… | |
… | |
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. If an error occurs |
105 | three parts of the HTTP Status-Line of the same name. If an error occurs |
… | |
… | |
150 | Whether to recurse requests or not, e.g. on redirects, authentication |
150 | Whether to recurse requests or not, e.g. on redirects, authentication |
151 | retries and so on, and how often to do so. |
151 | retries and so on, and how often to do so. |
152 | |
152 | |
153 | =item headers => hashref |
153 | =item headers => hashref |
154 | |
154 | |
155 | 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 |
156 | 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 |
157 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
157 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
158 | suppressed by using C<undef> for these headers in which case they won't be |
158 | (this can be suppressed by using C<undef> for these headers in which case |
159 | sent at all). |
159 | they won't be sent at all). |
160 | |
160 | |
161 | =item timeout => $seconds |
161 | =item timeout => $seconds |
162 | |
162 | |
163 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
174 | C<$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 |
175 | HTTPS. |
175 | HTTPS. |
176 | |
176 | |
177 | =item body => $string |
177 | =item body => $string |
178 | |
178 | |
179 | 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 |
180 | this module might offer more options). |
180 | this module might offer more options). |
181 | |
181 | |
182 | =item cookie_jar => $hash_ref |
182 | =item cookie_jar => $hash_ref |
183 | |
183 | |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
185 | based on the original netscape specification. |
185 | based on the original netscape specification. |
186 | |
186 | |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
188 | get updated automatically. It is possible to save the cookie_jar to |
188 | get updated automatically. It is possible to save the cookie jar to |
189 | persistent storage with something like JSON or Storable, but this is not |
189 | persistent storage with something like JSON or Storable, but this is not |
190 | recommended, as expiry times are currently being ignored. |
190 | recommended, as session-only cookies might survive longer than expected. |
191 | |
191 | |
192 | Note that this cookie implementation is not of very high quality, nor |
192 | Note that this cookie implementation is not meant to be complete. If |
193 | meant to be complete. If you want complete cookie management you have to |
193 | you want complete cookie management you have to do that on your |
194 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
194 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
195 | cookie-using sites working. Cookies are a privacy disaster, do not use |
195 | working. Cookies are a privacy disaster, do not use them unless required |
196 | them unless required to. |
196 | to. |
|
|
197 | |
|
|
198 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
199 | headers will be set and handled by this module, otherwise they will be |
|
|
200 | left untouched. |
197 | |
201 | |
198 | =item tls_ctx => $scheme | $tls_ctx |
202 | =item tls_ctx => $scheme | $tls_ctx |
199 | |
203 | |
200 | Specifies the AnyEvent::TLS context to be used for https connections. This |
204 | Specifies the AnyEvent::TLS context to be used for https connections. This |
201 | parameter follows the same rules as the C<tls_ctx> parameter to |
205 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
240 | |
244 | |
241 | This callback is useful, among other things, to quickly reject unwanted |
245 | This callback is useful, among other things, to quickly reject unwanted |
242 | content, which, if it is supposed to be rare, can be faster than first |
246 | content, which, if it is supposed to be rare, can be faster than first |
243 | doing a C<HEAD> request. |
247 | doing a C<HEAD> request. |
244 | |
248 | |
|
|
249 | The downside is that cancelling the request makes it impossible to re-use |
|
|
250 | the connection. Also, the C<on_header> callback will not receive any |
|
|
251 | trailer (headers sent after the response body). |
|
|
252 | |
245 | Example: cancel the request unless the content-type is "text/html". |
253 | Example: cancel the request unless the content-type is "text/html". |
246 | |
254 | |
247 | on_header => sub { |
255 | on_header => sub { |
248 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
256 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
249 | }, |
257 | }, |
… | |
… | |
255 | string instead of the body data. |
263 | string instead of the body data. |
256 | |
264 | |
257 | It has to return either true (in which case AnyEvent::HTTP will continue), |
265 | It has to return either true (in which case AnyEvent::HTTP will continue), |
258 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
266 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
259 | the completion callback with an error code of C<598>). |
267 | the completion callback with an error code of C<598>). |
|
|
268 | |
|
|
269 | The downside to cancelling the request is that it makes it impossible to |
|
|
270 | re-use the connection. |
260 | |
271 | |
261 | This callback is useful when the data is too large to be held in memory |
272 | This callback is useful when the data is too large to be held in memory |
262 | (so the callback writes it to a file) or when only some information should |
273 | (so the callback writes it to a file) or when only some information should |
263 | be extracted, or when the body should be processed incrementally. |
274 | be extracted, or when the body should be processed incrementally. |
264 | |
275 | |
… | |
… | |
290 | If you think you need this, first have a look at C<on_body>, to see if |
301 | If you think you need this, first have a look at C<on_body>, to see if |
291 | that doesn't solve your problem in a better way. |
302 | that doesn't solve your problem in a better way. |
292 | |
303 | |
293 | =back |
304 | =back |
294 | |
305 | |
295 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
306 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
307 | the response body. |
296 | |
308 | |
297 | http_request GET => "http://www.nethype.de/", sub { |
309 | http_request GET => "http://www.nethype.de/", sub { |
298 | my ($body, $hdr) = @_; |
310 | my ($body, $hdr) = @_; |
299 | print "$body\n"; |
311 | print "$body\n"; |
300 | }; |
312 | }; |
301 | |
313 | |
302 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
314 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
303 | timeout of 30 seconds. |
315 | timeout of 30 seconds. |
304 | |
316 | |
305 | http_request |
317 | http_request |
306 | GET => "https://www.google.com", |
318 | GET => "https://www.google.com", |
307 | timeout => 30, |
319 | timeout => 30, |
… | |
… | |
310 | use Data::Dumper; |
322 | use Data::Dumper; |
311 | print Dumper $hdr; |
323 | print Dumper $hdr; |
312 | } |
324 | } |
313 | ; |
325 | ; |
314 | |
326 | |
315 | Example: make another simple HTTP GET request, but immediately try to |
327 | Example: do another simple HTTP GET request, but immediately try to |
316 | cancel it. |
328 | cancel it. |
317 | |
329 | |
318 | my $request = http_request GET => "http://www.nethype.de/", sub { |
330 | my $request = http_request GET => "http://www.nethype.de/", sub { |
319 | my ($body, $hdr) = @_; |
331 | my ($body, $hdr) = @_; |
320 | print "$body\n"; |
332 | print "$body\n"; |
… | |
… | |
352 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
364 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
353 | |
365 | |
354 | _slot_schedule $_[0]; |
366 | _slot_schedule $_[0]; |
355 | } |
367 | } |
356 | |
368 | |
|
|
369 | # extract cookies from jar |
|
|
370 | sub cookie_jar_extract($$$$) { |
|
|
371 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
372 | |
|
|
373 | %$jar = () if $jar->{version} != 1; |
|
|
374 | |
|
|
375 | my @cookies; |
|
|
376 | |
|
|
377 | while (my ($chost, $paths) = each %$jar) { |
|
|
378 | next unless ref $paths; |
|
|
379 | |
|
|
380 | if ($chost =~ /^\./) { |
|
|
381 | next unless $chost eq substr $uhost, -length $chost; |
|
|
382 | } elsif ($chost =~ /\./) { |
|
|
383 | next unless $chost eq $uhost; |
|
|
384 | } else { |
|
|
385 | next; |
|
|
386 | } |
|
|
387 | |
|
|
388 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
389 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
390 | |
|
|
391 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
392 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
393 | |
|
|
394 | if (exists $kv->{expires}) { |
|
|
395 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
396 | delete $cookies->{$cookie}; |
|
|
397 | next; |
|
|
398 | } |
|
|
399 | } |
|
|
400 | |
|
|
401 | my $value = $kv->{value}; |
|
|
402 | |
|
|
403 | if ($value =~ /[=;,[:space:]]/) { |
|
|
404 | $value =~ s/([\\"])/\\$1/g; |
|
|
405 | $value = "\"$value\""; |
|
|
406 | } |
|
|
407 | |
|
|
408 | push @cookies, "$cookie=$value"; |
|
|
409 | } |
|
|
410 | } |
|
|
411 | } |
|
|
412 | |
|
|
413 | \@cookies |
|
|
414 | } |
|
|
415 | |
|
|
416 | # parse set_cookie header into jar |
|
|
417 | sub cookie_jar_set_cookie($$$) { |
|
|
418 | my ($jar, $set_cookie, $uhost) = @_; |
|
|
419 | |
|
|
420 | for ($set_cookie) { |
|
|
421 | # parse NAME=VALUE |
|
|
422 | my @kv; |
|
|
423 | |
|
|
424 | while ( |
|
|
425 | m{ |
|
|
426 | \G\s* |
|
|
427 | (?: |
|
|
428 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
|
|
429 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
|
|
430 | ) |
|
|
431 | }gcxsi |
|
|
432 | ) { |
|
|
433 | my $name = $2; |
|
|
434 | my $value = $4; |
|
|
435 | |
|
|
436 | unless (defined $name) { |
|
|
437 | # expires |
|
|
438 | $name = "expires"; |
|
|
439 | $value = $1; |
|
|
440 | } elsif (!defined $value) { |
|
|
441 | # quoted |
|
|
442 | $value = $3; |
|
|
443 | $value =~ s/\\(.)/$1/gs; |
|
|
444 | } |
|
|
445 | |
|
|
446 | push @kv, lc $name, $value; |
|
|
447 | |
|
|
448 | last unless /\G\s*;/gc; |
|
|
449 | } |
|
|
450 | |
|
|
451 | last unless @kv; |
|
|
452 | |
|
|
453 | my $name = shift @kv; |
|
|
454 | my %kv = (value => shift @kv, @kv); |
|
|
455 | |
|
|
456 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
457 | if exists $kv{"max-age"}; |
|
|
458 | |
|
|
459 | my $cdom; |
|
|
460 | my $cpath = (delete $kv{path}) || "/"; |
|
|
461 | |
|
|
462 | if (exists $kv{domain}) { |
|
|
463 | $cdom = delete $kv{domain}; |
|
|
464 | |
|
|
465 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
466 | |
|
|
467 | next if $cdom =~ /\.$/; |
|
|
468 | |
|
|
469 | # this is not rfc-like and not netscape-like. go figure. |
|
|
470 | my $ndots = $cdom =~ y/.//; |
|
|
471 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
472 | } else { |
|
|
473 | $cdom = $uhost; |
|
|
474 | } |
|
|
475 | |
|
|
476 | # store it |
|
|
477 | $jar->{version} = 1; |
|
|
478 | $jar->{$cdom}{$cpath}{$name} = \%kv; |
|
|
479 | |
|
|
480 | redo if /\G\s*,/gc; |
|
|
481 | } |
|
|
482 | } |
|
|
483 | |
|
|
484 | # continue to parse $_ for headers and place them into the arg |
|
|
485 | sub parse_hdr() { |
|
|
486 | my %hdr; |
|
|
487 | |
|
|
488 | # things seen, not parsed: |
|
|
489 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
490 | |
|
|
491 | $hdr{lc $1} .= ",$2" |
|
|
492 | while /\G |
|
|
493 | ([^:\000-\037]*): |
|
|
494 | [\011\040]* |
|
|
495 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
496 | \012 |
|
|
497 | /gxc; |
|
|
498 | |
|
|
499 | /\G$/ |
|
|
500 | or return; |
|
|
501 | |
|
|
502 | # remove the "," prefix we added to all headers above |
|
|
503 | substr $_, 0, 1, "" |
|
|
504 | for values %hdr; |
|
|
505 | |
|
|
506 | \%hdr |
|
|
507 | } |
|
|
508 | |
357 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
509 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
358 | |
510 | |
359 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
511 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
360 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
512 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
361 | |
513 | |
… | |
… | |
411 | |
563 | |
412 | $upath =~ s%^/?%/%; |
564 | $upath =~ s%^/?%/%; |
413 | |
565 | |
414 | # cookie processing |
566 | # cookie processing |
415 | if (my $jar = $arg{cookie_jar}) { |
567 | if (my $jar = $arg{cookie_jar}) { |
416 | %$jar = () if $jar->{version} != 1; |
568 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
417 | |
569 | |
418 | my @cookie; |
|
|
419 | |
|
|
420 | while (my ($chost, $v) = each %$jar) { |
|
|
421 | if ($chost =~ /^\./) { |
|
|
422 | next unless $chost eq substr $uhost, -length $chost; |
|
|
423 | } elsif ($chost =~ /\./) { |
|
|
424 | next unless $chost eq $uhost; |
|
|
425 | } else { |
|
|
426 | next; |
|
|
427 | } |
|
|
428 | |
|
|
429 | while (my ($cpath, $v) = each %$v) { |
|
|
430 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
431 | |
|
|
432 | while (my ($k, $v) = each %$v) { |
|
|
433 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
434 | my $value = $v->{value}; |
|
|
435 | $value =~ s/([\\"])/\\$1/g; |
|
|
436 | push @cookie, "$k=\"$value\""; |
|
|
437 | } |
|
|
438 | } |
|
|
439 | } |
|
|
440 | |
|
|
441 | $hdr{cookie} = join "; ", @cookie |
570 | $hdr{cookie} = join "; ", @$cookies |
442 | if @cookie; |
571 | if @$cookies; |
443 | } |
572 | } |
444 | |
573 | |
445 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
574 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
446 | |
575 | |
447 | if ($proxy) { |
576 | if ($proxy) { |
… | |
… | |
455 | } else { |
584 | } else { |
456 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
585 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
457 | } |
586 | } |
458 | |
587 | |
459 | # leave out fragment and query string, just a heuristic |
588 | # leave out fragment and query string, just a heuristic |
460 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
589 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
461 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
590 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
462 | |
591 | |
463 | $hdr{"content-length"} = length $arg{body} |
592 | $hdr{"content-length"} = length $arg{body} |
464 | if length $arg{body} || $method ne "GET"; |
593 | if length $arg{body} || $method ne "GET"; |
|
|
594 | |
|
|
595 | $hdr{connection} = "close TE"; #1.1 |
|
|
596 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
465 | |
597 | |
466 | my %state = (connect_guard => 1); |
598 | my %state = (connect_guard => 1); |
467 | |
599 | |
468 | _get_slot $uhost, sub { |
600 | _get_slot $uhost, sub { |
469 | $state{slot_guard} = shift; |
601 | $state{slot_guard} = shift; |
… | |
… | |
505 | # ++$KA_COUNT{$_[1]}; |
637 | # ++$KA_COUNT{$_[1]}; |
506 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
638 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
507 | # --$KA_COUNT{$_[1]} |
639 | # --$KA_COUNT{$_[1]} |
508 | # }; |
640 | # }; |
509 | # $hdr{connection} = "keep-alive"; |
641 | # $hdr{connection} = "keep-alive"; |
510 | # } else { |
|
|
511 | delete $hdr{connection}; |
|
|
512 | # } |
642 | # } |
513 | |
643 | |
514 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
644 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
515 | |
645 | |
516 | # handle actual, non-tunneled, request |
646 | # handle actual, non-tunneled, request |
517 | my $handle_actual_request = sub { |
647 | my $handle_actual_request = sub { |
518 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
648 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
519 | |
649 | |
520 | # send request |
650 | # send request |
521 | $state{handle}->push_write ( |
651 | $state{handle}->push_write ( |
522 | "$method $rpath HTTP/1.0\015\012" |
652 | "$method $rpath HTTP/1.1\015\012" |
523 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
653 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
524 | . "\015\012" |
654 | . "\015\012" |
525 | . (delete $arg{body}) |
655 | . (delete $arg{body}) |
526 | ); |
656 | ); |
527 | |
657 | |
… | |
… | |
529 | return unless %state; |
659 | return unless %state; |
530 | |
660 | |
531 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
661 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
532 | |
662 | |
533 | # status line and headers |
663 | # status line and headers |
534 | $state{handle}->push_read (line => $qr_nlnl, sub { |
664 | $state{read_response} = sub { |
535 | my $keepalive = pop; |
|
|
536 | |
|
|
537 | for ("$_[1]") { |
665 | for ("$_[1]") { |
538 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
666 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
539 | |
667 | |
540 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
668 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
541 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
669 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
670 | |
|
|
671 | # 100 Continue handling |
|
|
672 | # should not happen as we don't send expect: 100-continue, |
|
|
673 | # but we handle it just in case. |
|
|
674 | # since we send the request body regardless, if we get an error |
|
|
675 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
676 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
677 | if $2 eq 100; |
542 | |
678 | |
543 | push @pseudo, |
679 | push @pseudo, |
544 | HTTPVersion => $1, |
680 | HTTPVersion => $1, |
545 | Status => $2, |
681 | Status => $2, |
546 | Reason => $3, |
682 | Reason => $3, |
547 | ; |
683 | ; |
548 | |
684 | |
549 | # things seen, not parsed: |
685 | my $hdr = parse_hdr |
550 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
551 | |
|
|
552 | $hdr{lc $1} .= ",$2" |
|
|
553 | while /\G |
|
|
554 | ([^:\000-\037]*): |
|
|
555 | [\011\040]* |
|
|
556 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
557 | \012 |
|
|
558 | /gxc; |
|
|
559 | |
|
|
560 | /\G$/ |
|
|
561 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
686 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
687 | |
|
|
688 | %hdr = (%$hdr, @pseudo); |
562 | } |
689 | } |
563 | |
|
|
564 | # remove the "," prefix we added to all headers above |
|
|
565 | substr $_, 0, 1, "" |
|
|
566 | for values %hdr; |
|
|
567 | |
|
|
568 | # patch in all pseudo headers |
|
|
569 | %hdr = (%hdr, @pseudo); |
|
|
570 | |
690 | |
571 | # redirect handling |
691 | # redirect handling |
572 | # microsoft and other shitheads don't give a shit for following standards, |
692 | # microsoft and other shitheads don't give a shit for following standards, |
573 | # try to support some common forms of broken Location headers. |
693 | # try to support some common forms of broken Location headers. |
574 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
694 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
… | |
… | |
602 | $redirect = 1; |
722 | $redirect = 1; |
603 | } |
723 | } |
604 | } |
724 | } |
605 | |
725 | |
606 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
726 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
727 | my $may_keep_alive = $_[3]; |
|
|
728 | |
607 | $state{handle}->destroy if $state{handle}; |
729 | $state{handle}->destroy if $state{handle}; |
608 | %state = (); |
730 | %state = (); |
609 | |
731 | |
610 | if (defined $_[1]) { |
732 | if (defined $_[1]) { |
611 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
733 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
612 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
734 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
613 | } |
735 | } |
614 | |
736 | |
615 | # set-cookie processing |
737 | # set-cookie processing |
616 | if ($arg{cookie_jar}) { |
738 | if ($arg{cookie_jar}) { |
617 | for ($hdr{"set-cookie"}) { |
739 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost; |
618 | # parse NAME=VALUE |
|
|
619 | my @kv; |
|
|
620 | |
|
|
621 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
622 | my $name = $1; |
|
|
623 | my $value = $3; |
|
|
624 | |
|
|
625 | unless ($value) { |
|
|
626 | $value = $2; |
|
|
627 | $value =~ s/\\(.)/$1/gs; |
|
|
628 | } |
|
|
629 | |
|
|
630 | push @kv, $name => $value; |
|
|
631 | |
|
|
632 | last unless /\G\s*;/gc; |
|
|
633 | } |
|
|
634 | |
|
|
635 | last unless @kv; |
|
|
636 | |
|
|
637 | my $name = shift @kv; |
|
|
638 | my %kv = (value => shift @kv, @kv); |
|
|
639 | |
|
|
640 | my $cdom; |
|
|
641 | my $cpath = (delete $kv{path}) || "/"; |
|
|
642 | |
|
|
643 | if (exists $kv{domain}) { |
|
|
644 | $cdom = delete $kv{domain}; |
|
|
645 | |
|
|
646 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
647 | |
|
|
648 | next if $cdom =~ /\.$/; |
|
|
649 | |
|
|
650 | # this is not rfc-like and not netscape-like. go figure. |
|
|
651 | my $ndots = $cdom =~ y/.//; |
|
|
652 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
653 | } else { |
|
|
654 | $cdom = $uhost; |
|
|
655 | } |
|
|
656 | |
|
|
657 | # store it |
|
|
658 | $arg{cookie_jar}{version} = 1; |
|
|
659 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
660 | |
|
|
661 | redo if /\G\s*,/gc; |
|
|
662 | } |
|
|
663 | } |
740 | } |
664 | |
741 | |
665 | if ($redirect && exists $hdr{location}) { |
742 | if ($redirect && exists $hdr{location}) { |
666 | # we ignore any errors, as it is very common to receive |
743 | # we ignore any errors, as it is very common to receive |
667 | # Content-Length != 0 but no actual body |
744 | # Content-Length != 0 but no actual body |
… | |
… | |
687 | or (defined $len && !$len) |
764 | or (defined $len && !$len) |
688 | ) { |
765 | ) { |
689 | # no body |
766 | # no body |
690 | $finish->("", undef, undef, 1); |
767 | $finish->("", undef, undef, 1); |
691 | } else { |
768 | } else { |
692 | # body handling, four different code paths |
769 | # body handling, many different code paths |
693 | # for want_body_handle, on_body (2x), normal (2x) |
770 | # - no body expected |
694 | # we might read too much here, but it does not matter yet (no pipelining) |
771 | # - want_body_handle |
|
|
772 | # - te chunked |
|
|
773 | # - 2x length known (with or without on_body) |
|
|
774 | # - 2x length not known (with or without on_body) |
695 | if (!$redirect && $arg{want_body_handle}) { |
775 | if (!$redirect && $arg{want_body_handle}) { |
696 | $_[0]->on_eof (undef); |
776 | $_[0]->on_eof (undef); |
697 | $_[0]->on_error (undef); |
777 | $_[0]->on_error (undef); |
698 | $_[0]->on_read (undef); |
778 | $_[0]->on_read (undef); |
699 | |
779 | |
700 | $finish->(delete $state{handle}); |
780 | $finish->(delete $state{handle}); |
701 | |
781 | |
|
|
782 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
783 | my $cl = 0; |
|
|
784 | my $body = undef; |
|
|
785 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
786 | |
|
|
787 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
788 | |
|
|
789 | my $read_chunk; $read_chunk = sub { |
|
|
790 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
791 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
792 | |
|
|
793 | my $len = hex $1; |
|
|
794 | |
|
|
795 | if ($len) { |
|
|
796 | $cl += $len; |
|
|
797 | |
|
|
798 | $_[0]->push_read (chunk => $len, sub { |
|
|
799 | $on_body->($_[1], \%hdr) |
|
|
800 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
801 | |
|
|
802 | $_[0]->push_read (line => sub { |
|
|
803 | length $_[1] |
|
|
804 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
805 | $_[0]->push_read (line => $read_chunk); |
|
|
806 | }); |
|
|
807 | }); |
|
|
808 | } else { |
|
|
809 | $hdr{"content-length"} ||= $cl; |
|
|
810 | |
|
|
811 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
812 | if (length $_[1]) { |
|
|
813 | for ("$_[1]") { |
|
|
814 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
815 | |
|
|
816 | my $hdr = parse_hdr |
|
|
817 | or return $finish->(undef, 599 => "Garbled response trailers"); |
|
|
818 | |
|
|
819 | %hdr = (%hdr, %$hdr); |
|
|
820 | } |
|
|
821 | } |
|
|
822 | |
|
|
823 | $finish->($body, undef, undef, 1); |
|
|
824 | }); |
|
|
825 | } |
|
|
826 | }; |
|
|
827 | |
|
|
828 | $_[0]->push_read (line => $read_chunk); |
|
|
829 | |
702 | } elsif ($arg{on_body}) { |
830 | } elsif ($arg{on_body}) { |
703 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
831 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
832 | |
704 | if ($len) { |
833 | if ($len) { |
705 | $_[0]->on_read (sub { |
834 | $_[0]->on_read (sub { |
706 | $len -= length $_[0]{rbuf}; |
835 | $len -= length $_[0]{rbuf}; |
707 | |
836 | |
708 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
837 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
709 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
838 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
710 | |
839 | |
711 | $len > 0 |
840 | $len > 0 |
712 | or $finish->("", undef, undef, 1); |
841 | or $finish->("", undef, undef, 1); |
713 | }); |
842 | }); |
714 | } else { |
843 | } else { |
… | |
… | |
737 | }); |
866 | }); |
738 | $_[0]->on_read (sub { }); |
867 | $_[0]->on_read (sub { }); |
739 | } |
868 | } |
740 | } |
869 | } |
741 | } |
870 | } |
742 | }); |
871 | }; |
|
|
872 | |
|
|
873 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
743 | }; |
874 | }; |
744 | |
875 | |
745 | # now handle proxy-CONNECT method |
876 | # now handle proxy-CONNECT method |
746 | if ($proxy && $uscheme eq "https") { |
877 | if ($proxy && $uscheme eq "https") { |
747 | # oh dear, we have to wrap it into a connect request |
878 | # oh dear, we have to wrap it into a connect request |
… | |
… | |
819 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
950 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
820 | Date (RFC 2616). |
951 | Date (RFC 2616). |
821 | |
952 | |
822 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
953 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
823 | |
954 | |
824 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
955 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
825 | timestamp, or C<undef> if the date cannot be parsed. |
956 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
|
|
957 | be parsed. |
826 | |
958 | |
827 | =item $AnyEvent::HTTP::MAX_RECURSE |
959 | =item $AnyEvent::HTTP::MAX_RECURSE |
828 | |
960 | |
829 | The default value for the C<recurse> request parameter (default: C<10>). |
961 | The default value for the C<recurse> request parameter (default: C<10>). |
830 | |
962 | |
… | |
… | |
869 | sub parse_date($) { |
1001 | sub parse_date($) { |
870 | my ($date) = @_; |
1002 | my ($date) = @_; |
871 | |
1003 | |
872 | my ($d, $m, $y, $H, $M, $S); |
1004 | my ($d, $m, $y, $H, $M, $S); |
873 | |
1005 | |
874 | if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
1006 | if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9])[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
875 | # RFC 822/1123, required by RFC 2616 |
1007 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1008 | # cookie dates (with "-") |
|
|
1009 | |
876 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1010 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
877 | |
1011 | |
878 | } elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
1012 | } elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
879 | # RFC 850 |
1013 | # RFC 850 |
880 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1014 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |