
|
650 | |
|
|
651 | unless ($value) { |
|
|
652 | $value = $2; |
|
|
653 | $value =~ s/\\(.)/$1/gs; |
|
|
654 | } |
|
|
655 | |
|
|
656 | push @kv, $name => $value; |
|
|
657 | |
|
|
658 | last unless /\G\s*;/gc; |
|
|
659 | } |
|
|
660 | |
|
|
661 | last unless @kv; |
|
|
662 | |
|
|
663 | my $name = shift @kv; |
|
|
664 | my %kv = (value => shift @kv, @kv); |
|
|
665 | |
|
|
666 | my $cdom; |
|
|
667 | my $cpath = (delete $kv{path}) || "/"; |
|
|
668 | |
|
|
669 | if (exists $kv{domain}) { |
|
|
670 | $cdom = delete $kv{domain}; |
|
|
671 | |
|
|
672 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
673 | |
|
|
674 | next if $cdom =~ /\.$/; |
|
|
675 | |
|
|
676 | # this is not rfc-like and not netscape-like. go figure. |
|
|
677 | my $ndots = $cdom =~ y/.//; |
|
|
678 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
679 | } else { |
|
|
680 | $cdom = $uhost; |
|
|
681 | } |
|
|
682 | |
603 | $redirect = 1; |
683 | # store it |
|
|
684 | $arg{cookie_jar}{version} = 1; |
|
|
685 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
686 | |
|
|
687 | redo if /\G\s*,/gc; |
604 | } |
688 | } |
605 | } |
689 | } |
606 | |
690 | |
607 | my $finish = sub { |
|
|
608 | $state{handle}->destroy if $state{handle}; |
|
|
609 | %state = (); |
|
|
610 | |
|
|
611 | # set-cookie processing |
|
|
612 | if ($arg{cookie_jar}) { |
|
|
613 | for ($_[1]{"set-cookie"}) { |
|
|
614 | # parse NAME=VALUE |
|
|
615 | my @kv; |
|
|
616 | |
|
|
617 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
618 | my $name = $1; |
|
|
619 | my $value = $3; |
|
|
620 | |
|
|
621 | unless ($value) { |
|
|
622 | $value = $2; |
|
|
623 | $value =~ s/\\(.)/$1/gs; |
|
|
624 | } |
|
|
625 | |
|
|
626 | push @kv, $name => $value; |
|
|
627 | |
|
|
628 | last unless /\G\s*;/gc; |
|
|
629 | } |
|
|
630 | |
|
|
631 | last unless @kv; |
|
|
632 | |
|
|
633 | my $name = shift @kv; |
|
|
634 | my %kv = (value => shift @kv, @kv); |
|
|
635 | |
|
|
636 | my $cdom; |
|
|
637 | my $cpath = (delete $kv{path}) || "/"; |
|
|
638 | |
|
|
639 | if (exists $kv{domain}) { |
|
|
640 | $cdom = delete $kv{domain}; |
|
|
641 | |
|
|
642 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
643 | |
|
|
644 | next if $cdom =~ /\.$/; |
|
|
645 | |
|
|
646 | # this is not rfc-like and not netscape-like. go figure. |
|
|
647 | my $ndots = $cdom =~ y/.//; |
|
|
648 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
649 | } else { |
|
|
650 | $cdom = $uhost; |
|
|
651 | } |
|
|
652 | |
|
|
653 | # store it |
|
|
654 | $arg{cookie_jar}{version} = 1; |
|
|
655 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
656 | |
|
|
657 | redo if /\G\s*,/gc; |
|
|
658 | } |
|
|
659 | } |
|
|
660 | |
|
|
661 | if ($redirect && exists $hdr{location}) { |
691 | if ($redirect && exists $hdr{location}) { |
662 | # we ignore any errors, as it is very common to receive |
692 | # we ignore any errors, as it is very common to receive |
663 | # Content-Length != 0 but no actual body |
693 | # Content-Length != 0 but no actual body |
664 | # we also access %hdr, as $_[1] might be an erro |
694 | # we also access %hdr, as $_[1] might be an erro |
665 | http_request ( |
695 | http_request ( |
666 | $method => $hdr{location}, |
696 | $method => $hdr{location}, |
667 | %arg, |
697 | %arg, |
668 | recurse => $recurse - 1, |
698 | recurse => $recurse - 1, |
669 | Redirect => \@_, |
699 | Redirect => [$_[0], \%hdr], |
670 | $cb); |
700 | $cb); |
671 | } else { |
|
|
672 | $cb->($_[0], $_[1]); |
|
|
673 | } |
|
|
674 | }; |
|
|
675 | |
|
|
676 | my $len = $hdr{"content-length"}; |
|
|
677 | |
|
|
678 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
679 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo }); |
|
|
680 | } elsif ( |
|
|
681 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
682 | or $method eq "HEAD" |
|
|
683 | or (defined $len && !$len) |
|
|
684 | ) { |
|
|
685 | # no body |
|
|
686 | $finish->("", \%hdr); |
|
|
687 | } else { |
701 | } else { |
|
|
702 | $cb->($_[0], \%hdr); |
|
|
703 | } |
|
|
704 | }; |
|
|
705 | |
|
|
706 | my $len = $hdr{"content-length"}; |
|
|
707 | |
|
|
708 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
709 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
710 | } elsif ( |
|
|
711 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
712 | or $method eq "HEAD" |
|
|
713 | or (defined $len && !$len) |
|
|
714 | ) { |
|
|
715 | # no body |
|
|
716 | $finish->("", undef, undef, 1); |
|
|
717 | } else { |
688 | # body handling, four different code paths |
718 | # body handling, many different code paths |
689 | # for want_body_handle, on_body (2x), normal (2x) |
719 | # - no body expected |
690 | # we might read too much here, but it does not matter yet (no pers. connections) |
720 | # - want_body_handle |
|
|
721 | # - te chunked |
|
|
722 | # - 2x length known (with or without on_body) |
|
|
723 | # - 2x length not known (with or without on_body) |
691 | if (!$redirect && $arg{want_body_handle}) { |
724 | if (!$redirect && $arg{want_body_handle}) { |
692 | $_[0]->on_eof (undef); |
725 | $_[0]->on_eof (undef); |
693 | $_[0]->on_error (undef); |
726 | $_[0]->on_error (undef); |
694 | $_[0]->on_read (undef); |
727 | $_[0]->on_read (undef); |
695 | |
728 | |
696 | $finish->(delete $state{handle}, \%hdr); |
729 | $finish->(delete $state{handle}); |
697 | |
730 | |
698 | } elsif ($arg{on_body}) { |
731 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
732 | my $cl = 0; |
|
|
733 | my $body = undef; |
|
|
734 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
735 | |
699 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
736 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
737 | |
|
|
738 | my $read_chunk; $read_chunk = sub { |
|
|
739 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
740 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
741 | |
|
|
742 | my $len = hex $1; |
|
|
743 | |
700 | if ($len) { |
744 | if ($len) { |
701 | $_[0]->on_eof (undef); |
745 | $cl += $len; |
|
|
746 | |
|
|
747 | $_[0]->push_read (chunk => $len, sub { |
|
|
748 | $on_body->($_[1], \%hdr) |
|
|
749 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
750 | |
702 | $_[0]->on_read (sub { |
751 | $_[0]->push_read (line => sub { |
703 | $len -= length $_[0]{rbuf}; |
752 | length $_[1] |
704 | |
753 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
705 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
754 | $_[0]->push_read (line => $read_chunk); |
706 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
707 | |
|
|
708 | $len > 0 |
755 | }); |
709 | or $finish->("", \%hdr); |
|
|
710 | }); |
756 | }); |
711 | } else { |
757 | } else { |
712 | $_[0]->on_eof (sub { |
758 | $hdr{"content-length"} ||= $cl; |
713 | $finish->("", \%hdr); |
759 | |
|
|
760 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
761 | if (length $_[1]) { |
|
|
762 | for ("$_[1]") { |
|
|
763 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
764 | |
|
|
765 | my $hdr = parse_hdr |
|
|
766 | or return $finish->(undef, 599 => "Garbled response trailers"); |
|
|
767 | |
|
|
768 | %hdr = (%hdr, %$hdr); |
|
|
769 | } |
714 | }); |
770 | } |
715 | $_[0]->on_read (sub { |
771 | |
716 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
772 | $finish->($body, undef, undef, 1); |
717 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
718 | }); |
773 | }); |
719 | } |
774 | } |
|
|
775 | }; |
|
|
776 | |
|
|
777 | $_[0]->push_read (line => $read_chunk); |
|
|
778 | |
|
|
779 | } elsif ($arg{on_body}) { |
|
|
780 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
781 | |
|
|
782 | if ($len) { |
|
|
783 | $_[0]->on_read (sub { |
|
|
784 | $len -= length $_[0]{rbuf}; |
|
|
785 | |
|
|
786 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
787 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
788 | |
|
|
789 | $len > 0 |
|
|
790 | or $finish->("", undef, undef, 1); |
|
|
791 | }); |
720 | } else { |
792 | } else { |
721 | $_[0]->on_eof (undef); |
793 | $_[0]->on_eof (sub { |
722 | |
794 | $finish->(""); |
723 | if ($len) { |
795 | }); |
724 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
|
|
725 | $_[0]->on_read (sub { |
796 | $_[0]->on_read (sub { |
|
|
797 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
798 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
799 | }); |
|
|
800 | } |
|
|
801 | } else { |
|
|
802 | $_[0]->on_eof (undef); |
|
|
803 | |
|
|
804 | if ($len) { |
|
|
805 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
806 | $_[0]->on_read (sub { |
726 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
807 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
727 | if $len <= length $_[0]{rbuf}; |
808 | if $len <= length $_[0]{rbuf}; |
728 | }); |
809 | }); |
729 | } else { |
810 | } else { |
730 | $_[0]->on_error (sub { |
811 | $_[0]->on_error (sub { |
731 | ($! == Errno::EPIPE || !$!) |
812 | ($! == Errno::EPIPE || !$!) |
732 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
813 | ? $finish->(delete $_[0]{rbuf}) |
733 | : $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
814 | : $finish->(undef, 599 => $_[2]); |
734 | }); |
815 | }); |
735 | $_[0]->on_read (sub { }); |
816 | $_[0]->on_read (sub { }); |
736 | } |
|
|
737 | } |
817 | } |
738 | } |
818 | } |
739 | }); |
819 | } |
740 | }; |
820 | }; |
741 | |
821 | |
|
|
822 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
823 | }; |
|
|
824 | |
742 | # now handle proxy-CONNECT method |
825 | # now handle proxy-CONNECT method |
743 | if ($proxy && $uscheme eq "https") { |
826 | if ($proxy && $uscheme eq "https") { |
744 | # oh dear, we have to wrap it into a connect request |
827 | # oh dear, we have to wrap it into a connect request |
745 | |
828 | |
746 | # maybe re-use $uauthority with patched port? |
829 | # maybe re-use $uauthority with patched port? |
747 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
830 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
748 | $state{handle}->push_read (line => $qr_nlnl, sub { |
831 | $state{handle}->push_read (line => $qr_nlnl, sub { |
749 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
832 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
750 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo })); |
833 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
751 | |
834 | |
752 | if ($2 == 200) { |
835 | if ($2 == 200) { |
753 | $rpath = $upath; |
836 | $rpath = $upath; |
754 | &$handle_actual_request; |
837 | &$handle_actual_request; |
755 | } else { |
838 | } else { |
756 | %state = (); |
839 | %state = (); |
757 | $cb->(undef, { Status => $2, Reason => $3, @pseudo }); |
840 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
758 | } |
|
|
759 | }); |
841 | } |
|
|
842 | }); |
760 | } else { |
843 | } else { |
761 | &$handle_actual_request; |
844 | &$handle_actual_request; |
762 | } |
|
|
763 | |
|
|
764 | }, |
845 | } |
765 | $arg{on_prepare} || sub { $timeout } |
|
|
766 | ); |
846 | }; |
|
|
847 | |
|
|
848 | my $tcp_connect = $arg{tcp_connect} |
|
|
849 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
850 | |
|
|
851 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
852 | |
767 | }; |
853 | }; |
768 | |
854 | |
769 | defined wantarray && AnyEvent::Util::guard { %state = () } |
855 | defined wantarray && AnyEvent::Util::guard { %state = () } |
770 | } |
856 | } |
771 | |
857 | |