… | |
… | |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::HTTP; |
7 | use AnyEvent::HTTP; |
8 | |
8 | |
9 | http_get "http://www.nethype.de/", sub { print $_[1] }; |
9 | http_get "http://www.nethype.de/", sub { |
|
|
10 | my ($body, $hdr) = @_; |
|
|
11 | print "$hdr->{URL} Status: $hdr->{Status}\n"; |
|
|
12 | print $body; |
|
|
13 | }; |
10 | |
14 | |
11 | # ... do something else here |
15 | # ... do something else here |
12 | |
16 | |
13 | =head1 DESCRIPTION |
17 | =head1 DESCRIPTION |
14 | |
18 | |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
19 | This module is an L<AnyEvent> user, you need to make sure that you use and |
16 | run a supported event loop. |
20 | run a supported event loop. |
17 | |
21 | |
18 | This module implements a simple, stateless and non-blocking HTTP |
22 | This module implements a simple, stateless and non-blocking HTTP |
19 | client. It supports GET, POST and other request methods, cookies and more, |
23 | client. It supports GET, POST and other request methods, cookies and more, |
20 | all on a very low level. It can follow redirects supports proxies and |
24 | all on a very low level. It can follow redirects, supports proxies, and |
21 | automatically limits the number of connections to the values specified in |
25 | automatically limits the number of connections to the values specified in |
22 | the RFC. |
26 | the RFC. |
23 | |
27 | |
24 | It should generally be a "good client" that is enough for most HTTP |
28 | It should generally be a "good client" that is enough for most HTTP |
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
29 | tasks. Simple tasks should be simple, but complex tasks should still be |
… | |
… | |
46 | use AnyEvent::Util (); |
50 | use AnyEvent::Util (); |
47 | use AnyEvent::Handle (); |
51 | use AnyEvent::Handle (); |
48 | |
52 | |
49 | use base Exporter::; |
53 | use base Exporter::; |
50 | |
54 | |
51 | our $VERSION = '1.5'; |
55 | our $VERSION = 2.25; |
52 | |
56 | |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
57 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | |
58 | |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
59 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $MAX_RECURSE = 10; |
60 | our $MAX_RECURSE = 10; |
57 | our $MAX_PERSISTENT = 8; |
|
|
58 | our $PERSISTENT_TIMEOUT = 2; |
61 | our $PERSISTENT_TIMEOUT = 3; |
59 | our $TIMEOUT = 300; |
62 | our $TIMEOUT = 300; |
60 | |
63 | our $MAX_PER_HOST = 4; # changing this is evil |
61 | # changing these is evil |
|
|
62 | our $MAX_PERSISTENT_PER_HOST = 2; |
|
|
63 | our $MAX_PER_HOST = 4; |
|
|
64 | |
64 | |
65 | our $PROXY; |
65 | our $PROXY; |
66 | our $ACTIVE = 0; |
66 | our $ACTIVE = 0; |
67 | |
67 | |
68 | my %KA_COUNT; # number of open keep-alive connections per host |
68 | my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array |
69 | my %CO_SLOT; # number of open connections, and wait queue, per host |
69 | my %CO_SLOT; # number of open connections, and wait queue, per host |
70 | |
70 | |
71 | =item http_get $url, key => value..., $cb->($data, $headers) |
71 | =item http_get $url, key => value..., $cb->($data, $headers) |
72 | |
72 | |
73 | Executes an HTTP-GET request. See the http_request function for details on |
73 | Executes an HTTP-GET request. See the http_request function for details on |
… | |
… | |
93 | 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 |
94 | 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 |
95 | destroyed before the callback is called, the request will be cancelled. |
95 | destroyed before the callback is called, the request will be cancelled. |
96 | |
96 | |
97 | 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 |
98 | (or C<undef> if an error occured), and a hash-ref with response headers |
98 | (or C<undef> if an error occurred), and a hash-ref with response headers |
99 | (and trailers) as second argument. |
99 | (and trailers) as second argument. |
100 | |
100 | |
101 | 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 |
102 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
102 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
103 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
103 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
… | |
… | |
127 | C<590>-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 |
128 | message. Currently the following status codes are used: |
128 | message. Currently the following status codes are used: |
129 | |
129 | |
130 | =over 4 |
130 | =over 4 |
131 | |
131 | |
132 | =item 595 - errors during connection etsbalishment, proxy handshake. |
132 | =item 595 - errors during connection establishment, proxy handshake. |
133 | |
133 | |
134 | =item 596 - errors during TLS negotiation, request sending and header processing. |
134 | =item 596 - errors during TLS negotiation, request sending and header processing. |
135 | |
135 | |
136 | =item 597 - errors during body receiving or processing. |
136 | =item 597 - errors during body receiving or processing. |
137 | |
137 | |
… | |
… | |
158 | |
158 | |
159 | =over 4 |
159 | =over 4 |
160 | |
160 | |
161 | =item recurse => $count (default: $MAX_RECURSE) |
161 | =item recurse => $count (default: $MAX_RECURSE) |
162 | |
162 | |
163 | Whether to recurse requests or not, e.g. on redirects, authentication |
163 | Whether to recurse requests or not, e.g. on redirects, authentication and |
164 | retries and so on, and how often to do so. |
164 | other retries and so on, and how often to do so. |
|
|
165 | |
|
|
166 | Only redirects to http and https URLs are supported. While most common |
|
|
167 | redirection forms are handled entirely within this module, some require |
|
|
168 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
169 | the request will fail with an error. |
165 | |
170 | |
166 | =item headers => hashref |
171 | =item headers => hashref |
167 | |
172 | |
168 | The request headers to use. Currently, C<http_request> may provide its own |
173 | The request headers to use. Currently, C<http_request> may provide its own |
169 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
174 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
170 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
175 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
171 | (this can be suppressed by using C<undef> for these headers in which case |
176 | (this can be suppressed by using C<undef> for these headers in which case |
172 | they won't be sent at all). |
177 | they won't be sent at all). |
173 | |
178 | |
|
|
179 | You really should provide your own C<User-Agent:> header value that is |
|
|
180 | appropriate for your program - I wouldn't be surprised if the default |
|
|
181 | AnyEvent string gets blocked by webservers sooner or later. |
|
|
182 | |
|
|
183 | Also, make sure that your headers names and values do not contain any |
|
|
184 | embedded newlines. |
|
|
185 | |
174 | =item timeout => $seconds |
186 | =item timeout => $seconds |
175 | |
187 | |
176 | The time-out to use for various stages - each connect attempt will reset |
188 | The time-out to use for various stages - each connect attempt will reset |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
189 | the timeout, as will read or write activity, i.e. this is not an overall |
178 | timeout. |
190 | timeout. |
179 | |
191 | |
180 | Default timeout is 5 minutes. |
192 | Default timeout is 5 minutes. |
181 | |
193 | |
182 | =item proxy => [$host, $port[, $scheme]] or undef |
194 | =item proxy => [$host, $port[, $scheme]] or undef |
183 | |
195 | |
184 | Use the given http proxy for all requests. If not specified, then the |
196 | Use the given http proxy for all requests, or no proxy if C<undef> is |
185 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
197 | used. |
186 | |
198 | |
187 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
199 | C<$scheme> must be either missing or must be C<http> for HTTP. |
188 | HTTPS. |
200 | |
|
|
201 | If not specified, then the default proxy is used (see |
|
|
202 | C<AnyEvent::HTTP::set_proxy>). |
|
|
203 | |
|
|
204 | Currently, if your proxy requires authorization, you have to specify an |
|
|
205 | appropriate "Proxy-Authorization" header in every request. |
|
|
206 | |
|
|
207 | Note that this module will prefer an existing persistent connection, |
|
|
208 | even if that connection was made using another proxy. If you need to |
|
|
209 | ensure that a new connection is made in this case, you can either force |
|
|
210 | C<persistent> to false or e.g. use the proxy address in your C<sessionid>. |
189 | |
211 | |
190 | =item body => $string |
212 | =item body => $string |
191 | |
213 | |
192 | The request body, usually empty. Will be sent as-is (future versions of |
214 | The request body, usually empty. Will be sent as-is (future versions of |
193 | this module might offer more options). |
215 | this module might offer more options). |
… | |
… | |
224 | verification) TLS context. |
246 | verification) TLS context. |
225 | |
247 | |
226 | The default for this option is C<low>, which could be interpreted as "give |
248 | The default for this option is C<low>, which could be interpreted as "give |
227 | me the page, no matter what". |
249 | me the page, no matter what". |
228 | |
250 | |
|
|
251 | See also the C<sessionid> parameter. |
|
|
252 | |
|
|
253 | =item sessionid => $string |
|
|
254 | |
|
|
255 | The module might reuse connections to the same host internally (regardless |
|
|
256 | of other settings, such as C<tcp_connect> or C<proxy>). Sometimes (e.g. |
|
|
257 | when using TLS or a specfic proxy), you do not want to reuse connections |
|
|
258 | from other sessions. This can be achieved by setting this parameter to |
|
|
259 | some unique ID (such as the address of an object storing your state data |
|
|
260 | or the TLS context, or the proxy IP) - only connections using the same |
|
|
261 | unique ID will be reused. |
|
|
262 | |
229 | =item on_prepare => $callback->($fh) |
263 | =item on_prepare => $callback->($fh) |
230 | |
264 | |
231 | In rare cases you need to "tune" the socket before it is used to |
265 | In rare cases you need to "tune" the socket before it is used to |
232 | connect (for exmaple, to bind it on a given IP address). This parameter |
266 | connect (for example, to bind it on a given IP address). This parameter |
233 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
267 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
234 | and behaves exactly the same way (e.g. it has to provide a |
268 | and behaves exactly the same way (e.g. it has to provide a |
235 | timeout). See the description for the C<$prepare_cb> argument of |
269 | timeout). See the description for the C<$prepare_cb> argument of |
236 | C<AnyEvent::Socket::tcp_connect> for details. |
270 | C<AnyEvent::Socket::tcp_connect> for details. |
237 | |
271 | |
… | |
… | |
240 | In even rarer cases you want total control over how AnyEvent::HTTP |
274 | In even rarer cases you want total control over how AnyEvent::HTTP |
241 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
275 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
242 | to do this, but you can provide your own C<tcp_connect> function - |
276 | to do this, but you can provide your own C<tcp_connect> function - |
243 | obviously, it has to follow the same calling conventions, except that it |
277 | obviously, it has to follow the same calling conventions, except that it |
244 | may always return a connection guard object. |
278 | may always return a connection guard object. |
|
|
279 | |
|
|
280 | The connections made by this hook will be treated as equivalent to |
|
|
281 | connections made the built-in way, specifically, they will be put into |
|
|
282 | and taken from the persistent connection cache. If your C<$tcp_connect> |
|
|
283 | function is incompatible with this kind of re-use, consider switching off |
|
|
284 | C<persistent> connections and/or providing a C<sessionid> identifier. |
245 | |
285 | |
246 | There are probably lots of weird uses for this function, starting from |
286 | There are probably lots of weird uses for this function, starting from |
247 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
287 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
248 | but fast) host => IP address caching or even socks protocol support. |
288 | but fast) host => IP address caching or even socks protocol support. |
249 | |
289 | |
… | |
… | |
302 | called. Instead of the C<$body> argument containing the body data, the |
342 | called. Instead of the C<$body> argument containing the body data, the |
303 | callback will receive the L<AnyEvent::Handle> object associated with the |
343 | callback will receive the L<AnyEvent::Handle> object associated with the |
304 | connection. In error cases, C<undef> will be passed. When there is no body |
344 | connection. In error cases, C<undef> will be passed. When there is no body |
305 | (e.g. status C<304>), the empty string will be passed. |
345 | (e.g. status C<304>), the empty string will be passed. |
306 | |
346 | |
307 | The handle object might or might not be in TLS mode, might be connected to |
347 | The handle object might or might not be in TLS mode, might be connected |
308 | a proxy, be a persistent connection etc., and configured in unspecified |
348 | to a proxy, be a persistent connection, use chunked transfer encoding |
309 | ways. The user is responsible for this handle (it will not be used by this |
349 | etc., and configured in unspecified ways. The user is responsible for this |
310 | module anymore). |
350 | handle (it will not be used by this module anymore). |
311 | |
351 | |
312 | This is useful with some push-type services, where, after the initial |
352 | This is useful with some push-type services, where, after the initial |
313 | headers, an interactive protocol is used (typical example would be the |
353 | headers, an interactive protocol is used (typical example would be the |
314 | push-style twitter API which starts a JSON/XML stream). |
354 | push-style twitter API which starts a JSON/XML stream). |
315 | |
355 | |
316 | If you think you need this, first have a look at C<on_body>, to see if |
356 | If you think you need this, first have a look at C<on_body>, to see if |
317 | that doesn't solve your problem in a better way. |
357 | that doesn't solve your problem in a better way. |
|
|
358 | |
|
|
359 | =item persistent => $boolean |
|
|
360 | |
|
|
361 | Try to create/reuse a persistent connection. When this flag is set |
|
|
362 | (default: true for idempotent requests, false for all others), then |
|
|
363 | C<http_request> tries to re-use an existing (previously-created) |
|
|
364 | persistent connection to same host (i.e. identical URL scheme, hostname, |
|
|
365 | port and sessionid) and, failing that, tries to create a new one. |
|
|
366 | |
|
|
367 | Requests failing in certain ways will be automatically retried once, which |
|
|
368 | is dangerous for non-idempotent requests, which is why it defaults to off |
|
|
369 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
|
|
370 | made it impossible to distinguish between a fatal error and a normal |
|
|
371 | connection timeout, so you never know whether there was a problem with |
|
|
372 | your request or not. |
|
|
373 | |
|
|
374 | When reusing an existent connection, many parameters (such as TLS context) |
|
|
375 | will be ignored. See the C<sessionid> parameter for a workaround. |
|
|
376 | |
|
|
377 | =item keepalive => $boolean |
|
|
378 | |
|
|
379 | Only used when C<persistent> is also true. This parameter decides whether |
|
|
380 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
|
|
381 | (as opposed to only a HTTP/1.1 persistent connection). |
|
|
382 | |
|
|
383 | The default is true, except when using a proxy, in which case it defaults |
|
|
384 | to false, as HTTP/1.0 proxies cannot support this in a meaningful way. |
|
|
385 | |
|
|
386 | =item handle_params => { key => value ... } |
|
|
387 | |
|
|
388 | The key-value pairs in this hash will be passed to any L<AnyEvent::Handle> |
|
|
389 | constructor that is called - not all requests will create a handle, and |
|
|
390 | sometimes more than one is created, so this parameter is only good for |
|
|
391 | setting hints. |
|
|
392 | |
|
|
393 | Example: set the maximum read size to 4096, to potentially conserve memory |
|
|
394 | at the cost of speed. |
|
|
395 | |
|
|
396 | handle_params => { |
|
|
397 | max_read_size => 4096, |
|
|
398 | }, |
318 | |
399 | |
319 | =back |
400 | =back |
320 | |
401 | |
321 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
402 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
322 | the response body. |
403 | the response body. |
… | |
… | |
328 | |
409 | |
329 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
410 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
330 | timeout of 30 seconds. |
411 | timeout of 30 seconds. |
331 | |
412 | |
332 | http_request |
413 | http_request |
333 | GET => "https://www.google.com", |
414 | HEAD => "https://www.google.com", |
|
|
415 | headers => { "user-agent" => "MySearchClient 1.0" }, |
334 | timeout => 30, |
416 | timeout => 30, |
335 | sub { |
417 | sub { |
336 | my ($body, $hdr) = @_; |
418 | my ($body, $hdr) = @_; |
337 | use Data::Dumper; |
419 | use Data::Dumper; |
338 | print Dumper $hdr; |
420 | print Dumper $hdr; |
… | |
… | |
348 | }; |
430 | }; |
349 | |
431 | |
350 | undef $request; |
432 | undef $request; |
351 | |
433 | |
352 | =cut |
434 | =cut |
|
|
435 | |
|
|
436 | ############################################################################# |
|
|
437 | # wait queue/slots |
353 | |
438 | |
354 | sub _slot_schedule; |
439 | sub _slot_schedule; |
355 | sub _slot_schedule($) { |
440 | sub _slot_schedule($) { |
356 | my $host = shift; |
441 | my $host = shift; |
357 | |
442 | |
… | |
… | |
380 | |
465 | |
381 | _slot_schedule $_[0]; |
466 | _slot_schedule $_[0]; |
382 | } |
467 | } |
383 | |
468 | |
384 | ############################################################################# |
469 | ############################################################################# |
|
|
470 | # cookie handling |
385 | |
471 | |
386 | # expire cookies |
472 | # expire cookies |
387 | sub cookie_jar_expire($;$) { |
473 | sub cookie_jar_expire($;$) { |
388 | my ($jar, $session_end) = @_; |
474 | my ($jar, $session_end) = @_; |
389 | |
475 | |
390 | %$jar = () if $jar->{version} != 1; |
476 | %$jar = () if $jar->{version} != 2; |
391 | |
477 | |
392 | my $anow = AE::now; |
478 | my $anow = AE::now; |
393 | |
479 | |
394 | while (my ($chost, $paths) = each %$jar) { |
480 | while (my ($chost, $paths) = each %$jar) { |
395 | next unless ref $paths; |
481 | next unless ref $paths; |
… | |
… | |
413 | } |
499 | } |
414 | } |
500 | } |
415 | |
501 | |
416 | # extract cookies from jar |
502 | # extract cookies from jar |
417 | sub cookie_jar_extract($$$$) { |
503 | sub cookie_jar_extract($$$$) { |
418 | my ($jar, $uscheme, $uhost, $upath) = @_; |
504 | my ($jar, $scheme, $host, $path) = @_; |
419 | |
505 | |
420 | %$jar = () if $jar->{version} != 1; |
506 | %$jar = () if $jar->{version} != 2; |
|
|
507 | |
|
|
508 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
509 | if $host =~ /[^\x00-\x7f]/; |
421 | |
510 | |
422 | my @cookies; |
511 | my @cookies; |
423 | |
512 | |
424 | while (my ($chost, $paths) = each %$jar) { |
513 | while (my ($chost, $paths) = each %$jar) { |
425 | next unless ref $paths; |
514 | next unless ref $paths; |
426 | |
515 | |
427 | if ($chost =~ /^\./) { |
516 | # exact match or suffix including . match |
428 | next unless $chost eq substr $uhost, -length $chost; |
517 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
429 | } elsif ($chost =~ /\./) { |
|
|
430 | next unless $chost eq $uhost; |
|
|
431 | } else { |
|
|
432 | next; |
518 | or next; |
433 | } |
|
|
434 | |
519 | |
435 | while (my ($cpath, $cookies) = each %$paths) { |
520 | while (my ($cpath, $cookies) = each %$paths) { |
436 | next unless $cpath eq substr $upath, 0, length $cpath; |
521 | next unless $cpath eq substr $path, 0, length $cpath; |
437 | |
522 | |
438 | while (my ($cookie, $kv) = each %$cookies) { |
523 | while (my ($cookie, $kv) = each %$cookies) { |
439 | next if $uscheme ne "https" && exists $kv->{secure}; |
524 | next if $scheme ne "https" && exists $kv->{secure}; |
440 | |
525 | |
441 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
526 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
442 | delete $cookies->{$cookie}; |
527 | delete $cookies->{$cookie}; |
443 | next; |
528 | next; |
444 | } |
529 | } |
… | |
… | |
458 | \@cookies |
543 | \@cookies |
459 | } |
544 | } |
460 | |
545 | |
461 | # parse set_cookie header into jar |
546 | # parse set_cookie header into jar |
462 | sub cookie_jar_set_cookie($$$$) { |
547 | sub cookie_jar_set_cookie($$$$) { |
463 | my ($jar, $set_cookie, $uhost, $date) = @_; |
548 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
549 | |
|
|
550 | %$jar = () if $jar->{version} != 2; |
464 | |
551 | |
465 | my $anow = int AE::now; |
552 | my $anow = int AE::now; |
466 | my $snow; # server-now |
553 | my $snow; # server-now |
467 | |
554 | |
468 | for ($set_cookie) { |
555 | for ($set_cookie) { |
… | |
… | |
474 | while ( |
561 | while ( |
475 | m{ |
562 | m{ |
476 | \G\s* |
563 | \G\s* |
477 | (?: |
564 | (?: |
478 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
565 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
479 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
566 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )? |
480 | ) |
567 | ) |
481 | }gcxsi |
568 | }gcxsi |
482 | ) { |
569 | ) { |
483 | my $name = $2; |
570 | my $name = $2; |
484 | my $value = $4; |
571 | my $value = $4; |
… | |
… | |
491 | # quoted |
578 | # quoted |
492 | $value = $3; |
579 | $value = $3; |
493 | $value =~ s/\\(.)/$1/gs; |
580 | $value =~ s/\\(.)/$1/gs; |
494 | } |
581 | } |
495 | |
582 | |
496 | push @kv, lc $name, $value; |
583 | push @kv, @kv ? lc $name : $name, $value; |
497 | |
584 | |
498 | last unless /\G\s*;/gc; |
585 | last unless /\G\s*;/gc; |
499 | } |
586 | } |
500 | |
587 | |
501 | last unless @kv; |
588 | last unless @kv; |
… | |
… | |
514 | |
601 | |
515 | my $cdom; |
602 | my $cdom; |
516 | my $cpath = (delete $kv{path}) || "/"; |
603 | my $cpath = (delete $kv{path}) || "/"; |
517 | |
604 | |
518 | if (exists $kv{domain}) { |
605 | if (exists $kv{domain}) { |
519 | $cdom = delete $kv{domain}; |
606 | $cdom = $kv{domain}; |
520 | |
607 | |
521 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
608 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
522 | |
609 | |
523 | next if $cdom =~ /\.$/; |
610 | next if $cdom =~ /\.$/; |
524 | |
611 | |
525 | # this is not rfc-like and not netscape-like. go figure. |
612 | # this is not rfc-like and not netscape-like. go figure. |
526 | my $ndots = $cdom =~ y/.//; |
613 | my $ndots = $cdom =~ y/.//; |
527 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
614 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
615 | |
|
|
616 | $cdom = substr $cdom, 1; # remove initial . |
528 | } else { |
617 | } else { |
529 | $cdom = $uhost; |
618 | $cdom = $host; |
530 | } |
619 | } |
531 | |
620 | |
532 | # store it |
621 | # store it |
533 | $jar->{version} = 1; |
622 | $jar->{version} = 2; |
534 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
623 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
535 | |
624 | |
536 | redo if /\G\s*,/gc; |
625 | redo if /\G\s*,/gc; |
537 | } |
626 | } |
538 | } |
627 | } |
539 | |
628 | |
|
|
629 | ############################################################################# |
|
|
630 | # keepalive/persistent connection cache |
|
|
631 | |
|
|
632 | # fetch a connection from the keepalive cache |
|
|
633 | sub ka_fetch($) { |
|
|
634 | my $ka_key = shift; |
|
|
635 | |
|
|
636 | my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection |
|
|
637 | delete $KA_CACHE{$ka_key} |
|
|
638 | unless @{ $KA_CACHE{$ka_key} }; |
|
|
639 | |
|
|
640 | $hdl |
|
|
641 | } |
|
|
642 | |
|
|
643 | sub ka_store($$) { |
|
|
644 | my ($ka_key, $hdl) = @_; |
|
|
645 | |
|
|
646 | my $kaa = $KA_CACHE{$ka_key} ||= []; |
|
|
647 | |
|
|
648 | my $destroy = sub { |
|
|
649 | my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} }; |
|
|
650 | |
|
|
651 | $hdl->destroy; |
|
|
652 | |
|
|
653 | @ka |
|
|
654 | ? $KA_CACHE{$ka_key} = \@ka |
|
|
655 | : delete $KA_CACHE{$ka_key}; |
|
|
656 | }; |
|
|
657 | |
|
|
658 | # on error etc., destroy |
|
|
659 | $hdl->on_error ($destroy); |
|
|
660 | $hdl->on_eof ($destroy); |
|
|
661 | $hdl->on_read ($destroy); |
|
|
662 | $hdl->timeout ($PERSISTENT_TIMEOUT); |
|
|
663 | |
|
|
664 | push @$kaa, $hdl; |
|
|
665 | shift @$kaa while @$kaa > $MAX_PER_HOST; |
|
|
666 | } |
|
|
667 | |
|
|
668 | ############################################################################# |
|
|
669 | # utilities |
|
|
670 | |
540 | # continue to parse $_ for headers and place them into the arg |
671 | # continue to parse $_ for headers and place them into the arg |
541 | sub parse_hdr() { |
672 | sub _parse_hdr() { |
542 | my %hdr; |
673 | my %hdr; |
543 | |
674 | |
544 | # things seen, not parsed: |
675 | # things seen, not parsed: |
545 | # p3pP="NON CUR OTPi OUR NOR UNI" |
676 | # p3pP="NON CUR OTPi OUR NOR UNI" |
546 | |
677 | |
… | |
… | |
560 | for values %hdr; |
691 | for values %hdr; |
561 | |
692 | |
562 | \%hdr |
693 | \%hdr |
563 | } |
694 | } |
564 | |
695 | |
|
|
696 | ############################################################################# |
|
|
697 | # http_get |
|
|
698 | |
565 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
699 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
566 | |
700 | |
567 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
701 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
568 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
702 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
703 | |
|
|
704 | # maybe it should just become a normal object :/ |
|
|
705 | |
|
|
706 | sub _destroy_state(\%) { |
|
|
707 | my ($state) = @_; |
|
|
708 | |
|
|
709 | $state->{handle}->destroy if $state->{handle}; |
|
|
710 | %$state = (); |
|
|
711 | } |
|
|
712 | |
|
|
713 | sub _error(\%$$) { |
|
|
714 | my ($state, $cb, $hdr) = @_; |
|
|
715 | |
|
|
716 | &_destroy_state ($state); |
|
|
717 | |
|
|
718 | $cb->(undef, $hdr); |
|
|
719 | () |
|
|
720 | } |
|
|
721 | |
|
|
722 | our %IDEMPOTENT = ( |
|
|
723 | DELETE => 1, |
|
|
724 | GET => 1, |
|
|
725 | QUERY => 1, |
|
|
726 | HEAD => 1, |
|
|
727 | OPTIONS => 1, |
|
|
728 | PUT => 1, |
|
|
729 | TRACE => 1, |
|
|
730 | |
|
|
731 | ACL => 1, |
|
|
732 | "BASELINE-CONTROL" => 1, |
|
|
733 | BIND => 1, |
|
|
734 | CHECKIN => 1, |
|
|
735 | CHECKOUT => 1, |
|
|
736 | COPY => 1, |
|
|
737 | LABEL => 1, |
|
|
738 | LINK => 1, |
|
|
739 | MERGE => 1, |
|
|
740 | MKACTIVITY => 1, |
|
|
741 | MKCALENDAR => 1, |
|
|
742 | MKCOL => 1, |
|
|
743 | MKREDIRECTREF => 1, |
|
|
744 | MKWORKSPACE => 1, |
|
|
745 | MOVE => 1, |
|
|
746 | ORDERPATCH => 1, |
|
|
747 | PRI => 1, |
|
|
748 | PROPFIND => 1, |
|
|
749 | PROPPATCH => 1, |
|
|
750 | REBIND => 1, |
|
|
751 | REPORT => 1, |
|
|
752 | SEARCH => 1, |
|
|
753 | UNBIND => 1, |
|
|
754 | UNCHECKOUT => 1, |
|
|
755 | UNLINK => 1, |
|
|
756 | UNLOCK => 1, |
|
|
757 | UPDATE => 1, |
|
|
758 | UPDATEREDIRECTREF => 1, |
|
|
759 | "VERSION-CONTROL" => 1, |
|
|
760 | ); |
569 | |
761 | |
570 | sub http_request($$@) { |
762 | sub http_request($$@) { |
571 | my $cb = pop; |
763 | my $cb = pop; |
572 | my ($method, $url, %arg) = @_; |
764 | my ($method, $url, %arg) = @_; |
573 | |
765 | |
… | |
… | |
591 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
783 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
592 | |
784 | |
593 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
785 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
594 | if $recurse < 0; |
786 | if $recurse < 0; |
595 | |
787 | |
596 | my $proxy = $arg{proxy} || $PROXY; |
788 | my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY; |
597 | my $timeout = $arg{timeout} || $TIMEOUT; |
789 | my $timeout = $arg{timeout} || $TIMEOUT; |
598 | |
790 | |
599 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
791 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
600 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
792 | $url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
601 | |
793 | |
602 | $uscheme = lc $uscheme; |
794 | $uscheme = lc $uscheme; |
603 | |
795 | |
604 | my $uport = $uscheme eq "http" ? 80 |
796 | my $uport = $uscheme eq "http" ? 80 |
605 | : $uscheme eq "https" ? 443 |
797 | : $uscheme eq "https" ? 443 |
606 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
798 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
607 | |
799 | |
608 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
800 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
609 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
801 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
610 | |
802 | |
611 | my $uhost = lc $1; |
803 | my $uhost = lc $1; |
612 | $uport = $2 if defined $2; |
804 | $uport = $2 if defined $2; |
613 | |
805 | |
… | |
… | |
649 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
841 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
650 | |
842 | |
651 | $hdr{"content-length"} = length $arg{body} |
843 | $hdr{"content-length"} = length $arg{body} |
652 | if length $arg{body} || $method ne "GET"; |
844 | if length $arg{body} || $method ne "GET"; |
653 | |
845 | |
654 | $hdr{connection} = "close Te"; #1.1 |
846 | my $idempotent = $IDEMPOTENT{$method}; |
|
|
847 | |
|
|
848 | # default value for keepalive is true iff the request is for an idempotent method |
|
|
849 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
|
|
850 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
|
|
851 | my $was_persistent; # true if this is actually a recycled connection |
|
|
852 | |
|
|
853 | # the key to use in the keepalive cache |
|
|
854 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
|
|
855 | |
|
|
856 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
655 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
857 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
656 | |
858 | |
657 | my %state = (connect_guard => 1); |
859 | my %state = (connect_guard => 1); |
658 | |
860 | |
659 | my $ae_error = 595; # connecting |
861 | my $ae_error = 595; # connecting |
660 | |
862 | |
661 | # handle actual, non-tunneled, request |
863 | # handle actual, non-tunneled, request |
662 | my $handle_actual_request = sub { |
864 | my $handle_actual_request = sub { |
663 | $ae_error = 596; # request phase |
865 | $ae_error = 596; # request phase |
664 | |
866 | |
|
|
867 | my $hdl = $state{handle}; |
|
|
868 | |
665 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
869 | $hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls}; |
666 | |
870 | |
667 | # send request |
871 | # send request |
668 | $state{handle}->push_write ( |
872 | $hdl->push_write ( |
669 | "$method $rpath HTTP/1.1\015\012" |
873 | "$method $rpath HTTP/1.1\015\012" |
670 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
874 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
671 | . "\015\012" |
875 | . "\015\012" |
672 | . (delete $arg{body}) |
876 | . $arg{body} |
673 | ); |
877 | ); |
674 | |
878 | |
675 | # return if error occured during push_write() |
879 | # return if error occurred during push_write() |
676 | return unless %state; |
880 | return unless %state; |
677 | |
881 | |
678 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
882 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
|
|
883 | %hdr = (); |
679 | |
884 | |
680 | # status line and headers |
885 | # status line and headers |
681 | $state{read_response} = sub { |
886 | $state{read_response} = sub { |
|
|
887 | return unless %state; |
|
|
888 | |
682 | for ("$_[1]") { |
889 | for ("$_[1]") { |
683 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
890 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
684 | |
891 | |
685 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
892 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
686 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
893 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" }; |
687 | |
894 | |
688 | # 100 Continue handling |
895 | # 100 Continue handling |
689 | # should not happen as we don't send expect: 100-continue, |
896 | # should not happen as we don't send expect: 100-continue, |
690 | # but we handle it just in case. |
897 | # but we handle it just in case. |
691 | # since we send the request body regardless, if we get an error |
898 | # since we send the request body regardless, if we get an error |
… | |
… | |
697 | HTTPVersion => $1, |
904 | HTTPVersion => $1, |
698 | Status => $2, |
905 | Status => $2, |
699 | Reason => $3, |
906 | Reason => $3, |
700 | ; |
907 | ; |
701 | |
908 | |
702 | my $hdr = parse_hdr |
909 | my $hdr = _parse_hdr |
703 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
910 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" }; |
704 | |
911 | |
705 | %hdr = (%$hdr, @pseudo); |
912 | %hdr = (%$hdr, @pseudo); |
706 | } |
913 | } |
707 | |
914 | |
708 | # redirect handling |
915 | # redirect handling |
709 | # microsoft and other shitheads don't give a shit for following standards, |
916 | # relative uri handling forced by microsoft and other shitheads. |
710 | # try to support some common forms of broken Location headers. |
917 | # we give our best and fall back to URI if available. |
711 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
918 | if (exists $hdr{location}) { |
|
|
919 | my $loc = $hdr{location}; |
|
|
920 | |
|
|
921 | if ($loc =~ m%^//%) { # // |
|
|
922 | $loc = "$uscheme:$loc"; |
|
|
923 | |
|
|
924 | } elsif ($loc eq "") { |
|
|
925 | $loc = $url; |
|
|
926 | |
|
|
927 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
712 | $hdr{location} =~ s/^\.\/+//; |
928 | $loc =~ s/^\.\/+//; |
713 | |
929 | |
714 | my $url = "$rscheme://$uhost:$uport"; |
930 | if ($loc !~ m%^[.?#]%) { |
|
|
931 | my $prefix = "$uscheme://$uauthority"; |
715 | |
932 | |
716 | unless ($hdr{location} =~ s/^\///) { |
933 | unless ($loc =~ s/^\///) { |
717 | $url .= $upath; |
934 | $prefix .= $upath; |
718 | $url =~ s/\/[^\/]*$//; |
935 | $prefix =~ s/\/[^\/]*$//; |
|
|
936 | } |
|
|
937 | |
|
|
938 | $loc = "$prefix/$loc"; |
|
|
939 | |
|
|
940 | } elsif (eval { require URI }) { # uri |
|
|
941 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
942 | |
|
|
943 | } else { |
|
|
944 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
945 | #$hdr{Status} = 599; |
|
|
946 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
947 | #$recurse = 0; |
|
|
948 | } |
719 | } |
949 | } |
720 | |
950 | |
721 | $hdr{location} = "$url/$hdr{location}"; |
951 | $hdr{location} = $loc; |
722 | } |
952 | } |
723 | |
953 | |
724 | my $redirect; |
954 | my $redirect; |
725 | |
955 | |
726 | if ($recurse) { |
956 | if ($recurse) { |
… | |
… | |
728 | |
958 | |
729 | # industry standard is to redirect POST as GET for |
959 | # industry standard is to redirect POST as GET for |
730 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
960 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
731 | # also, the UA should ask the user for 301 and 307 and POST, |
961 | # also, the UA should ask the user for 301 and 307 and POST, |
732 | # industry standard seems to be to simply follow. |
962 | # industry standard seems to be to simply follow. |
733 | # we go with the industry standard. |
963 | # we go with the industry standard. 308 is defined |
|
|
964 | # by rfc7538 |
734 | if ($status == 301 or $status == 302 or $status == 303) { |
965 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
966 | $redirect = 1; |
735 | # HTTP/1.1 is unclear on how to mutate the method |
967 | # HTTP/1.1 is unclear on how to mutate the method |
736 | $method = "GET" unless $method eq "HEAD"; |
968 | unless ($method eq "HEAD") { |
737 | $redirect = 1; |
969 | $method = "GET"; |
|
|
970 | delete $arg{body}; |
|
|
971 | } |
738 | } elsif ($status == 307) { |
972 | } elsif ($status == 307 or $status == 308) { |
739 | $redirect = 1; |
973 | $redirect = 1; |
740 | } |
974 | } |
741 | } |
975 | } |
742 | |
976 | |
743 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
977 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
744 | my $may_keep_alive = $_[3]; |
978 | if ($state{handle}) { |
745 | |
979 | # handle keepalive |
|
|
980 | if ( |
|
|
981 | $persistent |
|
|
982 | && $_[3] |
|
|
983 | && ($hdr{HTTPVersion} < 1.1 |
|
|
984 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
|
|
985 | : $hdr{connection} !~ /\bclose\b/i) |
|
|
986 | ) { |
|
|
987 | ka_store $ka_key, delete $state{handle}; |
|
|
988 | } else { |
|
|
989 | # no keepalive, destroy the handle |
746 | $state{handle}->destroy if $state{handle}; |
990 | $state{handle}->destroy; |
|
|
991 | } |
|
|
992 | } |
|
|
993 | |
747 | %state = (); |
994 | %state = (); |
748 | |
995 | |
749 | if (defined $_[1]) { |
996 | if (defined $_[1]) { |
750 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
997 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
751 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
998 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
… | |
… | |
758 | |
1005 | |
759 | if ($redirect && exists $hdr{location}) { |
1006 | if ($redirect && exists $hdr{location}) { |
760 | # we ignore any errors, as it is very common to receive |
1007 | # we ignore any errors, as it is very common to receive |
761 | # Content-Length != 0 but no actual body |
1008 | # Content-Length != 0 but no actual body |
762 | # we also access %hdr, as $_[1] might be an erro |
1009 | # we also access %hdr, as $_[1] might be an erro |
|
|
1010 | $state{recurse} = |
763 | http_request ( |
1011 | http_request ( |
764 | $method => $hdr{location}, |
1012 | $method => $hdr{location}, |
765 | %arg, |
1013 | %arg, |
766 | recurse => $recurse - 1, |
1014 | recurse => $recurse - 1, |
767 | Redirect => [$_[0], \%hdr], |
1015 | Redirect => [$_[0], \%hdr], |
|
|
1016 | sub { |
|
|
1017 | %state = (); |
|
|
1018 | &$cb |
|
|
1019 | }, |
768 | $cb); |
1020 | ); |
769 | } else { |
1021 | } else { |
770 | $cb->($_[0], \%hdr); |
1022 | $cb->($_[0], \%hdr); |
771 | } |
1023 | } |
772 | }; |
1024 | }; |
773 | |
1025 | |
774 | $ae_error = 597; # body phase |
1026 | $ae_error = 597; # body phase |
775 | |
1027 | |
|
|
1028 | my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct... |
|
|
1029 | |
776 | my $len = $hdr{"content-length"}; |
1030 | my $len = $chunked ? undef : $hdr{"content-length"}; |
777 | |
1031 | |
778 | # body handling, many different code paths |
1032 | # body handling, many different code paths |
779 | # - no body expected |
1033 | # - no body expected |
780 | # - want_body_handle |
1034 | # - want_body_handle |
781 | # - te chunked |
1035 | # - te chunked |
… | |
… | |
796 | $_[0]->on_error (undef); |
1050 | $_[0]->on_error (undef); |
797 | $_[0]->on_read (undef); |
1051 | $_[0]->on_read (undef); |
798 | |
1052 | |
799 | $finish->(delete $state{handle}); |
1053 | $finish->(delete $state{handle}); |
800 | |
1054 | |
801 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
1055 | } elsif ($chunked) { |
802 | my $cl = 0; |
1056 | my $cl = 0; |
803 | my $body = undef; |
1057 | my $body = ""; |
804 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1058 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
805 | |
1059 | |
806 | $state{read_chunk} = sub { |
1060 | $state{read_chunk} = sub { |
807 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1061 | $_[1] =~ /^([0-9a-fA-F]+)/ |
808 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1062 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
809 | |
1063 | |
810 | my $len = hex $1; |
1064 | my $len = hex $1; |
811 | |
1065 | |
812 | if ($len) { |
1066 | if ($len) { |
813 | $cl += $len; |
1067 | $cl += $len; |
… | |
… | |
828 | $_[0]->push_read (line => $qr_nlnl, sub { |
1082 | $_[0]->push_read (line => $qr_nlnl, sub { |
829 | if (length $_[1]) { |
1083 | if (length $_[1]) { |
830 | for ("$_[1]") { |
1084 | for ("$_[1]") { |
831 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
1085 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
832 | |
1086 | |
833 | my $hdr = parse_hdr |
1087 | my $hdr = _parse_hdr |
834 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
1088 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
835 | |
1089 | |
836 | %hdr = (%hdr, %$hdr); |
1090 | %hdr = (%hdr, %$hdr); |
837 | } |
1091 | } |
838 | } |
1092 | } |
… | |
… | |
842 | } |
1096 | } |
843 | }; |
1097 | }; |
844 | |
1098 | |
845 | $_[0]->push_read (line => $state{read_chunk}); |
1099 | $_[0]->push_read (line => $state{read_chunk}); |
846 | |
1100 | |
847 | } elsif ($arg{on_body}) { |
1101 | } elsif (!$redirect && $arg{on_body}) { |
848 | if (defined $len) { |
1102 | if (defined $len) { |
849 | $_[0]->on_read (sub { |
1103 | $_[0]->on_read (sub { |
850 | $len -= length $_[0]{rbuf}; |
1104 | $len -= length $_[0]{rbuf}; |
851 | |
1105 | |
852 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1106 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
881 | $_[0]->on_read (sub { }); |
1135 | $_[0]->on_read (sub { }); |
882 | } |
1136 | } |
883 | } |
1137 | } |
884 | }; |
1138 | }; |
885 | |
1139 | |
|
|
1140 | # if keepalive is enabled, then the server closing the connection |
|
|
1141 | # before a response can happen legally - we retry on idempotent methods. |
|
|
1142 | if ($was_persistent && $idempotent) { |
|
|
1143 | my $old_eof = $hdl->{on_eof}; |
|
|
1144 | $hdl->{on_eof} = sub { |
|
|
1145 | _destroy_state %state; |
|
|
1146 | |
|
|
1147 | %state = (); |
|
|
1148 | $state{recurse} = |
|
|
1149 | http_request ( |
|
|
1150 | $method => $url, |
|
|
1151 | %arg, |
|
|
1152 | recurse => $recurse - 1, |
|
|
1153 | persistent => 0, |
|
|
1154 | sub { |
|
|
1155 | %state = (); |
|
|
1156 | &$cb |
|
|
1157 | } |
|
|
1158 | ); |
|
|
1159 | }; |
|
|
1160 | $hdl->on_read (sub { |
|
|
1161 | return unless %state; |
|
|
1162 | |
|
|
1163 | # as soon as we receive something, a connection close |
|
|
1164 | # once more becomes a hard error |
|
|
1165 | $hdl->{on_eof} = $old_eof; |
|
|
1166 | $hdl->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
1167 | }); |
|
|
1168 | } else { |
886 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
1169 | $hdl->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
1170 | } |
887 | }; |
1171 | }; |
888 | |
1172 | |
|
|
1173 | my $prepare_handle = sub { |
|
|
1174 | my ($hdl) = $state{handle}; |
|
|
1175 | |
|
|
1176 | $hdl->on_error (sub { |
|
|
1177 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
|
|
1178 | }); |
|
|
1179 | $hdl->on_eof (sub { |
|
|
1180 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
|
|
1181 | }); |
|
|
1182 | $hdl->timeout_reset; |
|
|
1183 | $hdl->timeout ($timeout); |
|
|
1184 | }; |
|
|
1185 | |
|
|
1186 | # connected to proxy (or origin server) |
889 | my $connect_cb = sub { |
1187 | my $connect_cb = sub { |
890 | $state{fh} = shift |
1188 | my $fh = shift |
891 | or do { |
|
|
892 | my $err = "$!"; |
|
|
893 | %state = (); |
|
|
894 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
1189 | or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" }; |
895 | }; |
|
|
896 | |
1190 | |
897 | return unless delete $state{connect_guard}; |
1191 | return unless delete $state{connect_guard}; |
898 | |
1192 | |
899 | # get handle |
1193 | # get handle |
900 | $state{handle} = new AnyEvent::Handle |
1194 | $state{handle} = new AnyEvent::Handle |
|
|
1195 | %{ $arg{handle_params} }, |
901 | fh => $state{fh}, |
1196 | fh => $fh, |
902 | peername => $rhost, |
1197 | peername => $uhost, |
903 | tls_ctx => $arg{tls_ctx}, |
1198 | tls_ctx => $arg{tls_ctx}, |
904 | # these need to be reconfigured on keepalive handles |
|
|
905 | timeout => $timeout, |
|
|
906 | on_error => sub { |
|
|
907 | %state = (); |
|
|
908 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
|
|
909 | }, |
|
|
910 | on_eof => sub { |
|
|
911 | %state = (); |
|
|
912 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
|
|
913 | }, |
|
|
914 | ; |
1199 | ; |
915 | |
1200 | |
916 | # limit the number of persistent connections |
1201 | $prepare_handle->(); |
917 | # keepalive not yet supported |
|
|
918 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
|
|
919 | # ++$KA_COUNT{$_[1]}; |
|
|
920 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
921 | # --$KA_COUNT{$_[1]} |
|
|
922 | # }; |
|
|
923 | # $hdr{connection} = "keep-alive"; |
|
|
924 | # } |
|
|
925 | |
1202 | |
926 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
1203 | #$state{handle}->starttls ("connect") if $rscheme eq "https"; |
927 | |
1204 | |
928 | # now handle proxy-CONNECT method |
1205 | # now handle proxy-CONNECT method |
929 | if ($proxy && $uscheme eq "https") { |
1206 | if ($proxy && $uscheme eq "https") { |
930 | # oh dear, we have to wrap it into a connect request |
1207 | # oh dear, we have to wrap it into a connect request |
931 | |
1208 | |
|
|
1209 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1210 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1211 | : ""; |
|
|
1212 | |
932 | # maybe re-use $uauthority with patched port? |
1213 | # maybe re-use $uauthority with patched port? |
933 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1214 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
934 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1215 | $state{handle}->push_read (line => $qr_nlnl, sub { |
935 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1216 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
936 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
1217 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
937 | |
1218 | |
938 | if ($2 == 200) { |
1219 | if ($2 == 200) { |
939 | $rpath = $upath; |
1220 | $rpath = $upath; |
940 | $handle_actual_request->(); |
1221 | $handle_actual_request->(); |
941 | } else { |
1222 | } else { |
942 | %state = (); |
|
|
943 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
1223 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
944 | } |
1224 | } |
945 | }); |
1225 | }); |
946 | } else { |
1226 | } else { |
|
|
1227 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1228 | |
947 | $handle_actual_request->(); |
1229 | $handle_actual_request->(); |
948 | } |
1230 | } |
949 | }; |
1231 | }; |
950 | |
1232 | |
951 | _get_slot $uhost, sub { |
1233 | _get_slot $uhost, sub { |
952 | $state{slot_guard} = shift; |
1234 | $state{slot_guard} = shift; |
953 | |
1235 | |
954 | return unless $state{connect_guard}; |
1236 | return unless $state{connect_guard}; |
955 | |
1237 | |
|
|
1238 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
|
|
1239 | # on a keepalive request (in theory, this should be a separate config option). |
|
|
1240 | if ($persistent && $KA_CACHE{$ka_key}) { |
|
|
1241 | $was_persistent = 1; |
|
|
1242 | |
|
|
1243 | $state{handle} = ka_fetch $ka_key; |
|
|
1244 | # $state{handle}->destroyed |
|
|
1245 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
|
|
1246 | $prepare_handle->(); |
|
|
1247 | # $state{handle}->destroyed |
|
|
1248 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
|
|
1249 | $rpath = $upath; |
|
|
1250 | $handle_actual_request->(); |
|
|
1251 | |
|
|
1252 | } else { |
956 | my $tcp_connect = $arg{tcp_connect} |
1253 | my $tcp_connect = $arg{tcp_connect} |
957 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1254 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
958 | |
1255 | |
959 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
1256 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
1257 | } |
960 | }; |
1258 | }; |
961 | |
1259 | |
962 | defined wantarray && AnyEvent::Util::guard { %state = () } |
1260 | defined wantarray && AnyEvent::Util::guard { _destroy_state %state } |
963 | } |
1261 | } |
964 | |
1262 | |
965 | sub http_get($@) { |
1263 | sub http_get($@) { |
966 | unshift @_, "GET"; |
1264 | unshift @_, "GET"; |
967 | &http_request |
1265 | &http_request |
… | |
… | |
985 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
1283 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
986 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
1284 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
987 | hostnames. The latter is a simple stub resolver and does no caching |
1285 | hostnames. The latter is a simple stub resolver and does no caching |
988 | on its own. If you want DNS caching, you currently have to provide |
1286 | on its own. If you want DNS caching, you currently have to provide |
989 | your own default resolver (by storing a suitable resolver object in |
1287 | your own default resolver (by storing a suitable resolver object in |
990 | C<$AnyEvent::DNS::RESOLVER>). |
1288 | C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback. |
991 | |
1289 | |
992 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
1290 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
993 | |
1291 | |
994 | =over 4 |
1292 | =over 4 |
995 | |
1293 | |
996 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
1294 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
997 | |
1295 | |
998 | Sets the default proxy server to use. The proxy-url must begin with a |
1296 | Sets the default proxy server to use. The proxy-url must begin with a |
999 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
1297 | string of the form C<http://host:port>, croaks otherwise. |
1000 | otherwise. |
|
|
1001 | |
1298 | |
1002 | To clear an already-set proxy, use C<undef>. |
1299 | To clear an already-set proxy, use C<undef>. |
|
|
1300 | |
|
|
1301 | When AnyEvent::HTTP is loaded for the first time it will query the |
|
|
1302 | default proxy from the operating system, currently by looking at |
|
|
1303 | C<$ENV{http_proxy>}. |
1003 | |
1304 | |
1004 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1305 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
1005 | |
1306 | |
1006 | Remove all cookies from the cookie jar that have been expired. If |
1307 | Remove all cookies from the cookie jar that have been expired. If |
1007 | C<$session_end> is given and true, then additionally remove all session |
1308 | C<$session_end> is given and true, then additionally remove all session |
1008 | cookies. |
1309 | cookies. |
1009 | |
1310 | |
1010 | You should call this function (with a true C<$session_end>) before you |
1311 | You should call this function (with a true C<$session_end>) before you |
1011 | save cookies to disk, and you should call this function after loading them |
1312 | save cookies to disk, and you should call this function after loading them |
1012 | again. If you have a long-running program you can additonally call this |
1313 | again. If you have a long-running program you can additionally call this |
1013 | function from time to time. |
1314 | function from time to time. |
1014 | |
1315 | |
1015 | A cookie jar is initially an empty hash-reference that is managed by this |
1316 | A cookie jar is initially an empty hash-reference that is managed by this |
1016 | module. It's format is subject to change, but currently it is like this: |
1317 | module. Its format is subject to change, but currently it is as follows: |
1017 | |
1318 | |
1018 | The key C<version> has to contain C<1>, otherwise the hash gets |
1319 | The key C<version> has to contain C<2>, otherwise the hash gets |
1019 | emptied. All other keys are hostnames or IP addresses pointing to |
1320 | cleared. All other keys are hostnames or IP addresses pointing to |
1020 | hash-references. The key for these inner hash references is the |
1321 | hash-references. The key for these inner hash references is the |
1021 | server path for which this cookie is meant, and the values are again |
1322 | server path for which this cookie is meant, and the values are again |
1022 | hash-references. The keys of those hash-references is the cookie name, and |
1323 | hash-references. Each key of those hash-references is a cookie name, and |
1023 | the value, you guessed it, is another hash-reference, this time with the |
1324 | the value, you guessed it, is another hash-reference, this time with the |
1024 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1325 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1025 | which have been replaced by a C<_expires> key that contains the cookie |
1326 | which have been replaced by a C<_expires> key that contains the cookie |
1026 | expiry timestamp. |
1327 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1328 | C<_expires> key. |
1027 | |
1329 | |
1028 | Here is an example of a cookie jar with a single cookie, so you have a |
1330 | Here is an example of a cookie jar with a single cookie, so you have a |
1029 | chance of understanding the above paragraph: |
1331 | chance of understanding the above paragraph: |
1030 | |
1332 | |
1031 | { |
1333 | { |
1032 | version => 1, |
1334 | version => 2, |
1033 | "10.0.0.1" => { |
1335 | "10.0.0.1" => { |
1034 | "/" => { |
1336 | "/" => { |
1035 | "mythweb_id" => { |
1337 | "mythweb_id" => { |
1036 | _expires => 1293917923, |
1338 | _expires => 1293917923, |
1037 | value => "ooRung9dThee3ooyXooM1Ohm", |
1339 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1053 | |
1355 | |
1054 | =item $AnyEvent::HTTP::MAX_RECURSE |
1356 | =item $AnyEvent::HTTP::MAX_RECURSE |
1055 | |
1357 | |
1056 | The default value for the C<recurse> request parameter (default: C<10>). |
1358 | The default value for the C<recurse> request parameter (default: C<10>). |
1057 | |
1359 | |
|
|
1360 | =item $AnyEvent::HTTP::TIMEOUT |
|
|
1361 | |
|
|
1362 | The default timeout for connection operations (default: C<300>). |
|
|
1363 | |
1058 | =item $AnyEvent::HTTP::USERAGENT |
1364 | =item $AnyEvent::HTTP::USERAGENT |
1059 | |
1365 | |
1060 | The default value for the C<User-Agent> header (the default is |
1366 | The default value for the C<User-Agent> header (the default is |
1061 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1367 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1062 | |
1368 | |
1063 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1369 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1064 | |
1370 | |
1065 | The maximum number of concurrent connections to the same host (identified |
1371 | The maximum number of concurrent connections to the same host (identified |
1066 | by the hostname). If the limit is exceeded, then the additional requests |
1372 | by the hostname). If the limit is exceeded, then additional requests |
1067 | are queued until previous connections are closed. |
1373 | are queued until previous connections are closed. Both persistent and |
|
|
1374 | non-persistent connections are counted in this limit. |
1068 | |
1375 | |
1069 | The default value for this is C<4>, and it is highly advisable to not |
1376 | The default value for this is C<4>, and it is highly advisable to not |
1070 | increase it. |
1377 | increase it much. |
|
|
1378 | |
|
|
1379 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
|
|
1380 | connections, older browsers used 2, newer ones (such as firefox 3) |
|
|
1381 | typically use 6, and Opera uses 8 because like, they have the fastest |
|
|
1382 | browser and give a shit for everybody else on the planet. |
|
|
1383 | |
|
|
1384 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
1385 | |
|
|
1386 | The time after which idle persistent connections get closed by |
|
|
1387 | AnyEvent::HTTP (default: C<3>). |
1071 | |
1388 | |
1072 | =item $AnyEvent::HTTP::ACTIVE |
1389 | =item $AnyEvent::HTTP::ACTIVE |
1073 | |
1390 | |
1074 | The number of active connections. This is not the number of currently |
1391 | The number of active connections. This is not the number of currently |
1075 | running requests, but the number of currently open and non-idle TCP |
1392 | running requests, but the number of currently open and non-idle TCP |
1076 | connections. This number of can be useful for load-leveling. |
1393 | connections. This number can be useful for load-leveling. |
1077 | |
1394 | |
1078 | =back |
1395 | =back |
1079 | |
1396 | |
1080 | =cut |
1397 | =cut |
1081 | |
1398 | |
… | |
… | |
1115 | # other formats fail in the loop below |
1432 | # other formats fail in the loop below |
1116 | |
1433 | |
1117 | for (0..11) { |
1434 | for (0..11) { |
1118 | if ($m eq $month[$_]) { |
1435 | if ($m eq $month[$_]) { |
1119 | require Time::Local; |
1436 | require Time::Local; |
1120 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1437 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
1121 | } |
1438 | } |
1122 | } |
1439 | } |
1123 | |
1440 | |
1124 | undef |
1441 | undef |
1125 | } |
1442 | } |
1126 | |
1443 | |
1127 | sub set_proxy($) { |
1444 | sub set_proxy($) { |
1128 | if (length $_[0]) { |
1445 | if (length $_[0]) { |
1129 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
1446 | $_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix |
1130 | or Carp::croak "$_[0]: invalid proxy URL"; |
1447 | or Carp::croak "$_[0]: invalid proxy URL"; |
1131 | $PROXY = [$2, $3 || 3128, $1] |
1448 | $PROXY = [$2, $3 || 3128, $1] |
1132 | } else { |
1449 | } else { |
1133 | undef $PROXY; |
1450 | undef $PROXY; |
1134 | } |
1451 | } |
… | |
… | |
1137 | # initialise proxy from environment |
1454 | # initialise proxy from environment |
1138 | eval { |
1455 | eval { |
1139 | set_proxy $ENV{http_proxy}; |
1456 | set_proxy $ENV{http_proxy}; |
1140 | }; |
1457 | }; |
1141 | |
1458 | |
|
|
1459 | =head2 SHOWCASE |
|
|
1460 | |
|
|
1461 | This section contains some more elaborate "real-world" examples or code |
|
|
1462 | snippets. |
|
|
1463 | |
|
|
1464 | =head2 HTTP/1.1 FILE DOWNLOAD |
|
|
1465 | |
|
|
1466 | Downloading files with HTTP can be quite tricky, especially when something |
|
|
1467 | goes wrong and you want to resume. |
|
|
1468 | |
|
|
1469 | Here is a function that initiates and resumes a download. It uses the |
|
|
1470 | last modified time to check for file content changes, and works with many |
|
|
1471 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
|
|
1472 | on older servers. |
|
|
1473 | |
|
|
1474 | It calls the completion callback with either C<undef>, which means a |
|
|
1475 | nonretryable error occurred, C<0> when the download was partial and should |
|
|
1476 | be retried, and C<1> if it was successful. |
|
|
1477 | |
|
|
1478 | use AnyEvent::HTTP; |
|
|
1479 | |
|
|
1480 | sub download($$$) { |
|
|
1481 | my ($url, $file, $cb) = @_; |
|
|
1482 | |
|
|
1483 | open my $fh, "+<", $file |
|
|
1484 | or die "$file: $!"; |
|
|
1485 | |
|
|
1486 | my %hdr; |
|
|
1487 | my $ofs = 0; |
|
|
1488 | |
|
|
1489 | if (stat $fh and -s _) { |
|
|
1490 | $ofs = -s _; |
|
|
1491 | warn "-s is ", $ofs; |
|
|
1492 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
|
|
1493 | $hdr{"range"} = "bytes=$ofs-"; |
|
|
1494 | } |
|
|
1495 | |
|
|
1496 | http_get $url, |
|
|
1497 | headers => \%hdr, |
|
|
1498 | on_header => sub { |
|
|
1499 | my ($hdr) = @_; |
|
|
1500 | |
|
|
1501 | if ($hdr->{Status} == 200 && $ofs) { |
|
|
1502 | # resume failed |
|
|
1503 | truncate $fh, $ofs = 0; |
|
|
1504 | } |
|
|
1505 | |
|
|
1506 | sysseek $fh, $ofs, 0; |
|
|
1507 | |
|
|
1508 | 1 |
|
|
1509 | }, |
|
|
1510 | on_body => sub { |
|
|
1511 | my ($data, $hdr) = @_; |
|
|
1512 | |
|
|
1513 | if ($hdr->{Status} =~ /^2/) { |
|
|
1514 | length $data == syswrite $fh, $data |
|
|
1515 | or return; # abort on write errors |
|
|
1516 | } |
|
|
1517 | |
|
|
1518 | 1 |
|
|
1519 | }, |
|
|
1520 | sub { |
|
|
1521 | my (undef, $hdr) = @_; |
|
|
1522 | |
|
|
1523 | my $status = $hdr->{Status}; |
|
|
1524 | |
|
|
1525 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
|
|
1526 | utime $time, $time, $fh; |
|
|
1527 | } |
|
|
1528 | |
|
|
1529 | if ($status == 200 || $status == 206 || $status == 416) { |
|
|
1530 | # download ok || resume ok || file already fully downloaded |
|
|
1531 | $cb->(1, $hdr); |
|
|
1532 | |
|
|
1533 | } elsif ($status == 412) { |
|
|
1534 | # file has changed while resuming, delete and retry |
|
|
1535 | unlink $file; |
|
|
1536 | $cb->(0, $hdr); |
|
|
1537 | |
|
|
1538 | } elsif ($status == 500 or $status == 503 or $status =~ /^59/) { |
|
|
1539 | # retry later |
|
|
1540 | $cb->(0, $hdr); |
|
|
1541 | |
|
|
1542 | } else { |
|
|
1543 | $cb->(undef, $hdr); |
|
|
1544 | } |
|
|
1545 | } |
|
|
1546 | ; |
|
|
1547 | } |
|
|
1548 | |
|
|
1549 | download "http://server/somelargefile", "/tmp/somelargefile", sub { |
|
|
1550 | if ($_[0]) { |
|
|
1551 | print "OK!\n"; |
|
|
1552 | } elsif (defined $_[0]) { |
|
|
1553 | print "please retry later\n"; |
|
|
1554 | } else { |
|
|
1555 | print "ERROR\n"; |
|
|
1556 | } |
|
|
1557 | }; |
|
|
1558 | |
1142 | =head2 SOCKS PROXIES |
1559 | =head3 SOCKS PROXIES |
1143 | |
1560 | |
1144 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
1561 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
1145 | compile your perl to support socks, or use an external program such as |
1562 | compile your perl to support socks, or use an external program such as |
1146 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
1563 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
1147 | transparently. |
1564 | transparently. |