… | |
… | |
36 | |
36 | |
37 | =cut |
37 | =cut |
38 | |
38 | |
39 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
40 | |
40 | |
41 | use strict; |
41 | use common::sense; |
42 | no warnings; |
|
|
43 | |
42 | |
44 | use Errno (); |
43 | use Errno (); |
45 | |
44 | |
46 | use AnyEvent 5.0 (); |
45 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
48 | use AnyEvent::Handle (); |
47 | use AnyEvent::Handle (); |
49 | |
48 | |
50 | use base Exporter::; |
49 | use base Exporter::; |
51 | |
50 | |
52 | our $VERSION = '1.46'; |
51 | our $VERSION = '1.5'; |
53 | |
52 | |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | |
54 | |
56 | 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)"; |
57 | our $MAX_RECURSE = 10; |
56 | our $MAX_RECURSE = 10; |
58 | our $MAX_PERSISTENT = 8; |
57 | our $MAX_PERSISTENT = 8; |
59 | our $PERSISTENT_TIMEOUT = 2; |
58 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $TIMEOUT = 300; |
59 | our $TIMEOUT = 300; |
61 | |
60 | |
62 | # changing these is evil |
61 | # changing these is evil |
63 | our $MAX_PERSISTENT_PER_HOST = 0; |
62 | our $MAX_PERSISTENT_PER_HOST = 2; |
64 | our $MAX_PER_HOST = 4; |
63 | our $MAX_PER_HOST = 4; |
65 | |
64 | |
66 | our $PROXY; |
65 | our $PROXY; |
67 | our $ACTIVE = 0; |
66 | our $ACTIVE = 0; |
68 | |
67 | |
… | |
… | |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
93 | 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 |
94 | 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. |
95 | destroyed before the callback is called, the request will be cancelled. |
97 | |
96 | |
98 | The callback will be called with the response body data as first argument |
97 | 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 |
98 | (or C<undef> if an error occured), and a hash-ref with response headers |
100 | second argument. |
99 | (and trailers) as second argument. |
101 | |
100 | |
102 | All the headers in that hash are lowercased. In addition to the response |
101 | All the headers in that hash are lowercased. In addition to the response |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
102 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
103 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
105 | three parts of the HTTP Status-Line of the same name. |
104 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
105 | during the body phase of a request, then the original C<Status> and |
|
|
106 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
107 | C<OrigReason>. |
106 | |
108 | |
107 | The pseudo-header C<URL> contains the actual URL (which can differ from |
109 | 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 |
110 | 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 |
111 | 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 |
112 | valid http URL because it redirected to an ftp URL, in which case you can |
… | |
… | |
119 | |
121 | |
120 | If the server sends a header multiple times, then their contents will be |
122 | If the server sends a header multiple times, then their contents will be |
121 | joined together with a comma (C<,>), as per the HTTP spec. |
123 | joined together with a comma (C<,>), as per the HTTP spec. |
122 | |
124 | |
123 | If an internal error occurs, such as not being able to resolve a hostname, |
125 | If an internal error occurs, such as not being able to resolve a hostname, |
124 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
126 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
125 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
127 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
126 | message. |
128 | message. Currently the following status codes are used: |
|
|
129 | |
|
|
130 | =over 4 |
|
|
131 | |
|
|
132 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
133 | |
|
|
134 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
135 | |
|
|
136 | =item 597 - errors during body receiving or processing. |
|
|
137 | |
|
|
138 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
139 | |
|
|
140 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
141 | |
|
|
142 | =back |
127 | |
143 | |
128 | A typical callback might look like this: |
144 | A typical callback might look like this: |
129 | |
145 | |
130 | sub { |
146 | sub { |
131 | my ($body, $hdr) = @_; |
147 | my ($body, $hdr) = @_; |
… | |
… | |
147 | Whether to recurse requests or not, e.g. on redirects, authentication |
163 | Whether to recurse requests or not, e.g. on redirects, authentication |
148 | retries and so on, and how often to do so. |
164 | retries and so on, and how often to do so. |
149 | |
165 | |
150 | =item headers => hashref |
166 | =item headers => hashref |
151 | |
167 | |
152 | The request headers to use. Currently, C<http_request> may provide its |
168 | 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 |
169 | 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 |
170 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
155 | suppressed by using C<undef> for these headers in which case they won't be |
171 | (this can be suppressed by using C<undef> for these headers in which case |
156 | sent at all). |
172 | they won't be sent at all). |
|
|
173 | |
|
|
174 | You really should provide your own C<User-Agent:> header value that is |
|
|
175 | appropriate for your program - I wouldn't be surprised if the default |
|
|
176 | AnyEvent string gets blocked by webservers sooner or later. |
157 | |
177 | |
158 | =item timeout => $seconds |
178 | =item timeout => $seconds |
159 | |
179 | |
160 | The time-out to use for various stages - each connect attempt will reset |
180 | The time-out to use for various stages - each connect attempt will reset |
161 | the timeout, as will read or write activity, i.e. this is not an overall |
181 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
171 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
191 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
172 | HTTPS. |
192 | HTTPS. |
173 | |
193 | |
174 | =item body => $string |
194 | =item body => $string |
175 | |
195 | |
176 | The request body, usually empty. Will be-sent as-is (future versions of |
196 | The request body, usually empty. Will be sent as-is (future versions of |
177 | this module might offer more options). |
197 | this module might offer more options). |
178 | |
198 | |
179 | =item cookie_jar => $hash_ref |
199 | =item cookie_jar => $hash_ref |
180 | |
200 | |
181 | Passing this parameter enables (simplified) cookie-processing, loosely |
201 | Passing this parameter enables (simplified) cookie-processing, loosely |
182 | based on the original netscape specification. |
202 | based on the original netscape specification. |
183 | |
203 | |
184 | The C<$hash_ref> must be an (initially empty) hash reference which will |
204 | The C<$hash_ref> must be an (initially empty) hash reference which |
185 | get updated automatically. It is possible to save the cookie_jar to |
205 | will get updated automatically. It is possible to save the cookie jar |
186 | persistent storage with something like JSON or Storable, but this is not |
206 | to persistent storage with something like JSON or Storable - see the |
187 | recommended, as expiry times are currently being ignored. |
207 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
208 | expired or session-only cookies, and also for documentation on the format |
|
|
209 | of the cookie jar. |
188 | |
210 | |
189 | Note that this cookie implementation is not of very high quality, nor |
211 | Note that this cookie implementation is not meant to be complete. If |
190 | meant to be complete. If you want complete cookie management you have to |
212 | you want complete cookie management you have to do that on your |
191 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
213 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
192 | cookie-using sites working. Cookies are a privacy disaster, do not use |
214 | working. Cookies are a privacy disaster, do not use them unless required |
193 | them unless required to. |
215 | to. |
|
|
216 | |
|
|
217 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
218 | headers will be set and handled by this module, otherwise they will be |
|
|
219 | left untouched. |
194 | |
220 | |
195 | =item tls_ctx => $scheme | $tls_ctx |
221 | =item tls_ctx => $scheme | $tls_ctx |
196 | |
222 | |
197 | Specifies the AnyEvent::TLS context to be used for https connections. This |
223 | Specifies the AnyEvent::TLS context to be used for https connections. This |
198 | parameter follows the same rules as the C<tls_ctx> parameter to |
224 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
237 | |
263 | |
238 | This callback is useful, among other things, to quickly reject unwanted |
264 | 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 |
265 | content, which, if it is supposed to be rare, can be faster than first |
240 | doing a C<HEAD> request. |
266 | doing a C<HEAD> request. |
241 | |
267 | |
|
|
268 | The downside is that cancelling the request makes it impossible to re-use |
|
|
269 | the connection. Also, the C<on_header> callback will not receive any |
|
|
270 | trailer (headers sent after the response body). |
|
|
271 | |
242 | Example: cancel the request unless the content-type is "text/html". |
272 | Example: cancel the request unless the content-type is "text/html". |
243 | |
273 | |
244 | on_header => sub { |
274 | on_header => sub { |
245 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
275 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
246 | }, |
276 | }, |
… | |
… | |
252 | string instead of the body data. |
282 | string instead of the body data. |
253 | |
283 | |
254 | It has to return either true (in which case AnyEvent::HTTP will continue), |
284 | 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 |
285 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
256 | the completion callback with an error code of C<598>). |
286 | the completion callback with an error code of C<598>). |
|
|
287 | |
|
|
288 | The downside to cancelling the request is that it makes it impossible to |
|
|
289 | re-use the connection. |
257 | |
290 | |
258 | This callback is useful when the data is too large to be held in memory |
291 | 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 |
292 | (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. |
293 | be extracted, or when the body should be processed incrementally. |
261 | |
294 | |
… | |
… | |
287 | If you think you need this, first have a look at C<on_body>, to see if |
320 | 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. |
321 | that doesn't solve your problem in a better way. |
289 | |
322 | |
290 | =back |
323 | =back |
291 | |
324 | |
292 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
325 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
326 | the response body. |
293 | |
327 | |
294 | http_request GET => "http://www.nethype.de/", sub { |
328 | http_request GET => "http://www.nethype.de/", sub { |
295 | my ($body, $hdr) = @_; |
329 | my ($body, $hdr) = @_; |
296 | print "$body\n"; |
330 | print "$body\n"; |
297 | }; |
331 | }; |
298 | |
332 | |
299 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
333 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
300 | timeout of 30 seconds. |
334 | timeout of 30 seconds. |
301 | |
335 | |
302 | http_request |
336 | http_request |
303 | GET => "https://www.google.com", |
337 | GET => "https://www.google.com", |
|
|
338 | headers => { "user-agent" => "MySearchClient 1.0" }, |
304 | timeout => 30, |
339 | timeout => 30, |
305 | sub { |
340 | sub { |
306 | my ($body, $hdr) = @_; |
341 | my ($body, $hdr) = @_; |
307 | use Data::Dumper; |
342 | use Data::Dumper; |
308 | print Dumper $hdr; |
343 | print Dumper $hdr; |
309 | } |
344 | } |
310 | ; |
345 | ; |
311 | |
346 | |
312 | Example: make another simple HTTP GET request, but immediately try to |
347 | Example: do another simple HTTP GET request, but immediately try to |
313 | cancel it. |
348 | cancel it. |
314 | |
349 | |
315 | my $request = http_request GET => "http://www.nethype.de/", sub { |
350 | my $request = http_request GET => "http://www.nethype.de/", sub { |
316 | my ($body, $hdr) = @_; |
351 | my ($body, $hdr) = @_; |
317 | print "$body\n"; |
352 | print "$body\n"; |
… | |
… | |
349 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
384 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
350 | |
385 | |
351 | _slot_schedule $_[0]; |
386 | _slot_schedule $_[0]; |
352 | } |
387 | } |
353 | |
388 | |
|
|
389 | ############################################################################# |
|
|
390 | |
|
|
391 | # expire cookies |
|
|
392 | sub cookie_jar_expire($;$) { |
|
|
393 | my ($jar, $session_end) = @_; |
|
|
394 | |
|
|
395 | %$jar = () if $jar->{version} != 1; |
|
|
396 | |
|
|
397 | my $anow = AE::now; |
|
|
398 | |
|
|
399 | while (my ($chost, $paths) = each %$jar) { |
|
|
400 | next unless ref $paths; |
|
|
401 | |
|
|
402 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
403 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
404 | if (exists $kv->{_expires}) { |
|
|
405 | delete $cookies->{$cookie} |
|
|
406 | if $anow > $kv->{_expires}; |
|
|
407 | } elsif ($session_end) { |
|
|
408 | delete $cookies->{$cookie}; |
|
|
409 | } |
|
|
410 | } |
|
|
411 | |
|
|
412 | delete $paths->{$cpath} |
|
|
413 | unless %$cookies; |
|
|
414 | } |
|
|
415 | |
|
|
416 | delete $jar->{$chost} |
|
|
417 | unless %$paths; |
|
|
418 | } |
|
|
419 | } |
|
|
420 | |
|
|
421 | # extract cookies from jar |
|
|
422 | sub cookie_jar_extract($$$$) { |
|
|
423 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
424 | |
|
|
425 | %$jar = () if $jar->{version} != 1; |
|
|
426 | |
|
|
427 | my @cookies; |
|
|
428 | |
|
|
429 | while (my ($chost, $paths) = each %$jar) { |
|
|
430 | next unless ref $paths; |
|
|
431 | |
|
|
432 | if ($chost =~ /^\./) { |
|
|
433 | next unless $chost eq substr $uhost, -length $chost; |
|
|
434 | } elsif ($chost =~ /\./) { |
|
|
435 | next unless $chost eq $uhost; |
|
|
436 | } else { |
|
|
437 | next; |
|
|
438 | } |
|
|
439 | |
|
|
440 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
441 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
442 | |
|
|
443 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
444 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
445 | |
|
|
446 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
447 | delete $cookies->{$cookie}; |
|
|
448 | next; |
|
|
449 | } |
|
|
450 | |
|
|
451 | my $value = $kv->{value}; |
|
|
452 | |
|
|
453 | if ($value =~ /[=;,[:space:]]/) { |
|
|
454 | $value =~ s/([\\"])/\\$1/g; |
|
|
455 | $value = "\"$value\""; |
|
|
456 | } |
|
|
457 | |
|
|
458 | push @cookies, "$cookie=$value"; |
|
|
459 | } |
|
|
460 | } |
|
|
461 | } |
|
|
462 | |
|
|
463 | \@cookies |
|
|
464 | } |
|
|
465 | |
|
|
466 | # parse set_cookie header into jar |
|
|
467 | sub cookie_jar_set_cookie($$$$) { |
|
|
468 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
469 | |
|
|
470 | my $anow = int AE::now; |
|
|
471 | my $snow; # server-now |
|
|
472 | |
|
|
473 | for ($set_cookie) { |
|
|
474 | # parse NAME=VALUE |
|
|
475 | my @kv; |
|
|
476 | |
|
|
477 | # expires is not http-compliant in the original cookie-spec, |
|
|
478 | # we support the official date format and some extensions |
|
|
479 | while ( |
|
|
480 | m{ |
|
|
481 | \G\s* |
|
|
482 | (?: |
|
|
483 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
484 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
|
|
485 | ) |
|
|
486 | }gcxsi |
|
|
487 | ) { |
|
|
488 | my $name = $2; |
|
|
489 | my $value = $4; |
|
|
490 | |
|
|
491 | if (defined $1) { |
|
|
492 | # expires |
|
|
493 | $name = "expires"; |
|
|
494 | $value = $1; |
|
|
495 | } elsif (defined $3) { |
|
|
496 | # quoted |
|
|
497 | $value = $3; |
|
|
498 | $value =~ s/\\(.)/$1/gs; |
|
|
499 | } |
|
|
500 | |
|
|
501 | push @kv, lc $name, $value; |
|
|
502 | |
|
|
503 | last unless /\G\s*;/gc; |
|
|
504 | } |
|
|
505 | |
|
|
506 | last unless @kv; |
|
|
507 | |
|
|
508 | my $name = shift @kv; |
|
|
509 | my %kv = (value => shift @kv, @kv); |
|
|
510 | |
|
|
511 | if (exists $kv{"max-age"}) { |
|
|
512 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
513 | } elsif (exists $kv{expires}) { |
|
|
514 | $snow ||= parse_date ($date) || $anow; |
|
|
515 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
516 | } else { |
|
|
517 | delete $kv{_expires}; |
|
|
518 | } |
|
|
519 | |
|
|
520 | my $cdom; |
|
|
521 | my $cpath = (delete $kv{path}) || "/"; |
|
|
522 | |
|
|
523 | if (exists $kv{domain}) { |
|
|
524 | $cdom = delete $kv{domain}; |
|
|
525 | |
|
|
526 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
527 | |
|
|
528 | next if $cdom =~ /\.$/; |
|
|
529 | |
|
|
530 | # this is not rfc-like and not netscape-like. go figure. |
|
|
531 | my $ndots = $cdom =~ y/.//; |
|
|
532 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
533 | } else { |
|
|
534 | $cdom = $uhost; |
|
|
535 | } |
|
|
536 | |
|
|
537 | # store it |
|
|
538 | $jar->{version} = 1; |
|
|
539 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
|
|
540 | |
|
|
541 | redo if /\G\s*,/gc; |
|
|
542 | } |
|
|
543 | } |
|
|
544 | |
|
|
545 | # continue to parse $_ for headers and place them into the arg |
|
|
546 | sub parse_hdr() { |
|
|
547 | my %hdr; |
|
|
548 | |
|
|
549 | # things seen, not parsed: |
|
|
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; |
|
|
562 | |
|
|
563 | # remove the "," prefix we added to all headers above |
|
|
564 | substr $_, 0, 1, "" |
|
|
565 | for values %hdr; |
|
|
566 | |
|
|
567 | \%hdr |
|
|
568 | } |
|
|
569 | |
354 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
570 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
355 | |
571 | |
356 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
572 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
357 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
573 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
358 | |
574 | |
… | |
… | |
377 | my @pseudo = (URL => $url); |
593 | my @pseudo = (URL => $url); |
378 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
594 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
379 | |
595 | |
380 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
596 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
381 | |
597 | |
382 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo }) |
598 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
383 | if $recurse < 0; |
599 | if $recurse < 0; |
384 | |
600 | |
385 | my $proxy = $arg{proxy} || $PROXY; |
601 | my $proxy = $arg{proxy} || $PROXY; |
386 | my $timeout = $arg{timeout} || $TIMEOUT; |
602 | my $timeout = $arg{timeout} || $TIMEOUT; |
387 | |
603 | |
… | |
… | |
390 | |
606 | |
391 | $uscheme = lc $uscheme; |
607 | $uscheme = lc $uscheme; |
392 | |
608 | |
393 | my $uport = $uscheme eq "http" ? 80 |
609 | my $uport = $uscheme eq "http" ? 80 |
394 | : $uscheme eq "https" ? 443 |
610 | : $uscheme eq "https" ? 443 |
395 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo }); |
611 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
396 | |
612 | |
397 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
613 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
398 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo }); |
614 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
399 | |
615 | |
400 | my $uhost = $1; |
616 | my $uhost = lc $1; |
401 | $uport = $2 if defined $2; |
617 | $uport = $2 if defined $2; |
402 | |
618 | |
403 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
619 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
404 | unless exists $hdr{host}; |
620 | unless exists $hdr{host}; |
405 | |
621 | |
… | |
… | |
408 | |
624 | |
409 | $upath =~ s%^/?%/%; |
625 | $upath =~ s%^/?%/%; |
410 | |
626 | |
411 | # cookie processing |
627 | # cookie processing |
412 | if (my $jar = $arg{cookie_jar}) { |
628 | if (my $jar = $arg{cookie_jar}) { |
413 | %$jar = () if $jar->{version} != 1; |
629 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
414 | |
630 | |
415 | my @cookie; |
|
|
416 | |
|
|
417 | while (my ($chost, $v) = each %$jar) { |
|
|
418 | if ($chost =~ /^\./) { |
|
|
419 | next unless $chost eq substr $uhost, -length $chost; |
|
|
420 | } elsif ($chost =~ /\./) { |
|
|
421 | next unless $chost eq $uhost; |
|
|
422 | } else { |
|
|
423 | next; |
|
|
424 | } |
|
|
425 | |
|
|
426 | while (my ($cpath, $v) = each %$v) { |
|
|
427 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
428 | |
|
|
429 | while (my ($k, $v) = each %$v) { |
|
|
430 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
431 | my $value = $v->{value}; |
|
|
432 | $value =~ s/([\\"])/\\$1/g; |
|
|
433 | push @cookie, "$k=\"$value\""; |
|
|
434 | } |
|
|
435 | } |
|
|
436 | } |
|
|
437 | |
|
|
438 | $hdr{cookie} = join "; ", @cookie |
631 | $hdr{cookie} = join "; ", @$cookies |
439 | if @cookie; |
632 | if @$cookies; |
440 | } |
633 | } |
441 | |
634 | |
442 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
635 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
443 | |
636 | |
444 | if ($proxy) { |
637 | if ($proxy) { |
… | |
… | |
447 | $rscheme = "http" unless defined $rscheme; |
640 | $rscheme = "http" unless defined $rscheme; |
448 | |
641 | |
449 | # don't support https requests over https-proxy transport, |
642 | # don't support https requests over https-proxy transport, |
450 | # can't be done with tls as spec'ed, unless you double-encrypt. |
643 | # can't be done with tls as spec'ed, unless you double-encrypt. |
451 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
644 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
|
|
645 | |
|
|
646 | $rhost = lc $rhost; |
|
|
647 | $rscheme = lc $rscheme; |
452 | } else { |
648 | } else { |
453 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
649 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
454 | } |
650 | } |
455 | |
651 | |
456 | # leave out fragment and query string, just a heuristic |
652 | # leave out fragment and query string, just a heuristic |
457 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
653 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
458 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
654 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
459 | |
655 | |
460 | $hdr{"content-length"} = length $arg{body} |
656 | $hdr{"content-length"} = length $arg{body} |
461 | if length $arg{body} || $method ne "GET"; |
657 | if length $arg{body} || $method ne "GET"; |
462 | |
658 | |
|
|
659 | my $idempotent = $method =~ /^(?:GET|HEAD|PUT|DELETE|OPTIONS|TRACE)$/; |
|
|
660 | |
|
|
661 | # default value for keepalive is true iff the request is for an idempotent method |
|
|
662 | my $keepalive = exists $arg{keepalive} |
|
|
663 | ? $arg{keepalive}*1 |
|
|
664 | : $idempotent ? $PERSISTENT_TIMEOUT : 0; |
|
|
665 | |
|
|
666 | $hdr{connection} = ($keepalive ? "" : "close ") . "Te"; #1.1 |
|
|
667 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
|
|
668 | |
463 | my %state = (connect_guard => 1); |
669 | my %state = (connect_guard => 1); |
464 | |
670 | |
465 | _get_slot $uhost, sub { |
671 | my $ae_error = 595; # connecting |
466 | $state{slot_guard} = shift; |
|
|
467 | |
672 | |
|
|
673 | # handle actual, non-tunneled, request |
|
|
674 | my $handle_actual_request = sub { |
|
|
675 | $ae_error = 596; # request phase |
|
|
676 | |
|
|
677 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
678 | |
|
|
679 | # send request |
|
|
680 | $state{handle}->push_write ( |
|
|
681 | "$method $rpath HTTP/1.1\015\012" |
|
|
682 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
683 | . "\015\012" |
|
|
684 | . (delete $arg{body}) |
|
|
685 | ); |
|
|
686 | |
|
|
687 | # return if error occured during push_write() |
468 | return unless $state{connect_guard}; |
688 | return unless %state; |
469 | |
689 | |
470 | my $tcp_connect = $arg{tcp_connect} |
690 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
471 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
691 | %hdr = (); |
472 | |
692 | |
473 | $state{connect_guard} = $tcp_connect->( |
693 | # status line and headers |
474 | $rhost, |
694 | $state{read_response} = sub { |
475 | $rport, |
695 | for ("$_[1]") { |
476 | sub { |
696 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
477 | $state{fh} = shift |
|
|
478 | or do { |
|
|
479 | my $err = "$!"; |
|
|
480 | %state = (); |
|
|
481 | return $cb->(undef, { Status => 599, Reason => $err, @pseudo }); |
|
|
482 | }; |
|
|
483 | |
697 | |
484 | pop; # free memory, save a tree |
698 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
699 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
485 | |
700 | |
486 | return unless delete $state{connect_guard}; |
701 | # 100 Continue handling |
|
|
702 | # should not happen as we don't send expect: 100-continue, |
|
|
703 | # but we handle it just in case. |
|
|
704 | # since we send the request body regardless, if we get an error |
|
|
705 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
706 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
707 | if $2 eq 100; |
487 | |
708 | |
488 | # get handle |
709 | push @pseudo, |
489 | $state{handle} = new AnyEvent::Handle |
710 | HTTPVersion => $1, |
490 | fh => $state{fh}, |
711 | Status => $2, |
491 | peername => $rhost, |
712 | Reason => $3, |
492 | tls_ctx => $arg{tls_ctx}, |
|
|
493 | # these need to be reconfigured on keepalive handles |
|
|
494 | timeout => $timeout, |
|
|
495 | on_error => sub { |
|
|
496 | %state = (); |
|
|
497 | $cb->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
|
|
498 | }, |
|
|
499 | on_eof => sub { |
|
|
500 | %state = (); |
|
|
501 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo }); |
|
|
502 | }, |
|
|
503 | ; |
713 | ; |
504 | |
714 | |
|
|
715 | my $hdr = parse_hdr |
|
|
716 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
717 | |
|
|
718 | %hdr = (%$hdr, @pseudo); |
|
|
719 | } |
|
|
720 | |
|
|
721 | # redirect handling |
|
|
722 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
723 | # try to support some common forms of broken Location headers. |
|
|
724 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
725 | $hdr{location} =~ s/^\.\/+//; |
|
|
726 | |
|
|
727 | my $url = "$rscheme://$uhost:$uport"; |
|
|
728 | |
|
|
729 | unless ($hdr{location} =~ s/^\///) { |
|
|
730 | $url .= $upath; |
|
|
731 | $url =~ s/\/[^\/]*$//; |
|
|
732 | } |
|
|
733 | |
|
|
734 | $hdr{location} = "$url/$hdr{location}"; |
|
|
735 | } |
|
|
736 | |
|
|
737 | my $redirect; |
|
|
738 | |
|
|
739 | if ($recurse) { |
|
|
740 | my $status = $hdr{Status}; |
|
|
741 | |
|
|
742 | # industry standard is to redirect POST as GET for |
|
|
743 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
744 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
745 | # industry standard seems to be to simply follow. |
|
|
746 | # we go with the industry standard. |
|
|
747 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
748 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
749 | $method = "GET" unless $method eq "HEAD"; |
|
|
750 | $redirect = 1; |
|
|
751 | } elsif ($status == 307) { |
|
|
752 | $redirect = 1; |
|
|
753 | } |
|
|
754 | } |
|
|
755 | |
|
|
756 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
757 | my $may_keep_alive = $_[3]; |
|
|
758 | |
|
|
759 | $state{handle}->destroy if $state{handle}; |
|
|
760 | %state = (); |
|
|
761 | |
|
|
762 | if (defined $_[1]) { |
|
|
763 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
764 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
765 | } |
|
|
766 | |
|
|
767 | # set-cookie processing |
|
|
768 | if ($arg{cookie_jar}) { |
|
|
769 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
|
|
770 | } |
|
|
771 | |
|
|
772 | if ($redirect && exists $hdr{location}) { |
|
|
773 | # we ignore any errors, as it is very common to receive |
|
|
774 | # Content-Length != 0 but no actual body |
|
|
775 | # we also access %hdr, as $_[1] might be an erro |
|
|
776 | http_request ( |
|
|
777 | $method => $hdr{location}, |
|
|
778 | %arg, |
|
|
779 | recurse => $recurse - 1, |
|
|
780 | Redirect => [$_[0], \%hdr], |
|
|
781 | $cb); |
|
|
782 | } else { |
|
|
783 | $cb->($_[0], \%hdr); |
|
|
784 | } |
|
|
785 | }; |
|
|
786 | |
|
|
787 | $ae_error = 597; # body phase |
|
|
788 | |
|
|
789 | my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct... |
|
|
790 | |
|
|
791 | my $len = $chunked ? undef : $hdr{"content-length"}; |
|
|
792 | |
|
|
793 | # body handling, many different code paths |
|
|
794 | # - no body expected |
|
|
795 | # - want_body_handle |
|
|
796 | # - te chunked |
|
|
797 | # - 2x length known (with or without on_body) |
|
|
798 | # - 2x length not known (with or without on_body) |
|
|
799 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
800 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
801 | } elsif ( |
|
|
802 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
803 | or $method eq "HEAD" |
|
|
804 | or (defined $len && $len == 0) # == 0, not !, because "0 " is true |
|
|
805 | ) { |
|
|
806 | # no body |
|
|
807 | $finish->("", undef, undef, 1); |
|
|
808 | |
|
|
809 | } elsif (!$redirect && $arg{want_body_handle}) { |
|
|
810 | $_[0]->on_eof (undef); |
|
|
811 | $_[0]->on_error (undef); |
|
|
812 | $_[0]->on_read (undef); |
|
|
813 | |
|
|
814 | $finish->(delete $state{handle}); |
|
|
815 | |
|
|
816 | } elsif ($chunked) { |
|
|
817 | my $cl = 0; |
|
|
818 | my $body = undef; |
|
|
819 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
820 | |
|
|
821 | $state{read_chunk} = sub { |
|
|
822 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
823 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
824 | |
|
|
825 | my $len = hex $1; |
|
|
826 | |
|
|
827 | if ($len) { |
|
|
828 | $cl += $len; |
|
|
829 | |
|
|
830 | $_[0]->push_read (chunk => $len, sub { |
|
|
831 | $on_body->($_[1], \%hdr) |
|
|
832 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
833 | |
|
|
834 | $_[0]->push_read (line => sub { |
|
|
835 | length $_[1] |
|
|
836 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
837 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
838 | }); |
|
|
839 | }); |
|
|
840 | } else { |
|
|
841 | $hdr{"content-length"} ||= $cl; |
|
|
842 | |
|
|
843 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
844 | if (length $_[1]) { |
|
|
845 | for ("$_[1]") { |
|
|
846 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
847 | |
|
|
848 | my $hdr = parse_hdr |
|
|
849 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
850 | |
|
|
851 | %hdr = (%hdr, %$hdr); |
|
|
852 | } |
|
|
853 | } |
|
|
854 | |
|
|
855 | $finish->($body, undef, undef, 1); |
|
|
856 | }); |
|
|
857 | } |
|
|
858 | }; |
|
|
859 | |
|
|
860 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
861 | |
|
|
862 | } elsif ($arg{on_body}) { |
|
|
863 | if (defined $len) { |
|
|
864 | $_[0]->on_read (sub { |
|
|
865 | $len -= length $_[0]{rbuf}; |
|
|
866 | |
|
|
867 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
868 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
869 | |
|
|
870 | $len > 0 |
|
|
871 | or $finish->("", undef, undef, 1); |
|
|
872 | }); |
|
|
873 | } else { |
|
|
874 | $_[0]->on_eof (sub { |
|
|
875 | $finish->(""); |
|
|
876 | }); |
|
|
877 | $_[0]->on_read (sub { |
|
|
878 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
879 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
880 | }); |
|
|
881 | } |
|
|
882 | } else { |
|
|
883 | $_[0]->on_eof (undef); |
|
|
884 | |
|
|
885 | if (defined $len) { |
|
|
886 | $_[0]->on_read (sub { |
|
|
887 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
888 | if $len <= length $_[0]{rbuf}; |
|
|
889 | }); |
|
|
890 | } else { |
|
|
891 | $_[0]->on_error (sub { |
|
|
892 | ($! == Errno::EPIPE || !$!) |
|
|
893 | ? $finish->(delete $_[0]{rbuf}) |
|
|
894 | : $finish->(undef, $ae_error => $_[2]); |
|
|
895 | }); |
|
|
896 | $_[0]->on_read (sub { }); |
|
|
897 | } |
|
|
898 | } |
|
|
899 | }; |
|
|
900 | |
|
|
901 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
902 | }; |
|
|
903 | |
|
|
904 | my $connect_cb = sub { |
|
|
905 | $state{fh} = shift |
|
|
906 | or do { |
|
|
907 | my $err = "$!"; |
|
|
908 | %state = (); |
|
|
909 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
|
|
910 | }; |
|
|
911 | |
|
|
912 | return unless delete $state{connect_guard}; |
|
|
913 | |
|
|
914 | # get handle |
|
|
915 | $state{handle} = new AnyEvent::Handle |
|
|
916 | fh => $state{fh}, |
|
|
917 | peername => $rhost, |
|
|
918 | tls_ctx => $arg{tls_ctx}, |
|
|
919 | # these need to be reconfigured on keepalive handles |
|
|
920 | timeout => $timeout, |
|
|
921 | on_error => sub { |
|
|
922 | %state = (); |
|
|
923 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
|
|
924 | }, |
|
|
925 | on_eof => sub { |
|
|
926 | %state = (); |
|
|
927 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
|
|
928 | }, |
|
|
929 | ; |
|
|
930 | |
505 | # limit the number of persistent connections |
931 | # limit the number of persistent connections |
506 | # keepalive not yet supported |
932 | # keepalive not yet supported |
507 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
933 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
508 | # ++$KA_COUNT{$_[1]}; |
934 | # ++$KA_COUNT{$_[1]}; |
509 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
935 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
510 | # --$KA_COUNT{$_[1]} |
936 | # --$KA_COUNT{$_[1]} |
511 | # }; |
937 | # }; |
512 | # $hdr{connection} = "keep-alive"; |
938 | # $hdr{connection} = "keep-alive"; |
513 | # } else { |
|
|
514 | delete $hdr{connection}; |
|
|
515 | # } |
939 | # } |
516 | |
940 | |
517 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
941 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
518 | |
942 | |
519 | # handle actual, non-tunneled, request |
|
|
520 | my $handle_actual_request = sub { |
|
|
521 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
522 | |
|
|
523 | # send request |
|
|
524 | $state{handle}->push_write ( |
|
|
525 | "$method $rpath HTTP/1.0\015\012" |
|
|
526 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
527 | . "\015\012" |
|
|
528 | . (delete $arg{body}) |
|
|
529 | ); |
|
|
530 | |
|
|
531 | # return if error occured during push_write() |
|
|
532 | return unless %state; |
|
|
533 | |
|
|
534 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
535 | |
|
|
536 | # status line and headers |
|
|
537 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
538 | for ("$_[1]") { |
|
|
539 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
540 | |
|
|
541 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
|
|
542 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo })); |
|
|
543 | |
|
|
544 | push @pseudo, |
|
|
545 | HTTPVersion => $1, |
|
|
546 | Status => $2, |
|
|
547 | Reason => $3, |
|
|
548 | ; |
|
|
549 | |
|
|
550 | # things seen, not parsed: |
|
|
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 })); |
|
|
563 | } |
|
|
564 | |
|
|
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}"; |
|
|
586 | } |
|
|
587 | |
|
|
588 | my $redirect; |
|
|
589 | |
|
|
590 | if ($recurse) { |
|
|
591 | my $status = $hdr{Status}; |
|
|
592 | |
|
|
593 | # industry standard is to redirect POST as GET for |
|
|
594 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
595 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
596 | # industry standard seems to be to simply follow. |
|
|
597 | # we go with the industry standard. |
|
|
598 | if ($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 | $redirect = 1; |
|
|
602 | } elsif ($status == 307) { |
|
|
603 | $redirect = 1; |
|
|
604 | } |
|
|
605 | } |
|
|
606 | |
|
|
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}) { |
|
|
662 | # we ignore any errors, as it is very common to receive |
|
|
663 | # Content-Length != 0 but no actual body |
|
|
664 | # we also access %hdr, as $_[1] might be an erro |
|
|
665 | http_request ( |
|
|
666 | $method => $hdr{location}, |
|
|
667 | %arg, |
|
|
668 | recurse => $recurse - 1, |
|
|
669 | Redirect => \@_, |
|
|
670 | $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 | $finish->("", \%hdr); |
|
|
687 | } else { |
|
|
688 | # body handling, four different code paths |
|
|
689 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
690 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
691 | if (!$redirect && $arg{want_body_handle}) { |
|
|
692 | $_[0]->on_eof (undef); |
|
|
693 | $_[0]->on_error (undef); |
|
|
694 | $_[0]->on_read (undef); |
|
|
695 | |
|
|
696 | $finish->(delete $state{handle}, \%hdr); |
|
|
697 | |
|
|
698 | } elsif ($arg{on_body}) { |
|
|
699 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
|
|
700 | if ($len) { |
|
|
701 | $_[0]->on_eof (undef); |
|
|
702 | $_[0]->on_read (sub { |
|
|
703 | $len -= length $_[0]{rbuf}; |
|
|
704 | |
|
|
705 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
706 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
707 | |
|
|
708 | $len > 0 |
|
|
709 | or $finish->("", \%hdr); |
|
|
710 | }); |
|
|
711 | } else { |
|
|
712 | $_[0]->on_eof (sub { |
|
|
713 | $finish->("", \%hdr); |
|
|
714 | }); |
|
|
715 | $_[0]->on_read (sub { |
|
|
716 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
717 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
|
|
718 | }); |
|
|
719 | } |
|
|
720 | } else { |
|
|
721 | $_[0]->on_eof (undef); |
|
|
722 | |
|
|
723 | if ($len) { |
|
|
724 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
|
|
725 | $_[0]->on_read (sub { |
|
|
726 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
727 | if $len <= length $_[0]{rbuf}; |
|
|
728 | }); |
|
|
729 | } else { |
|
|
730 | $_[0]->on_error (sub { |
|
|
731 | ($! == Errno::EPIPE || !$!) |
|
|
732 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
|
|
733 | : $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
|
|
734 | }); |
|
|
735 | $_[0]->on_read (sub { }); |
|
|
736 | } |
|
|
737 | } |
|
|
738 | } |
|
|
739 | }); |
|
|
740 | }; |
|
|
741 | |
|
|
742 | # now handle proxy-CONNECT method |
943 | # now handle proxy-CONNECT method |
743 | if ($proxy && $uscheme eq "https") { |
944 | if ($proxy && $uscheme eq "https") { |
744 | # oh dear, we have to wrap it into a connect request |
945 | # oh dear, we have to wrap it into a connect request |
745 | |
946 | |
746 | # maybe re-use $uauthority with patched port? |
947 | # 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"); |
948 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
748 | $state{handle}->push_read (line => $qr_nlnl, sub { |
949 | $state{handle}->push_read (line => $qr_nlnl, sub { |
749 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
950 | $_[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 })); |
951 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
751 | |
952 | |
752 | if ($2 == 200) { |
953 | if ($2 == 200) { |
753 | $rpath = $upath; |
954 | $rpath = $upath; |
754 | &$handle_actual_request; |
955 | $handle_actual_request->(); |
755 | } else { |
|
|
756 | %state = (); |
|
|
757 | $cb->(undef, { Status => $2, Reason => $3, @pseudo }); |
|
|
758 | } |
|
|
759 | }); |
|
|
760 | } else { |
956 | } else { |
761 | &$handle_actual_request; |
957 | %state = (); |
|
|
958 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
762 | } |
959 | } |
763 | |
|
|
764 | }, |
960 | }); |
765 | $arg{on_prepare} || sub { $timeout } |
961 | } else { |
|
|
962 | $handle_actual_request->(); |
766 | ); |
963 | } |
|
|
964 | }; |
|
|
965 | |
|
|
966 | _get_slot $uhost, sub { |
|
|
967 | $state{slot_guard} = shift; |
|
|
968 | |
|
|
969 | return unless $state{connect_guard}; |
|
|
970 | |
|
|
971 | my $tcp_connect = $arg{tcp_connect} |
|
|
972 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
973 | |
|
|
974 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
767 | }; |
975 | }; |
768 | |
976 | |
769 | defined wantarray && AnyEvent::Util::guard { %state = () } |
977 | defined wantarray && AnyEvent::Util::guard { %state = () } |
770 | } |
978 | } |
771 | |
979 | |
… | |
… | |
806 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
1014 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
807 | otherwise. |
1015 | otherwise. |
808 | |
1016 | |
809 | To clear an already-set proxy, use C<undef>. |
1017 | To clear an already-set proxy, use C<undef>. |
810 | |
1018 | |
|
|
1019 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1020 | |
|
|
1021 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1022 | C<$session_end> is given and true, then additionally remove all session |
|
|
1023 | cookies. |
|
|
1024 | |
|
|
1025 | You should call this function (with a true C<$session_end>) before you |
|
|
1026 | save cookies to disk, and you should call this function after loading them |
|
|
1027 | again. If you have a long-running program you can additonally call this |
|
|
1028 | function from time to time. |
|
|
1029 | |
|
|
1030 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1031 | module. It's format is subject to change, but currently it is like this: |
|
|
1032 | |
|
|
1033 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1034 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1035 | hash-references. The key for these inner hash references is the |
|
|
1036 | server path for which this cookie is meant, and the values are again |
|
|
1037 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1038 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1039 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1040 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1041 | expiry timestamp. |
|
|
1042 | |
|
|
1043 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1044 | chance of understanding the above paragraph: |
|
|
1045 | |
|
|
1046 | { |
|
|
1047 | version => 1, |
|
|
1048 | "10.0.0.1" => { |
|
|
1049 | "/" => { |
|
|
1050 | "mythweb_id" => { |
|
|
1051 | _expires => 1293917923, |
|
|
1052 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1053 | }, |
|
|
1054 | }, |
|
|
1055 | }, |
|
|
1056 | } |
|
|
1057 | |
811 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1058 | =item $date = AnyEvent::HTTP::format_date $timestamp |
812 | |
1059 | |
813 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1060 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
814 | Date (RFC 2616). |
1061 | Date (RFC 2616). |
815 | |
1062 | |
816 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1063 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
817 | |
1064 | |
818 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
1065 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1066 | bunch of minor variations of those, and returns the corresponding POSIX |
819 | timestamp, or C<undef> if the date cannot be parsed. |
1067 | timestamp, or C<undef> if the date cannot be parsed. |
820 | |
1068 | |
821 | =item $AnyEvent::HTTP::MAX_RECURSE |
1069 | =item $AnyEvent::HTTP::MAX_RECURSE |
822 | |
1070 | |
823 | The default value for the C<recurse> request parameter (default: C<10>). |
1071 | The default value for the C<recurse> request parameter (default: C<10>). |
… | |
… | |
863 | sub parse_date($) { |
1111 | sub parse_date($) { |
864 | my ($date) = @_; |
1112 | my ($date) = @_; |
865 | |
1113 | |
866 | my ($d, $m, $y, $H, $M, $S); |
1114 | my ($d, $m, $y, $H, $M, $S); |
867 | |
1115 | |
868 | if ($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$/) { |
1116 | if ($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$/) { |
869 | # RFC 822/1123, required by RFC 2616 |
1117 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1118 | # cookie dates (with "-") |
|
|
1119 | |
870 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1120 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
871 | |
1121 | |
872 | } elsif ($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$/) { |
1122 | } elsif ($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]?) GMT$/) { |
873 | # RFC 850 |
1123 | # RFC 850 |
874 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1124 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
875 | |
1125 | |
876 | } elsif ($date =~ /^[A-Z][a-z][a-z] ([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][0-9][0-9])$/) { |
1126 | } elsif ($date =~ /^[A-Z][a-z][a-z]+ ([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][0-9][0-9])$/) { |
877 | # ISO C's asctime |
1127 | # ISO C's asctime |
878 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1128 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
879 | } |
1129 | } |
880 | # other formats fail in the loop below |
1130 | # other formats fail in the loop below |
881 | |
1131 | |