… | |
… | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Errno (); |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent 4.452 (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
49 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
50 | |
50 | |
51 | use base Exporter::; |
51 | use base Exporter::; |
52 | |
52 | |
53 | our $VERSION = '1.12'; |
53 | our $VERSION = '1.45'; |
54 | |
54 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
56 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
59 | our $MAX_PERSISTENT = 8; |
59 | our $MAX_PERSISTENT = 8; |
60 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $PERSISTENT_TIMEOUT = 2; |
61 | our $TIMEOUT = 300; |
61 | our $TIMEOUT = 300; |
62 | |
62 | |
63 | # changing these is evil |
63 | # changing these is evil |
64 | our $MAX_PERSISTENT_PER_HOST = 2; |
64 | our $MAX_PERSISTENT_PER_HOST = 0; |
65 | our $MAX_PER_HOST = 4; |
65 | our $MAX_PER_HOST = 4; |
66 | |
66 | |
67 | our $PROXY; |
67 | our $PROXY; |
68 | our $ACTIVE = 0; |
68 | our $ACTIVE = 0; |
69 | |
69 | |
… | |
… | |
94 | When called in void context, nothing is returned. In other contexts, |
94 | When called in void context, nothing is returned. In other contexts, |
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
95 | 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 |
96 | 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. |
97 | destroyed before the callbakc is called, the request will be cancelled. |
98 | |
98 | |
99 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response body data as first argument |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if an error occured), and a hash-ref with response headers as |
101 | response headers as second argument. |
101 | second argument. |
102 | |
102 | |
103 | All the headers in that hash are lowercased. In addition to the response |
103 | 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> |
104 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
|
|
105 | 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 |
106 | three parts of the HTTP Status-Line of the same name. |
|
|
107 | |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
108 | The pseudo-header C<URL> contains the actual URL (which can differ from |
107 | requested URL when following redirects). |
109 | the requested URL when following redirects - for example, you might get |
|
|
110 | an error that your URL scheme is not supported even though your URL is a |
|
|
111 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
112 | look at the URL pseudo header). |
|
|
113 | |
|
|
114 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
115 | of an internal redirect. In that case it is an array reference with |
|
|
116 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
117 | response could in turn be the result of a redirect itself, and C<< |
|
|
118 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
119 | response, and so on. |
108 | |
120 | |
109 | If the server sends a header multiple times, then their contents will be |
121 | 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. |
122 | joined together with a comma (C<,>), as per the HTTP spec. |
111 | |
123 | |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
124 | If an internal error occurs, such as not being able to resolve a hostname, |
… | |
… | |
138 | |
150 | |
139 | =item headers => hashref |
151 | =item headers => hashref |
140 | |
152 | |
141 | The request headers to use. Currently, C<http_request> may provide its |
153 | The request headers to use. Currently, C<http_request> may provide its |
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
154 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
143 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
155 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
|
|
156 | suppressed by using C<undef> for these headers in which case they won't be |
|
|
157 | sent at all). |
144 | |
158 | |
145 | =item timeout => $seconds |
159 | =item timeout => $seconds |
146 | |
160 | |
147 | The time-out to use for various stages - each connect attempt will reset |
161 | The time-out to use for various stages - each connect attempt will reset |
148 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
162 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
163 | timeout. |
|
|
164 | |
|
|
165 | Default timeout is 5 minutes. |
149 | |
166 | |
150 | =item proxy => [$host, $port[, $scheme]] or undef |
167 | =item proxy => [$host, $port[, $scheme]] or undef |
151 | |
168 | |
152 | Use the given http proxy for all requests. If not specified, then the |
169 | Use the given http proxy for all requests. If not specified, then the |
153 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
170 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
154 | |
171 | |
155 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
172 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
156 | HTTPS. |
173 | HTTPS. |
157 | |
174 | |
158 | =item body => $string |
175 | =item body => $string |
159 | |
176 | |
160 | The request body, usually empty. Will be-sent as-is (future versions of |
177 | The request body, usually empty. Will be-sent as-is (future versions of |
… | |
… | |
186 | verification) TLS context. |
203 | verification) TLS context. |
187 | |
204 | |
188 | The default for this option is C<low>, which could be interpreted as "give |
205 | The default for this option is C<low>, which could be interpreted as "give |
189 | me the page, no matter what". |
206 | me the page, no matter what". |
190 | |
207 | |
|
|
208 | =item on_prepare => $callback->($fh) |
|
|
209 | |
|
|
210 | In rare cases you need to "tune" the socket before it is used to |
|
|
211 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
212 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
213 | and behaves exactly the same way (e.g. it has to provide a |
|
|
214 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
215 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
216 | |
191 | =item on_header => $callback->($hdr) |
217 | =item on_header => $callback->($headers) |
192 | |
218 | |
193 | When specified, this callback will be called with the header hash as soon |
219 | When specified, this callback will be called with the header hash as soon |
194 | as headers have been successfully received from the remote server (not on |
220 | as headers have been successfully received from the remote server (not on |
195 | locally-generated errors). |
221 | locally-generated errors). |
196 | |
222 | |
… | |
… | |
200 | |
226 | |
201 | This callback is useful, among other things, to quickly reject unwanted |
227 | This callback is useful, among other things, to quickly reject unwanted |
202 | content, which, if it is supposed to be rare, can be faster than first |
228 | content, which, if it is supposed to be rare, can be faster than first |
203 | doing a C<HEAD> request. |
229 | doing a C<HEAD> request. |
204 | |
230 | |
|
|
231 | Example: cancel the request unless the content-type is "text/html". |
|
|
232 | |
|
|
233 | on_header => sub { |
|
|
234 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
235 | }, |
|
|
236 | |
205 | =item on_body => $callback->($data, $hdr) |
237 | =item on_body => $callback->($partial_body, $headers) |
206 | |
238 | |
207 | When specified, all body data will be "filtered" through this callback. |
239 | When specified, all body data will be passed to this callback instead of |
|
|
240 | to the completion callback. The completion callback will get the empty |
|
|
241 | string instead of the body data. |
208 | |
242 | |
209 | The callback will incrementally receive body data, and is supposed to |
243 | It has to return either true (in which case AnyEvent::HTTP will continue), |
210 | return it or a modified version of it (empty strings are valid returns). |
244 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
245 | the completion callback with an error code of C<598>). |
211 | |
246 | |
212 | If the callback returns C<undef>, then the request will be cancelled. |
247 | This callback is useful when the data is too large to be held in memory |
213 | |
248 | (so the callback writes it to a file) or when only some information should |
214 | This callback is useful when you want to do some processing on the data, |
249 | be extracted, or when the body should be processed incrementally. |
215 | or the data is too large to be held in memory (so the callback writes it |
|
|
216 | to a file and returns the empty string) and so on. |
|
|
217 | |
250 | |
218 | It is usually preferred over doing your own body handling via |
251 | It is usually preferred over doing your own body handling via |
219 | C<want_body_handle>. |
252 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
253 | only used to create a connection, C<want_body_handle> is the better |
|
|
254 | alternative, as it allows you to install your own event handler, reducing |
|
|
255 | resource usage. |
220 | |
256 | |
221 | =item want_body_handle => $enable |
257 | =item want_body_handle => $enable |
222 | |
258 | |
223 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
259 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
224 | changes considerably: after parsing the headers, and instead of |
260 | changes considerably: after parsing the headers, and instead of |
… | |
… | |
236 | This is useful with some push-type services, where, after the initial |
272 | This is useful with some push-type services, where, after the initial |
237 | headers, an interactive protocol is used (typical example would be the |
273 | headers, an interactive protocol is used (typical example would be the |
238 | push-style twitter API which starts a JSON/XML stream). |
274 | push-style twitter API which starts a JSON/XML stream). |
239 | |
275 | |
240 | If you think you need this, first have a look at C<on_body>, to see if |
276 | If you think you need this, first have a look at C<on_body>, to see if |
241 | that doesn'T solve your problem in a better way. |
277 | that doesn't solve your problem in a better way. |
242 | |
278 | |
243 | =back |
279 | =back |
244 | |
280 | |
245 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
281 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
246 | |
282 | |
… | |
… | |
302 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
338 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
303 | |
339 | |
304 | _slot_schedule $_[0]; |
340 | _slot_schedule $_[0]; |
305 | } |
341 | } |
306 | |
342 | |
307 | our $qr_nl = qr<\015?\012>; |
343 | our $qr_nl = qr{\015?\012}; |
308 | our $qr_nlnl = qr<\015?\012\015?\012>; |
344 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
309 | |
345 | |
310 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
346 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
311 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
347 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
312 | |
348 | |
313 | sub http_request($$@) { |
349 | sub http_request($$@) { |
… | |
… | |
325 | while (my ($k, $v) = each %$hdr) { |
361 | while (my ($k, $v) = each %$hdr) { |
326 | $hdr{lc $k} = $v; |
362 | $hdr{lc $k} = $v; |
327 | } |
363 | } |
328 | } |
364 | } |
329 | |
365 | |
|
|
366 | # pseudo headers for all subsequent responses |
|
|
367 | my @pseudo = (URL => $url); |
|
|
368 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
369 | |
330 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
370 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
331 | |
371 | |
332 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
372 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo }) |
333 | if $recurse < 0; |
373 | if $recurse < 0; |
334 | |
374 | |
335 | my $proxy = $arg{proxy} || $PROXY; |
375 | my $proxy = $arg{proxy} || $PROXY; |
336 | my $timeout = $arg{timeout} || $TIMEOUT; |
376 | my $timeout = $arg{timeout} || $TIMEOUT; |
337 | |
377 | |
338 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
378 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
339 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
379 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
340 | |
380 | |
341 | $uscheme = lc $uscheme; |
381 | $uscheme = lc $uscheme; |
342 | |
382 | |
343 | my $uport = $uscheme eq "http" ? 80 |
383 | my $uport = $uscheme eq "http" ? 80 |
344 | : $uscheme eq "https" ? 443 |
384 | : $uscheme eq "https" ? 443 |
345 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
385 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo }); |
346 | |
386 | |
347 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
387 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
348 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
388 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo }); |
349 | |
389 | |
350 | my $uhost = $1; |
390 | my $uhost = $1; |
351 | $uport = $2 if defined $2; |
391 | $uport = $2 if defined $2; |
352 | |
392 | |
|
|
393 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
394 | unless exists $hdr{host}; |
|
|
395 | |
353 | $uhost =~ s/^\[(.*)\]$/$1/; |
396 | $uhost =~ s/^\[(.*)\]$/$1/; |
354 | $upath .= "?$query" if length $query; |
397 | $upath .= $query if length $query; |
355 | |
398 | |
356 | $upath =~ s%^/?%/%; |
399 | $upath =~ s%^/?%/%; |
357 | |
400 | |
358 | # cookie processing |
401 | # cookie processing |
359 | if (my $jar = $arg{cookie_jar}) { |
402 | if (my $jar = $arg{cookie_jar}) { |
… | |
… | |
389 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
432 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
390 | |
433 | |
391 | if ($proxy) { |
434 | if ($proxy) { |
392 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
435 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
393 | |
436 | |
|
|
437 | $rscheme = "http" unless defined $rscheme; |
|
|
438 | |
394 | # don't support https requests over https-proxy transport, |
439 | # don't support https requests over https-proxy transport, |
395 | # can't be done with tls as spec'ed, unless you double-encrypt. |
440 | # can't be done with tls as spec'ed, unless you double-encrypt. |
396 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
441 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
397 | } else { |
442 | } else { |
398 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
443 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
399 | } |
444 | } |
400 | |
445 | |
401 | $hdr{"user-agent"} ||= $USERAGENT; |
446 | # leave out fragment and query string, just a heuristic |
402 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
447 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
448 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
403 | |
449 | |
404 | $hdr{host} = "$uhost:$uport"; |
|
|
405 | $hdr{"content-length"} = length $arg{body}; |
450 | $hdr{"content-length"} = length $arg{body} |
|
|
451 | if length $arg{body} || $method ne "GET"; |
406 | |
452 | |
407 | my %state = (connect_guard => 1); |
453 | my %state = (connect_guard => 1); |
408 | |
454 | |
409 | _get_slot $uhost, sub { |
455 | _get_slot $uhost, sub { |
410 | $state{slot_guard} = shift; |
456 | $state{slot_guard} = shift; |
411 | |
457 | |
412 | return unless $state{connect_guard}; |
458 | return unless $state{connect_guard}; |
413 | |
459 | |
414 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
460 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
415 | $state{fh} = shift |
461 | $state{fh} = shift |
|
|
462 | or do { |
|
|
463 | my $err = "$!"; |
|
|
464 | %state = (); |
416 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url })); |
465 | return $cb->(undef, { Status => 599, Reason => $err, @pseudo }); |
|
|
466 | }; |
|
|
467 | |
417 | pop; # free memory, save a tree |
468 | pop; # free memory, save a tree |
418 | |
469 | |
419 | return unless delete $state{connect_guard}; |
470 | return unless delete $state{connect_guard}; |
420 | |
471 | |
421 | # get handle |
472 | # get handle |
422 | $state{handle} = new AnyEvent::Handle |
473 | $state{handle} = new AnyEvent::Handle |
423 | fh => $state{fh}, |
474 | fh => $state{fh}, |
|
|
475 | peername => $rhost, |
|
|
476 | tls_ctx => $arg{tls_ctx}, |
|
|
477 | # these need to be reconfigured on keepalive handles |
424 | timeout => $timeout, |
478 | timeout => $timeout, |
425 | peername => $rhost, |
479 | on_error => sub { |
426 | tls_ctx => $arg{tls_ctx}; |
480 | %state = (); |
|
|
481 | $cb->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
|
|
482 | }, |
|
|
483 | on_eof => sub { |
|
|
484 | %state = (); |
|
|
485 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo }); |
|
|
486 | }, |
|
|
487 | ; |
427 | |
488 | |
428 | # limit the number of persistent connections |
489 | # limit the number of persistent connections |
429 | # keepalive not yet supported |
490 | # keepalive not yet supported |
430 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
491 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
431 | ++$KA_COUNT{$_[1]}; |
492 | # ++$KA_COUNT{$_[1]}; |
432 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
493 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
433 | --$KA_COUNT{$_[1]} |
494 | # --$KA_COUNT{$_[1]} |
434 | }; |
495 | # }; |
435 | $hdr{connection} = "keep-alive"; |
496 | # $hdr{connection} = "keep-alive"; |
436 | } else { |
497 | # } else { |
437 | delete $hdr{connection}; |
498 | delete $hdr{connection}; |
438 | } |
499 | # } |
439 | |
|
|
440 | # (re-)configure handle |
|
|
441 | $state{handle}->on_error (sub { |
|
|
442 | %state = (); |
|
|
443 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
444 | }); |
|
|
445 | $state{handle}->on_eof (sub { |
|
|
446 | %state = (); |
|
|
447 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
|
|
448 | }); |
|
|
449 | |
500 | |
450 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
501 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
451 | |
502 | |
452 | # handle actual, non-tunneled, request |
503 | # handle actual, non-tunneled, request |
453 | my $handle_actual_request = sub { |
504 | my $handle_actual_request = sub { |
454 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
505 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
455 | |
506 | |
456 | # send request |
507 | # send request |
457 | $state{handle}->push_write ( |
508 | $state{handle}->push_write ( |
458 | "$method $rpath HTTP/1.0\015\012" |
509 | "$method $rpath HTTP/1.0\015\012" |
459 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
510 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
460 | . "\015\012" |
511 | . "\015\012" |
461 | . (delete $arg{body}) |
512 | . (delete $arg{body}) |
462 | ); |
513 | ); |
463 | |
514 | |
|
|
515 | # return if error occured during push_write() |
|
|
516 | return unless %state; |
|
|
517 | |
464 | %hdr = (); # reduce memory usage, save a kitten |
518 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
465 | |
519 | |
466 | # status line |
520 | # status line |
467 | $state{handle}->push_read (line => $qr_nl, sub { |
521 | $state{handle}->push_read (line => $qr_nl, sub { |
468 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
522 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
469 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
523 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", @pseudo })); |
470 | |
524 | |
471 | my %hdr = ( # response headers |
525 | push @pseudo, |
472 | HTTPVersion => ",$1", |
526 | HTTPVersion => $1, |
473 | Status => ",$2", |
527 | Status => $2, |
474 | Reason => ",$3", |
528 | Reason => $3, |
475 | URL => ",$url" |
|
|
476 | ); |
529 | ; |
477 | |
530 | |
478 | # headers, could be optimized a bit |
531 | # headers, could be optimized a bit |
479 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
532 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
480 | for ("$_[1]\012") { |
533 | for ("$_[1]") { |
481 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
534 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
482 | |
535 | |
483 | # things seen, not parsed: |
536 | # things seen, not parsed: |
484 | # p3pP="NON CUR OTPi OUR NOR UNI" |
537 | # p3pP="NON CUR OTPi OUR NOR UNI" |
485 | |
538 | |
486 | $hdr{lc $1} .= ",$2" |
539 | $hdr{lc $1} .= ",$2" |
487 | while /\G |
540 | while /\G |
488 | ([^:\000-\037]+): |
541 | ([^:\000-\037]*): |
489 | [\011\040]* |
542 | [\011\040]* |
490 | ((?: [^\012]+ | \012[\011\040] )*) |
543 | ((?: [^\012]+ | \012[\011\040] )*) |
491 | \012 |
544 | \012 |
492 | /gxc; |
545 | /gxc; |
493 | |
546 | |
494 | /\G$/ |
547 | /\G$/ |
495 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
548 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo })); |
496 | } |
549 | } |
497 | |
550 | |
|
|
551 | # remove the "," prefix we added to all headers above |
498 | substr $_, 0, 1, "" |
552 | substr $_, 0, 1, "" |
499 | for values %hdr; |
553 | for values %hdr; |
|
|
554 | |
|
|
555 | # patch in all pseudo headers |
|
|
556 | %hdr = (%hdr, @pseudo); |
500 | |
557 | |
501 | # redirect handling |
558 | # redirect handling |
502 | # microsoft and other shitheads don't give a shit for following standards, |
559 | # microsoft and other shitheads don't give a shit for following standards, |
503 | # try to support some common forms of broken Location headers. |
560 | # try to support some common forms of broken Location headers. |
504 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
561 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
… | |
… | |
515 | } |
572 | } |
516 | |
573 | |
517 | my $redirect; |
574 | my $redirect; |
518 | |
575 | |
519 | if ($recurse) { |
576 | if ($recurse) { |
|
|
577 | my $status = $hdr{Status}; |
|
|
578 | |
520 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
579 | if (($status == 301 || $status == 302) && $method ne "POST") { |
521 | # apparently, mozilla et al. just change POST to GET here |
580 | # apparently, mozilla et al. just change POST to GET here |
522 | # more research is needed before we do the same |
581 | # more research is needed before we do the same |
523 | $redirect = 1; |
582 | $redirect = 1; |
524 | } elsif ($hdr{Status} == 303) { |
583 | } elsif ($status == 303) { |
525 | # even http/1.1 is unclear on how to mutate the method |
584 | # even http/1.1 is unclear on how to mutate the method |
526 | $method = "GET" unless $method eq "HEAD"; |
585 | $method = "GET" unless $method eq "HEAD"; |
527 | $redirect = 1; |
586 | $redirect = 1; |
528 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
587 | } elsif ($status == 307 && $method =~ /^(?:GET|HEAD)$/) { |
529 | $redirect = 1; |
588 | $redirect = 1; |
530 | } |
589 | } |
531 | } |
590 | } |
532 | |
591 | |
533 | my $finish = sub { |
592 | my $finish = sub { |
… | |
… | |
582 | |
641 | |
583 | redo if /\G\s*,/gc; |
642 | redo if /\G\s*,/gc; |
584 | } |
643 | } |
585 | } |
644 | } |
586 | |
645 | |
587 | if ($redirect) { |
646 | if ($redirect && exists $hdr{location}) { |
588 | # we ignore any errors, as it is very common to receive |
647 | # we ignore any errors, as it is very common to receive |
589 | # Content-Length != 0 but no actual body |
648 | # Content-Length != 0 but no actual body |
590 | # we also access %hdr, as $_[1] might be an erro |
649 | # we also access %hdr, as $_[1] might be an erro |
591 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
650 | http_request ( |
|
|
651 | $method => $hdr{location}, |
|
|
652 | %arg, |
|
|
653 | recurse => $recurse - 1, |
|
|
654 | Redirect => \@_, |
|
|
655 | $cb); |
592 | } else { |
656 | } else { |
593 | $cb->($_[0], $_[1]); |
657 | $cb->($_[0], $_[1]); |
594 | } |
658 | } |
595 | }; |
659 | }; |
596 | |
660 | |
597 | my $len = $hdr{"content-length"}; |
661 | my $len = $hdr{"content-length"}; |
598 | |
662 | |
599 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
663 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
600 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
664 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo }); |
601 | } elsif ( |
665 | } elsif ( |
602 | $hdr{Status} =~ /^(?:1..|204|304)$/ |
666 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
603 | or $method eq "HEAD" |
667 | or $method eq "HEAD" |
604 | or (defined $len && !$len) |
668 | or (defined $len && !$len) |
605 | ) { |
669 | ) { |
606 | # no body |
670 | # no body |
607 | $finish->("", \%hdr); |
671 | $finish->("", \%hdr); |
… | |
… | |
615 | $_[0]->on_read (undef); |
679 | $_[0]->on_read (undef); |
616 | |
680 | |
617 | $finish->(delete $state{handle}, \%hdr); |
681 | $finish->(delete $state{handle}, \%hdr); |
618 | |
682 | |
619 | } elsif ($arg{on_body}) { |
683 | } elsif ($arg{on_body}) { |
620 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
684 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
621 | if ($len) { |
685 | if ($len) { |
622 | $_[0]->on_eof (undef); |
686 | $_[0]->on_eof (undef); |
623 | $_[0]->on_read (sub { |
687 | $_[0]->on_read (sub { |
624 | $len -= length $_[0]{rbuf}; |
688 | $len -= length $_[0]{rbuf}; |
625 | |
689 | |
626 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
690 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
627 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
691 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
628 | |
692 | |
629 | $len > 0 |
693 | $len > 0 |
630 | or $finish->("", \%hdr); |
694 | or $finish->("", \%hdr); |
631 | }); |
695 | }); |
632 | } else { |
696 | } else { |
633 | $_[0]->on_eof (sub { |
697 | $_[0]->on_eof (sub { |
634 | $finish->("", \%hdr); |
698 | $finish->("", \%hdr); |
635 | }); |
699 | }); |
636 | $_[0]->on_read (sub { |
700 | $_[0]->on_read (sub { |
637 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
701 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
638 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
702 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo }); |
639 | }); |
703 | }); |
640 | } |
704 | } |
641 | } else { |
705 | } else { |
642 | $_[0]->on_eof (undef); |
706 | $_[0]->on_eof (undef); |
643 | |
707 | |
644 | if ($len) { |
708 | if ($len) { |
645 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
709 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) }); |
646 | $_[0]->on_read (sub { |
710 | $_[0]->on_read (sub { |
647 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
711 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
648 | if $len <= length $_[0]{rbuf}; |
712 | if $len <= length $_[0]{rbuf}; |
649 | }); |
713 | }); |
650 | } else { |
714 | } else { |
651 | $_[0]->on_error (sub { |
715 | $_[0]->on_error (sub { |
652 | $! == Errno::EPIPE |
716 | $! == Errno::EPIPE || !$! |
653 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
717 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
654 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
718 | : $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }); |
655 | }); |
719 | }); |
656 | $_[0]->on_read (sub { }); |
720 | $_[0]->on_read (sub { }); |
657 | } |
721 | } |
658 | } |
722 | } |
659 | } |
723 | } |
… | |
… | |
667 | |
731 | |
668 | # maybe re-use $uauthority with patched port? |
732 | # maybe re-use $uauthority with patched port? |
669 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
733 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
670 | $state{handle}->push_read (line => $qr_nlnl, sub { |
734 | $state{handle}->push_read (line => $qr_nlnl, sub { |
671 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
735 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
672 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
736 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo })); |
673 | |
737 | |
674 | if ($2 == 200) { |
738 | if ($2 == 200) { |
675 | $rpath = $upath; |
739 | $rpath = $upath; |
676 | &$handle_actual_request; |
740 | &$handle_actual_request; |
677 | } else { |
741 | } else { |
678 | %state = (); |
742 | %state = (); |
679 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
743 | $cb->(undef, { Status => $2, Reason => $3, @pseudo }); |
680 | } |
744 | } |
681 | }); |
745 | }); |
682 | } else { |
746 | } else { |
683 | &$handle_actual_request; |
747 | &$handle_actual_request; |
684 | } |
748 | } |
685 | |
749 | |
686 | }, sub { |
750 | }, $arg{on_prepare} || sub { $timeout }; |
687 | $timeout |
|
|
688 | }; |
|
|
689 | }; |
751 | }; |
690 | |
752 | |
691 | defined wantarray && AnyEvent::Util::guard { %state = () } |
753 | defined wantarray && AnyEvent::Util::guard { %state = () } |
692 | } |
754 | } |
693 | |
755 | |
… | |
… | |
707 | &http_request |
769 | &http_request |
708 | } |
770 | } |
709 | |
771 | |
710 | =back |
772 | =back |
711 | |
773 | |
|
|
774 | =head2 DNS CACHING |
|
|
775 | |
|
|
776 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
777 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
778 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
779 | on its own. If you want DNS caching, you currently have to provide |
|
|
780 | your own default resolver (by storing a suitable resolver object in |
|
|
781 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
782 | |
712 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
783 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
713 | |
784 | |
714 | =over 4 |
785 | =over 4 |
715 | |
786 | |
716 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
787 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
717 | |
788 | |
718 | Sets the default proxy server to use. The proxy-url must begin with a |
789 | Sets the default proxy server to use. The proxy-url must begin with a |
719 | string of the form C<http://host:port> (optionally C<https:...>). |
790 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
791 | otherwise. |
|
|
792 | |
|
|
793 | To clear an already-set proxy, use C<undef>. |
720 | |
794 | |
721 | =item $AnyEvent::HTTP::MAX_RECURSE |
795 | =item $AnyEvent::HTTP::MAX_RECURSE |
722 | |
796 | |
723 | The default value for the C<recurse> request parameter (default: C<10>). |
797 | The default value for the C<recurse> request parameter (default: C<10>). |
724 | |
798 | |
725 | =item $AnyEvent::HTTP::USERAGENT |
799 | =item $AnyEvent::HTTP::USERAGENT |
726 | |
800 | |
727 | The default value for the C<User-Agent> header (the default is |
801 | The default value for the C<User-Agent> header (the default is |
728 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
802 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
729 | |
803 | |
730 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
804 | =item $AnyEvent::HTTP::MAX_PER_HOST |
731 | |
805 | |
732 | The maximum number of persistent connections to keep open (default: 8). |
806 | The maximum number of concurrent connections to the same host (identified |
|
|
807 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
808 | are queued until previous connections are closed. |
733 | |
809 | |
734 | Not implemented currently. |
810 | The default value for this is C<4>, and it is highly advisable to not |
735 | |
811 | increase it. |
736 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
737 | |
|
|
738 | The maximum time to cache a persistent connection, in seconds (default: 2). |
|
|
739 | |
|
|
740 | Not implemented currently. |
|
|
741 | |
812 | |
742 | =item $AnyEvent::HTTP::ACTIVE |
813 | =item $AnyEvent::HTTP::ACTIVE |
743 | |
814 | |
744 | The number of active connections. This is not the number of currently |
815 | The number of active connections. This is not the number of currently |
745 | running requests, but the number of currently open and non-idle TCP |
816 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
748 | =back |
819 | =back |
749 | |
820 | |
750 | =cut |
821 | =cut |
751 | |
822 | |
752 | sub set_proxy($) { |
823 | sub set_proxy($) { |
|
|
824 | if (length $_[0]) { |
753 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
825 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
826 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
827 | $PROXY = [$2, $3 || 3128, $1] |
|
|
828 | } else { |
|
|
829 | undef $PROXY; |
|
|
830 | } |
754 | } |
831 | } |
755 | |
832 | |
756 | # initialise proxy from environment |
833 | # initialise proxy from environment |
|
|
834 | eval { |
757 | set_proxy $ENV{http_proxy}; |
835 | set_proxy $ENV{http_proxy}; |
|
|
836 | }; |
758 | |
837 | |
759 | =head1 SEE ALSO |
838 | =head1 SEE ALSO |
760 | |
839 | |
761 | L<AnyEvent>. |
840 | L<AnyEvent>. |
762 | |
841 | |