… | |
… | |
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 5.0 (); |
43 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
44 | use AnyEvent::Socket (); |
|
|
45 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
46 | |
49 | |
47 | use base Exporter::; |
50 | use base Exporter::; |
48 | |
51 | |
49 | our $VERSION = '1.1'; |
52 | our $VERSION = '1.5'; |
50 | |
53 | |
51 | our @EXPORT = qw(http_get http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
52 | |
55 | |
53 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
54 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
55 | our $MAX_PERSISTENT = 8; |
58 | our $MAX_PERSISTENT = 8; |
56 | our $PERSISTENT_TIMEOUT = 2; |
59 | our $PERSISTENT_TIMEOUT = 2; |
57 | our $TIMEOUT = 300; |
60 | our $TIMEOUT = 300; |
58 | |
61 | |
59 | # changing these is evil |
62 | # changing these is evil |
60 | our $MAX_PERSISTENT_PER_HOST = 2; |
63 | our $MAX_PERSISTENT_PER_HOST = 0; |
61 | our $MAX_PER_HOST = 4; |
64 | our $MAX_PER_HOST = 4; |
62 | |
65 | |
63 | our $PROXY; |
66 | our $PROXY; |
64 | our $ACTIVE = 0; |
67 | our $ACTIVE = 0; |
65 | |
68 | |
… | |
… | |
67 | my %CO_SLOT; # number of open connections, and wait queue, per host |
70 | my %CO_SLOT; # number of open connections, and wait queue, per host |
68 | |
71 | |
69 | =item http_get $url, key => value..., $cb->($data, $headers) |
72 | =item http_get $url, key => value..., $cb->($data, $headers) |
70 | |
73 | |
71 | Executes an HTTP-GET request. See the http_request function for details on |
74 | Executes an HTTP-GET request. See the http_request function for details on |
72 | additional parameters. |
75 | additional parameters and the return value. |
73 | |
76 | |
74 | =item http_head $url, key => value..., $cb->($data, $headers) |
77 | =item http_head $url, key => value..., $cb->($data, $headers) |
75 | |
78 | |
76 | Executes an HTTP-HEAD request. See the http_request function for details on |
79 | Executes an HTTP-HEAD request. See the http_request function for details |
77 | additional parameters. |
80 | on additional parameters and the return value. |
78 | |
81 | |
79 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
82 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
80 | |
83 | |
81 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
84 | Executes an HTTP-POST request with a request body of C<$body>. See the |
82 | http_request function for details on additional parameters. |
85 | http_request function for details on additional parameters and the return |
|
|
86 | value. |
83 | |
87 | |
84 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
85 | |
89 | |
86 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
90 | 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. |
91 | must be an absolute http or https URL. |
88 | |
92 | |
|
|
93 | When called in void context, nothing is returned. In other contexts, |
|
|
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
95 | object at least alive until the callback get called. If the object gets |
|
|
96 | destroyed before the callback is called, the request will be cancelled. |
|
|
97 | |
89 | The callback will be called with the response data as first argument |
98 | 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 |
99 | (or C<undef> if an error occured), and a hash-ref with response headers as |
91 | response headers as second argument. |
100 | second argument. |
92 | |
101 | |
93 | All the headers in that hash are lowercased. In addition to the response |
102 | All the headers in that hash are lowercased. In addition to the response |
94 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
95 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
|
|
105 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
106 | during the body phase of a request, then the original C<Status> and |
|
|
107 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
108 | C<OrigReason>. |
|
|
109 | |
|
|
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
|
|
111 | the requested URL when following redirects - for example, you might get |
|
|
112 | an error that your URL scheme is not supported even though your URL is a |
|
|
113 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
114 | look at the URL pseudo header). |
|
|
115 | |
|
|
116 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
117 | of an internal redirect. In that case it is an array reference with |
|
|
118 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
119 | response could in turn be the result of a redirect itself, and C<< |
|
|
120 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
121 | response, and so on. |
|
|
122 | |
96 | name. If the server sends a header multiple lines, then their contents |
123 | If the server sends a header multiple times, then their contents will be |
97 | will be joined together with C<\x00>. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
98 | |
125 | |
99 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
100 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
101 | and the C<Reason> pseudo-header will contain an error message. |
128 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
|
|
129 | message. |
102 | |
130 | |
103 | A typical callback might look like this: |
131 | A typical callback might look like this: |
104 | |
132 | |
105 | sub { |
133 | sub { |
106 | my ($body, $hdr) = @_; |
134 | my ($body, $hdr) = @_; |
… | |
… | |
124 | |
152 | |
125 | =item headers => hashref |
153 | =item headers => hashref |
126 | |
154 | |
127 | The request headers to use. Currently, C<http_request> may provide its |
155 | The request headers to use. Currently, C<http_request> may provide its |
128 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
156 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
129 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
157 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
|
|
158 | suppressed by using C<undef> for these headers in which case they won't be |
|
|
159 | sent at all). |
130 | |
160 | |
131 | =item timeout => $seconds |
161 | =item timeout => $seconds |
132 | |
162 | |
133 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
134 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
165 | timeout. |
|
|
166 | |
|
|
167 | Default timeout is 5 minutes. |
135 | |
168 | |
136 | =item proxy => [$host, $port[, $scheme]] or undef |
169 | =item proxy => [$host, $port[, $scheme]] or undef |
137 | |
170 | |
138 | Use the given http proxy for all requests. If not specified, then the |
171 | Use the given http proxy for all requests. If not specified, then the |
139 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
172 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
140 | |
173 | |
141 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
174 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
142 | HTTPS. |
175 | HTTPS. |
143 | |
176 | |
144 | =item body => $string |
177 | =item body => $string |
145 | |
178 | |
146 | The request body, usually empty. Will be-sent as-is (future versions of |
179 | The request body, usually empty. Will be-sent as-is (future versions of |
… | |
… | |
152 | based on the original netscape specification. |
185 | based on the original netscape specification. |
153 | |
186 | |
154 | The C<$hash_ref> must be an (initially empty) hash reference which will |
187 | 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 |
188 | 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 |
189 | persistent storage with something like JSON or Storable, but this is not |
157 | recommended, as expire times are currently being ignored. |
190 | recommended, as expiry times are currently being ignored. |
158 | |
191 | |
159 | Note that this cookie implementation is not of very high quality, nor |
192 | 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 |
193 | 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 |
194 | 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 |
195 | cookie-using sites working. Cookies are a privacy disaster, do not use |
163 | them unless required to. |
196 | them unless required to. |
|
|
197 | |
|
|
198 | =item tls_ctx => $scheme | $tls_ctx |
|
|
199 | |
|
|
200 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
201 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
202 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
203 | C<high> can be specified, which give you a predefined low-security (no |
|
|
204 | verification, highest compatibility) and high-security (CA and common-name |
|
|
205 | verification) TLS context. |
|
|
206 | |
|
|
207 | The default for this option is C<low>, which could be interpreted as "give |
|
|
208 | me the page, no matter what". |
|
|
209 | |
|
|
210 | =item on_prepare => $callback->($fh) |
|
|
211 | |
|
|
212 | In rare cases you need to "tune" the socket before it is used to |
|
|
213 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
214 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
215 | and behaves exactly the same way (e.g. it has to provide a |
|
|
216 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
217 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
218 | |
|
|
219 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
220 | |
|
|
221 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
222 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
223 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
224 | obviously, it has to follow the same calling conventions, except that it |
|
|
225 | may always return a connection guard object. |
|
|
226 | |
|
|
227 | There are probably lots of weird uses for this function, starting from |
|
|
228 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
229 | but fast) host => IP address caching or even socks protocol support. |
|
|
230 | |
|
|
231 | =item on_header => $callback->($headers) |
|
|
232 | |
|
|
233 | When specified, this callback will be called with the header hash as soon |
|
|
234 | as headers have been successfully received from the remote server (not on |
|
|
235 | locally-generated errors). |
|
|
236 | |
|
|
237 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
238 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
239 | the finish callback with an error code of C<598>). |
|
|
240 | |
|
|
241 | This callback is useful, among other things, to quickly reject unwanted |
|
|
242 | content, which, if it is supposed to be rare, can be faster than first |
|
|
243 | doing a C<HEAD> request. |
|
|
244 | |
|
|
245 | Example: cancel the request unless the content-type is "text/html". |
|
|
246 | |
|
|
247 | on_header => sub { |
|
|
248 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
249 | }, |
|
|
250 | |
|
|
251 | =item on_body => $callback->($partial_body, $headers) |
|
|
252 | |
|
|
253 | When specified, all body data will be passed to this callback instead of |
|
|
254 | to the completion callback. The completion callback will get the empty |
|
|
255 | string instead of the body data. |
|
|
256 | |
|
|
257 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
258 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
259 | the completion callback with an error code of C<598>). |
|
|
260 | |
|
|
261 | This callback is useful when the data is too large to be held in memory |
|
|
262 | (so the callback writes it to a file) or when only some information should |
|
|
263 | be extracted, or when the body should be processed incrementally. |
|
|
264 | |
|
|
265 | It is usually preferred over doing your own body handling via |
|
|
266 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
267 | only used to create a connection, C<want_body_handle> is the better |
|
|
268 | alternative, as it allows you to install your own event handler, reducing |
|
|
269 | resource usage. |
|
|
270 | |
|
|
271 | =item want_body_handle => $enable |
|
|
272 | |
|
|
273 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
274 | changes considerably: after parsing the headers, and instead of |
|
|
275 | downloading the body (if any), the completion callback will be |
|
|
276 | called. Instead of the C<$body> argument containing the body data, the |
|
|
277 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
278 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
279 | (e.g. status C<304>), the empty string will be passed. |
|
|
280 | |
|
|
281 | The handle object might or might not be in TLS mode, might be connected to |
|
|
282 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
283 | ways. The user is responsible for this handle (it will not be used by this |
|
|
284 | module anymore). |
|
|
285 | |
|
|
286 | This is useful with some push-type services, where, after the initial |
|
|
287 | headers, an interactive protocol is used (typical example would be the |
|
|
288 | push-style twitter API which starts a JSON/XML stream). |
|
|
289 | |
|
|
290 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
291 | that doesn't solve your problem in a better way. |
164 | |
292 | |
165 | =back |
293 | =back |
166 | |
294 | |
167 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
295 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
168 | |
296 | |
… | |
… | |
181 | my ($body, $hdr) = @_; |
309 | my ($body, $hdr) = @_; |
182 | use Data::Dumper; |
310 | use Data::Dumper; |
183 | print Dumper $hdr; |
311 | print Dumper $hdr; |
184 | } |
312 | } |
185 | ; |
313 | ; |
|
|
314 | |
|
|
315 | Example: make another simple HTTP GET request, but immediately try to |
|
|
316 | cancel it. |
|
|
317 | |
|
|
318 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
319 | my ($body, $hdr) = @_; |
|
|
320 | print "$body\n"; |
|
|
321 | }; |
|
|
322 | |
|
|
323 | undef $request; |
186 | |
324 | |
187 | =cut |
325 | =cut |
188 | |
326 | |
189 | sub _slot_schedule; |
327 | sub _slot_schedule; |
190 | sub _slot_schedule($) { |
328 | sub _slot_schedule($) { |
… | |
… | |
214 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
352 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
215 | |
353 | |
216 | _slot_schedule $_[0]; |
354 | _slot_schedule $_[0]; |
217 | } |
355 | } |
218 | |
356 | |
|
|
357 | # continue to parse $_ for headers and place them into the arg |
|
|
358 | sub parse_hdr() { |
|
|
359 | my %hdr; |
|
|
360 | |
|
|
361 | # things seen, not parsed: |
|
|
362 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
363 | |
|
|
364 | $hdr{lc $1} .= ",$2" |
|
|
365 | while /\G |
|
|
366 | ([^:\000-\037]*): |
|
|
367 | [\011\040]* |
|
|
368 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
369 | \012 |
|
|
370 | /gxc; |
|
|
371 | |
|
|
372 | /\G$/ |
|
|
373 | or return; |
|
|
374 | |
|
|
375 | # remove the "," prefix we added to all headers above |
|
|
376 | substr $_, 0, 1, "" |
|
|
377 | for values %hdr; |
|
|
378 | |
|
|
379 | \%hdr |
|
|
380 | } |
|
|
381 | |
|
|
382 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
|
|
383 | |
|
|
384 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
385 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
386 | |
219 | sub http_request($$@) { |
387 | sub http_request($$@) { |
220 | my $cb = pop; |
388 | my $cb = pop; |
221 | my ($method, $url, %arg) = @_; |
389 | my ($method, $url, %arg) = @_; |
222 | |
390 | |
223 | my %hdr; |
391 | my %hdr; |
|
|
392 | |
|
|
393 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
394 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
224 | |
395 | |
225 | $method = uc $method; |
396 | $method = uc $method; |
226 | |
397 | |
227 | if (my $hdr = $arg{headers}) { |
398 | if (my $hdr = $arg{headers}) { |
228 | while (my ($k, $v) = each %$hdr) { |
399 | while (my ($k, $v) = each %$hdr) { |
229 | $hdr{lc $k} = $v; |
400 | $hdr{lc $k} = $v; |
230 | } |
401 | } |
231 | } |
402 | } |
232 | |
403 | |
|
|
404 | # pseudo headers for all subsequent responses |
|
|
405 | my @pseudo = (URL => $url); |
|
|
406 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
407 | |
233 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
408 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
234 | |
409 | |
235 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
410 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
236 | if $recurse < 0; |
411 | if $recurse < 0; |
237 | |
412 | |
238 | my $proxy = $arg{proxy} || $PROXY; |
413 | my $proxy = $arg{proxy} || $PROXY; |
239 | my $timeout = $arg{timeout} || $TIMEOUT; |
414 | my $timeout = $arg{timeout} || $TIMEOUT; |
240 | |
415 | |
241 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
242 | |
|
|
243 | my ($scheme, $authority, $upath, $query, $fragment) = |
416 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
244 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
417 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
245 | |
418 | |
246 | $scheme = lc $scheme; |
419 | $uscheme = lc $uscheme; |
247 | |
420 | |
248 | my $uport = $scheme eq "http" ? 80 |
421 | my $uport = $uscheme eq "http" ? 80 |
249 | : $scheme eq "https" ? 443 |
422 | : $uscheme eq "https" ? 443 |
250 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); |
423 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
251 | |
424 | |
252 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
|
|
253 | |
|
|
254 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
425 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
255 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); |
426 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
256 | |
427 | |
257 | my $uhost = $1; |
428 | my $uhost = $1; |
258 | $uport = $2 if defined $2; |
429 | $uport = $2 if defined $2; |
259 | |
430 | |
|
|
431 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
432 | unless exists $hdr{host}; |
|
|
433 | |
260 | $uhost =~ s/^\[(.*)\]$/$1/; |
434 | $uhost =~ s/^\[(.*)\]$/$1/; |
261 | $upath .= "?$query" if length $query; |
435 | $upath .= $query if length $query; |
262 | |
436 | |
263 | $upath =~ s%^/?%/%; |
437 | $upath =~ s%^/?%/%; |
264 | |
438 | |
265 | # cookie processing |
439 | # cookie processing |
266 | if (my $jar = $arg{cookie_jar}) { |
440 | if (my $jar = $arg{cookie_jar}) { |
267 | %$jar = () if $jar->{version} < 1; |
441 | %$jar = () if $jar->{version} != 1; |
268 | |
442 | |
269 | my @cookie; |
443 | my @cookie; |
270 | |
444 | |
271 | while (my ($chost, $v) = each %$jar) { |
445 | while (my ($chost, $v) = each %$jar) { |
|
|
446 | if ($chost =~ /^\./) { |
272 | next unless $chost eq substr $uhost, -length $chost; |
447 | next unless $chost eq substr $uhost, -length $chost; |
273 | next unless $chost =~ /^\./; |
448 | } elsif ($chost =~ /\./) { |
|
|
449 | next unless $chost eq $uhost; |
|
|
450 | } else { |
|
|
451 | next; |
|
|
452 | } |
274 | |
453 | |
275 | while (my ($cpath, $v) = each %$v) { |
454 | while (my ($cpath, $v) = each %$v) { |
276 | next unless $cpath eq substr $upath, 0, length $cpath; |
455 | next unless $cpath eq substr $upath, 0, length $cpath; |
277 | |
456 | |
278 | while (my ($k, $v) = each %$v) { |
457 | while (my ($k, $v) = each %$v) { |
279 | next if $scheme ne "https" && exists $v->{secure}; |
458 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
459 | my $value = $v->{value}; |
|
|
460 | $value =~ s/([\\"])/\\$1/g; |
280 | push @cookie, "$k=$v->{value}"; |
461 | push @cookie, "$k=\"$value\""; |
281 | } |
462 | } |
282 | } |
463 | } |
283 | } |
464 | } |
284 | |
465 | |
285 | $hdr{cookie} = join "; ", @cookie |
466 | $hdr{cookie} = join "; ", @cookie |
286 | if @cookie; |
467 | if @cookie; |
287 | } |
468 | } |
288 | |
469 | |
289 | my ($rhost, $rport, $rpath); # request host, port, path |
470 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
290 | |
471 | |
291 | if ($proxy) { |
472 | if ($proxy) { |
292 | ($rhost, $rport, $scheme) = @$proxy; |
473 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
293 | $rpath = $url; |
474 | |
|
|
475 | $rscheme = "http" unless defined $rscheme; |
|
|
476 | |
|
|
477 | # don't support https requests over https-proxy transport, |
|
|
478 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
479 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
294 | } else { |
480 | } else { |
295 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
481 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
296 | $hdr{host} = $uhost; |
|
|
297 | } |
482 | } |
298 | |
483 | |
|
|
484 | # leave out fragment and query string, just a heuristic |
|
|
485 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
486 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
|
|
487 | |
299 | $hdr{"content-length"} = length $arg{body}; |
488 | $hdr{"content-length"} = length $arg{body} |
|
|
489 | if length $arg{body} || $method ne "GET"; |
|
|
490 | |
|
|
491 | $hdr{connection} = "close TE"; |
|
|
492 | $hdr{te} = "trailers" unless exists $hdr{te}; |
300 | |
493 | |
301 | my %state = (connect_guard => 1); |
494 | my %state = (connect_guard => 1); |
302 | |
495 | |
303 | _get_slot $uhost, sub { |
496 | _get_slot $uhost, sub { |
304 | $state{slot_guard} = shift; |
497 | $state{slot_guard} = shift; |
305 | |
498 | |
306 | return unless $state{connect_guard}; |
499 | return unless $state{connect_guard}; |
307 | |
500 | |
308 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
501 | my $connect_cb = sub { |
309 | $state{fh} = shift |
502 | $state{fh} = shift |
|
|
503 | or do { |
|
|
504 | my $err = "$!"; |
|
|
505 | %state = (); |
310 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
506 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
|
|
507 | }; |
311 | |
508 | |
312 | delete $state{connect_guard}; # reduce memory usage, save a tree |
509 | pop; # free memory, save a tree |
|
|
510 | |
|
|
511 | return unless delete $state{connect_guard}; |
313 | |
512 | |
314 | # get handle |
513 | # get handle |
315 | $state{handle} = new AnyEvent::Handle |
514 | $state{handle} = new AnyEvent::Handle |
316 | fh => $state{fh}, |
515 | fh => $state{fh}, |
317 | ($scheme eq "https" ? (tls => "connect") : ()); |
516 | peername => $rhost, |
|
|
517 | tls_ctx => $arg{tls_ctx}, |
|
|
518 | # these need to be reconfigured on keepalive handles |
|
|
519 | timeout => $timeout, |
|
|
520 | on_error => sub { |
|
|
521 | %state = (); |
|
|
522 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
|
|
523 | }, |
|
|
524 | on_eof => sub { |
|
|
525 | %state = (); |
|
|
526 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
|
|
527 | }, |
|
|
528 | ; |
318 | |
529 | |
319 | # limit the number of persistent connections |
530 | # limit the number of persistent connections |
|
|
531 | # keepalive not yet supported |
320 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
532 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
321 | ++$KA_COUNT{$_[1]}; |
533 | # ++$KA_COUNT{$_[1]}; |
322 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
534 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
535 | # --$KA_COUNT{$_[1]} |
|
|
536 | # }; |
323 | $hdr{connection} = "keep-alive"; |
537 | # $hdr{connection} = "keep-alive"; |
324 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
325 | } else { |
538 | # } else { |
326 | delete $hdr{connection}; |
539 | # delete $hdr{connection}; |
327 | } |
540 | # } |
328 | |
541 | |
329 | # (re-)configure handle |
542 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
330 | $state{handle}->timeout ($timeout); |
|
|
331 | $state{handle}->on_error (sub { |
|
|
332 | my $errno = "$!"; |
|
|
333 | %state = (); |
|
|
334 | $cb->(undef, { Status => 599, Reason => $errno }); |
|
|
335 | }); |
|
|
336 | $state{handle}->on_eof (sub { |
|
|
337 | %state = (); |
|
|
338 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
|
|
339 | }); |
|
|
340 | |
543 | |
|
|
544 | # handle actual, non-tunneled, request |
|
|
545 | my $handle_actual_request = sub { |
|
|
546 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
547 | |
341 | # send request |
548 | # send request |
342 | $state{handle}->push_write ( |
549 | $state{handle}->push_write ( |
343 | "$method $rpath HTTP/1.0\015\012" |
550 | "$method $rpath HTTP/1.1\015\012" |
344 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
551 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
345 | . "\015\012" |
552 | . "\015\012" |
346 | . (delete $arg{body}) |
553 | . (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 | ); |
554 | ); |
361 | |
555 | |
362 | # headers, could be optimized a bit |
556 | # return if error occured during push_write() |
|
|
557 | return unless %state; |
|
|
558 | |
|
|
559 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
560 | |
|
|
561 | # status line and headers |
363 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
562 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
563 | my $keepalive = pop; |
|
|
564 | |
364 | for ("$_[1]\012") { |
565 | for ("$_[1]") { |
365 | # we support spaces in field names, as lotus domino |
566 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
366 | # creates them. |
|
|
367 | $hdr{lc $1} .= "\x00$2" |
|
|
368 | while /\G |
|
|
369 | ([^:\000-\037]+): |
|
|
370 | [\011\040]* |
|
|
371 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
|
|
372 | \015?\012 |
|
|
373 | /gxc; |
|
|
374 | |
567 | |
|
|
568 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
|
|
569 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
570 | |
|
|
571 | push @pseudo, |
|
|
572 | HTTPVersion => $1, |
|
|
573 | Status => $2, |
|
|
574 | Reason => $3, |
375 | /\G$/ |
575 | ; |
|
|
576 | |
|
|
577 | my $hdr = parse_hdr |
376 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); |
578 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
579 | |
|
|
580 | %hdr = (%$hdr, @pseudo); |
377 | } |
581 | } |
378 | |
582 | |
379 | substr $_, 0, 1, "" |
583 | # redirect handling |
380 | for values %hdr; |
584 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
585 | # try to support some common forms of broken Location headers. |
|
|
586 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
587 | $hdr{location} =~ s/^\.\/+//; |
381 | |
588 | |
382 | my $finish = sub { |
589 | my $url = "$rscheme://$uhost:$uport"; |
|
|
590 | |
|
|
591 | unless ($hdr{location} =~ s/^\///) { |
|
|
592 | $url .= $upath; |
|
|
593 | $url =~ s/\/[^\/]*$//; |
|
|
594 | } |
|
|
595 | |
|
|
596 | $hdr{location} = "$url/$hdr{location}"; |
|
|
597 | } |
|
|
598 | |
|
|
599 | my $redirect; |
|
|
600 | |
|
|
601 | if ($recurse) { |
|
|
602 | my $status = $hdr{Status}; |
|
|
603 | |
|
|
604 | # industry standard is to redirect POST as GET for |
|
|
605 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
606 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
607 | # industry standard seems to be to simply follow. |
|
|
608 | # we go with the industry standard. |
|
|
609 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
610 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
611 | $method = "GET" unless $method eq "HEAD"; |
|
|
612 | $redirect = 1; |
|
|
613 | } elsif ($status == 307) { |
|
|
614 | $redirect = 1; |
|
|
615 | } |
|
|
616 | } |
|
|
617 | |
|
|
618 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
619 | $state{handle}->destroy if $state{handle}; |
383 | %state = (); |
620 | %state = (); |
384 | |
621 | |
|
|
622 | if (defined $_[1]) { |
|
|
623 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
624 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
625 | } |
|
|
626 | |
385 | # set-cookie processing |
627 | # set-cookie processing |
386 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
628 | if ($arg{cookie_jar}) { |
387 | for (split /\x00/, $hdr{"set-cookie"}) { |
629 | for ($hdr{"set-cookie"}) { |
388 | my ($cookie, @arg) = split /;\s*/; |
630 | # parse NAME=VALUE |
389 | my ($name, $value) = split /=/, $cookie, 2; |
631 | my @kv; |
390 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
632 | |
|
|
633 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
634 | my $name = $1; |
|
|
635 | my $value = $3; |
|
|
636 | |
|
|
637 | unless ($value) { |
|
|
638 | $value = $2; |
|
|
639 | $value =~ s/\\(.)/$1/gs; |
|
|
640 | } |
|
|
641 | |
|
|
642 | push @kv, $name => $value; |
|
|
643 | |
|
|
644 | last unless /\G\s*;/gc; |
|
|
645 | } |
|
|
646 | |
|
|
647 | last unless @kv; |
|
|
648 | |
|
|
649 | my $name = shift @kv; |
|
|
650 | my %kv = (value => shift @kv, @kv); |
|
|
651 | |
|
|
652 | my $cdom; |
|
|
653 | my $cpath = (delete $kv{path}) || "/"; |
|
|
654 | |
|
|
655 | if (exists $kv{domain}) { |
|
|
656 | $cdom = delete $kv{domain}; |
391 | |
657 | |
392 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
393 | my $cpath = (delete $kv{path}) || "/"; |
|
|
394 | |
|
|
395 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
658 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
396 | |
659 | |
397 | next if $cdom =~ /\.$/; |
660 | next if $cdom =~ /\.$/; |
398 | |
661 | |
399 | # this is not rfc-like and not netscape-like. go figure. |
662 | # this is not rfc-like and not netscape-like. go figure. |
400 | my $ndots = $cdom =~ y/.//; |
663 | my $ndots = $cdom =~ y/.//; |
401 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
664 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
665 | } else { |
|
|
666 | $cdom = $uhost; |
|
|
667 | } |
402 | |
668 | |
403 | # store it |
669 | # store it |
404 | $arg{cookie_jar}{version} = 1; |
670 | $arg{cookie_jar}{version} = 1; |
405 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
671 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
672 | |
|
|
673 | redo if /\G\s*,/gc; |
406 | } |
674 | } |
407 | } |
675 | } |
408 | |
676 | |
409 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { |
677 | if ($redirect && exists $hdr{location}) { |
410 | # microsoft and other assholes don't give a shit for following standards, |
678 | # we ignore any errors, as it is very common to receive |
411 | # try to support a common form of broken Location header. |
679 | # Content-Length != 0 but no actual body |
412 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
680 | # we also access %hdr, as $_[1] might be an erro |
413 | |
681 | http_request ( |
414 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
682 | $method => $hdr{location}, |
|
|
683 | %arg, |
|
|
684 | recurse => $recurse - 1, |
|
|
685 | Redirect => [$_[0], \%hdr], |
|
|
686 | $cb); |
415 | } else { |
687 | } else { |
416 | $cb->($_[0], $_[1]); |
688 | $cb->($_[0], \%hdr); |
417 | } |
689 | } |
418 | }; |
690 | }; |
419 | |
691 | |
420 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
692 | my $len = $hdr{"content-length"}; |
|
|
693 | |
|
|
694 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
695 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
696 | } elsif ( |
|
|
697 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
698 | or $method eq "HEAD" |
|
|
699 | or (defined $len && !$len) |
|
|
700 | ) { |
|
|
701 | # no body |
421 | $finish->(undef, \%hdr); |
702 | $finish->("", undef, undef, 1); |
422 | } else { |
703 | } else { |
423 | if (exists $hdr{"content-length"}) { |
704 | # body handling, many different code paths |
424 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
705 | # - no body expected |
425 | # could cache persistent connection now |
706 | # - want_body_handle |
426 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
707 | # - te chunked |
427 | # but we don't, due to misdesigns, this is annoyingly complex |
708 | # - 2x length known (with or without on_body) |
|
|
709 | # - 2x length not known (with or without on_body) |
|
|
710 | if (!$redirect && $arg{want_body_handle}) { |
|
|
711 | $_[0]->on_eof (undef); |
|
|
712 | $_[0]->on_error (undef); |
|
|
713 | $_[0]->on_read (undef); |
|
|
714 | |
|
|
715 | $finish->(delete $state{handle}); |
|
|
716 | |
|
|
717 | } elsif ($hdr{"transfer-encoding"} =~ /chunked/) { |
|
|
718 | my $body = undef; |
|
|
719 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
720 | |
|
|
721 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
722 | |
|
|
723 | my $read_chunk; $read_chunk = sub { |
|
|
724 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
725 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
726 | |
|
|
727 | my $len = hex $1; |
|
|
728 | |
|
|
729 | if ($len) { |
|
|
730 | $_[0]->push_read (chunk => hex $1, sub { |
|
|
731 | $on_body->($_[1], \%hdr) |
|
|
732 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
733 | |
|
|
734 | $_[0]->push_read (line => sub { |
|
|
735 | length $_[1] |
|
|
736 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
737 | $_[0]->push_read (line => $read_chunk); |
|
|
738 | }); |
|
|
739 | }); |
|
|
740 | } else { |
|
|
741 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
742 | if (length $_[1]) { |
|
|
743 | for ("$_[1]") { |
|
|
744 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
745 | |
|
|
746 | my $hdr = parse_hdr |
|
|
747 | or return $finish->(undef, 599 => "Garbled response trailers"); |
|
|
748 | |
|
|
749 | %hdr = (%hdr, %$hdr); |
|
|
750 | } |
|
|
751 | } |
|
|
752 | |
|
|
753 | $finish->($body, undef, undef, 1); |
|
|
754 | }); |
|
|
755 | } |
|
|
756 | }; |
|
|
757 | |
|
|
758 | $_[0]->push_read (line => $read_chunk); |
|
|
759 | |
|
|
760 | } elsif ($arg{on_body}) { |
|
|
761 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
762 | |
|
|
763 | if ($len) { |
|
|
764 | $_[0]->on_read (sub { |
|
|
765 | $len -= length $_[0]{rbuf}; |
|
|
766 | |
|
|
767 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
768 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
769 | |
|
|
770 | $len > 0 |
|
|
771 | or $finish->("", undef, undef, 1); |
428 | }; |
772 | }); |
429 | |
773 | } else { |
|
|
774 | $_[0]->on_eof (sub { |
430 | $finish->($_[1], \%hdr); |
775 | $finish->(""); |
|
|
776 | }); |
|
|
777 | $_[0]->on_read (sub { |
|
|
778 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
779 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
780 | }); |
431 | }); |
781 | } |
432 | } else { |
782 | } 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); |
783 | $_[0]->on_eof (undef); |
|
|
784 | |
|
|
785 | if ($len) { |
|
|
786 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
787 | $_[0]->on_read (sub { |
|
|
788 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
789 | if $len <= length $_[0]{rbuf}; |
|
|
790 | }); |
|
|
791 | } else { |
|
|
792 | $_[0]->on_error (sub { |
|
|
793 | ($! == Errno::EPIPE || !$!) |
|
|
794 | ? $finish->(delete $_[0]{rbuf}) |
|
|
795 | : $finish->(undef, 599 => $_[2]); |
|
|
796 | }); |
439 | $_[0]->on_read (sub { }); |
797 | $_[0]->on_read (sub { }); |
|
|
798 | } |
440 | } |
799 | } |
441 | } |
800 | } |
442 | }); |
801 | }); |
443 | }); |
802 | }; |
444 | }, sub { |
803 | |
445 | $timeout |
804 | # now handle proxy-CONNECT method |
|
|
805 | if ($proxy && $uscheme eq "https") { |
|
|
806 | # oh dear, we have to wrap it into a connect request |
|
|
807 | |
|
|
808 | # maybe re-use $uauthority with patched port? |
|
|
809 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
810 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
811 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
812 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
|
|
813 | |
|
|
814 | if ($2 == 200) { |
|
|
815 | $rpath = $upath; |
|
|
816 | &$handle_actual_request; |
|
|
817 | } else { |
|
|
818 | %state = (); |
|
|
819 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
|
|
820 | } |
|
|
821 | }); |
|
|
822 | } else { |
|
|
823 | &$handle_actual_request; |
|
|
824 | } |
446 | }; |
825 | }; |
|
|
826 | |
|
|
827 | my $tcp_connect = $arg{tcp_connect} |
|
|
828 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
829 | |
|
|
830 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
831 | |
447 | }; |
832 | }; |
448 | |
833 | |
449 | defined wantarray && AnyEvent::Util::guard { %state = () } |
834 | defined wantarray && AnyEvent::Util::guard { %state = () } |
450 | } |
835 | } |
451 | |
836 | |
… | |
… | |
458 | unshift @_, "HEAD"; |
843 | unshift @_, "HEAD"; |
459 | &http_request |
844 | &http_request |
460 | } |
845 | } |
461 | |
846 | |
462 | sub http_post($$@) { |
847 | sub http_post($$@) { |
|
|
848 | my $url = shift; |
463 | unshift @_, "POST", "body"; |
849 | unshift @_, "POST", $url, "body"; |
464 | &http_request |
850 | &http_request |
465 | } |
851 | } |
466 | |
852 | |
467 | =back |
853 | =back |
468 | |
854 | |
|
|
855 | =head2 DNS CACHING |
|
|
856 | |
|
|
857 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
858 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
859 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
860 | on its own. If you want DNS caching, you currently have to provide |
|
|
861 | your own default resolver (by storing a suitable resolver object in |
|
|
862 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
863 | |
469 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
864 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
470 | |
865 | |
471 | =over 4 |
866 | =over 4 |
472 | |
867 | |
473 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
868 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
474 | |
869 | |
475 | Sets the default proxy server to use. The proxy-url must begin with a |
870 | Sets the default proxy server to use. The proxy-url must begin with a |
476 | string of the form C<http://host:port> (optionally C<https:...>). |
871 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
872 | otherwise. |
|
|
873 | |
|
|
874 | To clear an already-set proxy, use C<undef>. |
|
|
875 | |
|
|
876 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
877 | |
|
|
878 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
879 | Date (RFC 2616). |
|
|
880 | |
|
|
881 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
882 | |
|
|
883 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
|
|
884 | timestamp, or C<undef> if the date cannot be parsed. |
477 | |
885 | |
478 | =item $AnyEvent::HTTP::MAX_RECURSE |
886 | =item $AnyEvent::HTTP::MAX_RECURSE |
479 | |
887 | |
480 | The default value for the C<recurse> request parameter (default: C<10>). |
888 | The default value for the C<recurse> request parameter (default: C<10>). |
481 | |
889 | |
482 | =item $AnyEvent::HTTP::USERAGENT |
890 | =item $AnyEvent::HTTP::USERAGENT |
483 | |
891 | |
484 | The default value for the C<User-Agent> header (the default is |
892 | The default value for the C<User-Agent> header (the default is |
485 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
893 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
486 | |
894 | |
487 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
895 | =item $AnyEvent::HTTP::MAX_PER_HOST |
488 | |
896 | |
489 | The maximum number of persistent connections to keep open (default: 8). |
897 | The maximum number of concurrent connections to the same host (identified |
|
|
898 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
899 | are queued until previous connections are closed. |
490 | |
900 | |
491 | Not implemented currently. |
901 | The default value for this is C<4>, and it is highly advisable to not |
492 | |
902 | 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 | |
903 | |
499 | =item $AnyEvent::HTTP::ACTIVE |
904 | =item $AnyEvent::HTTP::ACTIVE |
500 | |
905 | |
501 | The number of active connections. This is not the number of currently |
906 | The number of active connections. This is not the number of currently |
502 | running requests, but the number of currently open and non-idle TCP |
907 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
504 | |
909 | |
505 | =back |
910 | =back |
506 | |
911 | |
507 | =cut |
912 | =cut |
508 | |
913 | |
|
|
914 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
915 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
916 | |
|
|
917 | sub format_date($) { |
|
|
918 | my ($time) = @_; |
|
|
919 | |
|
|
920 | # RFC 822/1123 format |
|
|
921 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
922 | |
|
|
923 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
924 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
925 | $H, $M, $S; |
|
|
926 | } |
|
|
927 | |
|
|
928 | sub parse_date($) { |
|
|
929 | my ($date) = @_; |
|
|
930 | |
|
|
931 | my ($d, $m, $y, $H, $M, $S); |
|
|
932 | |
|
|
933 | if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
|
|
934 | # RFC 822/1123, required by RFC 2616 |
|
|
935 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
936 | |
|
|
937 | } elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) { |
|
|
938 | # RFC 850 |
|
|
939 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
940 | |
|
|
941 | } elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) { |
|
|
942 | # ISO C's asctime |
|
|
943 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
944 | } |
|
|
945 | # other formats fail in the loop below |
|
|
946 | |
|
|
947 | for (0..11) { |
|
|
948 | if ($m eq $month[$_]) { |
|
|
949 | require Time::Local; |
|
|
950 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
951 | } |
|
|
952 | } |
|
|
953 | |
|
|
954 | undef |
|
|
955 | } |
|
|
956 | |
509 | sub set_proxy($) { |
957 | sub set_proxy($) { |
|
|
958 | if (length $_[0]) { |
510 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
959 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
960 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
961 | $PROXY = [$2, $3 || 3128, $1] |
|
|
962 | } else { |
|
|
963 | undef $PROXY; |
|
|
964 | } |
511 | } |
965 | } |
512 | |
966 | |
513 | # initialise proxy from environment |
967 | # initialise proxy from environment |
|
|
968 | eval { |
514 | set_proxy $ENV{http_proxy}; |
969 | set_proxy $ENV{http_proxy}; |
|
|
970 | }; |
|
|
971 | |
|
|
972 | =head2 SOCKS PROXIES |
|
|
973 | |
|
|
974 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
975 | compile your perl to support socks, or use an external program such as |
|
|
976 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
977 | transparently. |
|
|
978 | |
|
|
979 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
980 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
981 | that works with socks4a proxies: |
|
|
982 | |
|
|
983 | use Errno; |
|
|
984 | use AnyEvent::Util; |
|
|
985 | use AnyEvent::Socket; |
|
|
986 | use AnyEvent::Handle; |
|
|
987 | |
|
|
988 | # host, port and username of/for your socks4a proxy |
|
|
989 | my $socks_host = "10.0.0.23"; |
|
|
990 | my $socks_port = 9050; |
|
|
991 | my $socks_user = ""; |
|
|
992 | |
|
|
993 | sub socks4a_connect { |
|
|
994 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
995 | |
|
|
996 | my $hdl = new AnyEvent::Handle |
|
|
997 | connect => [$socks_host, $socks_port], |
|
|
998 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
999 | on_error => sub { $connect_cb->() }, |
|
|
1000 | ; |
|
|
1001 | |
|
|
1002 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1003 | |
|
|
1004 | $hdl->push_read (chunk => 8, sub { |
|
|
1005 | my ($hdl, $chunk) = @_; |
|
|
1006 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1007 | |
|
|
1008 | if ($status == 0x5a) { |
|
|
1009 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1010 | } else { |
|
|
1011 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1012 | } |
|
|
1013 | }); |
|
|
1014 | |
|
|
1015 | $hdl |
|
|
1016 | } |
|
|
1017 | |
|
|
1018 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1019 | possibly after switching off other proxy types: |
|
|
1020 | |
|
|
1021 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1022 | |
|
|
1023 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1024 | my ($data, $headers) = @_; |
|
|
1025 | ... |
|
|
1026 | }; |
515 | |
1027 | |
516 | =head1 SEE ALSO |
1028 | =head1 SEE ALSO |
517 | |
1029 | |
518 | L<AnyEvent>. |
1030 | L<AnyEvent>. |
519 | |
1031 | |
520 | =head1 AUTHOR |
1032 | =head1 AUTHOR |
521 | |
1033 | |
522 | Marc Lehmann <schmorp@schmorp.de> |
1034 | Marc Lehmann <schmorp@schmorp.de> |
523 | http://home.schmorp.de/ |
1035 | http://home.schmorp.de/ |
|
|
1036 | |
|
|
1037 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
1038 | testcases and bugreports. |
524 | |
1039 | |
525 | =cut |
1040 | =cut |
526 | |
1041 | |
527 | 1 |
1042 | 1 |
528 | |
1043 | |