… | |
… | |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::HTTP; |
7 | use AnyEvent::HTTP; |
|
|
8 | |
|
|
9 | http_get "http://www.nethype.de/", sub { print $_[1] }; |
|
|
10 | |
|
|
11 | # ... do something else here |
8 | |
12 | |
9 | =head1 DESCRIPTION |
13 | =head1 DESCRIPTION |
10 | |
14 | |
11 | This module is an L<AnyEvent> user, you need to make sure that you use and |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
12 | run a supported event loop. |
16 | run a supported event loop. |
… | |
… | |
35 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
36 | |
40 | |
37 | use strict; |
41 | use strict; |
38 | no warnings; |
42 | no warnings; |
39 | |
43 | |
40 | use Carp; |
44 | use Errno (); |
41 | |
45 | |
42 | use AnyEvent (); |
46 | use AnyEvent 4.8 (); |
43 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
44 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
45 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
46 | |
50 | |
47 | use base Exporter::; |
51 | use base Exporter::; |
48 | |
52 | |
49 | our $VERSION = '1.1'; |
53 | our $VERSION = '1.4'; |
50 | |
54 | |
51 | our @EXPORT = qw(http_get http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
52 | |
56 | |
53 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
54 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
55 | our $MAX_PERSISTENT = 8; |
59 | our $MAX_PERSISTENT = 8; |
56 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $PERSISTENT_TIMEOUT = 2; |
57 | our $TIMEOUT = 300; |
61 | our $TIMEOUT = 300; |
58 | |
62 | |
59 | # changing these is evil |
63 | # changing these is evil |
60 | our $MAX_PERSISTENT_PER_HOST = 2; |
64 | our $MAX_PERSISTENT_PER_HOST = 0; |
61 | our $MAX_PER_HOST = 4; |
65 | our $MAX_PER_HOST = 4; |
62 | |
66 | |
63 | our $PROXY; |
67 | our $PROXY; |
64 | our $ACTIVE = 0; |
68 | our $ACTIVE = 0; |
65 | |
69 | |
… | |
… | |
67 | my %CO_SLOT; # number of open connections, and wait queue, per host |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
68 | |
72 | |
69 | =item http_get $url, key => value..., $cb->($data, $headers) |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
70 | |
74 | |
71 | Executes an HTTP-GET request. See the http_request function for details on |
75 | Executes an HTTP-GET request. See the http_request function for details on |
72 | additional parameters. |
76 | additional parameters and the return value. |
73 | |
77 | |
74 | =item http_head $url, key => value..., $cb->($data, $headers) |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
75 | |
79 | |
76 | Executes an HTTP-HEAD request. See the http_request function for details on |
80 | Executes an HTTP-HEAD request. See the http_request function for details |
77 | additional parameters. |
81 | on additional parameters and the return value. |
78 | |
82 | |
79 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
80 | |
84 | |
81 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
82 | http_request function for details on additional parameters. |
86 | http_request function for details on additional parameters and the return |
|
|
87 | value. |
83 | |
88 | |
84 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
85 | |
90 | |
86 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
87 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
88 | |
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
|
|
98 | |
89 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response body data as first argument |
90 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if an error occured), and a hash-ref with response headers as |
91 | response headers as second argument. |
101 | second argument. |
92 | |
102 | |
93 | All the headers in that hash are lowercased. In addition to the response |
103 | All the headers in that hash are lowercased. In addition to the response |
94 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
95 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
|
|
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
107 | requested URL when following redirects). |
|
|
108 | |
96 | name. If the server sends a header multiple lines, then their contents |
109 | If the server sends a header multiple times, then their contents will be |
97 | will be joined together with C<\x00>. |
110 | joined together with a comma (C<,>), as per the HTTP spec. |
98 | |
111 | |
99 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
100 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
101 | and the C<Reason> pseudo-header will contain an error message. |
114 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
|
|
115 | message. |
102 | |
116 | |
103 | A typical callback might look like this: |
117 | A typical callback might look like this: |
104 | |
118 | |
105 | sub { |
119 | sub { |
106 | my ($body, $hdr) = @_; |
120 | my ($body, $hdr) = @_; |
… | |
… | |
152 | based on the original netscape specification. |
166 | based on the original netscape specification. |
153 | |
167 | |
154 | The C<$hash_ref> must be an (initially empty) hash reference which will |
168 | The C<$hash_ref> must be an (initially empty) hash reference which will |
155 | get updated automatically. It is possible to save the cookie_jar to |
169 | get updated automatically. It is possible to save the cookie_jar to |
156 | persistent storage with something like JSON or Storable, but this is not |
170 | persistent storage with something like JSON or Storable, but this is not |
157 | recommended, as expire times are currently being ignored. |
171 | recommended, as expiry times are currently being ignored. |
158 | |
172 | |
159 | Note that this cookie implementation is not of very high quality, nor |
173 | Note that this cookie implementation is not of very high quality, nor |
160 | meant to be complete. If you want complete cookie management you have to |
174 | meant to be complete. If you want complete cookie management you have to |
161 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
175 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
162 | cookie-using sites working. Cookies are a privacy disaster, do not use |
176 | cookie-using sites working. Cookies are a privacy disaster, do not use |
163 | them unless required to. |
177 | them unless required to. |
|
|
178 | |
|
|
179 | =item tls_ctx => $scheme | $tls_ctx |
|
|
180 | |
|
|
181 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
182 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
183 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
184 | C<high> can be specified, which give you a predefined low-security (no |
|
|
185 | verification, highest compatibility) and high-security (CA and common-name |
|
|
186 | verification) TLS context. |
|
|
187 | |
|
|
188 | The default for this option is C<low>, which could be interpreted as "give |
|
|
189 | me the page, no matter what". |
|
|
190 | |
|
|
191 | =item on_header => $callback->($headers) |
|
|
192 | |
|
|
193 | 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 |
|
|
195 | locally-generated errors). |
|
|
196 | |
|
|
197 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
198 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
199 | the finish callback with an error code of C<598>). |
|
|
200 | |
|
|
201 | 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 |
|
|
203 | doing a C<HEAD> request. |
|
|
204 | |
|
|
205 | Example: cancel the request unless the content-type is "text/html". |
|
|
206 | |
|
|
207 | on_header => sub { |
|
|
208 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
209 | }, |
|
|
210 | |
|
|
211 | =item on_body => $callback->($partial_body, $headers) |
|
|
212 | |
|
|
213 | When specified, all body data will be passed to this callback instead of |
|
|
214 | to the completion callback. The completion callback will get the empty |
|
|
215 | string instead of the body data. |
|
|
216 | |
|
|
217 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
218 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
219 | the completion callback with an error code of C<598>). |
|
|
220 | |
|
|
221 | This callback is useful when the data is too large to be held in memory |
|
|
222 | (so the callback writes it to a file) or when only some information should |
|
|
223 | be extracted, or when the body should be processed incrementally. |
|
|
224 | |
|
|
225 | It is usually preferred over doing your own body handling via |
|
|
226 | C<want_body_handle>. |
|
|
227 | |
|
|
228 | =item want_body_handle => $enable |
|
|
229 | |
|
|
230 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
231 | changes considerably: after parsing the headers, and instead of |
|
|
232 | downloading the body (if any), the completion callback will be |
|
|
233 | called. Instead of the C<$body> argument containing the body data, the |
|
|
234 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
235 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
236 | (e.g. status C<304>), the empty string will be passed. |
|
|
237 | |
|
|
238 | The handle object might or might not be in TLS mode, might be connected to |
|
|
239 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
240 | ways. The user is responsible for this handle (it will not be used by this |
|
|
241 | module anymore). |
|
|
242 | |
|
|
243 | This is useful with some push-type services, where, after the initial |
|
|
244 | headers, an interactive protocol is used (typical example would be the |
|
|
245 | push-style twitter API which starts a JSON/XML stream). |
|
|
246 | |
|
|
247 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
248 | that doesn'T solve your problem in a better way. |
164 | |
249 | |
165 | =back |
250 | =back |
166 | |
251 | |
167 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
252 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
168 | |
253 | |
… | |
… | |
181 | my ($body, $hdr) = @_; |
266 | my ($body, $hdr) = @_; |
182 | use Data::Dumper; |
267 | use Data::Dumper; |
183 | print Dumper $hdr; |
268 | print Dumper $hdr; |
184 | } |
269 | } |
185 | ; |
270 | ; |
|
|
271 | |
|
|
272 | Example: make another simple HTTP GET request, but immediately try to |
|
|
273 | cancel it. |
|
|
274 | |
|
|
275 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
276 | my ($body, $hdr) = @_; |
|
|
277 | print "$body\n"; |
|
|
278 | }; |
|
|
279 | |
|
|
280 | undef $request; |
186 | |
281 | |
187 | =cut |
282 | =cut |
188 | |
283 | |
189 | sub _slot_schedule; |
284 | sub _slot_schedule; |
190 | sub _slot_schedule($) { |
285 | sub _slot_schedule($) { |
… | |
… | |
214 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
309 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
215 | |
310 | |
216 | _slot_schedule $_[0]; |
311 | _slot_schedule $_[0]; |
217 | } |
312 | } |
218 | |
313 | |
|
|
314 | our $qr_nl = qr<\015?\012>; |
|
|
315 | our $qr_nlnl = qr<\015?\012\015?\012>; |
|
|
316 | |
|
|
317 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
318 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
319 | |
219 | sub http_request($$@) { |
320 | sub http_request($$@) { |
220 | my $cb = pop; |
321 | my $cb = pop; |
221 | my ($method, $url, %arg) = @_; |
322 | my ($method, $url, %arg) = @_; |
222 | |
323 | |
223 | my %hdr; |
324 | my %hdr; |
|
|
325 | |
|
|
326 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
327 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
224 | |
328 | |
225 | $method = uc $method; |
329 | $method = uc $method; |
226 | |
330 | |
227 | if (my $hdr = $arg{headers}) { |
331 | if (my $hdr = $arg{headers}) { |
228 | while (my ($k, $v) = each %$hdr) { |
332 | while (my ($k, $v) = each %$hdr) { |
229 | $hdr{lc $k} = $v; |
333 | $hdr{lc $k} = $v; |
230 | } |
334 | } |
231 | } |
335 | } |
232 | |
336 | |
233 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
337 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
234 | |
338 | |
235 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
339 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
236 | if $recurse < 0; |
340 | if $recurse < 0; |
237 | |
341 | |
238 | my $proxy = $arg{proxy} || $PROXY; |
342 | my $proxy = $arg{proxy} || $PROXY; |
239 | my $timeout = $arg{timeout} || $TIMEOUT; |
343 | my $timeout = $arg{timeout} || $TIMEOUT; |
240 | |
344 | |
241 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
242 | |
|
|
243 | my ($scheme, $authority, $upath, $query, $fragment) = |
345 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
244 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
346 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
245 | |
347 | |
246 | $scheme = lc $scheme; |
348 | $uscheme = lc $uscheme; |
247 | |
349 | |
248 | my $uport = $scheme eq "http" ? 80 |
350 | my $uport = $uscheme eq "http" ? 80 |
249 | : $scheme eq "https" ? 443 |
351 | : $uscheme eq "https" ? 443 |
250 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); |
352 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
251 | |
353 | |
252 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
|
|
253 | |
|
|
254 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
354 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
255 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); |
355 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
256 | |
356 | |
257 | my $uhost = $1; |
357 | my $uhost = $1; |
258 | $uport = $2 if defined $2; |
358 | $uport = $2 if defined $2; |
259 | |
359 | |
|
|
360 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"; |
|
|
361 | |
260 | $uhost =~ s/^\[(.*)\]$/$1/; |
362 | $uhost =~ s/^\[(.*)\]$/$1/; |
261 | $upath .= "?$query" if length $query; |
363 | $upath .= "?$query" if length $query; |
262 | |
364 | |
263 | $upath =~ s%^/?%/%; |
365 | $upath =~ s%^/?%/%; |
264 | |
366 | |
265 | # cookie processing |
367 | # cookie processing |
266 | if (my $jar = $arg{cookie_jar}) { |
368 | if (my $jar = $arg{cookie_jar}) { |
267 | %$jar = () if $jar->{version} < 1; |
369 | %$jar = () if $jar->{version} != 1; |
268 | |
370 | |
269 | my @cookie; |
371 | my @cookie; |
270 | |
372 | |
271 | while (my ($chost, $v) = each %$jar) { |
373 | while (my ($chost, $v) = each %$jar) { |
|
|
374 | if ($chost =~ /^\./) { |
272 | next unless $chost eq substr $uhost, -length $chost; |
375 | next unless $chost eq substr $uhost, -length $chost; |
273 | next unless $chost =~ /^\./; |
376 | } elsif ($chost =~ /\./) { |
|
|
377 | next unless $chost eq $uhost; |
|
|
378 | } else { |
|
|
379 | next; |
|
|
380 | } |
274 | |
381 | |
275 | while (my ($cpath, $v) = each %$v) { |
382 | while (my ($cpath, $v) = each %$v) { |
276 | next unless $cpath eq substr $upath, 0, length $cpath; |
383 | next unless $cpath eq substr $upath, 0, length $cpath; |
277 | |
384 | |
278 | while (my ($k, $v) = each %$v) { |
385 | while (my ($k, $v) = each %$v) { |
279 | next if $scheme ne "https" && exists $v->{secure}; |
386 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
387 | my $value = $v->{value}; |
|
|
388 | $value =~ s/([\\"])/\\$1/g; |
280 | push @cookie, "$k=$v->{value}"; |
389 | push @cookie, "$k=\"$value\""; |
281 | } |
390 | } |
282 | } |
391 | } |
283 | } |
392 | } |
284 | |
393 | |
285 | $hdr{cookie} = join "; ", @cookie |
394 | $hdr{cookie} = join "; ", @cookie |
286 | if @cookie; |
395 | if @cookie; |
287 | } |
396 | } |
288 | |
397 | |
289 | my ($rhost, $rport, $rpath); # request host, port, path |
398 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
290 | |
399 | |
291 | if ($proxy) { |
400 | if ($proxy) { |
292 | ($rhost, $rport, $scheme) = @$proxy; |
401 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
293 | $rpath = $url; |
402 | |
|
|
403 | # don't support https requests over https-proxy transport, |
|
|
404 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
405 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
294 | } else { |
406 | } else { |
295 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
407 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
296 | $hdr{host} = $uhost; |
|
|
297 | } |
408 | } |
|
|
409 | |
|
|
410 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
411 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
298 | |
412 | |
299 | $hdr{"content-length"} = length $arg{body}; |
413 | $hdr{"content-length"} = length $arg{body}; |
300 | |
414 | |
301 | my %state = (connect_guard => 1); |
415 | my %state = (connect_guard => 1); |
302 | |
416 | |
… | |
… | |
305 | |
419 | |
306 | return unless $state{connect_guard}; |
420 | return unless $state{connect_guard}; |
307 | |
421 | |
308 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
422 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
309 | $state{fh} = shift |
423 | $state{fh} = shift |
|
|
424 | or do { |
|
|
425 | my $err = "$!"; |
|
|
426 | %state = (); |
310 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
427 | return $cb->(undef, { Status => 599, Reason => $err, URL => $url }); |
|
|
428 | }; |
311 | |
429 | |
312 | delete $state{connect_guard}; # reduce memory usage, save a tree |
430 | pop; # free memory, save a tree |
|
|
431 | |
|
|
432 | return unless delete $state{connect_guard}; |
313 | |
433 | |
314 | # get handle |
434 | # get handle |
315 | $state{handle} = new AnyEvent::Handle |
435 | $state{handle} = new AnyEvent::Handle |
316 | fh => $state{fh}, |
436 | fh => $state{fh}, |
317 | ($scheme eq "https" ? (tls => "connect") : ()); |
437 | timeout => $timeout, |
|
|
438 | peername => $rhost, |
|
|
439 | tls_ctx => $arg{tls_ctx}; |
318 | |
440 | |
319 | # limit the number of persistent connections |
441 | # limit the number of persistent connections |
|
|
442 | # keepalive not yet supported |
320 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
443 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
321 | ++$KA_COUNT{$_[1]}; |
444 | ++$KA_COUNT{$_[1]}; |
322 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
445 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
446 | --$KA_COUNT{$_[1]} |
|
|
447 | }; |
323 | $hdr{connection} = "keep-alive"; |
448 | $hdr{connection} = "keep-alive"; |
324 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
325 | } else { |
449 | } else { |
326 | delete $hdr{connection}; |
450 | delete $hdr{connection}; |
327 | } |
451 | } |
328 | |
452 | |
329 | # (re-)configure handle |
453 | # (re-)configure handle |
330 | $state{handle}->timeout ($timeout); |
|
|
331 | $state{handle}->on_error (sub { |
454 | $state{handle}->on_error (sub { |
332 | my $errno = "$!"; |
|
|
333 | %state = (); |
455 | %state = (); |
334 | $cb->(undef, { Status => 599, Reason => $errno }); |
456 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
335 | }); |
457 | }); |
336 | $state{handle}->on_eof (sub { |
458 | $state{handle}->on_eof (sub { |
337 | %state = (); |
459 | %state = (); |
338 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
460 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
339 | }); |
461 | }); |
340 | |
462 | |
|
|
463 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
464 | |
|
|
465 | # handle actual, non-tunneled, request |
|
|
466 | my $handle_actual_request = sub { |
|
|
467 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
468 | |
341 | # send request |
469 | # send request |
342 | $state{handle}->push_write ( |
470 | $state{handle}->push_write ( |
343 | "$method $rpath HTTP/1.0\015\012" |
471 | "$method $rpath HTTP/1.0\015\012" |
344 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
472 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
345 | . "\015\012" |
473 | . "\015\012" |
346 | . (delete $arg{body}) |
474 | . (delete $arg{body}) |
347 | ); |
|
|
348 | |
|
|
349 | %hdr = (); # reduce memory usage, save a kitten |
|
|
350 | |
|
|
351 | # status line |
|
|
352 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
353 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
354 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
355 | |
|
|
356 | my %hdr = ( # response headers |
|
|
357 | HTTPVersion => "\x00$1", |
|
|
358 | Status => "\x00$2", |
|
|
359 | Reason => "\x00$3", |
|
|
360 | ); |
475 | ); |
361 | |
476 | |
|
|
477 | %hdr = (); # reduce memory usage, save a kitten |
|
|
478 | |
|
|
479 | # status line |
|
|
480 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
481 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
482 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
483 | |
|
|
484 | my %hdr = ( # response headers |
|
|
485 | HTTPVersion => ",$1", |
|
|
486 | Status => ",$2", |
|
|
487 | Reason => ",$3", |
|
|
488 | URL => ",$url" |
|
|
489 | ); |
|
|
490 | |
362 | # headers, could be optimized a bit |
491 | # headers, could be optimized a bit |
363 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
492 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
364 | for ("$_[1]\012") { |
493 | for ("$_[1]\012") { |
365 | # we support spaces in field names, as lotus domino |
494 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
366 | # creates them. |
495 | |
|
|
496 | # things seen, not parsed: |
|
|
497 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
498 | |
367 | $hdr{lc $1} .= "\x00$2" |
499 | $hdr{lc $1} .= ",$2" |
368 | while /\G |
500 | while /\G |
369 | ([^:\000-\037]+): |
501 | ([^:\000-\037]*): |
370 | [\011\040]* |
502 | [\011\040]* |
371 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
503 | ((?: [^\012]+ | \012[\011\040] )*) |
372 | \015?\012 |
504 | \012 |
373 | /gxc; |
505 | /gxc; |
374 | |
506 | |
375 | /\G$/ |
507 | /\G$/ |
376 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); |
508 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
377 | } |
509 | } |
378 | |
510 | |
379 | substr $_, 0, 1, "" |
511 | substr $_, 0, 1, "" |
380 | for values %hdr; |
512 | for values %hdr; |
381 | |
513 | |
382 | my $finish = sub { |
514 | # redirect handling |
383 | %state = (); |
515 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
516 | # try to support some common forms of broken Location headers. |
|
|
517 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
518 | $hdr{location} =~ s/^\.\/+//; |
384 | |
519 | |
385 | # set-cookie processing |
520 | my $url = "$rscheme://$uhost:$uport"; |
386 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
|
|
387 | for (split /\x00/, $hdr{"set-cookie"}) { |
|
|
388 | my ($cookie, @arg) = split /;\s*/; |
|
|
389 | my ($name, $value) = split /=/, $cookie, 2; |
|
|
390 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
|
|
391 | |
|
|
392 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
393 | my $cpath = (delete $kv{path}) || "/"; |
|
|
394 | |
|
|
395 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
|
|
396 | |
521 | |
397 | next if $cdom =~ /\.$/; |
522 | unless ($hdr{location} =~ s/^\///) { |
398 | |
523 | $url .= $upath; |
399 | # this is not rfc-like and not netscape-like. go figure. |
524 | $url =~ s/\/[^\/]*$//; |
400 | my $ndots = $cdom =~ y/.//; |
525 | } |
401 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
526 | |
402 | |
527 | $hdr{location} = "$url/$hdr{location}"; |
|
|
528 | } |
|
|
529 | |
|
|
530 | my $redirect; |
|
|
531 | |
|
|
532 | if ($recurse) { |
|
|
533 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
|
|
534 | # apparently, mozilla et al. just change POST to GET here |
|
|
535 | # more research is needed before we do the same |
403 | # store it |
536 | $redirect = 1; |
404 | $arg{cookie_jar}{version} = 1; |
537 | } elsif ($hdr{Status} == 303) { |
405 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
538 | # even http/1.1 is unclear on how to mutate the method |
|
|
539 | $method = "GET" unless $method eq "HEAD"; |
|
|
540 | $redirect = 1; |
|
|
541 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
|
|
542 | $redirect = 1; |
406 | } |
543 | } |
407 | } |
544 | } |
408 | |
545 | |
409 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { |
546 | my $finish = sub { |
410 | # microsoft and other assholes don't give a shit for following standards, |
547 | $state{handle}->destroy if $state{handle}; |
411 | # try to support a common form of broken Location header. |
548 | %state = (); |
412 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
|
|
413 | |
549 | |
|
|
550 | # set-cookie processing |
|
|
551 | if ($arg{cookie_jar}) { |
|
|
552 | for ($_[1]{"set-cookie"}) { |
|
|
553 | # parse NAME=VALUE |
|
|
554 | my @kv; |
|
|
555 | |
|
|
556 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
557 | my $name = $1; |
|
|
558 | my $value = $3; |
|
|
559 | |
|
|
560 | unless ($value) { |
|
|
561 | $value = $2; |
|
|
562 | $value =~ s/\\(.)/$1/gs; |
|
|
563 | } |
|
|
564 | |
|
|
565 | push @kv, $name => $value; |
|
|
566 | |
|
|
567 | last unless /\G\s*;/gc; |
|
|
568 | } |
|
|
569 | |
|
|
570 | last unless @kv; |
|
|
571 | |
|
|
572 | my $name = shift @kv; |
|
|
573 | my %kv = (value => shift @kv, @kv); |
|
|
574 | |
|
|
575 | my $cdom; |
|
|
576 | my $cpath = (delete $kv{path}) || "/"; |
|
|
577 | |
|
|
578 | if (exists $kv{domain}) { |
|
|
579 | $cdom = delete $kv{domain}; |
|
|
580 | |
|
|
581 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
582 | |
|
|
583 | next if $cdom =~ /\.$/; |
|
|
584 | |
|
|
585 | # this is not rfc-like and not netscape-like. go figure. |
|
|
586 | my $ndots = $cdom =~ y/.//; |
|
|
587 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
588 | } else { |
|
|
589 | $cdom = $uhost; |
|
|
590 | } |
|
|
591 | |
|
|
592 | # store it |
|
|
593 | $arg{cookie_jar}{version} = 1; |
|
|
594 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
595 | |
|
|
596 | redo if /\G\s*,/gc; |
|
|
597 | } |
|
|
598 | } |
|
|
599 | |
|
|
600 | if ($redirect) { |
|
|
601 | # we ignore any errors, as it is very common to receive |
|
|
602 | # Content-Length != 0 but no actual body |
|
|
603 | # we also access %hdr, as $_[1] might be an erro |
414 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
604 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
605 | } else { |
|
|
606 | $cb->($_[0], $_[1]); |
|
|
607 | } |
|
|
608 | }; |
|
|
609 | |
|
|
610 | my $len = $hdr{"content-length"}; |
|
|
611 | |
|
|
612 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
613 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
|
|
614 | } elsif ( |
|
|
615 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
616 | or $method eq "HEAD" |
|
|
617 | or (defined $len && !$len) |
|
|
618 | ) { |
|
|
619 | # no body |
|
|
620 | $finish->("", \%hdr); |
415 | } else { |
621 | } else { |
416 | $cb->($_[0], $_[1]); |
622 | # body handling, four different code paths |
|
|
623 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
624 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
625 | if (!$redirect && $arg{want_body_handle}) { |
|
|
626 | $_[0]->on_eof (undef); |
|
|
627 | $_[0]->on_error (undef); |
|
|
628 | $_[0]->on_read (undef); |
|
|
629 | |
|
|
630 | $finish->(delete $state{handle}, \%hdr); |
|
|
631 | |
|
|
632 | } elsif ($arg{on_body}) { |
|
|
633 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
634 | if ($len) { |
|
|
635 | $_[0]->on_eof (undef); |
|
|
636 | $_[0]->on_read (sub { |
|
|
637 | $len -= length $_[0]{rbuf}; |
|
|
638 | |
|
|
639 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
640 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
641 | |
|
|
642 | $len > 0 |
|
|
643 | or $finish->("", \%hdr); |
|
|
644 | }); |
|
|
645 | } else { |
|
|
646 | $_[0]->on_eof (sub { |
|
|
647 | $finish->("", \%hdr); |
|
|
648 | }); |
|
|
649 | $_[0]->on_read (sub { |
|
|
650 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
651 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
652 | }); |
|
|
653 | } |
|
|
654 | } else { |
|
|
655 | $_[0]->on_eof (undef); |
|
|
656 | |
|
|
657 | if ($len) { |
|
|
658 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
659 | $_[0]->on_read (sub { |
|
|
660 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
661 | if $len <= length $_[0]{rbuf}; |
|
|
662 | }); |
|
|
663 | } else { |
|
|
664 | $_[0]->on_error (sub { |
|
|
665 | $! == Errno::EPIPE || !$! |
|
|
666 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
|
|
667 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
668 | }); |
|
|
669 | $_[0]->on_read (sub { }); |
|
|
670 | } |
|
|
671 | } |
417 | } |
672 | } |
418 | }; |
673 | }); |
|
|
674 | }); |
|
|
675 | }; |
419 | |
676 | |
420 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
677 | # now handle proxy-CONNECT method |
421 | $finish->(undef, \%hdr); |
678 | if ($proxy && $uscheme eq "https") { |
|
|
679 | # oh dear, we have to wrap it into a connect request |
|
|
680 | |
|
|
681 | # maybe re-use $uauthority with patched port? |
|
|
682 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
683 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
684 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
685 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
|
|
686 | |
|
|
687 | if ($2 == 200) { |
|
|
688 | $rpath = $upath; |
|
|
689 | &$handle_actual_request; |
422 | } else { |
690 | } else { |
423 | if (exists $hdr{"content-length"}) { |
691 | %state = (); |
424 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
692 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
425 | # could cache persistent connection now |
|
|
426 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
427 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
428 | }; |
|
|
429 | |
|
|
430 | $finish->($_[1], \%hdr); |
|
|
431 | }); |
|
|
432 | } else { |
|
|
433 | # too bad, need to read until we get an error or EOF, |
|
|
434 | # no way to detect winged data. |
|
|
435 | $_[0]->on_error (sub { |
|
|
436 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
437 | }); |
|
|
438 | $_[0]->on_eof (undef); |
|
|
439 | $_[0]->on_read (sub { }); |
|
|
440 | } |
|
|
441 | } |
693 | } |
442 | }); |
694 | }); |
|
|
695 | } else { |
|
|
696 | &$handle_actual_request; |
443 | }); |
697 | } |
|
|
698 | |
444 | }, sub { |
699 | }, sub { |
445 | $timeout |
700 | $timeout |
446 | }; |
701 | }; |
447 | }; |
702 | }; |
448 | |
703 | |
… | |
… | |
458 | unshift @_, "HEAD"; |
713 | unshift @_, "HEAD"; |
459 | &http_request |
714 | &http_request |
460 | } |
715 | } |
461 | |
716 | |
462 | sub http_post($$@) { |
717 | sub http_post($$@) { |
|
|
718 | my $url = shift; |
463 | unshift @_, "POST", "body"; |
719 | unshift @_, "POST", $url, "body"; |
464 | &http_request |
720 | &http_request |
465 | } |
721 | } |
466 | |
722 | |
467 | =back |
723 | =back |
468 | |
724 | |
… | |
… | |
480 | The default value for the C<recurse> request parameter (default: C<10>). |
736 | The default value for the C<recurse> request parameter (default: C<10>). |
481 | |
737 | |
482 | =item $AnyEvent::HTTP::USERAGENT |
738 | =item $AnyEvent::HTTP::USERAGENT |
483 | |
739 | |
484 | The default value for the C<User-Agent> header (the default is |
740 | The default value for the C<User-Agent> header (the default is |
485 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
741 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
486 | |
742 | |
487 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
743 | =item $AnyEvent::HTTP::MAX_PER_HOST |
488 | |
744 | |
489 | The maximum number of persistent connections to keep open (default: 8). |
745 | The maximum number of concurrent conenctions to the same host (identified |
|
|
746 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
747 | are queued until previous connections are closed. |
490 | |
748 | |
491 | Not implemented currently. |
749 | The default value for this is C<4>, and it is highly advisable to not |
492 | |
750 | increase it. |
493 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
494 | |
|
|
495 | The maximum time to cache a persistent connection, in seconds (default: 2). |
|
|
496 | |
|
|
497 | Not implemented currently. |
|
|
498 | |
751 | |
499 | =item $AnyEvent::HTTP::ACTIVE |
752 | =item $AnyEvent::HTTP::ACTIVE |
500 | |
753 | |
501 | The number of active connections. This is not the number of currently |
754 | The number of active connections. This is not the number of currently |
502 | running requests, but the number of currently open and non-idle TCP |
755 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
517 | |
770 | |
518 | L<AnyEvent>. |
771 | L<AnyEvent>. |
519 | |
772 | |
520 | =head1 AUTHOR |
773 | =head1 AUTHOR |
521 | |
774 | |
522 | Marc Lehmann <schmorp@schmorp.de> |
775 | Marc Lehmann <schmorp@schmorp.de> |
523 | http://home.schmorp.de/ |
776 | http://home.schmorp.de/ |
|
|
777 | |
|
|
778 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
779 | testcases and bugreports. |
524 | |
780 | |
525 | =cut |
781 | =cut |
526 | |
782 | |
527 | 1 |
783 | 1 |
528 | |
784 | |