… | |
… | |
43 | |
43 | |
44 | use Errno (); |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent 5.0 (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
|
|
49 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
50 | |
49 | |
51 | use base Exporter::; |
50 | use base Exporter::; |
52 | |
51 | |
53 | our $VERSION = '1.44'; |
52 | our $VERSION = '1.5'; |
54 | |
53 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
55 | |
57 | 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)"; |
58 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
… | |
… | |
92 | must be an absolute http or https URL. |
91 | must be an absolute http or https URL. |
93 | |
92 | |
94 | When called in void context, nothing is returned. In other contexts, |
93 | When called in void context, nothing is returned. In other contexts, |
95 | 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 |
96 | 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 |
97 | destroyed before the callbakc is called, the request will be cancelled. |
96 | destroyed before the callback is called, the request will be cancelled. |
98 | |
97 | |
99 | 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 |
100 | (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 |
101 | second argument. |
100 | (and trailers) as second argument. |
102 | |
101 | |
103 | 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 |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
|
|
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
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>. |
|
|
109 | |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
107 | requested URL when following redirects). |
111 | the requested URL when following redirects - for example, you might get |
|
|
112 | an error that your URL scheme is not supported even though your URL is a |
|
|
113 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
114 | look at the URL pseudo header). |
|
|
115 | |
|
|
116 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
117 | of an internal redirect. In that case it is an array reference with |
|
|
118 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
119 | response could in turn be the result of a redirect itself, and C<< |
|
|
120 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
121 | response, and so on. |
108 | |
122 | |
109 | If the server sends a header multiple times, then their contents will be |
123 | If the server sends a header multiple times, then their contents will be |
110 | joined together with a comma (C<,>), as per the HTTP spec. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
111 | |
125 | |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
114 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
128 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
115 | message. |
129 | message. Currently the following status codes are used: |
|
|
130 | |
|
|
131 | =over 4 |
|
|
132 | |
|
|
133 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
134 | |
|
|
135 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
136 | |
|
|
137 | =item 597 - errors during body receiving or processing. |
|
|
138 | |
|
|
139 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
140 | |
|
|
141 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
142 | |
|
|
143 | =back |
116 | |
144 | |
117 | A typical callback might look like this: |
145 | A typical callback might look like this: |
118 | |
146 | |
119 | sub { |
147 | sub { |
120 | my ($body, $hdr) = @_; |
148 | my ($body, $hdr) = @_; |
… | |
… | |
136 | Whether to recurse requests or not, e.g. on redirects, authentication |
164 | Whether to recurse requests or not, e.g. on redirects, authentication |
137 | retries and so on, and how often to do so. |
165 | retries and so on, and how often to do so. |
138 | |
166 | |
139 | =item headers => hashref |
167 | =item headers => hashref |
140 | |
168 | |
141 | The request headers to use. Currently, C<http_request> may provide its |
169 | The request headers to use. Currently, C<http_request> may provide its own |
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
143 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
144 | suppressed by using C<undef> for these headers in which case they won't be |
172 | (this can be suppressed by using C<undef> for these headers in which case |
145 | sent at all). |
173 | they won't be sent at all). |
146 | |
174 | |
147 | =item timeout => $seconds |
175 | =item timeout => $seconds |
148 | |
176 | |
149 | The time-out to use for various stages - each connect attempt will reset |
177 | The time-out to use for various stages - each connect attempt will reset |
150 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
160 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
188 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
161 | HTTPS. |
189 | HTTPS. |
162 | |
190 | |
163 | =item body => $string |
191 | =item body => $string |
164 | |
192 | |
165 | The request body, usually empty. Will be-sent as-is (future versions of |
193 | The request body, usually empty. Will be sent as-is (future versions of |
166 | this module might offer more options). |
194 | this module might offer more options). |
167 | |
195 | |
168 | =item cookie_jar => $hash_ref |
196 | =item cookie_jar => $hash_ref |
169 | |
197 | |
170 | Passing this parameter enables (simplified) cookie-processing, loosely |
198 | Passing this parameter enables (simplified) cookie-processing, loosely |
171 | based on the original netscape specification. |
199 | based on the original netscape specification. |
172 | |
200 | |
173 | The C<$hash_ref> must be an (initially empty) hash reference which will |
201 | The C<$hash_ref> must be an (initially empty) hash reference which |
174 | get updated automatically. It is possible to save the cookie_jar to |
202 | will get updated automatically. It is possible to save the cookie jar |
175 | persistent storage with something like JSON or Storable, but this is not |
203 | to persistent storage with something like JSON or Storable - see the |
176 | recommended, as expiry times are currently being ignored. |
204 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
205 | expired or session-only cookies, and also for documentation on the format |
|
|
206 | of the cookie jar. |
177 | |
207 | |
178 | Note that this cookie implementation is not of very high quality, nor |
208 | Note that this cookie implementation is not meant to be complete. If |
179 | meant to be complete. If you want complete cookie management you have to |
209 | you want complete cookie management you have to do that on your |
180 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
210 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
181 | cookie-using sites working. Cookies are a privacy disaster, do not use |
211 | working. Cookies are a privacy disaster, do not use them unless required |
182 | them unless required to. |
212 | to. |
|
|
213 | |
|
|
214 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
215 | headers will be set and handled by this module, otherwise they will be |
|
|
216 | left untouched. |
183 | |
217 | |
184 | =item tls_ctx => $scheme | $tls_ctx |
218 | =item tls_ctx => $scheme | $tls_ctx |
185 | |
219 | |
186 | Specifies the AnyEvent::TLS context to be used for https connections. This |
220 | Specifies the AnyEvent::TLS context to be used for https connections. This |
187 | parameter follows the same rules as the C<tls_ctx> parameter to |
221 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
200 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
234 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
201 | and behaves exactly the same way (e.g. it has to provide a |
235 | and behaves exactly the same way (e.g. it has to provide a |
202 | timeout). See the description for the C<$prepare_cb> argument of |
236 | timeout). See the description for the C<$prepare_cb> argument of |
203 | C<AnyEvent::Socket::tcp_connect> for details. |
237 | C<AnyEvent::Socket::tcp_connect> for details. |
204 | |
238 | |
|
|
239 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
240 | |
|
|
241 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
242 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
243 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
244 | obviously, it has to follow the same calling conventions, except that it |
|
|
245 | may always return a connection guard object. |
|
|
246 | |
|
|
247 | There are probably lots of weird uses for this function, starting from |
|
|
248 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
249 | but fast) host => IP address caching or even socks protocol support. |
|
|
250 | |
205 | =item on_header => $callback->($headers) |
251 | =item on_header => $callback->($headers) |
206 | |
252 | |
207 | When specified, this callback will be called with the header hash as soon |
253 | When specified, this callback will be called with the header hash as soon |
208 | as headers have been successfully received from the remote server (not on |
254 | as headers have been successfully received from the remote server (not on |
209 | locally-generated errors). |
255 | locally-generated errors). |
… | |
… | |
214 | |
260 | |
215 | This callback is useful, among other things, to quickly reject unwanted |
261 | This callback is useful, among other things, to quickly reject unwanted |
216 | content, which, if it is supposed to be rare, can be faster than first |
262 | content, which, if it is supposed to be rare, can be faster than first |
217 | doing a C<HEAD> request. |
263 | doing a C<HEAD> request. |
218 | |
264 | |
|
|
265 | The downside is that cancelling the request makes it impossible to re-use |
|
|
266 | the connection. Also, the C<on_header> callback will not receive any |
|
|
267 | trailer (headers sent after the response body). |
|
|
268 | |
219 | Example: cancel the request unless the content-type is "text/html". |
269 | Example: cancel the request unless the content-type is "text/html". |
220 | |
270 | |
221 | on_header => sub { |
271 | on_header => sub { |
222 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
272 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
223 | }, |
273 | }, |
… | |
… | |
229 | string instead of the body data. |
279 | string instead of the body data. |
230 | |
280 | |
231 | It has to return either true (in which case AnyEvent::HTTP will continue), |
281 | It has to return either true (in which case AnyEvent::HTTP will continue), |
232 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
282 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
233 | the completion callback with an error code of C<598>). |
283 | the completion callback with an error code of C<598>). |
|
|
284 | |
|
|
285 | The downside to cancelling the request is that it makes it impossible to |
|
|
286 | re-use the connection. |
234 | |
287 | |
235 | This callback is useful when the data is too large to be held in memory |
288 | This callback is useful when the data is too large to be held in memory |
236 | (so the callback writes it to a file) or when only some information should |
289 | (so the callback writes it to a file) or when only some information should |
237 | be extracted, or when the body should be processed incrementally. |
290 | be extracted, or when the body should be processed incrementally. |
238 | |
291 | |
… | |
… | |
264 | If you think you need this, first have a look at C<on_body>, to see if |
317 | If you think you need this, first have a look at C<on_body>, to see if |
265 | that doesn't solve your problem in a better way. |
318 | that doesn't solve your problem in a better way. |
266 | |
319 | |
267 | =back |
320 | =back |
268 | |
321 | |
269 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
322 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
323 | the response body. |
270 | |
324 | |
271 | http_request GET => "http://www.nethype.de/", sub { |
325 | http_request GET => "http://www.nethype.de/", sub { |
272 | my ($body, $hdr) = @_; |
326 | my ($body, $hdr) = @_; |
273 | print "$body\n"; |
327 | print "$body\n"; |
274 | }; |
328 | }; |
275 | |
329 | |
276 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
330 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
277 | timeout of 30 seconds. |
331 | timeout of 30 seconds. |
278 | |
332 | |
279 | http_request |
333 | http_request |
280 | GET => "https://www.google.com", |
334 | GET => "https://www.google.com", |
281 | timeout => 30, |
335 | timeout => 30, |
… | |
… | |
284 | use Data::Dumper; |
338 | use Data::Dumper; |
285 | print Dumper $hdr; |
339 | print Dumper $hdr; |
286 | } |
340 | } |
287 | ; |
341 | ; |
288 | |
342 | |
289 | Example: make another simple HTTP GET request, but immediately try to |
343 | Example: do another simple HTTP GET request, but immediately try to |
290 | cancel it. |
344 | cancel it. |
291 | |
345 | |
292 | my $request = http_request GET => "http://www.nethype.de/", sub { |
346 | my $request = http_request GET => "http://www.nethype.de/", sub { |
293 | my ($body, $hdr) = @_; |
347 | my ($body, $hdr) = @_; |
294 | print "$body\n"; |
348 | print "$body\n"; |
… | |
… | |
326 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
380 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
327 | |
381 | |
328 | _slot_schedule $_[0]; |
382 | _slot_schedule $_[0]; |
329 | } |
383 | } |
330 | |
384 | |
331 | our $qr_nl = qr{\015?\012}; |
385 | ############################################################################# |
|
|
386 | |
|
|
387 | # expire cookies |
|
|
388 | sub cookie_jar_expire($;$) { |
|
|
389 | my ($jar, $session_end) = @_; |
|
|
390 | |
|
|
391 | %$jar = () if $jar->{version} != 1; |
|
|
392 | |
|
|
393 | my $anow = AE::now; |
|
|
394 | |
|
|
395 | while (my ($chost, $paths) = each %$jar) { |
|
|
396 | next unless ref $paths; |
|
|
397 | |
|
|
398 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
399 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
400 | if (exists $kv->{_expires}) { |
|
|
401 | delete $cookies->{$cookie} |
|
|
402 | if $anow > $kv->{_expires}; |
|
|
403 | } elsif ($session_end) { |
|
|
404 | delete $cookies->{$cookie}; |
|
|
405 | } |
|
|
406 | } |
|
|
407 | |
|
|
408 | delete $paths->{$cpath} |
|
|
409 | unless %$cookies; |
|
|
410 | } |
|
|
411 | |
|
|
412 | delete $jar->{$chost} |
|
|
413 | unless %$paths; |
|
|
414 | } |
|
|
415 | } |
|
|
416 | |
|
|
417 | # extract cookies from jar |
|
|
418 | sub cookie_jar_extract($$$$) { |
|
|
419 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
420 | |
|
|
421 | $uhost = lc $uhost; |
|
|
422 | |
|
|
423 | %$jar = () if $jar->{version} != 1; |
|
|
424 | |
|
|
425 | my @cookies; |
|
|
426 | |
|
|
427 | while (my ($chost, $paths) = each %$jar) { |
|
|
428 | next unless ref $paths; |
|
|
429 | |
|
|
430 | if ($chost =~ /^\./) { |
|
|
431 | next unless $chost eq substr $uhost, -length $chost; |
|
|
432 | } elsif ($chost =~ /\./) { |
|
|
433 | next unless $chost eq $uhost; |
|
|
434 | } else { |
|
|
435 | next; |
|
|
436 | } |
|
|
437 | |
|
|
438 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
439 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
440 | |
|
|
441 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
442 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
443 | |
|
|
444 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
445 | delete $cookies->{$cookie}; |
|
|
446 | next; |
|
|
447 | } |
|
|
448 | |
|
|
449 | my $value = $kv->{value}; |
|
|
450 | |
|
|
451 | if ($value =~ /[=;,[:space:]]/) { |
|
|
452 | $value =~ s/([\\"])/\\$1/g; |
|
|
453 | $value = "\"$value\""; |
|
|
454 | } |
|
|
455 | |
|
|
456 | push @cookies, "$cookie=$value"; |
|
|
457 | } |
|
|
458 | } |
|
|
459 | } |
|
|
460 | |
|
|
461 | \@cookies |
|
|
462 | } |
|
|
463 | |
|
|
464 | # parse set_cookie header into jar |
|
|
465 | sub cookie_jar_set_cookie($$$$) { |
|
|
466 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
467 | |
|
|
468 | my $anow = int AE::now; |
|
|
469 | my $snow; # server-now |
|
|
470 | |
|
|
471 | for ($set_cookie) { |
|
|
472 | # parse NAME=VALUE |
|
|
473 | my @kv; |
|
|
474 | |
|
|
475 | # expires is not http-compliant in the original cookie-spec, |
|
|
476 | # we support the official date format and some extensions |
|
|
477 | while ( |
|
|
478 | m{ |
|
|
479 | \G\s* |
|
|
480 | (?: |
|
|
481 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
482 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
|
|
483 | ) |
|
|
484 | }gcxsi |
|
|
485 | ) { |
|
|
486 | my $name = $2; |
|
|
487 | my $value = $4; |
|
|
488 | |
|
|
489 | if (defined $1) { |
|
|
490 | # expires |
|
|
491 | $name = "expires"; |
|
|
492 | $value = $1; |
|
|
493 | } elsif (defined $3) { |
|
|
494 | # quoted |
|
|
495 | $value = $3; |
|
|
496 | $value =~ s/\\(.)/$1/gs; |
|
|
497 | } |
|
|
498 | |
|
|
499 | push @kv, lc $name, $value; |
|
|
500 | |
|
|
501 | last unless /\G\s*;/gc; |
|
|
502 | } |
|
|
503 | |
|
|
504 | last unless @kv; |
|
|
505 | |
|
|
506 | my $name = shift @kv; |
|
|
507 | my %kv = (value => shift @kv, @kv); |
|
|
508 | |
|
|
509 | if (exists $kv{"max-age"}) { |
|
|
510 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
511 | } elsif (exists $kv{expires}) { |
|
|
512 | $snow ||= parse_date ($date) || $anow; |
|
|
513 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
514 | } else { |
|
|
515 | delete $kv{_expires}; |
|
|
516 | } |
|
|
517 | |
|
|
518 | my $cdom; |
|
|
519 | my $cpath = (delete $kv{path}) || "/"; |
|
|
520 | |
|
|
521 | if (exists $kv{domain}) { |
|
|
522 | $cdom = delete $kv{domain}; |
|
|
523 | |
|
|
524 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
525 | |
|
|
526 | next if $cdom =~ /\.$/; |
|
|
527 | |
|
|
528 | # this is not rfc-like and not netscape-like. go figure. |
|
|
529 | my $ndots = $cdom =~ y/.//; |
|
|
530 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
531 | } else { |
|
|
532 | $cdom = $uhost; |
|
|
533 | } |
|
|
534 | |
|
|
535 | # store it |
|
|
536 | $jar->{version} = 1; |
|
|
537 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
|
|
538 | |
|
|
539 | redo if /\G\s*,/gc; |
|
|
540 | } |
|
|
541 | } |
|
|
542 | |
|
|
543 | # continue to parse $_ for headers and place them into the arg |
|
|
544 | sub parse_hdr() { |
|
|
545 | my %hdr; |
|
|
546 | |
|
|
547 | # things seen, not parsed: |
|
|
548 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
549 | |
|
|
550 | $hdr{lc $1} .= ",$2" |
|
|
551 | while /\G |
|
|
552 | ([^:\000-\037]*): |
|
|
553 | [\011\040]* |
|
|
554 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
555 | \012 |
|
|
556 | /gxc; |
|
|
557 | |
|
|
558 | /\G$/ |
|
|
559 | or return; |
|
|
560 | |
|
|
561 | # remove the "," prefix we added to all headers above |
|
|
562 | substr $_, 0, 1, "" |
|
|
563 | for values %hdr; |
|
|
564 | |
|
|
565 | \%hdr |
|
|
566 | } |
|
|
567 | |
332 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
568 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
333 | |
569 | |
334 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
570 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
335 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
571 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
336 | |
572 | |
… | |
… | |
349 | while (my ($k, $v) = each %$hdr) { |
585 | while (my ($k, $v) = each %$hdr) { |
350 | $hdr{lc $k} = $v; |
586 | $hdr{lc $k} = $v; |
351 | } |
587 | } |
352 | } |
588 | } |
353 | |
589 | |
|
|
590 | # pseudo headers for all subsequent responses |
|
|
591 | my @pseudo = (URL => $url); |
|
|
592 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
593 | |
354 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
594 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
355 | |
595 | |
356 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
596 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
357 | if $recurse < 0; |
597 | if $recurse < 0; |
358 | |
598 | |
359 | my $proxy = $arg{proxy} || $PROXY; |
599 | my $proxy = $arg{proxy} || $PROXY; |
360 | my $timeout = $arg{timeout} || $TIMEOUT; |
600 | my $timeout = $arg{timeout} || $TIMEOUT; |
361 | |
601 | |
362 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
602 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
363 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
603 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
364 | |
604 | |
365 | $uscheme = lc $uscheme; |
605 | $uscheme = lc $uscheme; |
366 | |
606 | |
367 | my $uport = $uscheme eq "http" ? 80 |
607 | my $uport = $uscheme eq "http" ? 80 |
368 | : $uscheme eq "https" ? 443 |
608 | : $uscheme eq "https" ? 443 |
369 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
609 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
370 | |
610 | |
371 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
611 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
372 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
612 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
373 | |
613 | |
374 | my $uhost = $1; |
614 | my $uhost = $1; |
375 | $uport = $2 if defined $2; |
615 | $uport = $2 if defined $2; |
376 | |
616 | |
377 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
617 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
378 | unless exists $hdr{host}; |
618 | unless exists $hdr{host}; |
379 | |
619 | |
380 | $uhost =~ s/^\[(.*)\]$/$1/; |
620 | $uhost =~ s/^\[(.*)\]$/$1/; |
381 | $upath .= "?$query" if length $query; |
621 | $upath .= $query if length $query; |
382 | |
622 | |
383 | $upath =~ s%^/?%/%; |
623 | $upath =~ s%^/?%/%; |
384 | |
624 | |
385 | # cookie processing |
625 | # cookie processing |
386 | if (my $jar = $arg{cookie_jar}) { |
626 | if (my $jar = $arg{cookie_jar}) { |
387 | %$jar = () if $jar->{version} != 1; |
627 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
388 | |
628 | |
389 | my @cookie; |
|
|
390 | |
|
|
391 | while (my ($chost, $v) = each %$jar) { |
|
|
392 | if ($chost =~ /^\./) { |
|
|
393 | next unless $chost eq substr $uhost, -length $chost; |
|
|
394 | } elsif ($chost =~ /\./) { |
|
|
395 | next unless $chost eq $uhost; |
|
|
396 | } else { |
|
|
397 | next; |
|
|
398 | } |
|
|
399 | |
|
|
400 | while (my ($cpath, $v) = each %$v) { |
|
|
401 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
402 | |
|
|
403 | while (my ($k, $v) = each %$v) { |
|
|
404 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
405 | my $value = $v->{value}; |
|
|
406 | $value =~ s/([\\"])/\\$1/g; |
|
|
407 | push @cookie, "$k=\"$value\""; |
|
|
408 | } |
|
|
409 | } |
|
|
410 | } |
|
|
411 | |
|
|
412 | $hdr{cookie} = join "; ", @cookie |
629 | $hdr{cookie} = join "; ", @$cookies |
413 | if @cookie; |
630 | if @$cookies; |
414 | } |
631 | } |
415 | |
632 | |
416 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
633 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
417 | |
634 | |
418 | if ($proxy) { |
635 | if ($proxy) { |
… | |
… | |
426 | } else { |
643 | } else { |
427 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
644 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
428 | } |
645 | } |
429 | |
646 | |
430 | # leave out fragment and query string, just a heuristic |
647 | # leave out fragment and query string, just a heuristic |
431 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
648 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
432 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
649 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
433 | |
650 | |
434 | $hdr{"content-length"} = length $arg{body} |
651 | $hdr{"content-length"} = length $arg{body} |
435 | if length $arg{body} || $method ne "GET"; |
652 | if length $arg{body} || $method ne "GET"; |
436 | |
653 | |
|
|
654 | $hdr{connection} = "close TE"; #1.1 |
|
|
655 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
|
|
656 | |
437 | my %state = (connect_guard => 1); |
657 | my %state = (connect_guard => 1); |
438 | |
658 | |
439 | _get_slot $uhost, sub { |
659 | _get_slot $uhost, sub { |
440 | $state{slot_guard} = shift; |
660 | $state{slot_guard} = shift; |
441 | |
661 | |
442 | return unless $state{connect_guard}; |
662 | return unless $state{connect_guard}; |
443 | |
663 | |
444 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
664 | my $ae_error = 595; # connecting |
|
|
665 | |
|
|
666 | # handle actual, non-tunneled, request |
|
|
667 | my $handle_actual_request = sub { |
|
|
668 | $ae_error = 596; # request phase |
|
|
669 | |
|
|
670 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
671 | |
|
|
672 | # send request |
|
|
673 | $state{handle}->push_write ( |
|
|
674 | "$method $rpath HTTP/1.1\015\012" |
|
|
675 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
676 | . "\015\012" |
|
|
677 | . (delete $arg{body}) |
|
|
678 | ); |
|
|
679 | |
|
|
680 | # return if error occured during push_write() |
|
|
681 | return unless %state; |
|
|
682 | |
|
|
683 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
684 | |
|
|
685 | # status line and headers |
|
|
686 | $state{read_response} = sub { |
|
|
687 | for ("$_[1]") { |
|
|
688 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
689 | |
|
|
690 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
691 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
692 | |
|
|
693 | # 100 Continue handling |
|
|
694 | # should not happen as we don't send expect: 100-continue, |
|
|
695 | # but we handle it just in case. |
|
|
696 | # since we send the request body regardless, if we get an error |
|
|
697 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
698 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
699 | if $2 eq 100; |
|
|
700 | |
|
|
701 | push @pseudo, |
|
|
702 | HTTPVersion => $1, |
|
|
703 | Status => $2, |
|
|
704 | Reason => $3, |
|
|
705 | ; |
|
|
706 | |
|
|
707 | my $hdr = parse_hdr |
|
|
708 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
709 | |
|
|
710 | %hdr = (%$hdr, @pseudo); |
|
|
711 | } |
|
|
712 | |
|
|
713 | # redirect handling |
|
|
714 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
715 | # try to support some common forms of broken Location headers. |
|
|
716 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
717 | $hdr{location} =~ s/^\.\/+//; |
|
|
718 | |
|
|
719 | my $url = "$rscheme://$uhost:$uport"; |
|
|
720 | |
|
|
721 | unless ($hdr{location} =~ s/^\///) { |
|
|
722 | $url .= $upath; |
|
|
723 | $url =~ s/\/[^\/]*$//; |
|
|
724 | } |
|
|
725 | |
|
|
726 | $hdr{location} = "$url/$hdr{location}"; |
|
|
727 | } |
|
|
728 | |
|
|
729 | my $redirect; |
|
|
730 | |
|
|
731 | if ($recurse) { |
|
|
732 | my $status = $hdr{Status}; |
|
|
733 | |
|
|
734 | # industry standard is to redirect POST as GET for |
|
|
735 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
736 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
737 | # industry standard seems to be to simply follow. |
|
|
738 | # we go with the industry standard. |
|
|
739 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
740 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
741 | $method = "GET" unless $method eq "HEAD"; |
|
|
742 | $redirect = 1; |
|
|
743 | } elsif ($status == 307) { |
|
|
744 | $redirect = 1; |
|
|
745 | } |
|
|
746 | } |
|
|
747 | |
|
|
748 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
749 | my $may_keep_alive = $_[3]; |
|
|
750 | |
|
|
751 | $state{handle}->destroy if $state{handle}; |
|
|
752 | %state = (); |
|
|
753 | |
|
|
754 | if (defined $_[1]) { |
|
|
755 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
756 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
757 | } |
|
|
758 | |
|
|
759 | # set-cookie processing |
|
|
760 | if ($arg{cookie_jar}) { |
|
|
761 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
|
|
762 | } |
|
|
763 | |
|
|
764 | if ($redirect && exists $hdr{location}) { |
|
|
765 | # we ignore any errors, as it is very common to receive |
|
|
766 | # Content-Length != 0 but no actual body |
|
|
767 | # we also access %hdr, as $_[1] might be an erro |
|
|
768 | http_request ( |
|
|
769 | $method => $hdr{location}, |
|
|
770 | %arg, |
|
|
771 | recurse => $recurse - 1, |
|
|
772 | Redirect => [$_[0], \%hdr], |
|
|
773 | $cb); |
|
|
774 | } else { |
|
|
775 | $cb->($_[0], \%hdr); |
|
|
776 | } |
|
|
777 | }; |
|
|
778 | |
|
|
779 | $ae_error = 597; # body phase |
|
|
780 | |
|
|
781 | my $len = $hdr{"content-length"}; |
|
|
782 | |
|
|
783 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
784 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
785 | } elsif ( |
|
|
786 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
787 | or $method eq "HEAD" |
|
|
788 | or (defined $len && !$len) |
|
|
789 | ) { |
|
|
790 | # no body |
|
|
791 | $finish->("", undef, undef, 1); |
|
|
792 | } else { |
|
|
793 | # body handling, many different code paths |
|
|
794 | # - no body expected |
|
|
795 | # - want_body_handle |
|
|
796 | # - te chunked |
|
|
797 | # - 2x length known (with or without on_body) |
|
|
798 | # - 2x length not known (with or without on_body) |
|
|
799 | if (!$redirect && $arg{want_body_handle}) { |
|
|
800 | $_[0]->on_eof (undef); |
|
|
801 | $_[0]->on_error (undef); |
|
|
802 | $_[0]->on_read (undef); |
|
|
803 | |
|
|
804 | $finish->(delete $state{handle}); |
|
|
805 | |
|
|
806 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
807 | my $cl = 0; |
|
|
808 | my $body = undef; |
|
|
809 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
810 | |
|
|
811 | $state{read_chunk} = sub { |
|
|
812 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
813 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
814 | |
|
|
815 | my $len = hex $1; |
|
|
816 | |
|
|
817 | if ($len) { |
|
|
818 | $cl += $len; |
|
|
819 | |
|
|
820 | $_[0]->push_read (chunk => $len, sub { |
|
|
821 | $on_body->($_[1], \%hdr) |
|
|
822 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
823 | |
|
|
824 | $_[0]->push_read (line => sub { |
|
|
825 | length $_[1] |
|
|
826 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
827 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
828 | }); |
|
|
829 | }); |
|
|
830 | } else { |
|
|
831 | $hdr{"content-length"} ||= $cl; |
|
|
832 | |
|
|
833 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
834 | if (length $_[1]) { |
|
|
835 | for ("$_[1]") { |
|
|
836 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
837 | |
|
|
838 | my $hdr = parse_hdr |
|
|
839 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
840 | |
|
|
841 | %hdr = (%hdr, %$hdr); |
|
|
842 | } |
|
|
843 | } |
|
|
844 | |
|
|
845 | $finish->($body, undef, undef, 1); |
|
|
846 | }); |
|
|
847 | } |
|
|
848 | }; |
|
|
849 | |
|
|
850 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
851 | |
|
|
852 | } elsif ($arg{on_body}) { |
|
|
853 | if ($len) { |
|
|
854 | $_[0]->on_read (sub { |
|
|
855 | $len -= length $_[0]{rbuf}; |
|
|
856 | |
|
|
857 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
858 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
859 | |
|
|
860 | $len > 0 |
|
|
861 | or $finish->("", undef, undef, 1); |
|
|
862 | }); |
|
|
863 | } else { |
|
|
864 | $_[0]->on_eof (sub { |
|
|
865 | $finish->(""); |
|
|
866 | }); |
|
|
867 | $_[0]->on_read (sub { |
|
|
868 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
869 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
870 | }); |
|
|
871 | } |
|
|
872 | } else { |
|
|
873 | $_[0]->on_eof (undef); |
|
|
874 | |
|
|
875 | if ($len) { |
|
|
876 | $_[0]->on_read (sub { |
|
|
877 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
878 | if $len <= length $_[0]{rbuf}; |
|
|
879 | }); |
|
|
880 | } else { |
|
|
881 | $_[0]->on_error (sub { |
|
|
882 | ($! == Errno::EPIPE || !$!) |
|
|
883 | ? $finish->(delete $_[0]{rbuf}) |
|
|
884 | : $finish->(undef, $ae_error => $_[2]); |
|
|
885 | }); |
|
|
886 | $_[0]->on_read (sub { }); |
|
|
887 | } |
|
|
888 | } |
|
|
889 | } |
|
|
890 | }; |
|
|
891 | |
|
|
892 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
893 | }; |
|
|
894 | |
|
|
895 | my $connect_cb = sub { |
445 | $state{fh} = shift |
896 | $state{fh} = shift |
446 | or do { |
897 | or do { |
447 | my $err = "$!"; |
898 | my $err = "$!"; |
448 | %state = (); |
899 | %state = (); |
449 | return $cb->(undef, { Status => 599, Reason => $err, URL => $url }); |
900 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
450 | }; |
901 | }; |
451 | |
|
|
452 | pop; # free memory, save a tree |
|
|
453 | |
902 | |
454 | return unless delete $state{connect_guard}; |
903 | return unless delete $state{connect_guard}; |
455 | |
904 | |
456 | # get handle |
905 | # get handle |
457 | $state{handle} = new AnyEvent::Handle |
906 | $state{handle} = new AnyEvent::Handle |
458 | fh => $state{fh}, |
907 | fh => $state{fh}, |
|
|
908 | peername => $rhost, |
|
|
909 | tls_ctx => $arg{tls_ctx}, |
|
|
910 | # these need to be reconfigured on keepalive handles |
459 | timeout => $timeout, |
911 | timeout => $timeout, |
460 | peername => $rhost, |
912 | on_error => sub { |
461 | tls_ctx => $arg{tls_ctx}; |
913 | %state = (); |
|
|
914 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
|
|
915 | }, |
|
|
916 | on_eof => sub { |
|
|
917 | %state = (); |
|
|
918 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
|
|
919 | }, |
|
|
920 | ; |
462 | |
921 | |
463 | # limit the number of persistent connections |
922 | # limit the number of persistent connections |
464 | # keepalive not yet supported |
923 | # keepalive not yet supported |
465 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
924 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
466 | ++$KA_COUNT{$_[1]}; |
925 | # ++$KA_COUNT{$_[1]}; |
467 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
926 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
468 | --$KA_COUNT{$_[1]} |
927 | # --$KA_COUNT{$_[1]} |
469 | }; |
928 | # }; |
470 | $hdr{connection} = "keep-alive"; |
929 | # $hdr{connection} = "keep-alive"; |
471 | } else { |
|
|
472 | delete $hdr{connection}; |
|
|
473 | } |
930 | # } |
474 | |
|
|
475 | # (re-)configure handle |
|
|
476 | $state{handle}->on_error (sub { |
|
|
477 | %state = (); |
|
|
478 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
479 | }); |
|
|
480 | $state{handle}->on_eof (sub { |
|
|
481 | %state = (); |
|
|
482 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
|
|
483 | }); |
|
|
484 | |
931 | |
485 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
932 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
486 | |
|
|
487 | # handle actual, non-tunneled, request |
|
|
488 | my $handle_actual_request = sub { |
|
|
489 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
490 | |
|
|
491 | # send request |
|
|
492 | $state{handle}->push_write ( |
|
|
493 | "$method $rpath HTTP/1.0\015\012" |
|
|
494 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
495 | . "\015\012" |
|
|
496 | . (delete $arg{body}) |
|
|
497 | ); |
|
|
498 | |
|
|
499 | # return if error occured during push_write() |
|
|
500 | return unless %state; |
|
|
501 | |
|
|
502 | %hdr = (); # reduce memory usage, save a kitten |
|
|
503 | |
|
|
504 | # status line |
|
|
505 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
506 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
507 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
508 | |
|
|
509 | my %hdr = ( # response headers |
|
|
510 | HTTPVersion => ",$1", |
|
|
511 | Status => ",$2", |
|
|
512 | Reason => ",$3", |
|
|
513 | URL => ",$url" |
|
|
514 | ); |
|
|
515 | |
|
|
516 | # headers, could be optimized a bit |
|
|
517 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
|
|
518 | for ("$_[1]") { |
|
|
519 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
520 | |
|
|
521 | # things seen, not parsed: |
|
|
522 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
523 | |
|
|
524 | $hdr{lc $1} .= ",$2" |
|
|
525 | while /\G |
|
|
526 | ([^:\000-\037]*): |
|
|
527 | [\011\040]* |
|
|
528 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
529 | \012 |
|
|
530 | /gxc; |
|
|
531 | |
|
|
532 | /\G$/ |
|
|
533 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
|
|
534 | } |
|
|
535 | |
|
|
536 | substr $_, 0, 1, "" |
|
|
537 | for values %hdr; |
|
|
538 | |
|
|
539 | # redirect handling |
|
|
540 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
541 | # try to support some common forms of broken Location headers. |
|
|
542 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
543 | $hdr{location} =~ s/^\.\/+//; |
|
|
544 | |
|
|
545 | my $url = "$rscheme://$uhost:$uport"; |
|
|
546 | |
|
|
547 | unless ($hdr{location} =~ s/^\///) { |
|
|
548 | $url .= $upath; |
|
|
549 | $url =~ s/\/[^\/]*$//; |
|
|
550 | } |
|
|
551 | |
|
|
552 | $hdr{location} = "$url/$hdr{location}"; |
|
|
553 | } |
|
|
554 | |
|
|
555 | my $redirect; |
|
|
556 | |
|
|
557 | if ($recurse) { |
|
|
558 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
|
|
559 | # apparently, mozilla et al. just change POST to GET here |
|
|
560 | # more research is needed before we do the same |
|
|
561 | $redirect = 1; |
|
|
562 | } elsif ($hdr{Status} == 303) { |
|
|
563 | # even http/1.1 is unclear on how to mutate the method |
|
|
564 | $method = "GET" unless $method eq "HEAD"; |
|
|
565 | $redirect = 1; |
|
|
566 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
|
|
567 | $redirect = 1; |
|
|
568 | } |
|
|
569 | } |
|
|
570 | |
|
|
571 | my $finish = sub { |
|
|
572 | $state{handle}->destroy if $state{handle}; |
|
|
573 | %state = (); |
|
|
574 | |
|
|
575 | # set-cookie processing |
|
|
576 | if ($arg{cookie_jar}) { |
|
|
577 | for ($_[1]{"set-cookie"}) { |
|
|
578 | # parse NAME=VALUE |
|
|
579 | my @kv; |
|
|
580 | |
|
|
581 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
582 | my $name = $1; |
|
|
583 | my $value = $3; |
|
|
584 | |
|
|
585 | unless ($value) { |
|
|
586 | $value = $2; |
|
|
587 | $value =~ s/\\(.)/$1/gs; |
|
|
588 | } |
|
|
589 | |
|
|
590 | push @kv, $name => $value; |
|
|
591 | |
|
|
592 | last unless /\G\s*;/gc; |
|
|
593 | } |
|
|
594 | |
|
|
595 | last unless @kv; |
|
|
596 | |
|
|
597 | my $name = shift @kv; |
|
|
598 | my %kv = (value => shift @kv, @kv); |
|
|
599 | |
|
|
600 | my $cdom; |
|
|
601 | my $cpath = (delete $kv{path}) || "/"; |
|
|
602 | |
|
|
603 | if (exists $kv{domain}) { |
|
|
604 | $cdom = delete $kv{domain}; |
|
|
605 | |
|
|
606 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
607 | |
|
|
608 | next if $cdom =~ /\.$/; |
|
|
609 | |
|
|
610 | # this is not rfc-like and not netscape-like. go figure. |
|
|
611 | my $ndots = $cdom =~ y/.//; |
|
|
612 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
613 | } else { |
|
|
614 | $cdom = $uhost; |
|
|
615 | } |
|
|
616 | |
|
|
617 | # store it |
|
|
618 | $arg{cookie_jar}{version} = 1; |
|
|
619 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
620 | |
|
|
621 | redo if /\G\s*,/gc; |
|
|
622 | } |
|
|
623 | } |
|
|
624 | |
|
|
625 | if ($redirect && exists $hdr{location}) { |
|
|
626 | # we ignore any errors, as it is very common to receive |
|
|
627 | # Content-Length != 0 but no actual body |
|
|
628 | # we also access %hdr, as $_[1] might be an erro |
|
|
629 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
630 | } else { |
|
|
631 | $cb->($_[0], $_[1]); |
|
|
632 | } |
|
|
633 | }; |
|
|
634 | |
|
|
635 | my $len = $hdr{"content-length"}; |
|
|
636 | |
|
|
637 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
638 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
|
|
639 | } elsif ( |
|
|
640 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
641 | or $method eq "HEAD" |
|
|
642 | or (defined $len && !$len) |
|
|
643 | ) { |
|
|
644 | # no body |
|
|
645 | $finish->("", \%hdr); |
|
|
646 | } else { |
|
|
647 | # body handling, four different code paths |
|
|
648 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
649 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
650 | if (!$redirect && $arg{want_body_handle}) { |
|
|
651 | $_[0]->on_eof (undef); |
|
|
652 | $_[0]->on_error (undef); |
|
|
653 | $_[0]->on_read (undef); |
|
|
654 | |
|
|
655 | $finish->(delete $state{handle}, \%hdr); |
|
|
656 | |
|
|
657 | } elsif ($arg{on_body}) { |
|
|
658 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
659 | if ($len) { |
|
|
660 | $_[0]->on_eof (undef); |
|
|
661 | $_[0]->on_read (sub { |
|
|
662 | $len -= length $_[0]{rbuf}; |
|
|
663 | |
|
|
664 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
665 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
666 | |
|
|
667 | $len > 0 |
|
|
668 | or $finish->("", \%hdr); |
|
|
669 | }); |
|
|
670 | } else { |
|
|
671 | $_[0]->on_eof (sub { |
|
|
672 | $finish->("", \%hdr); |
|
|
673 | }); |
|
|
674 | $_[0]->on_read (sub { |
|
|
675 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
676 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
677 | }); |
|
|
678 | } |
|
|
679 | } else { |
|
|
680 | $_[0]->on_eof (undef); |
|
|
681 | |
|
|
682 | if ($len) { |
|
|
683 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
684 | $_[0]->on_read (sub { |
|
|
685 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
686 | if $len <= length $_[0]{rbuf}; |
|
|
687 | }); |
|
|
688 | } else { |
|
|
689 | $_[0]->on_error (sub { |
|
|
690 | $! == Errno::EPIPE || !$! |
|
|
691 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
|
|
692 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
693 | }); |
|
|
694 | $_[0]->on_read (sub { }); |
|
|
695 | } |
|
|
696 | } |
|
|
697 | } |
|
|
698 | }); |
|
|
699 | }); |
|
|
700 | }; |
|
|
701 | |
933 | |
702 | # now handle proxy-CONNECT method |
934 | # now handle proxy-CONNECT method |
703 | if ($proxy && $uscheme eq "https") { |
935 | if ($proxy && $uscheme eq "https") { |
704 | # oh dear, we have to wrap it into a connect request |
936 | # oh dear, we have to wrap it into a connect request |
705 | |
937 | |
706 | # maybe re-use $uauthority with patched port? |
938 | # maybe re-use $uauthority with patched port? |
707 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
939 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
708 | $state{handle}->push_read (line => $qr_nlnl, sub { |
940 | $state{handle}->push_read (line => $qr_nlnl, sub { |
709 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
941 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
710 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
942 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
711 | |
943 | |
712 | if ($2 == 200) { |
944 | if ($2 == 200) { |
713 | $rpath = $upath; |
945 | $rpath = $upath; |
714 | &$handle_actual_request; |
946 | $handle_actual_request->(); |
715 | } else { |
947 | } else { |
716 | %state = (); |
948 | %state = (); |
717 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
949 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
718 | } |
950 | } |
719 | }); |
951 | }); |
720 | } else { |
952 | } else { |
721 | &$handle_actual_request; |
953 | $handle_actual_request->(); |
722 | } |
954 | } |
|
|
955 | }; |
723 | |
956 | |
724 | }, $arg{on_prepare} || sub { $timeout }; |
957 | my $tcp_connect = $arg{tcp_connect} |
|
|
958 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
959 | |
|
|
960 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
725 | }; |
961 | }; |
726 | |
962 | |
727 | defined wantarray && AnyEvent::Util::guard { %state = () } |
963 | defined wantarray && AnyEvent::Util::guard { %state = () } |
728 | } |
964 | } |
729 | |
965 | |
… | |
… | |
743 | &http_request |
979 | &http_request |
744 | } |
980 | } |
745 | |
981 | |
746 | =back |
982 | =back |
747 | |
983 | |
|
|
984 | =head2 DNS CACHING |
|
|
985 | |
|
|
986 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
987 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
988 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
989 | on its own. If you want DNS caching, you currently have to provide |
|
|
990 | your own default resolver (by storing a suitable resolver object in |
|
|
991 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
992 | |
748 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
993 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
749 | |
994 | |
750 | =over 4 |
995 | =over 4 |
751 | |
996 | |
752 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
997 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
… | |
… | |
755 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
1000 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
756 | otherwise. |
1001 | otherwise. |
757 | |
1002 | |
758 | To clear an already-set proxy, use C<undef>. |
1003 | To clear an already-set proxy, use C<undef>. |
759 | |
1004 | |
|
|
1005 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1006 | |
|
|
1007 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1008 | C<$session_end> is given and true, then additionally remove all session |
|
|
1009 | cookies. |
|
|
1010 | |
|
|
1011 | You should call this function (with a true C<$session_end>) before you |
|
|
1012 | save cookies to disk, and you should call this function after loading them |
|
|
1013 | again. If you have a long-running program you can additonally call this |
|
|
1014 | function from time to time. |
|
|
1015 | |
|
|
1016 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1017 | module. It's format is subject to change, but currently it is like this: |
|
|
1018 | |
|
|
1019 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1020 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1021 | hash-references. The key for these inner hash references is the |
|
|
1022 | server path for which this cookie is meant, and the values are again |
|
|
1023 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1024 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1025 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1026 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1027 | expiry timestamp. |
|
|
1028 | |
|
|
1029 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1030 | chance of understanding the above paragraph: |
|
|
1031 | |
|
|
1032 | { |
|
|
1033 | version => 1, |
|
|
1034 | "10.0.0.1" => { |
|
|
1035 | "/" => { |
|
|
1036 | "mythweb_id" => { |
|
|
1037 | _expires => 1293917923, |
|
|
1038 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1039 | }, |
|
|
1040 | }, |
|
|
1041 | }, |
|
|
1042 | } |
|
|
1043 | |
|
|
1044 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
1045 | |
|
|
1046 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
1047 | Date (RFC 2616). |
|
|
1048 | |
|
|
1049 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
1050 | |
|
|
1051 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1052 | bunch of minor variations of those, and returns the corresponding POSIX |
|
|
1053 | timestamp, or C<undef> if the date cannot be parsed. |
|
|
1054 | |
760 | =item $AnyEvent::HTTP::MAX_RECURSE |
1055 | =item $AnyEvent::HTTP::MAX_RECURSE |
761 | |
1056 | |
762 | The default value for the C<recurse> request parameter (default: C<10>). |
1057 | The default value for the C<recurse> request parameter (default: C<10>). |
763 | |
1058 | |
764 | =item $AnyEvent::HTTP::USERAGENT |
1059 | =item $AnyEvent::HTTP::USERAGENT |
… | |
… | |
782 | connections. This number of can be useful for load-leveling. |
1077 | connections. This number of can be useful for load-leveling. |
783 | |
1078 | |
784 | =back |
1079 | =back |
785 | |
1080 | |
786 | =cut |
1081 | =cut |
|
|
1082 | |
|
|
1083 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
1084 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
1085 | |
|
|
1086 | sub format_date($) { |
|
|
1087 | my ($time) = @_; |
|
|
1088 | |
|
|
1089 | # RFC 822/1123 format |
|
|
1090 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
1091 | |
|
|
1092 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
1093 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
1094 | $H, $M, $S; |
|
|
1095 | } |
|
|
1096 | |
|
|
1097 | sub parse_date($) { |
|
|
1098 | my ($date) = @_; |
|
|
1099 | |
|
|
1100 | my ($d, $m, $y, $H, $M, $S); |
|
|
1101 | |
|
|
1102 | if ($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$/) { |
|
|
1103 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1104 | # cookie dates (with "-") |
|
|
1105 | |
|
|
1106 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
1107 | |
|
|
1108 | } elsif ($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$/) { |
|
|
1109 | # RFC 850 |
|
|
1110 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
1111 | |
|
|
1112 | } elsif ($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])$/) { |
|
|
1113 | # ISO C's asctime |
|
|
1114 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
1115 | } |
|
|
1116 | # other formats fail in the loop below |
|
|
1117 | |
|
|
1118 | for (0..11) { |
|
|
1119 | if ($m eq $month[$_]) { |
|
|
1120 | require Time::Local; |
|
|
1121 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
1122 | } |
|
|
1123 | } |
|
|
1124 | |
|
|
1125 | undef |
|
|
1126 | } |
787 | |
1127 | |
788 | sub set_proxy($) { |
1128 | sub set_proxy($) { |
789 | if (length $_[0]) { |
1129 | if (length $_[0]) { |
790 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
1130 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
791 | or Carp::croak "$_[0]: invalid proxy URL"; |
1131 | or Carp::croak "$_[0]: invalid proxy URL"; |
… | |
… | |
798 | # initialise proxy from environment |
1138 | # initialise proxy from environment |
799 | eval { |
1139 | eval { |
800 | set_proxy $ENV{http_proxy}; |
1140 | set_proxy $ENV{http_proxy}; |
801 | }; |
1141 | }; |
802 | |
1142 | |
|
|
1143 | =head2 SOCKS PROXIES |
|
|
1144 | |
|
|
1145 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
1146 | compile your perl to support socks, or use an external program such as |
|
|
1147 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
1148 | transparently. |
|
|
1149 | |
|
|
1150 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
1151 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
1152 | that works with socks4a proxies: |
|
|
1153 | |
|
|
1154 | use Errno; |
|
|
1155 | use AnyEvent::Util; |
|
|
1156 | use AnyEvent::Socket; |
|
|
1157 | use AnyEvent::Handle; |
|
|
1158 | |
|
|
1159 | # host, port and username of/for your socks4a proxy |
|
|
1160 | my $socks_host = "10.0.0.23"; |
|
|
1161 | my $socks_port = 9050; |
|
|
1162 | my $socks_user = ""; |
|
|
1163 | |
|
|
1164 | sub socks4a_connect { |
|
|
1165 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
1166 | |
|
|
1167 | my $hdl = new AnyEvent::Handle |
|
|
1168 | connect => [$socks_host, $socks_port], |
|
|
1169 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
1170 | on_error => sub { $connect_cb->() }, |
|
|
1171 | ; |
|
|
1172 | |
|
|
1173 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1174 | |
|
|
1175 | $hdl->push_read (chunk => 8, sub { |
|
|
1176 | my ($hdl, $chunk) = @_; |
|
|
1177 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1178 | |
|
|
1179 | if ($status == 0x5a) { |
|
|
1180 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1181 | } else { |
|
|
1182 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1183 | } |
|
|
1184 | }); |
|
|
1185 | |
|
|
1186 | $hdl |
|
|
1187 | } |
|
|
1188 | |
|
|
1189 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1190 | possibly after switching off other proxy types: |
|
|
1191 | |
|
|
1192 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1193 | |
|
|
1194 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1195 | my ($data, $headers) = @_; |
|
|
1196 | ... |
|
|
1197 | }; |
|
|
1198 | |
803 | =head1 SEE ALSO |
1199 | =head1 SEE ALSO |
804 | |
1200 | |
805 | L<AnyEvent>. |
1201 | L<AnyEvent>. |
806 | |
1202 | |
807 | =head1 AUTHOR |
1203 | =head1 AUTHOR |