… | |
… | |
36 | |
36 | |
37 | =cut |
37 | =cut |
38 | |
38 | |
39 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
40 | |
40 | |
41 | use strict; |
41 | use common::sense; |
42 | no warnings; |
|
|
43 | |
42 | |
44 | use Carp; |
43 | use Errno (); |
45 | |
44 | |
46 | use AnyEvent (); |
45 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
|
|
49 | use AnyEvent::Handle (); |
47 | use AnyEvent::Handle (); |
50 | |
48 | |
51 | use base Exporter::; |
49 | use base Exporter::; |
52 | |
50 | |
53 | our $VERSION = '1.01'; |
51 | our $VERSION = '1.5'; |
54 | |
52 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
54 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
56 | our $MAX_RECURSE = 10; |
59 | our $MAX_PERSISTENT = 8; |
57 | our $MAX_PERSISTENT = 8; |
60 | our $PERSISTENT_TIMEOUT = 2; |
58 | our $PERSISTENT_TIMEOUT = 2; |
61 | our $TIMEOUT = 300; |
59 | our $TIMEOUT = 300; |
62 | |
60 | |
63 | # changing these is evil |
61 | # changing these is evil |
64 | our $MAX_PERSISTENT_PER_HOST = 2; |
62 | our $MAX_PERSISTENT_PER_HOST = 0; |
65 | our $MAX_PER_HOST = 4; |
63 | our $MAX_PER_HOST = 4; |
66 | |
64 | |
67 | our $PROXY; |
65 | our $PROXY; |
68 | our $ACTIVE = 0; |
66 | our $ACTIVE = 0; |
69 | |
67 | |
… | |
… | |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
69 | my %CO_SLOT; # number of open connections, and wait queue, per host |
72 | |
70 | |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
71 | =item http_get $url, key => value..., $cb->($data, $headers) |
74 | |
72 | |
75 | Executes an HTTP-GET request. See the http_request function for details on |
73 | Executes an HTTP-GET request. See the http_request function for details on |
76 | additional parameters. |
74 | additional parameters and the return value. |
77 | |
75 | |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
76 | =item http_head $url, key => value..., $cb->($data, $headers) |
79 | |
77 | |
80 | Executes an HTTP-HEAD request. See the http_request function for details on |
78 | Executes an HTTP-HEAD request. See the http_request function for details |
81 | additional parameters. |
79 | on additional parameters and the return value. |
82 | |
80 | |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
81 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
84 | |
82 | |
85 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
83 | Executes an HTTP-POST request with a request body of C<$body>. See the |
86 | http_request function for details on additional parameters. |
84 | http_request function for details on additional parameters and the return |
|
|
85 | value. |
87 | |
86 | |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
87 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | |
88 | |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
89 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | must be an absolute http or https URL. |
90 | must be an absolute http or https URL. |
92 | |
91 | |
|
|
92 | When called in void context, nothing is returned. In other contexts, |
|
|
93 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
94 | object at least alive until the callback get called. If the object gets |
|
|
95 | destroyed before the callback is called, the request will be cancelled. |
|
|
96 | |
93 | The callback will be called with the response data as first argument |
97 | The callback will be called with the response body data as first argument |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
98 | (or C<undef> if an error occured), and a hash-ref with response headers |
95 | response headers as second argument. |
99 | (and trailers) as second argument. |
96 | |
100 | |
97 | All the headers in that hash are lowercased. In addition to the response |
101 | All the headers in that hash are lowercased. In addition to the response |
98 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
102 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
99 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
103 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
|
|
104 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
105 | during the body phase of a request, then the original C<Status> and |
|
|
106 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
107 | C<OrigReason>. |
|
|
108 | |
|
|
109 | The pseudo-header C<URL> contains the actual URL (which can differ from |
|
|
110 | the requested URL when following redirects - for example, you might get |
|
|
111 | an error that your URL scheme is not supported even though your URL is a |
|
|
112 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
113 | look at the URL pseudo header). |
|
|
114 | |
|
|
115 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
116 | of an internal redirect. In that case it is an array reference with |
|
|
117 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
118 | response could in turn be the result of a redirect itself, and C<< |
|
|
119 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
120 | response, and so on. |
|
|
121 | |
100 | name. If the server sends a header multiple lines, then their contents |
122 | If the server sends a header multiple times, then their contents will be |
101 | will be joined together with C<\x00>. |
123 | joined together with a comma (C<,>), as per the HTTP spec. |
102 | |
124 | |
103 | If an internal error occurs, such as not being able to resolve a hostname, |
125 | If an internal error occurs, such as not being able to resolve a hostname, |
104 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
126 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
105 | and the C<Reason> pseudo-header will contain an error message. |
127 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
|
|
128 | message. Currently the following status codes are used: |
|
|
129 | |
|
|
130 | =over 4 |
|
|
131 | |
|
|
132 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
133 | |
|
|
134 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
135 | |
|
|
136 | =item 597 - errors during body receiving or processing. |
|
|
137 | |
|
|
138 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
139 | |
|
|
140 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
141 | |
|
|
142 | =back |
106 | |
143 | |
107 | A typical callback might look like this: |
144 | A typical callback might look like this: |
108 | |
145 | |
109 | sub { |
146 | sub { |
110 | my ($body, $hdr) = @_; |
147 | my ($body, $hdr) = @_; |
… | |
… | |
126 | Whether to recurse requests or not, e.g. on redirects, authentication |
163 | Whether to recurse requests or not, e.g. on redirects, authentication |
127 | retries and so on, and how often to do so. |
164 | retries and so on, and how often to do so. |
128 | |
165 | |
129 | =item headers => hashref |
166 | =item headers => hashref |
130 | |
167 | |
131 | The request headers to use. Currently, C<http_request> may provide its |
168 | The request headers to use. Currently, C<http_request> may provide its own |
132 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
169 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
133 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
170 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
|
|
171 | (this can be suppressed by using C<undef> for these headers in which case |
|
|
172 | they won't be sent at all). |
134 | |
173 | |
135 | =item timeout => $seconds |
174 | =item timeout => $seconds |
136 | |
175 | |
137 | The time-out to use for various stages - each connect attempt will reset |
176 | The time-out to use for various stages - each connect attempt will reset |
138 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
177 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
178 | timeout. |
|
|
179 | |
|
|
180 | Default timeout is 5 minutes. |
139 | |
181 | |
140 | =item proxy => [$host, $port[, $scheme]] or undef |
182 | =item proxy => [$host, $port[, $scheme]] or undef |
141 | |
183 | |
142 | Use the given http proxy for all requests. If not specified, then the |
184 | Use the given http proxy for all requests. If not specified, then the |
143 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
185 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
144 | |
186 | |
145 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
187 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
146 | HTTPS. |
188 | HTTPS. |
147 | |
189 | |
148 | =item body => $string |
190 | =item body => $string |
149 | |
191 | |
150 | The request body, usually empty. Will be-sent as-is (future versions of |
192 | The request body, usually empty. Will be sent as-is (future versions of |
151 | this module might offer more options). |
193 | this module might offer more options). |
152 | |
194 | |
153 | =item cookie_jar => $hash_ref |
195 | =item cookie_jar => $hash_ref |
154 | |
196 | |
155 | Passing this parameter enables (simplified) cookie-processing, loosely |
197 | Passing this parameter enables (simplified) cookie-processing, loosely |
156 | based on the original netscape specification. |
198 | based on the original netscape specification. |
157 | |
199 | |
158 | The C<$hash_ref> must be an (initially empty) hash reference which will |
200 | The C<$hash_ref> must be an (initially empty) hash reference which |
159 | get updated automatically. It is possible to save the cookie_jar to |
201 | will get updated automatically. It is possible to save the cookie jar |
160 | persistent storage with something like JSON or Storable, but this is not |
202 | to persistent storage with something like JSON or Storable - see the |
161 | recommended, as expire times are currently being ignored. |
203 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
204 | expired or session-only cookies, and also for documentation on the format |
|
|
205 | of the cookie jar. |
162 | |
206 | |
163 | Note that this cookie implementation is not of very high quality, nor |
207 | Note that this cookie implementation is not meant to be complete. If |
164 | meant to be complete. If you want complete cookie management you have to |
208 | you want complete cookie management you have to do that on your |
165 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
209 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
166 | cookie-using sites working. Cookies are a privacy disaster, do not use |
210 | working. Cookies are a privacy disaster, do not use them unless required |
167 | them unless required to. |
211 | to. |
|
|
212 | |
|
|
213 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
214 | headers will be set and handled by this module, otherwise they will be |
|
|
215 | left untouched. |
|
|
216 | |
|
|
217 | =item tls_ctx => $scheme | $tls_ctx |
|
|
218 | |
|
|
219 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
220 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
221 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
222 | C<high> can be specified, which give you a predefined low-security (no |
|
|
223 | verification, highest compatibility) and high-security (CA and common-name |
|
|
224 | verification) TLS context. |
|
|
225 | |
|
|
226 | The default for this option is C<low>, which could be interpreted as "give |
|
|
227 | me the page, no matter what". |
|
|
228 | |
|
|
229 | =item on_prepare => $callback->($fh) |
|
|
230 | |
|
|
231 | In rare cases you need to "tune" the socket before it is used to |
|
|
232 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
233 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
234 | and behaves exactly the same way (e.g. it has to provide a |
|
|
235 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
236 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
237 | |
|
|
238 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
239 | |
|
|
240 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
241 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
242 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
243 | obviously, it has to follow the same calling conventions, except that it |
|
|
244 | may always return a connection guard object. |
|
|
245 | |
|
|
246 | There are probably lots of weird uses for this function, starting from |
|
|
247 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
248 | but fast) host => IP address caching or even socks protocol support. |
|
|
249 | |
|
|
250 | =item on_header => $callback->($headers) |
|
|
251 | |
|
|
252 | When specified, this callback will be called with the header hash as soon |
|
|
253 | as headers have been successfully received from the remote server (not on |
|
|
254 | locally-generated errors). |
|
|
255 | |
|
|
256 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
257 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
258 | the finish callback with an error code of C<598>). |
|
|
259 | |
|
|
260 | This callback is useful, among other things, to quickly reject unwanted |
|
|
261 | content, which, if it is supposed to be rare, can be faster than first |
|
|
262 | doing a C<HEAD> request. |
|
|
263 | |
|
|
264 | The downside is that cancelling the request makes it impossible to re-use |
|
|
265 | the connection. Also, the C<on_header> callback will not receive any |
|
|
266 | trailer (headers sent after the response body). |
|
|
267 | |
|
|
268 | Example: cancel the request unless the content-type is "text/html". |
|
|
269 | |
|
|
270 | on_header => sub { |
|
|
271 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
272 | }, |
|
|
273 | |
|
|
274 | =item on_body => $callback->($partial_body, $headers) |
|
|
275 | |
|
|
276 | When specified, all body data will be passed to this callback instead of |
|
|
277 | to the completion callback. The completion callback will get the empty |
|
|
278 | string instead of the body data. |
|
|
279 | |
|
|
280 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
281 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
282 | the completion callback with an error code of C<598>). |
|
|
283 | |
|
|
284 | The downside to cancelling the request is that it makes it impossible to |
|
|
285 | re-use the connection. |
|
|
286 | |
|
|
287 | This callback is useful when the data is too large to be held in memory |
|
|
288 | (so the callback writes it to a file) or when only some information should |
|
|
289 | be extracted, or when the body should be processed incrementally. |
|
|
290 | |
|
|
291 | It is usually preferred over doing your own body handling via |
|
|
292 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
293 | only used to create a connection, C<want_body_handle> is the better |
|
|
294 | alternative, as it allows you to install your own event handler, reducing |
|
|
295 | resource usage. |
|
|
296 | |
|
|
297 | =item want_body_handle => $enable |
|
|
298 | |
|
|
299 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
300 | changes considerably: after parsing the headers, and instead of |
|
|
301 | downloading the body (if any), the completion callback will be |
|
|
302 | called. Instead of the C<$body> argument containing the body data, the |
|
|
303 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
304 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
305 | (e.g. status C<304>), the empty string will be passed. |
|
|
306 | |
|
|
307 | The handle object might or might not be in TLS mode, might be connected to |
|
|
308 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
309 | ways. The user is responsible for this handle (it will not be used by this |
|
|
310 | module anymore). |
|
|
311 | |
|
|
312 | This is useful with some push-type services, where, after the initial |
|
|
313 | headers, an interactive protocol is used (typical example would be the |
|
|
314 | push-style twitter API which starts a JSON/XML stream). |
|
|
315 | |
|
|
316 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
317 | that doesn't solve your problem in a better way. |
168 | |
318 | |
169 | =back |
319 | =back |
170 | |
320 | |
171 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
321 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
322 | the response body. |
172 | |
323 | |
173 | http_request GET => "http://www.nethype.de/", sub { |
324 | http_request GET => "http://www.nethype.de/", sub { |
174 | my ($body, $hdr) = @_; |
325 | my ($body, $hdr) = @_; |
175 | print "$body\n"; |
326 | print "$body\n"; |
176 | }; |
327 | }; |
177 | |
328 | |
178 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
329 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
179 | timeout of 30 seconds. |
330 | timeout of 30 seconds. |
180 | |
331 | |
181 | http_request |
332 | http_request |
182 | GET => "https://www.google.com", |
333 | GET => "https://www.google.com", |
183 | timeout => 30, |
334 | timeout => 30, |
… | |
… | |
185 | my ($body, $hdr) = @_; |
336 | my ($body, $hdr) = @_; |
186 | use Data::Dumper; |
337 | use Data::Dumper; |
187 | print Dumper $hdr; |
338 | print Dumper $hdr; |
188 | } |
339 | } |
189 | ; |
340 | ; |
|
|
341 | |
|
|
342 | Example: do another simple HTTP GET request, but immediately try to |
|
|
343 | cancel it. |
|
|
344 | |
|
|
345 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
346 | my ($body, $hdr) = @_; |
|
|
347 | print "$body\n"; |
|
|
348 | }; |
|
|
349 | |
|
|
350 | undef $request; |
190 | |
351 | |
191 | =cut |
352 | =cut |
192 | |
353 | |
193 | sub _slot_schedule; |
354 | sub _slot_schedule; |
194 | sub _slot_schedule($) { |
355 | sub _slot_schedule($) { |
… | |
… | |
218 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
379 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
219 | |
380 | |
220 | _slot_schedule $_[0]; |
381 | _slot_schedule $_[0]; |
221 | } |
382 | } |
222 | |
383 | |
|
|
384 | ############################################################################# |
|
|
385 | |
|
|
386 | # expire cookies |
|
|
387 | sub cookie_jar_expire($;$) { |
|
|
388 | my ($jar, $session_end) = @_; |
|
|
389 | |
|
|
390 | %$jar = () if $jar->{version} != 1; |
|
|
391 | |
|
|
392 | my $anow = AE::now; |
|
|
393 | |
|
|
394 | while (my ($chost, $paths) = each %$jar) { |
|
|
395 | next unless ref $paths; |
|
|
396 | |
|
|
397 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
398 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
399 | if (exists $kv->{_expires}) { |
|
|
400 | delete $cookies->{$cookie} |
|
|
401 | if $anow > $kv->{_expires}; |
|
|
402 | } elsif ($session_end) { |
|
|
403 | delete $cookies->{$cookie}; |
|
|
404 | } |
|
|
405 | } |
|
|
406 | |
|
|
407 | delete $paths->{$cpath} |
|
|
408 | unless %$cookies; |
|
|
409 | } |
|
|
410 | |
|
|
411 | delete $jar->{$chost} |
|
|
412 | unless %$paths; |
|
|
413 | } |
|
|
414 | } |
|
|
415 | |
|
|
416 | # extract cookies from jar |
|
|
417 | sub cookie_jar_extract($$$$) { |
|
|
418 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
419 | |
|
|
420 | $uhost = lc $uhost; |
|
|
421 | |
|
|
422 | %$jar = () if $jar->{version} != 1; |
|
|
423 | |
|
|
424 | my @cookies; |
|
|
425 | |
|
|
426 | while (my ($chost, $paths) = each %$jar) { |
|
|
427 | next unless ref $paths; |
|
|
428 | |
|
|
429 | if ($chost =~ /^\./) { |
|
|
430 | next unless $chost eq substr $uhost, -length $chost; |
|
|
431 | } elsif ($chost =~ /\./) { |
|
|
432 | next unless $chost eq $uhost; |
|
|
433 | } else { |
|
|
434 | next; |
|
|
435 | } |
|
|
436 | |
|
|
437 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
438 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
439 | |
|
|
440 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
441 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
442 | |
|
|
443 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
444 | delete $cookies->{$cookie}; |
|
|
445 | next; |
|
|
446 | } |
|
|
447 | |
|
|
448 | my $value = $kv->{value}; |
|
|
449 | |
|
|
450 | if ($value =~ /[=;,[:space:]]/) { |
|
|
451 | $value =~ s/([\\"])/\\$1/g; |
|
|
452 | $value = "\"$value\""; |
|
|
453 | } |
|
|
454 | |
|
|
455 | push @cookies, "$cookie=$value"; |
|
|
456 | } |
|
|
457 | } |
|
|
458 | } |
|
|
459 | |
|
|
460 | \@cookies |
|
|
461 | } |
|
|
462 | |
|
|
463 | # parse set_cookie header into jar |
|
|
464 | sub cookie_jar_set_cookie($$$$) { |
|
|
465 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
466 | |
|
|
467 | my $anow = int AE::now; |
|
|
468 | my $snow; # server-now |
|
|
469 | |
|
|
470 | for ($set_cookie) { |
|
|
471 | # parse NAME=VALUE |
|
|
472 | my @kv; |
|
|
473 | |
|
|
474 | # expires is not http-compliant in the original cookie-spec, |
|
|
475 | # we support the official date format and some extensions |
|
|
476 | while ( |
|
|
477 | m{ |
|
|
478 | \G\s* |
|
|
479 | (?: |
|
|
480 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
481 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) )? |
|
|
482 | ) |
|
|
483 | }gcxsi |
|
|
484 | ) { |
|
|
485 | my $name = $2; |
|
|
486 | my $value = $4; |
|
|
487 | |
|
|
488 | if (defined $1) { |
|
|
489 | # expires |
|
|
490 | $name = "expires"; |
|
|
491 | $value = $1; |
|
|
492 | } elsif (defined $3) { |
|
|
493 | # quoted |
|
|
494 | $value = $3; |
|
|
495 | $value =~ s/\\(.)/$1/gs; |
|
|
496 | } |
|
|
497 | |
|
|
498 | push @kv, lc $name, $value; |
|
|
499 | |
|
|
500 | last unless /\G\s*;/gc; |
|
|
501 | } |
|
|
502 | |
|
|
503 | last unless @kv; |
|
|
504 | |
|
|
505 | my $name = shift @kv; |
|
|
506 | my %kv = (value => shift @kv, @kv); |
|
|
507 | |
|
|
508 | if (exists $kv{"max-age"}) { |
|
|
509 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
510 | } elsif (exists $kv{expires}) { |
|
|
511 | $snow ||= parse_date ($date) || $anow; |
|
|
512 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
513 | } else { |
|
|
514 | delete $kv{_expires}; |
|
|
515 | } |
|
|
516 | |
|
|
517 | my $cdom; |
|
|
518 | my $cpath = (delete $kv{path}) || "/"; |
|
|
519 | |
|
|
520 | if (exists $kv{domain}) { |
|
|
521 | $cdom = delete $kv{domain}; |
|
|
522 | |
|
|
523 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
524 | |
|
|
525 | next if $cdom =~ /\.$/; |
|
|
526 | |
|
|
527 | # this is not rfc-like and not netscape-like. go figure. |
|
|
528 | my $ndots = $cdom =~ y/.//; |
|
|
529 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
530 | } else { |
|
|
531 | $cdom = $uhost; |
|
|
532 | } |
|
|
533 | |
|
|
534 | # store it |
|
|
535 | $jar->{version} = 1; |
|
|
536 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
|
|
537 | |
|
|
538 | redo if /\G\s*,/gc; |
|
|
539 | } |
|
|
540 | } |
|
|
541 | |
|
|
542 | # continue to parse $_ for headers and place them into the arg |
|
|
543 | sub parse_hdr() { |
|
|
544 | my %hdr; |
|
|
545 | |
|
|
546 | # things seen, not parsed: |
|
|
547 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
548 | |
|
|
549 | $hdr{lc $1} .= ",$2" |
|
|
550 | while /\G |
|
|
551 | ([^:\000-\037]*): |
|
|
552 | [\011\040]* |
|
|
553 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
554 | \012 |
|
|
555 | /gxc; |
|
|
556 | |
|
|
557 | /\G$/ |
|
|
558 | or return; |
|
|
559 | |
|
|
560 | # remove the "," prefix we added to all headers above |
|
|
561 | substr $_, 0, 1, "" |
|
|
562 | for values %hdr; |
|
|
563 | |
|
|
564 | \%hdr |
|
|
565 | } |
|
|
566 | |
|
|
567 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
|
|
568 | |
|
|
569 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
570 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
571 | |
223 | sub http_request($$@) { |
572 | sub http_request($$@) { |
224 | my $cb = pop; |
573 | my $cb = pop; |
225 | my ($method, $url, %arg) = @_; |
574 | my ($method, $url, %arg) = @_; |
226 | |
575 | |
227 | my %hdr; |
576 | my %hdr; |
|
|
577 | |
|
|
578 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
579 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
228 | |
580 | |
229 | $method = uc $method; |
581 | $method = uc $method; |
230 | |
582 | |
231 | if (my $hdr = $arg{headers}) { |
583 | if (my $hdr = $arg{headers}) { |
232 | while (my ($k, $v) = each %$hdr) { |
584 | while (my ($k, $v) = each %$hdr) { |
233 | $hdr{lc $k} = $v; |
585 | $hdr{lc $k} = $v; |
234 | } |
586 | } |
235 | } |
587 | } |
236 | |
588 | |
|
|
589 | # pseudo headers for all subsequent responses |
|
|
590 | my @pseudo = (URL => $url); |
|
|
591 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
592 | |
237 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
593 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
238 | |
594 | |
239 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
595 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
240 | if $recurse < 0; |
596 | if $recurse < 0; |
241 | |
597 | |
242 | my $proxy = $arg{proxy} || $PROXY; |
598 | my $proxy = $arg{proxy} || $PROXY; |
243 | my $timeout = $arg{timeout} || $TIMEOUT; |
599 | my $timeout = $arg{timeout} || $TIMEOUT; |
244 | |
600 | |
245 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
246 | |
|
|
247 | my ($scheme, $authority, $upath, $query, $fragment) = |
601 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
248 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
602 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
249 | |
603 | |
250 | $scheme = lc $scheme; |
604 | $uscheme = lc $uscheme; |
251 | |
605 | |
252 | my $uport = $scheme eq "http" ? 80 |
606 | my $uport = $uscheme eq "http" ? 80 |
253 | : $scheme eq "https" ? 443 |
607 | : $uscheme eq "https" ? 443 |
254 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
608 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
255 | |
609 | |
256 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
|
|
257 | |
|
|
258 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
610 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
259 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
611 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
260 | |
612 | |
261 | my $uhost = $1; |
613 | my $uhost = $1; |
262 | $uport = $2 if defined $2; |
614 | $uport = $2 if defined $2; |
263 | |
615 | |
|
|
616 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
617 | unless exists $hdr{host}; |
|
|
618 | |
264 | $uhost =~ s/^\[(.*)\]$/$1/; |
619 | $uhost =~ s/^\[(.*)\]$/$1/; |
265 | $upath .= "?$query" if length $query; |
620 | $upath .= $query if length $query; |
266 | |
621 | |
267 | $upath =~ s%^/?%/%; |
622 | $upath =~ s%^/?%/%; |
268 | |
623 | |
269 | # cookie processing |
624 | # cookie processing |
270 | if (my $jar = $arg{cookie_jar}) { |
625 | if (my $jar = $arg{cookie_jar}) { |
271 | %$jar = () if $jar->{version} < 1; |
626 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
272 | |
627 | |
273 | my @cookie; |
|
|
274 | |
|
|
275 | while (my ($chost, $v) = each %$jar) { |
|
|
276 | next unless $chost eq substr $uhost, -length $chost; |
|
|
277 | next unless $chost =~ /^\./; |
|
|
278 | |
|
|
279 | while (my ($cpath, $v) = each %$v) { |
|
|
280 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
281 | |
|
|
282 | while (my ($k, $v) = each %$v) { |
|
|
283 | next if $scheme ne "https" && exists $v->{secure}; |
|
|
284 | push @cookie, "$k=$v->{value}"; |
|
|
285 | } |
|
|
286 | } |
|
|
287 | } |
|
|
288 | |
|
|
289 | $hdr{cookie} = join "; ", @cookie |
628 | $hdr{cookie} = join "; ", @$cookies |
290 | if @cookie; |
629 | if @$cookies; |
291 | } |
630 | } |
292 | |
631 | |
293 | my ($rhost, $rport, $rpath); # request host, port, path |
632 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
294 | |
633 | |
295 | if ($proxy) { |
634 | if ($proxy) { |
296 | ($rhost, $rport, $scheme) = @$proxy; |
635 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
297 | $rpath = $url; |
636 | |
|
|
637 | $rscheme = "http" unless defined $rscheme; |
|
|
638 | |
|
|
639 | # don't support https requests over https-proxy transport, |
|
|
640 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
641 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
298 | } else { |
642 | } else { |
299 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
643 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
300 | $hdr{host} = $uhost; |
|
|
301 | } |
644 | } |
302 | |
645 | |
|
|
646 | # leave out fragment and query string, just a heuristic |
|
|
647 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
648 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
|
|
649 | |
303 | $hdr{"content-length"} = length $arg{body}; |
650 | $hdr{"content-length"} = length $arg{body} |
|
|
651 | if length $arg{body} || $method ne "GET"; |
|
|
652 | |
|
|
653 | $hdr{connection} = "close TE"; #1.1 |
|
|
654 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
304 | |
655 | |
305 | my %state = (connect_guard => 1); |
656 | my %state = (connect_guard => 1); |
306 | |
657 | |
307 | _get_slot $uhost, sub { |
658 | _get_slot $uhost, sub { |
308 | $state{slot_guard} = shift; |
659 | $state{slot_guard} = shift; |
309 | |
660 | |
310 | return unless $state{connect_guard}; |
661 | return unless $state{connect_guard}; |
311 | |
662 | |
312 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
663 | my $ae_error = 595; # connecting |
313 | $state{fh} = shift |
|
|
314 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
|
|
315 | |
664 | |
316 | delete $state{connect_guard}; # reduce memory usage, save a tree |
665 | # handle actual, non-tunneled, request |
|
|
666 | my $handle_actual_request = sub { |
|
|
667 | $ae_error = 596; # request phase |
317 | |
668 | |
318 | # get handle |
669 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
319 | $state{handle} = new AnyEvent::Handle |
|
|
320 | fh => $state{fh}, |
|
|
321 | ($scheme eq "https" ? (tls => "connect") : ()); |
|
|
322 | |
|
|
323 | # limit the number of persistent connections |
|
|
324 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
|
|
325 | ++$KA_COUNT{$_[1]}; |
|
|
326 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
|
|
327 | $hdr{connection} = "keep-alive"; |
|
|
328 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
329 | } else { |
|
|
330 | delete $hdr{connection}; |
|
|
331 | } |
|
|
332 | |
|
|
333 | # (re-)configure handle |
|
|
334 | $state{handle}->timeout ($timeout); |
|
|
335 | $state{handle}->on_error (sub { |
|
|
336 | my $errno = "$!"; |
|
|
337 | %state = (); |
|
|
338 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
|
|
339 | }); |
|
|
340 | $state{handle}->on_eof (sub { |
|
|
341 | %state = (); |
|
|
342 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
|
|
343 | }); |
|
|
344 | |
670 | |
345 | # send request |
671 | # send request |
346 | $state{handle}->push_write ( |
672 | $state{handle}->push_write ( |
347 | "$method $rpath HTTP/1.0\015\012" |
673 | "$method $rpath HTTP/1.1\015\012" |
348 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
674 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
349 | . "\015\012" |
675 | . "\015\012" |
350 | . (delete $arg{body}) |
676 | . (delete $arg{body}) |
351 | ); |
677 | ); |
352 | |
678 | |
|
|
679 | # return if error occured during push_write() |
|
|
680 | return unless %state; |
|
|
681 | |
353 | %hdr = (); # reduce memory usage, save a kitten |
682 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
354 | |
683 | |
355 | # status line |
684 | # status line and headers |
356 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
685 | $state{read_response} = sub { |
357 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
358 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
|
|
359 | |
|
|
360 | my %hdr = ( # response headers |
|
|
361 | HTTPVersion => "\x00$1", |
|
|
362 | Status => "\x00$2", |
|
|
363 | Reason => "\x00$3", |
|
|
364 | URL => "\x00$url" |
|
|
365 | ); |
|
|
366 | |
|
|
367 | # headers, could be optimized a bit |
|
|
368 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
|
|
369 | for ("$_[1]\012") { |
686 | for ("$_[1]") { |
370 | # we support spaces in field names, as lotus domino |
687 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
371 | # creates them. |
|
|
372 | $hdr{lc $1} .= "\x00$2" |
|
|
373 | while /\G |
|
|
374 | ([^:\000-\037]+): |
|
|
375 | [\011\040]* |
|
|
376 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
|
|
377 | \015?\012 |
|
|
378 | /gxc; |
|
|
379 | |
688 | |
|
|
689 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
690 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
691 | |
|
|
692 | # 100 Continue handling |
|
|
693 | # should not happen as we don't send expect: 100-continue, |
|
|
694 | # but we handle it just in case. |
|
|
695 | # since we send the request body regardless, if we get an error |
|
|
696 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
697 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
698 | if $2 eq 100; |
|
|
699 | |
|
|
700 | push @pseudo, |
|
|
701 | HTTPVersion => $1, |
|
|
702 | Status => $2, |
|
|
703 | Reason => $3, |
380 | /\G$/ |
704 | ; |
|
|
705 | |
|
|
706 | my $hdr = parse_hdr |
381 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
707 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
708 | |
|
|
709 | %hdr = (%$hdr, @pseudo); |
|
|
710 | } |
|
|
711 | |
|
|
712 | # redirect handling |
|
|
713 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
714 | # try to support some common forms of broken Location headers. |
|
|
715 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
716 | $hdr{location} =~ s/^\.\/+//; |
|
|
717 | |
|
|
718 | my $url = "$rscheme://$uhost:$uport"; |
|
|
719 | |
|
|
720 | unless ($hdr{location} =~ s/^\///) { |
|
|
721 | $url .= $upath; |
|
|
722 | $url =~ s/\/[^\/]*$//; |
382 | } |
723 | } |
383 | |
724 | |
384 | substr $_, 0, 1, "" |
725 | $hdr{location} = "$url/$hdr{location}"; |
385 | for values %hdr; |
726 | } |
386 | |
727 | |
387 | my $finish = sub { |
728 | my $redirect; |
|
|
729 | |
|
|
730 | if ($recurse) { |
|
|
731 | my $status = $hdr{Status}; |
|
|
732 | |
|
|
733 | # industry standard is to redirect POST as GET for |
|
|
734 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
735 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
736 | # industry standard seems to be to simply follow. |
|
|
737 | # we go with the industry standard. |
|
|
738 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
739 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
740 | $method = "GET" unless $method eq "HEAD"; |
|
|
741 | $redirect = 1; |
|
|
742 | } elsif ($status == 307) { |
|
|
743 | $redirect = 1; |
|
|
744 | } |
|
|
745 | } |
|
|
746 | |
|
|
747 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
748 | my $may_keep_alive = $_[3]; |
|
|
749 | |
|
|
750 | $state{handle}->destroy if $state{handle}; |
388 | %state = (); |
751 | %state = (); |
389 | |
752 | |
|
|
753 | if (defined $_[1]) { |
|
|
754 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
755 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
756 | } |
|
|
757 | |
390 | # set-cookie processing |
758 | # set-cookie processing |
391 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
759 | if ($arg{cookie_jar}) { |
392 | for (split /\x00/, $hdr{"set-cookie"}) { |
760 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
393 | my ($cookie, @arg) = split /;\s*/; |
761 | } |
394 | my ($name, $value) = split /=/, $cookie, 2; |
|
|
395 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
|
|
396 | |
|
|
397 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
398 | my $cpath = (delete $kv{path}) || "/"; |
|
|
399 | |
|
|
400 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
|
|
401 | |
762 | |
402 | next if $cdom =~ /\.$/; |
763 | if ($redirect && exists $hdr{location}) { |
403 | |
764 | # we ignore any errors, as it is very common to receive |
404 | # this is not rfc-like and not netscape-like. go figure. |
765 | # Content-Length != 0 but no actual body |
405 | my $ndots = $cdom =~ y/.//; |
766 | # we also access %hdr, as $_[1] might be an erro |
406 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
767 | http_request ( |
407 | |
768 | $method => $hdr{location}, |
|
|
769 | %arg, |
|
|
770 | recurse => $recurse - 1, |
|
|
771 | Redirect => [$_[0], \%hdr], |
|
|
772 | $cb); |
|
|
773 | } else { |
|
|
774 | $cb->($_[0], \%hdr); |
|
|
775 | } |
|
|
776 | }; |
|
|
777 | |
|
|
778 | $ae_error = 597; # body phase |
|
|
779 | |
|
|
780 | my $len = $hdr{"content-length"}; |
|
|
781 | |
|
|
782 | # body handling, many different code paths |
|
|
783 | # - no body expected |
|
|
784 | # - want_body_handle |
|
|
785 | # - te chunked |
|
|
786 | # - 2x length known (with or without on_body) |
|
|
787 | # - 2x length not known (with or without on_body) |
|
|
788 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
789 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
790 | } elsif ( |
|
|
791 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
792 | or $method eq "HEAD" |
|
|
793 | or (defined $len && $len == 0) # == 0, not !, because "0 " is true |
|
|
794 | ) { |
|
|
795 | # no body |
|
|
796 | $finish->("", undef, undef, 1); |
|
|
797 | |
|
|
798 | } elsif (!$redirect && $arg{want_body_handle}) { |
|
|
799 | $_[0]->on_eof (undef); |
|
|
800 | $_[0]->on_error (undef); |
|
|
801 | $_[0]->on_read (undef); |
|
|
802 | |
|
|
803 | $finish->(delete $state{handle}); |
|
|
804 | |
|
|
805 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
806 | my $cl = 0; |
|
|
807 | my $body = undef; |
|
|
808 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
809 | |
|
|
810 | $state{read_chunk} = sub { |
|
|
811 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
812 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
813 | |
|
|
814 | my $len = hex $1; |
|
|
815 | |
|
|
816 | if ($len) { |
|
|
817 | $cl += $len; |
|
|
818 | |
|
|
819 | $_[0]->push_read (chunk => $len, sub { |
|
|
820 | $on_body->($_[1], \%hdr) |
|
|
821 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
822 | |
|
|
823 | $_[0]->push_read (line => sub { |
|
|
824 | length $_[1] |
|
|
825 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
826 | $_[0]->push_read (line => $state{read_chunk}); |
408 | # store it |
827 | }); |
409 | $arg{cookie_jar}{version} = 1; |
|
|
410 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
411 | } |
828 | }); |
412 | } |
|
|
413 | |
|
|
414 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { |
|
|
415 | # microsoft and other assholes don't give a shit for following standards, |
|
|
416 | # try to support a common form of broken Location header. |
|
|
417 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
|
|
418 | |
|
|
419 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
420 | } else { |
829 | } else { |
421 | $cb->($_[0], $_[1]); |
830 | $hdr{"content-length"} ||= $cl; |
|
|
831 | |
|
|
832 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
833 | if (length $_[1]) { |
|
|
834 | for ("$_[1]") { |
|
|
835 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
836 | |
|
|
837 | my $hdr = parse_hdr |
|
|
838 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
839 | |
|
|
840 | %hdr = (%hdr, %$hdr); |
|
|
841 | } |
|
|
842 | } |
|
|
843 | |
|
|
844 | $finish->($body, undef, undef, 1); |
|
|
845 | }); |
422 | } |
846 | } |
423 | }; |
847 | }; |
424 | |
848 | |
425 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
849 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
850 | |
|
|
851 | } elsif ($arg{on_body}) { |
|
|
852 | if (defined $len) { |
|
|
853 | $_[0]->on_read (sub { |
|
|
854 | $len -= length $_[0]{rbuf}; |
|
|
855 | |
|
|
856 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
857 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
858 | |
|
|
859 | $len > 0 |
426 | $finish->(undef, \%hdr); |
860 | or $finish->("", undef, undef, 1); |
|
|
861 | }); |
427 | } else { |
862 | } else { |
428 | if (exists $hdr{"content-length"}) { |
863 | $_[0]->on_eof (sub { |
429 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
430 | # could cache persistent connection now |
|
|
431 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
432 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
433 | }; |
|
|
434 | |
|
|
435 | $finish->($_[1], \%hdr); |
864 | $finish->(""); |
436 | }); |
865 | }); |
|
|
866 | $_[0]->on_read (sub { |
|
|
867 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
868 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
869 | }); |
|
|
870 | } |
|
|
871 | } else { |
|
|
872 | $_[0]->on_eof (undef); |
|
|
873 | |
|
|
874 | if (defined $len) { |
|
|
875 | $_[0]->on_read (sub { |
|
|
876 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
877 | if $len <= length $_[0]{rbuf}; |
|
|
878 | }); |
437 | } else { |
879 | } else { |
438 | # too bad, need to read until we get an error or EOF, |
|
|
439 | # no way to detect winged data. |
|
|
440 | $_[0]->on_error (sub { |
880 | $_[0]->on_error (sub { |
|
|
881 | ($! == Errno::EPIPE || !$!) |
441 | $finish->($_[0]{rbuf}, \%hdr); |
882 | ? $finish->(delete $_[0]{rbuf}) |
|
|
883 | : $finish->(undef, $ae_error => $_[2]); |
442 | }); |
884 | }); |
443 | $_[0]->on_eof (undef); |
|
|
444 | $_[0]->on_read (sub { }); |
885 | $_[0]->on_read (sub { }); |
445 | } |
886 | } |
|
|
887 | } |
|
|
888 | }; |
|
|
889 | |
|
|
890 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
891 | }; |
|
|
892 | |
|
|
893 | my $connect_cb = sub { |
|
|
894 | $state{fh} = shift |
|
|
895 | or do { |
|
|
896 | my $err = "$!"; |
|
|
897 | %state = (); |
|
|
898 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
|
|
899 | }; |
|
|
900 | |
|
|
901 | return unless delete $state{connect_guard}; |
|
|
902 | |
|
|
903 | # get handle |
|
|
904 | $state{handle} = new AnyEvent::Handle |
|
|
905 | fh => $state{fh}, |
|
|
906 | peername => $rhost, |
|
|
907 | tls_ctx => $arg{tls_ctx}, |
|
|
908 | # these need to be reconfigured on keepalive handles |
|
|
909 | timeout => $timeout, |
|
|
910 | on_error => sub { |
|
|
911 | %state = (); |
|
|
912 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
|
|
913 | }, |
|
|
914 | on_eof => sub { |
|
|
915 | %state = (); |
|
|
916 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
|
|
917 | }, |
|
|
918 | ; |
|
|
919 | |
|
|
920 | # limit the number of persistent connections |
|
|
921 | # keepalive not yet supported |
|
|
922 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
|
|
923 | # ++$KA_COUNT{$_[1]}; |
|
|
924 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
925 | # --$KA_COUNT{$_[1]} |
|
|
926 | # }; |
|
|
927 | # $hdr{connection} = "keep-alive"; |
|
|
928 | # } |
|
|
929 | |
|
|
930 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
931 | |
|
|
932 | # now handle proxy-CONNECT method |
|
|
933 | if ($proxy && $uscheme eq "https") { |
|
|
934 | # oh dear, we have to wrap it into a connect request |
|
|
935 | |
|
|
936 | # maybe re-use $uauthority with patched port? |
|
|
937 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
938 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
939 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
940 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
|
|
941 | |
|
|
942 | if ($2 == 200) { |
|
|
943 | $rpath = $upath; |
|
|
944 | $handle_actual_request->(); |
|
|
945 | } else { |
|
|
946 | %state = (); |
|
|
947 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
446 | } |
948 | } |
447 | }); |
949 | }); |
|
|
950 | } else { |
|
|
951 | $handle_actual_request->(); |
448 | }); |
952 | } |
449 | }, sub { |
|
|
450 | $timeout |
|
|
451 | }; |
953 | }; |
|
|
954 | |
|
|
955 | my $tcp_connect = $arg{tcp_connect} |
|
|
956 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
957 | |
|
|
958 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
452 | }; |
959 | }; |
453 | |
960 | |
454 | defined wantarray && AnyEvent::Util::guard { %state = () } |
961 | defined wantarray && AnyEvent::Util::guard { %state = () } |
455 | } |
962 | } |
456 | |
963 | |
… | |
… | |
463 | unshift @_, "HEAD"; |
970 | unshift @_, "HEAD"; |
464 | &http_request |
971 | &http_request |
465 | } |
972 | } |
466 | |
973 | |
467 | sub http_post($$@) { |
974 | sub http_post($$@) { |
|
|
975 | my $url = shift; |
468 | unshift @_, "POST", "body"; |
976 | unshift @_, "POST", $url, "body"; |
469 | &http_request |
977 | &http_request |
470 | } |
978 | } |
471 | |
979 | |
472 | =back |
980 | =back |
473 | |
981 | |
|
|
982 | =head2 DNS CACHING |
|
|
983 | |
|
|
984 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
985 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
986 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
987 | on its own. If you want DNS caching, you currently have to provide |
|
|
988 | your own default resolver (by storing a suitable resolver object in |
|
|
989 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
990 | |
474 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
991 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
475 | |
992 | |
476 | =over 4 |
993 | =over 4 |
477 | |
994 | |
478 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
995 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
479 | |
996 | |
480 | Sets the default proxy server to use. The proxy-url must begin with a |
997 | Sets the default proxy server to use. The proxy-url must begin with a |
481 | string of the form C<http://host:port> (optionally C<https:...>). |
998 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
999 | otherwise. |
|
|
1000 | |
|
|
1001 | To clear an already-set proxy, use C<undef>. |
|
|
1002 | |
|
|
1003 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1004 | |
|
|
1005 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1006 | C<$session_end> is given and true, then additionally remove all session |
|
|
1007 | cookies. |
|
|
1008 | |
|
|
1009 | You should call this function (with a true C<$session_end>) before you |
|
|
1010 | save cookies to disk, and you should call this function after loading them |
|
|
1011 | again. If you have a long-running program you can additonally call this |
|
|
1012 | function from time to time. |
|
|
1013 | |
|
|
1014 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1015 | module. It's format is subject to change, but currently it is like this: |
|
|
1016 | |
|
|
1017 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1018 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1019 | hash-references. The key for these inner hash references is the |
|
|
1020 | server path for which this cookie is meant, and the values are again |
|
|
1021 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1022 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1023 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1024 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1025 | expiry timestamp. |
|
|
1026 | |
|
|
1027 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1028 | chance of understanding the above paragraph: |
|
|
1029 | |
|
|
1030 | { |
|
|
1031 | version => 1, |
|
|
1032 | "10.0.0.1" => { |
|
|
1033 | "/" => { |
|
|
1034 | "mythweb_id" => { |
|
|
1035 | _expires => 1293917923, |
|
|
1036 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1037 | }, |
|
|
1038 | }, |
|
|
1039 | }, |
|
|
1040 | } |
|
|
1041 | |
|
|
1042 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
1043 | |
|
|
1044 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
1045 | Date (RFC 2616). |
|
|
1046 | |
|
|
1047 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
1048 | |
|
|
1049 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1050 | bunch of minor variations of those, and returns the corresponding POSIX |
|
|
1051 | timestamp, or C<undef> if the date cannot be parsed. |
482 | |
1052 | |
483 | =item $AnyEvent::HTTP::MAX_RECURSE |
1053 | =item $AnyEvent::HTTP::MAX_RECURSE |
484 | |
1054 | |
485 | The default value for the C<recurse> request parameter (default: C<10>). |
1055 | The default value for the C<recurse> request parameter (default: C<10>). |
486 | |
1056 | |
487 | =item $AnyEvent::HTTP::USERAGENT |
1057 | =item $AnyEvent::HTTP::USERAGENT |
488 | |
1058 | |
489 | The default value for the C<User-Agent> header (the default is |
1059 | The default value for the C<User-Agent> header (the default is |
490 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1060 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
491 | |
1061 | |
492 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
1062 | =item $AnyEvent::HTTP::MAX_PER_HOST |
493 | |
1063 | |
494 | The maximum number of persistent connections to keep open (default: 8). |
1064 | The maximum number of concurrent connections to the same host (identified |
|
|
1065 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
1066 | are queued until previous connections are closed. |
495 | |
1067 | |
496 | Not implemented currently. |
1068 | The default value for this is C<4>, and it is highly advisable to not |
497 | |
1069 | increase it. |
498 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
499 | |
|
|
500 | The maximum time to cache a persistent connection, in seconds (default: 2). |
|
|
501 | |
|
|
502 | Not implemented currently. |
|
|
503 | |
1070 | |
504 | =item $AnyEvent::HTTP::ACTIVE |
1071 | =item $AnyEvent::HTTP::ACTIVE |
505 | |
1072 | |
506 | The number of active connections. This is not the number of currently |
1073 | The number of active connections. This is not the number of currently |
507 | running requests, but the number of currently open and non-idle TCP |
1074 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
509 | |
1076 | |
510 | =back |
1077 | =back |
511 | |
1078 | |
512 | =cut |
1079 | =cut |
513 | |
1080 | |
|
|
1081 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
1082 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
1083 | |
|
|
1084 | sub format_date($) { |
|
|
1085 | my ($time) = @_; |
|
|
1086 | |
|
|
1087 | # RFC 822/1123 format |
|
|
1088 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
1089 | |
|
|
1090 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
1091 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
1092 | $H, $M, $S; |
|
|
1093 | } |
|
|
1094 | |
|
|
1095 | sub parse_date($) { |
|
|
1096 | my ($date) = @_; |
|
|
1097 | |
|
|
1098 | my ($d, $m, $y, $H, $M, $S); |
|
|
1099 | |
|
|
1100 | if ($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$/) { |
|
|
1101 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1102 | # cookie dates (with "-") |
|
|
1103 | |
|
|
1104 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
1105 | |
|
|
1106 | } elsif ($date =~ /^[A-Z][a-z][a-z]+, ([0-9][0-9]?)-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]?):([0-9][0-9]?):([0-9][0-9]?) GMT$/) { |
|
|
1107 | # RFC 850 |
|
|
1108 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
1109 | |
|
|
1110 | } elsif ($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])$/) { |
|
|
1111 | # ISO C's asctime |
|
|
1112 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
1113 | } |
|
|
1114 | # other formats fail in the loop below |
|
|
1115 | |
|
|
1116 | for (0..11) { |
|
|
1117 | if ($m eq $month[$_]) { |
|
|
1118 | require Time::Local; |
|
|
1119 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
1120 | } |
|
|
1121 | } |
|
|
1122 | |
|
|
1123 | undef |
|
|
1124 | } |
|
|
1125 | |
514 | sub set_proxy($) { |
1126 | sub set_proxy($) { |
|
|
1127 | if (length $_[0]) { |
515 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
1128 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
1129 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
1130 | $PROXY = [$2, $3 || 3128, $1] |
|
|
1131 | } else { |
|
|
1132 | undef $PROXY; |
|
|
1133 | } |
516 | } |
1134 | } |
517 | |
1135 | |
518 | # initialise proxy from environment |
1136 | # initialise proxy from environment |
|
|
1137 | eval { |
519 | set_proxy $ENV{http_proxy}; |
1138 | set_proxy $ENV{http_proxy}; |
|
|
1139 | }; |
|
|
1140 | |
|
|
1141 | =head2 SOCKS PROXIES |
|
|
1142 | |
|
|
1143 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
1144 | compile your perl to support socks, or use an external program such as |
|
|
1145 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
1146 | transparently. |
|
|
1147 | |
|
|
1148 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
1149 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
1150 | that works with socks4a proxies: |
|
|
1151 | |
|
|
1152 | use Errno; |
|
|
1153 | use AnyEvent::Util; |
|
|
1154 | use AnyEvent::Socket; |
|
|
1155 | use AnyEvent::Handle; |
|
|
1156 | |
|
|
1157 | # host, port and username of/for your socks4a proxy |
|
|
1158 | my $socks_host = "10.0.0.23"; |
|
|
1159 | my $socks_port = 9050; |
|
|
1160 | my $socks_user = ""; |
|
|
1161 | |
|
|
1162 | sub socks4a_connect { |
|
|
1163 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
1164 | |
|
|
1165 | my $hdl = new AnyEvent::Handle |
|
|
1166 | connect => [$socks_host, $socks_port], |
|
|
1167 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
1168 | on_error => sub { $connect_cb->() }, |
|
|
1169 | ; |
|
|
1170 | |
|
|
1171 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1172 | |
|
|
1173 | $hdl->push_read (chunk => 8, sub { |
|
|
1174 | my ($hdl, $chunk) = @_; |
|
|
1175 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1176 | |
|
|
1177 | if ($status == 0x5a) { |
|
|
1178 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1179 | } else { |
|
|
1180 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1181 | } |
|
|
1182 | }); |
|
|
1183 | |
|
|
1184 | $hdl |
|
|
1185 | } |
|
|
1186 | |
|
|
1187 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1188 | possibly after switching off other proxy types: |
|
|
1189 | |
|
|
1190 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1191 | |
|
|
1192 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1193 | my ($data, $headers) = @_; |
|
|
1194 | ... |
|
|
1195 | }; |
520 | |
1196 | |
521 | =head1 SEE ALSO |
1197 | =head1 SEE ALSO |
522 | |
1198 | |
523 | L<AnyEvent>. |
1199 | L<AnyEvent>. |
524 | |
1200 | |
525 | =head1 AUTHOR |
1201 | =head1 AUTHOR |
526 | |
1202 | |
527 | Marc Lehmann <schmorp@schmorp.de> |
1203 | Marc Lehmann <schmorp@schmorp.de> |
528 | http://home.schmorp.de/ |
1204 | http://home.schmorp.de/ |
529 | |
1205 | |
|
|
1206 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
1207 | testcases and bugreports. |
|
|
1208 | |
530 | =cut |
1209 | =cut |
531 | |
1210 | |
532 | 1 |
1211 | 1 |
533 | |
1212 | |