… | |
… | |
15 | 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 |
16 | run a supported event loop. |
16 | run a supported event loop. |
17 | |
17 | |
18 | This module implements a simple, stateless and non-blocking HTTP |
18 | This module implements a simple, stateless and non-blocking HTTP |
19 | client. It supports GET, POST and other request methods, cookies and more, |
19 | client. It supports GET, POST and other request methods, cookies and more, |
20 | all on a very low level. It can follow redirects supports proxies and |
20 | all on a very low level. It can follow redirects, supports proxies, and |
21 | automatically limits the number of connections to the values specified in |
21 | automatically limits the number of connections to the values specified in |
22 | the RFC. |
22 | the RFC. |
23 | |
23 | |
24 | It should generally be a "good client" that is enough for most HTTP |
24 | It should generally be a "good client" that is enough for most HTTP |
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
… | |
… | |
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 Errno (); |
43 | use Errno (); |
45 | |
44 | |
46 | use AnyEvent 5.0 (); |
45 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
48 | use AnyEvent::Handle (); |
47 | use AnyEvent::Handle (); |
49 | |
48 | |
50 | use base Exporter::; |
49 | use base Exporter::; |
51 | |
50 | |
52 | our $VERSION = '1.5'; |
51 | our $VERSION = 2.21; |
53 | |
52 | |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | |
54 | |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $MAX_RECURSE = 10; |
56 | our $MAX_RECURSE = 10; |
58 | our $MAX_PERSISTENT = 8; |
|
|
59 | our $PERSISTENT_TIMEOUT = 2; |
57 | our $PERSISTENT_TIMEOUT = 3; |
60 | our $TIMEOUT = 300; |
58 | our $TIMEOUT = 300; |
61 | |
59 | our $MAX_PER_HOST = 4; # changing this is evil |
62 | # changing these is evil |
|
|
63 | our $MAX_PERSISTENT_PER_HOST = 0; |
|
|
64 | our $MAX_PER_HOST = 4; |
|
|
65 | |
60 | |
66 | our $PROXY; |
61 | our $PROXY; |
67 | our $ACTIVE = 0; |
62 | our $ACTIVE = 0; |
68 | |
63 | |
69 | my %KA_COUNT; # number of open keep-alive connections per host |
64 | my %KA_CACHE; # indexed by uhost currently, points to [$handle...] array |
70 | my %CO_SLOT; # number of open connections, and wait queue, per host |
65 | my %CO_SLOT; # number of open connections, and wait queue, per host |
71 | |
66 | |
72 | =item http_get $url, key => value..., $cb->($data, $headers) |
67 | =item http_get $url, key => value..., $cb->($data, $headers) |
73 | |
68 | |
74 | Executes an HTTP-GET request. See the http_request function for details on |
69 | Executes an HTTP-GET request. See the http_request function for details on |
… | |
… | |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
89 | 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 |
90 | 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. |
91 | destroyed before the callback is called, the request will be cancelled. |
97 | |
92 | |
98 | The callback will be called with the response body data as first argument |
93 | The callback will be called with the response body data as first argument |
99 | (or C<undef> if an error occured), and a hash-ref with response headers as |
94 | (or C<undef> if an error occurred), and a hash-ref with response headers |
100 | second argument. |
95 | (and trailers) as second argument. |
101 | |
96 | |
102 | All the headers in that hash are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
98 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
99 | 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 |
100 | three parts of the HTTP Status-Line of the same name. If an error occurs |
… | |
… | |
122 | |
117 | |
123 | If the server sends a header multiple times, then their contents will be |
118 | If the server sends a header multiple times, then their contents will be |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
119 | joined together with a comma (C<,>), as per the HTTP spec. |
125 | |
120 | |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
121 | If an internal error occurs, such as not being able to resolve a hostname, |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
122 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
128 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
123 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
129 | message. |
124 | message. Currently the following status codes are used: |
|
|
125 | |
|
|
126 | =over 4 |
|
|
127 | |
|
|
128 | =item 595 - errors during connection establishment, proxy handshake. |
|
|
129 | |
|
|
130 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
131 | |
|
|
132 | =item 597 - errors during body receiving or processing. |
|
|
133 | |
|
|
134 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
135 | |
|
|
136 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
137 | |
|
|
138 | =back |
130 | |
139 | |
131 | A typical callback might look like this: |
140 | A typical callback might look like this: |
132 | |
141 | |
133 | sub { |
142 | sub { |
134 | my ($body, $hdr) = @_; |
143 | my ($body, $hdr) = @_; |
… | |
… | |
145 | |
154 | |
146 | =over 4 |
155 | =over 4 |
147 | |
156 | |
148 | =item recurse => $count (default: $MAX_RECURSE) |
157 | =item recurse => $count (default: $MAX_RECURSE) |
149 | |
158 | |
150 | Whether to recurse requests or not, e.g. on redirects, authentication |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
151 | retries and so on, and how often to do so. |
160 | other retries and so on, and how often to do so. |
|
|
161 | |
|
|
162 | Only redirects to http and https URLs are supported. While most common |
|
|
163 | redirection forms are handled entirely within this module, some require |
|
|
164 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
165 | the request will fail with an error. |
152 | |
166 | |
153 | =item headers => hashref |
167 | =item headers => hashref |
154 | |
168 | |
155 | The request headers to use. Currently, C<http_request> may provide its |
169 | The request headers to use. Currently, C<http_request> may provide its own |
156 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
157 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
158 | suppressed by using C<undef> for these headers in which case they won't be |
172 | (this can be suppressed by using C<undef> for these headers in which case |
159 | sent at all). |
173 | they won't be sent at all). |
|
|
174 | |
|
|
175 | You really should provide your own C<User-Agent:> header value that is |
|
|
176 | appropriate for your program - I wouldn't be surprised if the default |
|
|
177 | AnyEvent string gets blocked by webservers sooner or later. |
|
|
178 | |
|
|
179 | Also, make sure that your headers names and values do not contain any |
|
|
180 | embedded newlines. |
160 | |
181 | |
161 | =item timeout => $seconds |
182 | =item timeout => $seconds |
162 | |
183 | |
163 | The time-out to use for various stages - each connect attempt will reset |
184 | The time-out to use for various stages - each connect attempt will reset |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
185 | the timeout, as will read or write activity, i.e. this is not an overall |
… | |
… | |
166 | |
187 | |
167 | Default timeout is 5 minutes. |
188 | Default timeout is 5 minutes. |
168 | |
189 | |
169 | =item proxy => [$host, $port[, $scheme]] or undef |
190 | =item proxy => [$host, $port[, $scheme]] or undef |
170 | |
191 | |
171 | Use the given http proxy for all requests. If not specified, then the |
192 | Use the given http proxy for all requests, or no proxy if C<undef> is |
172 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
193 | used. |
173 | |
194 | |
174 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
195 | C<$scheme> must be either missing or must be C<http> for HTTP. |
175 | HTTPS. |
196 | |
|
|
197 | If not specified, then the default proxy is used (see |
|
|
198 | C<AnyEvent::HTTP::set_proxy>). |
|
|
199 | |
|
|
200 | Currently, if your proxy requires authorization, you have to specify an |
|
|
201 | appropriate "Proxy-Authorization" header in every request. |
176 | |
202 | |
177 | =item body => $string |
203 | =item body => $string |
178 | |
204 | |
179 | The request body, usually empty. Will be-sent as-is (future versions of |
205 | The request body, usually empty. Will be sent as-is (future versions of |
180 | this module might offer more options). |
206 | this module might offer more options). |
181 | |
207 | |
182 | =item cookie_jar => $hash_ref |
208 | =item cookie_jar => $hash_ref |
183 | |
209 | |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
210 | Passing this parameter enables (simplified) cookie-processing, loosely |
185 | based on the original netscape specification. |
211 | based on the original netscape specification. |
186 | |
212 | |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
213 | The C<$hash_ref> must be an (initially empty) hash reference which |
188 | get updated automatically. It is possible to save the cookie_jar to |
214 | will get updated automatically. It is possible to save the cookie jar |
189 | persistent storage with something like JSON or Storable, but this is not |
215 | to persistent storage with something like JSON or Storable - see the |
190 | recommended, as expiry times are currently being ignored. |
216 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
217 | expired or session-only cookies, and also for documentation on the format |
|
|
218 | of the cookie jar. |
191 | |
219 | |
192 | Note that this cookie implementation is not of very high quality, nor |
220 | Note that this cookie implementation is not meant to be complete. If |
193 | meant to be complete. If you want complete cookie management you have to |
221 | you want complete cookie management you have to do that on your |
194 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
222 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
195 | cookie-using sites working. Cookies are a privacy disaster, do not use |
223 | working. Cookies are a privacy disaster, do not use them unless required |
196 | them unless required to. |
224 | to. |
|
|
225 | |
|
|
226 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
227 | headers will be set and handled by this module, otherwise they will be |
|
|
228 | left untouched. |
197 | |
229 | |
198 | =item tls_ctx => $scheme | $tls_ctx |
230 | =item tls_ctx => $scheme | $tls_ctx |
199 | |
231 | |
200 | Specifies the AnyEvent::TLS context to be used for https connections. This |
232 | 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 |
233 | parameter follows the same rules as the C<tls_ctx> parameter to |
… | |
… | |
205 | verification) TLS context. |
237 | verification) TLS context. |
206 | |
238 | |
207 | The default for this option is C<low>, which could be interpreted as "give |
239 | The default for this option is C<low>, which could be interpreted as "give |
208 | me the page, no matter what". |
240 | me the page, no matter what". |
209 | |
241 | |
|
|
242 | See also the C<sessionid> parameter. |
|
|
243 | |
|
|
244 | =item session => $string |
|
|
245 | |
|
|
246 | The module might reuse connections to the same host internally. Sometimes |
|
|
247 | (e.g. when using TLS), you do not want to reuse connections from other |
|
|
248 | sessions. This can be achieved by setting this parameter to some unique |
|
|
249 | ID (such as the address of an object storing your state data, or the TLS |
|
|
250 | context) - only connections using the same unique ID will be reused. |
|
|
251 | |
210 | =item on_prepare => $callback->($fh) |
252 | =item on_prepare => $callback->($fh) |
211 | |
253 | |
212 | In rare cases you need to "tune" the socket before it is used to |
254 | 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 |
255 | connect (for example, to bind it on a given IP address). This parameter |
214 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
256 | 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 |
257 | and behaves exactly the same way (e.g. it has to provide a |
216 | timeout). See the description for the C<$prepare_cb> argument of |
258 | timeout). See the description for the C<$prepare_cb> argument of |
217 | C<AnyEvent::Socket::tcp_connect> for details. |
259 | C<AnyEvent::Socket::tcp_connect> for details. |
218 | |
260 | |
… | |
… | |
240 | |
282 | |
241 | This callback is useful, among other things, to quickly reject unwanted |
283 | 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 |
284 | content, which, if it is supposed to be rare, can be faster than first |
243 | doing a C<HEAD> request. |
285 | doing a C<HEAD> request. |
244 | |
286 | |
|
|
287 | The downside is that cancelling the request makes it impossible to re-use |
|
|
288 | the connection. Also, the C<on_header> callback will not receive any |
|
|
289 | trailer (headers sent after the response body). |
|
|
290 | |
245 | Example: cancel the request unless the content-type is "text/html". |
291 | Example: cancel the request unless the content-type is "text/html". |
246 | |
292 | |
247 | on_header => sub { |
293 | on_header => sub { |
248 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
294 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
249 | }, |
295 | }, |
… | |
… | |
255 | string instead of the body data. |
301 | string instead of the body data. |
256 | |
302 | |
257 | It has to return either true (in which case AnyEvent::HTTP will continue), |
303 | 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 |
304 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
259 | the completion callback with an error code of C<598>). |
305 | the completion callback with an error code of C<598>). |
|
|
306 | |
|
|
307 | The downside to cancelling the request is that it makes it impossible to |
|
|
308 | re-use the connection. |
260 | |
309 | |
261 | This callback is useful when the data is too large to be held in memory |
310 | 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 |
311 | (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. |
312 | be extracted, or when the body should be processed incrementally. |
264 | |
313 | |
… | |
… | |
276 | called. Instead of the C<$body> argument containing the body data, the |
325 | called. Instead of the C<$body> argument containing the body data, the |
277 | callback will receive the L<AnyEvent::Handle> object associated with the |
326 | 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 |
327 | 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. |
328 | (e.g. status C<304>), the empty string will be passed. |
280 | |
329 | |
281 | The handle object might or might not be in TLS mode, might be connected to |
330 | The handle object might or might not be in TLS mode, might be connected |
282 | a proxy, be a persistent connection etc., and configured in unspecified |
331 | to a proxy, be a persistent connection, use chunked transfer encoding |
283 | ways. The user is responsible for this handle (it will not be used by this |
332 | etc., and configured in unspecified ways. The user is responsible for this |
284 | module anymore). |
333 | handle (it will not be used by this module anymore). |
285 | |
334 | |
286 | This is useful with some push-type services, where, after the initial |
335 | This is useful with some push-type services, where, after the initial |
287 | headers, an interactive protocol is used (typical example would be the |
336 | headers, an interactive protocol is used (typical example would be the |
288 | push-style twitter API which starts a JSON/XML stream). |
337 | push-style twitter API which starts a JSON/XML stream). |
289 | |
338 | |
290 | If you think you need this, first have a look at C<on_body>, to see if |
339 | 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. |
340 | that doesn't solve your problem in a better way. |
292 | |
341 | |
|
|
342 | =item persistent => $boolean |
|
|
343 | |
|
|
344 | Try to create/reuse a persistent connection. When this flag is set |
|
|
345 | (default: true for idempotent requests, false for all others), then |
|
|
346 | C<http_request> tries to re-use an existing (previously-created) |
|
|
347 | persistent connection to the host and, failing that, tries to create a new |
|
|
348 | one. |
|
|
349 | |
|
|
350 | Requests failing in certain ways will be automatically retried once, which |
|
|
351 | is dangerous for non-idempotent requests, which is why it defaults to off |
|
|
352 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
|
|
353 | made it impossible to distinguish between a fatal error and a normal |
|
|
354 | connection timeout, so you never know whether there was a problem with |
|
|
355 | your request or not. |
|
|
356 | |
|
|
357 | When reusing an existent connection, many parameters (such as TLS context) |
|
|
358 | will be ignored. See the C<session> parameter for a workaround. |
|
|
359 | |
|
|
360 | =item keepalive => $boolean |
|
|
361 | |
|
|
362 | Only used when C<persistent> is also true. This parameter decides whether |
|
|
363 | C<http_request> tries to handshake a HTTP/1.0-style keep-alive connection |
|
|
364 | (as opposed to only a HTTP/1.1 persistent connection). |
|
|
365 | |
|
|
366 | The default is true, except when using a proxy, in which case it defaults |
|
|
367 | to false, as HTTP/1.0 proxies cannot support this in a meaningful way. |
|
|
368 | |
|
|
369 | =item handle_params => { key => value ... } |
|
|
370 | |
|
|
371 | The key-value pairs in this hash will be passed to any L<AnyEvent::Handle> |
|
|
372 | constructor that is called - not all requests will create a handle, and |
|
|
373 | sometimes more than one is created, so this parameter is only good for |
|
|
374 | setting hints. |
|
|
375 | |
|
|
376 | Example: set the maximum read size to 4096, to potentially conserve memory |
|
|
377 | at the cost of speed. |
|
|
378 | |
|
|
379 | handle_params => { |
|
|
380 | max_read_size => 4096, |
|
|
381 | }, |
|
|
382 | |
293 | =back |
383 | =back |
294 | |
384 | |
295 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
385 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
386 | the response body. |
296 | |
387 | |
297 | http_request GET => "http://www.nethype.de/", sub { |
388 | http_request GET => "http://www.nethype.de/", sub { |
298 | my ($body, $hdr) = @_; |
389 | my ($body, $hdr) = @_; |
299 | print "$body\n"; |
390 | print "$body\n"; |
300 | }; |
391 | }; |
301 | |
392 | |
302 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
393 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
303 | timeout of 30 seconds. |
394 | timeout of 30 seconds. |
304 | |
395 | |
305 | http_request |
396 | http_request |
306 | GET => "https://www.google.com", |
397 | HEAD => "https://www.google.com", |
|
|
398 | headers => { "user-agent" => "MySearchClient 1.0" }, |
307 | timeout => 30, |
399 | timeout => 30, |
308 | sub { |
400 | sub { |
309 | my ($body, $hdr) = @_; |
401 | my ($body, $hdr) = @_; |
310 | use Data::Dumper; |
402 | use Data::Dumper; |
311 | print Dumper $hdr; |
403 | print Dumper $hdr; |
312 | } |
404 | } |
313 | ; |
405 | ; |
314 | |
406 | |
315 | Example: make another simple HTTP GET request, but immediately try to |
407 | Example: do another simple HTTP GET request, but immediately try to |
316 | cancel it. |
408 | cancel it. |
317 | |
409 | |
318 | my $request = http_request GET => "http://www.nethype.de/", sub { |
410 | my $request = http_request GET => "http://www.nethype.de/", sub { |
319 | my ($body, $hdr) = @_; |
411 | my ($body, $hdr) = @_; |
320 | print "$body\n"; |
412 | print "$body\n"; |
321 | }; |
413 | }; |
322 | |
414 | |
323 | undef $request; |
415 | undef $request; |
324 | |
416 | |
325 | =cut |
417 | =cut |
|
|
418 | |
|
|
419 | ############################################################################# |
|
|
420 | # wait queue/slots |
326 | |
421 | |
327 | sub _slot_schedule; |
422 | sub _slot_schedule; |
328 | sub _slot_schedule($) { |
423 | sub _slot_schedule($) { |
329 | my $host = shift; |
424 | my $host = shift; |
330 | |
425 | |
… | |
… | |
352 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
447 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
353 | |
448 | |
354 | _slot_schedule $_[0]; |
449 | _slot_schedule $_[0]; |
355 | } |
450 | } |
356 | |
451 | |
|
|
452 | ############################################################################# |
|
|
453 | # cookie handling |
|
|
454 | |
|
|
455 | # expire cookies |
|
|
456 | sub cookie_jar_expire($;$) { |
|
|
457 | my ($jar, $session_end) = @_; |
|
|
458 | |
|
|
459 | %$jar = () if $jar->{version} != 1; |
|
|
460 | |
|
|
461 | my $anow = AE::now; |
|
|
462 | |
|
|
463 | while (my ($chost, $paths) = each %$jar) { |
|
|
464 | next unless ref $paths; |
|
|
465 | |
|
|
466 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
467 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
468 | if (exists $kv->{_expires}) { |
|
|
469 | delete $cookies->{$cookie} |
|
|
470 | if $anow > $kv->{_expires}; |
|
|
471 | } elsif ($session_end) { |
|
|
472 | delete $cookies->{$cookie}; |
|
|
473 | } |
|
|
474 | } |
|
|
475 | |
|
|
476 | delete $paths->{$cpath} |
|
|
477 | unless %$cookies; |
|
|
478 | } |
|
|
479 | |
|
|
480 | delete $jar->{$chost} |
|
|
481 | unless %$paths; |
|
|
482 | } |
|
|
483 | } |
|
|
484 | |
|
|
485 | # extract cookies from jar |
|
|
486 | sub cookie_jar_extract($$$$) { |
|
|
487 | my ($jar, $scheme, $host, $path) = @_; |
|
|
488 | |
|
|
489 | %$jar = () if $jar->{version} != 1; |
|
|
490 | |
|
|
491 | my @cookies; |
|
|
492 | |
|
|
493 | while (my ($chost, $paths) = each %$jar) { |
|
|
494 | next unless ref $paths; |
|
|
495 | |
|
|
496 | if ($chost =~ /^\./) { |
|
|
497 | next unless $chost eq substr $host, -length $chost; |
|
|
498 | } elsif ($chost =~ /\./) { |
|
|
499 | next unless $chost eq $host; |
|
|
500 | } else { |
|
|
501 | next; |
|
|
502 | } |
|
|
503 | |
|
|
504 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
505 | next unless $cpath eq substr $path, 0, length $cpath; |
|
|
506 | |
|
|
507 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
508 | next if $scheme ne "https" && exists $kv->{secure}; |
|
|
509 | |
|
|
510 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
511 | delete $cookies->{$cookie}; |
|
|
512 | next; |
|
|
513 | } |
|
|
514 | |
|
|
515 | my $value = $kv->{value}; |
|
|
516 | |
|
|
517 | if ($value =~ /[=;,[:space:]]/) { |
|
|
518 | $value =~ s/([\\"])/\\$1/g; |
|
|
519 | $value = "\"$value\""; |
|
|
520 | } |
|
|
521 | |
|
|
522 | push @cookies, "$cookie=$value"; |
|
|
523 | } |
|
|
524 | } |
|
|
525 | } |
|
|
526 | |
|
|
527 | \@cookies |
|
|
528 | } |
|
|
529 | |
|
|
530 | # parse set_cookie header into jar |
|
|
531 | sub cookie_jar_set_cookie($$$$) { |
|
|
532 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
533 | |
|
|
534 | my $anow = int AE::now; |
|
|
535 | my $snow; # server-now |
|
|
536 | |
|
|
537 | for ($set_cookie) { |
|
|
538 | # parse NAME=VALUE |
|
|
539 | my @kv; |
|
|
540 | |
|
|
541 | # expires is not http-compliant in the original cookie-spec, |
|
|
542 | # we support the official date format and some extensions |
|
|
543 | while ( |
|
|
544 | m{ |
|
|
545 | \G\s* |
|
|
546 | (?: |
|
|
547 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
548 | | ([^=;,[:space:]]+) (?: \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^;,[:space:]]*) ) )? |
|
|
549 | ) |
|
|
550 | }gcxsi |
|
|
551 | ) { |
|
|
552 | my $name = $2; |
|
|
553 | my $value = $4; |
|
|
554 | |
|
|
555 | if (defined $1) { |
|
|
556 | # expires |
|
|
557 | $name = "expires"; |
|
|
558 | $value = $1; |
|
|
559 | } elsif (defined $3) { |
|
|
560 | # quoted |
|
|
561 | $value = $3; |
|
|
562 | $value =~ s/\\(.)/$1/gs; |
|
|
563 | } |
|
|
564 | |
|
|
565 | push @kv, @kv ? lc $name : $name, $value; |
|
|
566 | |
|
|
567 | last unless /\G\s*;/gc; |
|
|
568 | } |
|
|
569 | |
|
|
570 | last unless @kv; |
|
|
571 | |
|
|
572 | my $name = shift @kv; |
|
|
573 | my %kv = (value => shift @kv, @kv); |
|
|
574 | |
|
|
575 | if (exists $kv{"max-age"}) { |
|
|
576 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
577 | } elsif (exists $kv{expires}) { |
|
|
578 | $snow ||= parse_date ($date) || $anow; |
|
|
579 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
580 | } else { |
|
|
581 | delete $kv{_expires}; |
|
|
582 | } |
|
|
583 | |
|
|
584 | my $cdom; |
|
|
585 | my $cpath = (delete $kv{path}) || "/"; |
|
|
586 | |
|
|
587 | if (exists $kv{domain}) { |
|
|
588 | $cdom = delete $kv{domain}; |
|
|
589 | |
|
|
590 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
591 | |
|
|
592 | next if $cdom =~ /\.$/; |
|
|
593 | |
|
|
594 | # this is not rfc-like and not netscape-like. go figure. |
|
|
595 | my $ndots = $cdom =~ y/.//; |
|
|
596 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
597 | } else { |
|
|
598 | $cdom = $host; |
|
|
599 | } |
|
|
600 | |
|
|
601 | # store it |
|
|
602 | $jar->{version} = 1; |
|
|
603 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
|
|
604 | |
|
|
605 | redo if /\G\s*,/gc; |
|
|
606 | } |
|
|
607 | } |
|
|
608 | |
|
|
609 | ############################################################################# |
|
|
610 | # keepalive/persistent connection cache |
|
|
611 | |
|
|
612 | # fetch a connection from the keepalive cache |
|
|
613 | sub ka_fetch($) { |
|
|
614 | my $ka_key = shift; |
|
|
615 | |
|
|
616 | my $hdl = pop @{ $KA_CACHE{$ka_key} }; # currently we reuse the MOST RECENTLY USED connection |
|
|
617 | delete $KA_CACHE{$ka_key} |
|
|
618 | unless @{ $KA_CACHE{$ka_key} }; |
|
|
619 | |
|
|
620 | $hdl |
|
|
621 | } |
|
|
622 | |
|
|
623 | sub ka_store($$) { |
|
|
624 | my ($ka_key, $hdl) = @_; |
|
|
625 | |
|
|
626 | my $kaa = $KA_CACHE{$ka_key} ||= []; |
|
|
627 | |
|
|
628 | my $destroy = sub { |
|
|
629 | my @ka = grep $_ != $hdl, @{ $KA_CACHE{$ka_key} }; |
|
|
630 | |
|
|
631 | $hdl->destroy; |
|
|
632 | |
|
|
633 | @ka |
|
|
634 | ? $KA_CACHE{$ka_key} = \@ka |
|
|
635 | : delete $KA_CACHE{$ka_key}; |
|
|
636 | }; |
|
|
637 | |
|
|
638 | # on error etc., destroy |
|
|
639 | $hdl->on_error ($destroy); |
|
|
640 | $hdl->on_eof ($destroy); |
|
|
641 | $hdl->on_read ($destroy); |
|
|
642 | $hdl->timeout ($PERSISTENT_TIMEOUT); |
|
|
643 | |
|
|
644 | push @$kaa, $hdl; |
|
|
645 | shift @$kaa while @$kaa > $MAX_PER_HOST; |
|
|
646 | } |
|
|
647 | |
|
|
648 | ############################################################################# |
|
|
649 | # utilities |
|
|
650 | |
|
|
651 | # continue to parse $_ for headers and place them into the arg |
|
|
652 | sub _parse_hdr() { |
|
|
653 | my %hdr; |
|
|
654 | |
|
|
655 | # things seen, not parsed: |
|
|
656 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
657 | |
|
|
658 | $hdr{lc $1} .= ",$2" |
|
|
659 | while /\G |
|
|
660 | ([^:\000-\037]*): |
|
|
661 | [\011\040]* |
|
|
662 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
663 | \012 |
|
|
664 | /gxc; |
|
|
665 | |
|
|
666 | /\G$/ |
|
|
667 | or return; |
|
|
668 | |
|
|
669 | # remove the "," prefix we added to all headers above |
|
|
670 | substr $_, 0, 1, "" |
|
|
671 | for values %hdr; |
|
|
672 | |
|
|
673 | \%hdr |
|
|
674 | } |
|
|
675 | |
|
|
676 | ############################################################################# |
|
|
677 | # http_get |
|
|
678 | |
357 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
679 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
358 | |
680 | |
359 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
681 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
360 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
682 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
683 | |
|
|
684 | # maybe it should just become a normal object :/ |
|
|
685 | |
|
|
686 | sub _destroy_state(\%) { |
|
|
687 | my ($state) = @_; |
|
|
688 | |
|
|
689 | $state->{handle}->destroy if $state->{handle}; |
|
|
690 | %$state = (); |
|
|
691 | } |
|
|
692 | |
|
|
693 | sub _error(\%$$) { |
|
|
694 | my ($state, $cb, $hdr) = @_; |
|
|
695 | |
|
|
696 | &_destroy_state ($state); |
|
|
697 | |
|
|
698 | $cb->(undef, $hdr); |
|
|
699 | () |
|
|
700 | } |
|
|
701 | |
|
|
702 | our %IDEMPOTENT = ( |
|
|
703 | DELETE => 1, |
|
|
704 | GET => 1, |
|
|
705 | HEAD => 1, |
|
|
706 | OPTIONS => 1, |
|
|
707 | PUT => 1, |
|
|
708 | TRACE => 1, |
|
|
709 | |
|
|
710 | ACL => 1, |
|
|
711 | "BASELINE-CONTROL" => 1, |
|
|
712 | BIND => 1, |
|
|
713 | CHECKIN => 1, |
|
|
714 | CHECKOUT => 1, |
|
|
715 | COPY => 1, |
|
|
716 | LABEL => 1, |
|
|
717 | LINK => 1, |
|
|
718 | MERGE => 1, |
|
|
719 | MKACTIVITY => 1, |
|
|
720 | MKCALENDAR => 1, |
|
|
721 | MKCOL => 1, |
|
|
722 | MKREDIRECTREF => 1, |
|
|
723 | MKWORKSPACE => 1, |
|
|
724 | MOVE => 1, |
|
|
725 | ORDERPATCH => 1, |
|
|
726 | PROPFIND => 1, |
|
|
727 | PROPPATCH => 1, |
|
|
728 | REBIND => 1, |
|
|
729 | REPORT => 1, |
|
|
730 | SEARCH => 1, |
|
|
731 | UNBIND => 1, |
|
|
732 | UNCHECKOUT => 1, |
|
|
733 | UNLINK => 1, |
|
|
734 | UNLOCK => 1, |
|
|
735 | UPDATE => 1, |
|
|
736 | UPDATEREDIRECTREF => 1, |
|
|
737 | "VERSION-CONTROL" => 1, |
|
|
738 | ); |
361 | |
739 | |
362 | sub http_request($$@) { |
740 | sub http_request($$@) { |
363 | my $cb = pop; |
741 | my $cb = pop; |
364 | my ($method, $url, %arg) = @_; |
742 | my ($method, $url, %arg) = @_; |
365 | |
743 | |
… | |
… | |
383 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
761 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
384 | |
762 | |
385 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
763 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
386 | if $recurse < 0; |
764 | if $recurse < 0; |
387 | |
765 | |
388 | my $proxy = $arg{proxy} || $PROXY; |
766 | my $proxy = exists $arg{proxy} ? $arg{proxy} : $PROXY; |
389 | my $timeout = $arg{timeout} || $TIMEOUT; |
767 | my $timeout = $arg{timeout} || $TIMEOUT; |
390 | |
768 | |
391 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
769 | my ($uscheme, $uauthority, $upath, $query, undef) = # ignore fragment |
392 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
770 | $url =~ m|^([^:]+):(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?$|; |
393 | |
771 | |
394 | $uscheme = lc $uscheme; |
772 | $uscheme = lc $uscheme; |
395 | |
773 | |
396 | my $uport = $uscheme eq "http" ? 80 |
774 | my $uport = $uscheme eq "http" ? 80 |
397 | : $uscheme eq "https" ? 443 |
775 | : $uscheme eq "https" ? 443 |
398 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
776 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
399 | |
777 | |
400 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
778 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
401 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
779 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
402 | |
780 | |
403 | my $uhost = $1; |
781 | my $uhost = lc $1; |
404 | $uport = $2 if defined $2; |
782 | $uport = $2 if defined $2; |
405 | |
783 | |
406 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
784 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
407 | unless exists $hdr{host}; |
785 | unless exists $hdr{host}; |
408 | |
786 | |
… | |
… | |
411 | |
789 | |
412 | $upath =~ s%^/?%/%; |
790 | $upath =~ s%^/?%/%; |
413 | |
791 | |
414 | # cookie processing |
792 | # cookie processing |
415 | if (my $jar = $arg{cookie_jar}) { |
793 | if (my $jar = $arg{cookie_jar}) { |
416 | %$jar = () if $jar->{version} != 1; |
794 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
417 | |
795 | |
418 | my @cookie; |
|
|
419 | |
|
|
420 | while (my ($chost, $v) = each %$jar) { |
|
|
421 | if ($chost =~ /^\./) { |
|
|
422 | next unless $chost eq substr $uhost, -length $chost; |
|
|
423 | } elsif ($chost =~ /\./) { |
|
|
424 | next unless $chost eq $uhost; |
|
|
425 | } else { |
|
|
426 | next; |
|
|
427 | } |
|
|
428 | |
|
|
429 | while (my ($cpath, $v) = each %$v) { |
|
|
430 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
431 | |
|
|
432 | while (my ($k, $v) = each %$v) { |
|
|
433 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
434 | my $value = $v->{value}; |
|
|
435 | $value =~ s/([\\"])/\\$1/g; |
|
|
436 | push @cookie, "$k=\"$value\""; |
|
|
437 | } |
|
|
438 | } |
|
|
439 | } |
|
|
440 | |
|
|
441 | $hdr{cookie} = join "; ", @cookie |
796 | $hdr{cookie} = join "; ", @$cookies |
442 | if @cookie; |
797 | if @$cookies; |
443 | } |
798 | } |
444 | |
799 | |
445 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
800 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
446 | |
801 | |
447 | if ($proxy) { |
802 | if ($proxy) { |
… | |
… | |
450 | $rscheme = "http" unless defined $rscheme; |
805 | $rscheme = "http" unless defined $rscheme; |
451 | |
806 | |
452 | # don't support https requests over https-proxy transport, |
807 | # don't support https requests over https-proxy transport, |
453 | # can't be done with tls as spec'ed, unless you double-encrypt. |
808 | # can't be done with tls as spec'ed, unless you double-encrypt. |
454 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
809 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
|
|
810 | |
|
|
811 | $rhost = lc $rhost; |
|
|
812 | $rscheme = lc $rscheme; |
455 | } else { |
813 | } else { |
456 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
814 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
457 | } |
815 | } |
458 | |
816 | |
459 | # leave out fragment and query string, just a heuristic |
817 | # leave out fragment and query string, just a heuristic |
460 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
818 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
461 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
819 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
462 | |
820 | |
463 | $hdr{"content-length"} = length $arg{body} |
821 | $hdr{"content-length"} = length $arg{body} |
464 | if length $arg{body} || $method ne "GET"; |
822 | if length $arg{body} || $method ne "GET"; |
465 | |
823 | |
|
|
824 | my $idempotent = $IDEMPOTENT{$method}; |
|
|
825 | |
|
|
826 | # default value for keepalive is true iff the request is for an idempotent method |
|
|
827 | my $persistent = exists $arg{persistent} ? !!$arg{persistent} : $idempotent; |
|
|
828 | my $keepalive = exists $arg{keepalive} ? !!$arg{keepalive} : !$proxy; |
|
|
829 | my $was_persistent; # true if this is actually a recycled connection |
|
|
830 | |
|
|
831 | # the key to use in the keepalive cache |
|
|
832 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
|
|
833 | |
|
|
834 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
|
|
835 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
|
|
836 | |
466 | my %state = (connect_guard => 1); |
837 | my %state = (connect_guard => 1); |
|
|
838 | |
|
|
839 | my $ae_error = 595; # connecting |
|
|
840 | |
|
|
841 | # handle actual, non-tunneled, request |
|
|
842 | my $handle_actual_request = sub { |
|
|
843 | $ae_error = 596; # request phase |
|
|
844 | |
|
|
845 | my $hdl = $state{handle}; |
|
|
846 | |
|
|
847 | $hdl->starttls ("connect") if $uscheme eq "https" && !exists $hdl->{tls}; |
|
|
848 | |
|
|
849 | # send request |
|
|
850 | $hdl->push_write ( |
|
|
851 | "$method $rpath HTTP/1.1\015\012" |
|
|
852 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
853 | . "\015\012" |
|
|
854 | . $arg{body} |
|
|
855 | ); |
|
|
856 | |
|
|
857 | # return if error occurred during push_write() |
|
|
858 | return unless %state; |
|
|
859 | |
|
|
860 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
|
|
861 | %hdr = (); |
|
|
862 | |
|
|
863 | # status line and headers |
|
|
864 | $state{read_response} = sub { |
|
|
865 | return unless %state; |
|
|
866 | |
|
|
867 | for ("$_[1]") { |
|
|
868 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
869 | |
|
|
870 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
871 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid server response" }; |
|
|
872 | |
|
|
873 | # 100 Continue handling |
|
|
874 | # should not happen as we don't send expect: 100-continue, |
|
|
875 | # but we handle it just in case. |
|
|
876 | # since we send the request body regardless, if we get an error |
|
|
877 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
878 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
879 | if $2 eq 100; |
|
|
880 | |
|
|
881 | push @pseudo, |
|
|
882 | HTTPVersion => $1, |
|
|
883 | Status => $2, |
|
|
884 | Reason => $3, |
|
|
885 | ; |
|
|
886 | |
|
|
887 | my $hdr = _parse_hdr |
|
|
888 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Garbled response headers" }; |
|
|
889 | |
|
|
890 | %hdr = (%$hdr, @pseudo); |
|
|
891 | } |
|
|
892 | |
|
|
893 | # redirect handling |
|
|
894 | # relative uri handling forced by microsoft and other shitheads. |
|
|
895 | # we give our best and fall back to URI if available. |
|
|
896 | if (exists $hdr{location}) { |
|
|
897 | my $loc = $hdr{location}; |
|
|
898 | |
|
|
899 | if ($loc =~ m%^//%) { # // |
|
|
900 | $loc = "$rscheme:$loc"; |
|
|
901 | |
|
|
902 | } elsif ($loc eq "") { |
|
|
903 | $loc = $url; |
|
|
904 | |
|
|
905 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
|
|
906 | $loc =~ s/^\.\/+//; |
|
|
907 | |
|
|
908 | if ($loc !~ m%^[.?#]%) { |
|
|
909 | my $prefix = "$rscheme://$uhost:$uport"; |
|
|
910 | |
|
|
911 | unless ($loc =~ s/^\///) { |
|
|
912 | $prefix .= $upath; |
|
|
913 | $prefix =~ s/\/[^\/]*$//; |
|
|
914 | } |
|
|
915 | |
|
|
916 | $loc = "$prefix/$loc"; |
|
|
917 | |
|
|
918 | } elsif (eval { require URI }) { # uri |
|
|
919 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
920 | |
|
|
921 | } else { |
|
|
922 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
923 | #$hdr{Status} = 599; |
|
|
924 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
925 | #$recurse = 0; |
|
|
926 | } |
|
|
927 | } |
|
|
928 | |
|
|
929 | $hdr{location} = $loc; |
|
|
930 | } |
|
|
931 | |
|
|
932 | my $redirect; |
|
|
933 | |
|
|
934 | if ($recurse) { |
|
|
935 | my $status = $hdr{Status}; |
|
|
936 | |
|
|
937 | # industry standard is to redirect POST as GET for |
|
|
938 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
939 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
940 | # industry standard seems to be to simply follow. |
|
|
941 | # we go with the industry standard. 308 is defined |
|
|
942 | # by rfc7538 |
|
|
943 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
944 | $redirect = 1; |
|
|
945 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
946 | unless ($method eq "HEAD") { |
|
|
947 | $method = "GET"; |
|
|
948 | delete $arg{body}; |
|
|
949 | } |
|
|
950 | } elsif ($status == 307 or $status == 308) { |
|
|
951 | $redirect = 1; |
|
|
952 | } |
|
|
953 | } |
|
|
954 | |
|
|
955 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
|
|
956 | if ($state{handle}) { |
|
|
957 | # handle keepalive |
|
|
958 | if ( |
|
|
959 | $persistent |
|
|
960 | && $_[3] |
|
|
961 | && ($hdr{HTTPVersion} < 1.1 |
|
|
962 | ? $hdr{connection} =~ /\bkeep-?alive\b/i |
|
|
963 | : $hdr{connection} !~ /\bclose\b/i) |
|
|
964 | ) { |
|
|
965 | ka_store $ka_key, delete $state{handle}; |
|
|
966 | } else { |
|
|
967 | # no keepalive, destroy the handle |
|
|
968 | $state{handle}->destroy; |
|
|
969 | } |
|
|
970 | } |
|
|
971 | |
|
|
972 | %state = (); |
|
|
973 | |
|
|
974 | if (defined $_[1]) { |
|
|
975 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
976 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
977 | } |
|
|
978 | |
|
|
979 | # set-cookie processing |
|
|
980 | if ($arg{cookie_jar}) { |
|
|
981 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
|
|
982 | } |
|
|
983 | |
|
|
984 | if ($redirect && exists $hdr{location}) { |
|
|
985 | # we ignore any errors, as it is very common to receive |
|
|
986 | # Content-Length != 0 but no actual body |
|
|
987 | # we also access %hdr, as $_[1] might be an erro |
|
|
988 | $state{recurse} = |
|
|
989 | http_request ( |
|
|
990 | $method => $hdr{location}, |
|
|
991 | %arg, |
|
|
992 | recurse => $recurse - 1, |
|
|
993 | Redirect => [$_[0], \%hdr], |
|
|
994 | sub { |
|
|
995 | %state = (); |
|
|
996 | &$cb |
|
|
997 | }, |
|
|
998 | ); |
|
|
999 | } else { |
|
|
1000 | $cb->($_[0], \%hdr); |
|
|
1001 | } |
|
|
1002 | }; |
|
|
1003 | |
|
|
1004 | $ae_error = 597; # body phase |
|
|
1005 | |
|
|
1006 | my $chunked = $hdr{"transfer-encoding"} =~ /\bchunked\b/i; # not quite correct... |
|
|
1007 | |
|
|
1008 | my $len = $chunked ? undef : $hdr{"content-length"}; |
|
|
1009 | |
|
|
1010 | # body handling, many different code paths |
|
|
1011 | # - no body expected |
|
|
1012 | # - want_body_handle |
|
|
1013 | # - te chunked |
|
|
1014 | # - 2x length known (with or without on_body) |
|
|
1015 | # - 2x length not known (with or without on_body) |
|
|
1016 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
1017 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
1018 | } elsif ( |
|
|
1019 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
1020 | or $method eq "HEAD" |
|
|
1021 | or (defined $len && $len == 0) # == 0, not !, because "0 " is true |
|
|
1022 | ) { |
|
|
1023 | # no body |
|
|
1024 | $finish->("", undef, undef, 1); |
|
|
1025 | |
|
|
1026 | } elsif (!$redirect && $arg{want_body_handle}) { |
|
|
1027 | $_[0]->on_eof (undef); |
|
|
1028 | $_[0]->on_error (undef); |
|
|
1029 | $_[0]->on_read (undef); |
|
|
1030 | |
|
|
1031 | $finish->(delete $state{handle}); |
|
|
1032 | |
|
|
1033 | } elsif ($chunked) { |
|
|
1034 | my $cl = 0; |
|
|
1035 | my $body = ""; |
|
|
1036 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
1037 | |
|
|
1038 | $state{read_chunk} = sub { |
|
|
1039 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
1040 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
1041 | |
|
|
1042 | my $len = hex $1; |
|
|
1043 | |
|
|
1044 | if ($len) { |
|
|
1045 | $cl += $len; |
|
|
1046 | |
|
|
1047 | $_[0]->push_read (chunk => $len, sub { |
|
|
1048 | $on_body->($_[1], \%hdr) |
|
|
1049 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
1050 | |
|
|
1051 | $_[0]->push_read (line => sub { |
|
|
1052 | length $_[1] |
|
|
1053 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
1054 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
1055 | }); |
|
|
1056 | }); |
|
|
1057 | } else { |
|
|
1058 | $hdr{"content-length"} ||= $cl; |
|
|
1059 | |
|
|
1060 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
1061 | if (length $_[1]) { |
|
|
1062 | for ("$_[1]") { |
|
|
1063 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
1064 | |
|
|
1065 | my $hdr = _parse_hdr |
|
|
1066 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
1067 | |
|
|
1068 | %hdr = (%hdr, %$hdr); |
|
|
1069 | } |
|
|
1070 | } |
|
|
1071 | |
|
|
1072 | $finish->($body, undef, undef, 1); |
|
|
1073 | }); |
|
|
1074 | } |
|
|
1075 | }; |
|
|
1076 | |
|
|
1077 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
1078 | |
|
|
1079 | } elsif ($arg{on_body}) { |
|
|
1080 | if (defined $len) { |
|
|
1081 | $_[0]->on_read (sub { |
|
|
1082 | $len -= length $_[0]{rbuf}; |
|
|
1083 | |
|
|
1084 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
1085 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
1086 | |
|
|
1087 | $len > 0 |
|
|
1088 | or $finish->("", undef, undef, 1); |
|
|
1089 | }); |
|
|
1090 | } else { |
|
|
1091 | $_[0]->on_eof (sub { |
|
|
1092 | $finish->(""); |
|
|
1093 | }); |
|
|
1094 | $_[0]->on_read (sub { |
|
|
1095 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
1096 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
1097 | }); |
|
|
1098 | } |
|
|
1099 | } else { |
|
|
1100 | $_[0]->on_eof (undef); |
|
|
1101 | |
|
|
1102 | if (defined $len) { |
|
|
1103 | $_[0]->on_read (sub { |
|
|
1104 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
1105 | if $len <= length $_[0]{rbuf}; |
|
|
1106 | }); |
|
|
1107 | } else { |
|
|
1108 | $_[0]->on_error (sub { |
|
|
1109 | ($! == Errno::EPIPE || !$!) |
|
|
1110 | ? $finish->(delete $_[0]{rbuf}) |
|
|
1111 | : $finish->(undef, $ae_error => $_[2]); |
|
|
1112 | }); |
|
|
1113 | $_[0]->on_read (sub { }); |
|
|
1114 | } |
|
|
1115 | } |
|
|
1116 | }; |
|
|
1117 | |
|
|
1118 | # if keepalive is enabled, then the server closing the connection |
|
|
1119 | # before a response can happen legally - we retry on idempotent methods. |
|
|
1120 | if ($was_persistent && $idempotent) { |
|
|
1121 | my $old_eof = $hdl->{on_eof}; |
|
|
1122 | $hdl->{on_eof} = sub { |
|
|
1123 | _destroy_state %state; |
|
|
1124 | |
|
|
1125 | %state = (); |
|
|
1126 | $state{recurse} = |
|
|
1127 | http_request ( |
|
|
1128 | $method => $url, |
|
|
1129 | %arg, |
|
|
1130 | recurse => $recurse - 1, |
|
|
1131 | keepalive => 0, |
|
|
1132 | sub { |
|
|
1133 | %state = (); |
|
|
1134 | &$cb |
|
|
1135 | } |
|
|
1136 | ); |
|
|
1137 | }; |
|
|
1138 | $hdl->on_read (sub { |
|
|
1139 | return unless %state; |
|
|
1140 | |
|
|
1141 | # as soon as we receive something, a connection close |
|
|
1142 | # once more becomes a hard error |
|
|
1143 | $hdl->{on_eof} = $old_eof; |
|
|
1144 | $hdl->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
1145 | }); |
|
|
1146 | } else { |
|
|
1147 | $hdl->push_read (line => $qr_nlnl, $state{read_response}); |
|
|
1148 | } |
|
|
1149 | }; |
|
|
1150 | |
|
|
1151 | my $prepare_handle = sub { |
|
|
1152 | my ($hdl) = $state{handle}; |
|
|
1153 | |
|
|
1154 | $hdl->on_error (sub { |
|
|
1155 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => $_[2] }; |
|
|
1156 | }); |
|
|
1157 | $hdl->on_eof (sub { |
|
|
1158 | _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }; |
|
|
1159 | }); |
|
|
1160 | $hdl->timeout_reset; |
|
|
1161 | $hdl->timeout ($timeout); |
|
|
1162 | }; |
|
|
1163 | |
|
|
1164 | # connected to proxy (or origin server) |
|
|
1165 | my $connect_cb = sub { |
|
|
1166 | my $fh = shift |
|
|
1167 | or return _error %state, $cb, { @pseudo, Status => $ae_error, Reason => "$!" }; |
|
|
1168 | |
|
|
1169 | return unless delete $state{connect_guard}; |
|
|
1170 | |
|
|
1171 | # get handle |
|
|
1172 | $state{handle} = new AnyEvent::Handle |
|
|
1173 | %{ $arg{handle_params} }, |
|
|
1174 | fh => $fh, |
|
|
1175 | peername => $uhost, |
|
|
1176 | tls_ctx => $arg{tls_ctx}, |
|
|
1177 | ; |
|
|
1178 | |
|
|
1179 | $prepare_handle->(); |
|
|
1180 | |
|
|
1181 | #$state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
1182 | |
|
|
1183 | # now handle proxy-CONNECT method |
|
|
1184 | if ($proxy && $uscheme eq "https") { |
|
|
1185 | # oh dear, we have to wrap it into a connect request |
|
|
1186 | |
|
|
1187 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1188 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1189 | : ""; |
|
|
1190 | |
|
|
1191 | # maybe re-use $uauthority with patched port? |
|
|
1192 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
|
|
1193 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
1194 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
1195 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
|
|
1196 | |
|
|
1197 | if ($2 == 200) { |
|
|
1198 | $rpath = $upath; |
|
|
1199 | $handle_actual_request->(); |
|
|
1200 | } else { |
|
|
1201 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
|
|
1202 | } |
|
|
1203 | }); |
|
|
1204 | } else { |
|
|
1205 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1206 | |
|
|
1207 | $handle_actual_request->(); |
|
|
1208 | } |
|
|
1209 | }; |
467 | |
1210 | |
468 | _get_slot $uhost, sub { |
1211 | _get_slot $uhost, sub { |
469 | $state{slot_guard} = shift; |
1212 | $state{slot_guard} = shift; |
470 | |
1213 | |
471 | return unless $state{connect_guard}; |
1214 | return unless $state{connect_guard}; |
472 | |
1215 | |
473 | my $connect_cb = sub { |
1216 | # try to use an existing keepalive connection, but only if we, ourselves, plan |
474 | $state{fh} = shift |
1217 | # on a keepalive request (in theory, this should be a separate config option). |
475 | or do { |
1218 | if ($persistent && $KA_CACHE{$ka_key}) { |
476 | my $err = "$!"; |
1219 | $was_persistent = 1; |
477 | %state = (); |
|
|
478 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
|
|
479 | }; |
|
|
480 | |
1220 | |
481 | pop; # free memory, save a tree |
1221 | $state{handle} = ka_fetch $ka_key; |
482 | |
|
|
483 | return unless delete $state{connect_guard}; |
|
|
484 | |
|
|
485 | # get handle |
|
|
486 | $state{handle} = new AnyEvent::Handle |
|
|
487 | fh => $state{fh}, |
|
|
488 | peername => $rhost, |
|
|
489 | tls_ctx => $arg{tls_ctx}, |
|
|
490 | # these need to be reconfigured on keepalive handles |
|
|
491 | timeout => $timeout, |
|
|
492 | on_error => sub { |
|
|
493 | %state = (); |
|
|
494 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
|
|
495 | }, |
|
|
496 | on_eof => sub { |
|
|
497 | %state = (); |
|
|
498 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
|
|
499 | }, |
|
|
500 | ; |
|
|
501 | |
|
|
502 | # limit the number of persistent connections |
|
|
503 | # keepalive not yet supported |
|
|
504 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
|
|
505 | # ++$KA_COUNT{$_[1]}; |
|
|
506 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
507 | # --$KA_COUNT{$_[1]} |
|
|
508 | # }; |
|
|
509 | # $hdr{connection} = "keep-alive"; |
|
|
510 | # } else { |
|
|
511 | delete $hdr{connection}; |
|
|
512 | # } |
|
|
513 | |
|
|
514 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
515 | |
|
|
516 | # handle actual, non-tunneled, request |
|
|
517 | my $handle_actual_request = sub { |
|
|
518 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
519 | |
|
|
520 | # send request |
|
|
521 | $state{handle}->push_write ( |
1222 | $state{handle}->destroyed |
522 | "$method $rpath HTTP/1.0\015\012" |
1223 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
523 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
1224 | $prepare_handle->(); |
524 | . "\015\012" |
1225 | $state{handle}->destroyed |
525 | . (delete $arg{body}) |
1226 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
526 | ); |
|
|
527 | |
|
|
528 | # return if error occured during push_write() |
|
|
529 | return unless %state; |
|
|
530 | |
|
|
531 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
532 | |
|
|
533 | # status line and headers |
|
|
534 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
535 | my $keepalive = pop; |
|
|
536 | |
|
|
537 | for ("$_[1]") { |
|
|
538 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
539 | |
|
|
540 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc |
|
|
541 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
542 | |
|
|
543 | push @pseudo, |
|
|
544 | HTTPVersion => $1, |
|
|
545 | Status => $2, |
|
|
546 | Reason => $3, |
|
|
547 | ; |
|
|
548 | |
|
|
549 | # things seen, not parsed: |
|
|
550 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
551 | |
|
|
552 | $hdr{lc $1} .= ",$2" |
|
|
553 | while /\G |
|
|
554 | ([^:\000-\037]*): |
|
|
555 | [\011\040]* |
|
|
556 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
557 | \012 |
|
|
558 | /gxc; |
|
|
559 | |
|
|
560 | /\G$/ |
|
|
561 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
562 | } |
|
|
563 | |
|
|
564 | # remove the "," prefix we added to all headers above |
|
|
565 | substr $_, 0, 1, "" |
|
|
566 | for values %hdr; |
|
|
567 | |
|
|
568 | # patch in all pseudo headers |
|
|
569 | %hdr = (%hdr, @pseudo); |
|
|
570 | |
|
|
571 | # redirect handling |
|
|
572 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
573 | # try to support some common forms of broken Location headers. |
|
|
574 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
575 | $hdr{location} =~ s/^\.\/+//; |
|
|
576 | |
|
|
577 | my $url = "$rscheme://$uhost:$uport"; |
|
|
578 | |
|
|
579 | unless ($hdr{location} =~ s/^\///) { |
|
|
580 | $url .= $upath; |
|
|
581 | $url =~ s/\/[^\/]*$//; |
|
|
582 | } |
|
|
583 | |
|
|
584 | $hdr{location} = "$url/$hdr{location}"; |
|
|
585 | } |
|
|
586 | |
|
|
587 | my $redirect; |
|
|
588 | |
|
|
589 | if ($recurse) { |
|
|
590 | my $status = $hdr{Status}; |
|
|
591 | |
|
|
592 | # industry standard is to redirect POST as GET for |
|
|
593 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
594 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
595 | # industry standard seems to be to simply follow. |
|
|
596 | # we go with the industry standard. |
|
|
597 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
598 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
599 | $method = "GET" unless $method eq "HEAD"; |
|
|
600 | $redirect = 1; |
|
|
601 | } elsif ($status == 307) { |
|
|
602 | $redirect = 1; |
|
|
603 | } |
|
|
604 | } |
|
|
605 | |
|
|
606 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
607 | $state{handle}->destroy if $state{handle}; |
|
|
608 | %state = (); |
|
|
609 | |
|
|
610 | if (defined $_[1]) { |
|
|
611 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
612 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
613 | } |
|
|
614 | |
|
|
615 | # set-cookie processing |
|
|
616 | if ($arg{cookie_jar}) { |
|
|
617 | for ($hdr{"set-cookie"}) { |
|
|
618 | # parse NAME=VALUE |
|
|
619 | my @kv; |
|
|
620 | |
|
|
621 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
622 | my $name = $1; |
|
|
623 | my $value = $3; |
|
|
624 | |
|
|
625 | unless ($value) { |
|
|
626 | $value = $2; |
|
|
627 | $value =~ s/\\(.)/$1/gs; |
|
|
628 | } |
|
|
629 | |
|
|
630 | push @kv, $name => $value; |
|
|
631 | |
|
|
632 | last unless /\G\s*;/gc; |
|
|
633 | } |
|
|
634 | |
|
|
635 | last unless @kv; |
|
|
636 | |
|
|
637 | my $name = shift @kv; |
|
|
638 | my %kv = (value => shift @kv, @kv); |
|
|
639 | |
|
|
640 | my $cdom; |
|
|
641 | my $cpath = (delete $kv{path}) || "/"; |
|
|
642 | |
|
|
643 | if (exists $kv{domain}) { |
|
|
644 | $cdom = delete $kv{domain}; |
|
|
645 | |
|
|
646 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
647 | |
|
|
648 | next if $cdom =~ /\.$/; |
|
|
649 | |
|
|
650 | # this is not rfc-like and not netscape-like. go figure. |
|
|
651 | my $ndots = $cdom =~ y/.//; |
|
|
652 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
653 | } else { |
|
|
654 | $cdom = $uhost; |
|
|
655 | } |
|
|
656 | |
|
|
657 | # store it |
|
|
658 | $arg{cookie_jar}{version} = 1; |
|
|
659 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
660 | |
|
|
661 | redo if /\G\s*,/gc; |
|
|
662 | } |
|
|
663 | } |
|
|
664 | |
|
|
665 | if ($redirect && exists $hdr{location}) { |
|
|
666 | # we ignore any errors, as it is very common to receive |
|
|
667 | # Content-Length != 0 but no actual body |
|
|
668 | # we also access %hdr, as $_[1] might be an erro |
|
|
669 | http_request ( |
|
|
670 | $method => $hdr{location}, |
|
|
671 | %arg, |
|
|
672 | recurse => $recurse - 1, |
|
|
673 | Redirect => [$_[0], \%hdr], |
|
|
674 | $cb); |
|
|
675 | } else { |
|
|
676 | $cb->($_[0], \%hdr); |
|
|
677 | } |
|
|
678 | }; |
|
|
679 | |
|
|
680 | my $len = $hdr{"content-length"}; |
|
|
681 | |
|
|
682 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
683 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
684 | } elsif ( |
|
|
685 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
686 | or $method eq "HEAD" |
|
|
687 | or (defined $len && !$len) |
|
|
688 | ) { |
|
|
689 | # no body |
|
|
690 | $finish->("", undef, undef, 1); |
|
|
691 | } else { |
|
|
692 | # body handling, four different code paths |
|
|
693 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
694 | # we might read too much here, but it does not matter yet (no pipelining) |
|
|
695 | if (!$redirect && $arg{want_body_handle}) { |
|
|
696 | $_[0]->on_eof (undef); |
|
|
697 | $_[0]->on_error (undef); |
|
|
698 | $_[0]->on_read (undef); |
|
|
699 | |
|
|
700 | $finish->(delete $state{handle}); |
|
|
701 | |
|
|
702 | } elsif ($arg{on_body}) { |
|
|
703 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
704 | if ($len) { |
|
|
705 | $_[0]->on_read (sub { |
|
|
706 | $len -= length $_[0]{rbuf}; |
|
|
707 | |
|
|
708 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
709 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
710 | |
|
|
711 | $len > 0 |
|
|
712 | or $finish->("", undef, undef, 1); |
|
|
713 | }); |
|
|
714 | } else { |
|
|
715 | $_[0]->on_eof (sub { |
|
|
716 | $finish->(""); |
|
|
717 | }); |
|
|
718 | $_[0]->on_read (sub { |
|
|
719 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
720 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
721 | }); |
|
|
722 | } |
|
|
723 | } else { |
|
|
724 | $_[0]->on_eof (undef); |
|
|
725 | |
|
|
726 | if ($len) { |
|
|
727 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
728 | $_[0]->on_read (sub { |
|
|
729 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
730 | if $len <= length $_[0]{rbuf}; |
|
|
731 | }); |
|
|
732 | } else { |
|
|
733 | $_[0]->on_error (sub { |
|
|
734 | ($! == Errno::EPIPE || !$!) |
|
|
735 | ? $finish->(delete $_[0]{rbuf}) |
|
|
736 | : $finish->(undef, 599 => $_[2]); |
|
|
737 | }); |
|
|
738 | $_[0]->on_read (sub { }); |
|
|
739 | } |
|
|
740 | } |
|
|
741 | } |
|
|
742 | }); |
|
|
743 | }; |
|
|
744 | |
|
|
745 | # now handle proxy-CONNECT method |
|
|
746 | if ($proxy && $uscheme eq "https") { |
|
|
747 | # oh dear, we have to wrap it into a connect request |
|
|
748 | |
|
|
749 | # maybe re-use $uauthority with patched port? |
|
|
750 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
751 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
752 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
753 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
|
|
754 | |
|
|
755 | if ($2 == 200) { |
|
|
756 | $rpath = $upath; |
|
|
757 | &$handle_actual_request; |
1227 | $handle_actual_request->(); |
758 | } else { |
1228 | |
759 | %state = (); |
|
|
760 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
|
|
761 | } |
|
|
762 | }); |
|
|
763 | } else { |
1229 | } else { |
764 | &$handle_actual_request; |
|
|
765 | } |
|
|
766 | }; |
|
|
767 | |
|
|
768 | my $tcp_connect = $arg{tcp_connect} |
1230 | my $tcp_connect = $arg{tcp_connect} |
769 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1231 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
770 | |
1232 | |
771 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
1233 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
772 | |
1234 | } |
773 | }; |
1235 | }; |
774 | |
1236 | |
775 | defined wantarray && AnyEvent::Util::guard { %state = () } |
1237 | defined wantarray && AnyEvent::Util::guard { _destroy_state %state } |
776 | } |
1238 | } |
777 | |
1239 | |
778 | sub http_get($@) { |
1240 | sub http_get($@) { |
779 | unshift @_, "GET"; |
1241 | unshift @_, "GET"; |
780 | &http_request |
1242 | &http_request |
… | |
… | |
798 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
1260 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
799 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
1261 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
800 | hostnames. The latter is a simple stub resolver and does no caching |
1262 | hostnames. The latter is a simple stub resolver and does no caching |
801 | on its own. If you want DNS caching, you currently have to provide |
1263 | on its own. If you want DNS caching, you currently have to provide |
802 | your own default resolver (by storing a suitable resolver object in |
1264 | your own default resolver (by storing a suitable resolver object in |
803 | C<$AnyEvent::DNS::RESOLVER>). |
1265 | C<$AnyEvent::DNS::RESOLVER>) or your own C<tcp_connect> callback. |
804 | |
1266 | |
805 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
1267 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
806 | |
1268 | |
807 | =over 4 |
1269 | =over 4 |
808 | |
1270 | |
809 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
1271 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
810 | |
1272 | |
811 | Sets the default proxy server to use. The proxy-url must begin with a |
1273 | Sets the default proxy server to use. The proxy-url must begin with a |
812 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
1274 | string of the form C<http://host:port>, croaks otherwise. |
813 | otherwise. |
|
|
814 | |
1275 | |
815 | To clear an already-set proxy, use C<undef>. |
1276 | To clear an already-set proxy, use C<undef>. |
|
|
1277 | |
|
|
1278 | When AnyEvent::HTTP is loaded for the first time it will query the |
|
|
1279 | default proxy from the operating system, currently by looking at |
|
|
1280 | C<$ENV{http_proxy>}. |
|
|
1281 | |
|
|
1282 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1283 | |
|
|
1284 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1285 | C<$session_end> is given and true, then additionally remove all session |
|
|
1286 | cookies. |
|
|
1287 | |
|
|
1288 | You should call this function (with a true C<$session_end>) before you |
|
|
1289 | save cookies to disk, and you should call this function after loading them |
|
|
1290 | again. If you have a long-running program you can additionally call this |
|
|
1291 | function from time to time. |
|
|
1292 | |
|
|
1293 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1294 | module. Its format is subject to change, but currently it is as follows: |
|
|
1295 | |
|
|
1296 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1297 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1298 | hash-references. The key for these inner hash references is the |
|
|
1299 | server path for which this cookie is meant, and the values are again |
|
|
1300 | hash-references. Each key of those hash-references is a cookie name, and |
|
|
1301 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1302 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1303 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1304 | expiry timestamp. Session cookies are indicated by not having an |
|
|
1305 | C<_expires> key. |
|
|
1306 | |
|
|
1307 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1308 | chance of understanding the above paragraph: |
|
|
1309 | |
|
|
1310 | { |
|
|
1311 | version => 1, |
|
|
1312 | "10.0.0.1" => { |
|
|
1313 | "/" => { |
|
|
1314 | "mythweb_id" => { |
|
|
1315 | _expires => 1293917923, |
|
|
1316 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1317 | }, |
|
|
1318 | }, |
|
|
1319 | }, |
|
|
1320 | } |
816 | |
1321 | |
817 | =item $date = AnyEvent::HTTP::format_date $timestamp |
1322 | =item $date = AnyEvent::HTTP::format_date $timestamp |
818 | |
1323 | |
819 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
1324 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
820 | Date (RFC 2616). |
1325 | Date (RFC 2616). |
821 | |
1326 | |
822 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
1327 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
823 | |
1328 | |
824 | Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX |
1329 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1330 | bunch of minor variations of those, and returns the corresponding POSIX |
825 | timestamp, or C<undef> if the date cannot be parsed. |
1331 | timestamp, or C<undef> if the date cannot be parsed. |
826 | |
1332 | |
827 | =item $AnyEvent::HTTP::MAX_RECURSE |
1333 | =item $AnyEvent::HTTP::MAX_RECURSE |
828 | |
1334 | |
829 | The default value for the C<recurse> request parameter (default: C<10>). |
1335 | The default value for the C<recurse> request parameter (default: C<10>). |
|
|
1336 | |
|
|
1337 | =item $AnyEvent::HTTP::TIMEOUT |
|
|
1338 | |
|
|
1339 | The default timeout for connection operations (default: C<300>). |
830 | |
1340 | |
831 | =item $AnyEvent::HTTP::USERAGENT |
1341 | =item $AnyEvent::HTTP::USERAGENT |
832 | |
1342 | |
833 | The default value for the C<User-Agent> header (the default is |
1343 | The default value for the C<User-Agent> header (the default is |
834 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1344 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
835 | |
1345 | |
836 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1346 | =item $AnyEvent::HTTP::MAX_PER_HOST |
837 | |
1347 | |
838 | The maximum number of concurrent connections to the same host (identified |
1348 | The maximum number of concurrent connections to the same host (identified |
839 | by the hostname). If the limit is exceeded, then the additional requests |
1349 | by the hostname). If the limit is exceeded, then additional requests |
840 | are queued until previous connections are closed. |
1350 | are queued until previous connections are closed. Both persistent and |
|
|
1351 | non-persistent connections are counted in this limit. |
841 | |
1352 | |
842 | The default value for this is C<4>, and it is highly advisable to not |
1353 | The default value for this is C<4>, and it is highly advisable to not |
843 | increase it. |
1354 | increase it much. |
|
|
1355 | |
|
|
1356 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
|
|
1357 | connections, older browsers used 2, newer ones (such as firefox 3) |
|
|
1358 | typically use 6, and Opera uses 8 because like, they have the fastest |
|
|
1359 | browser and give a shit for everybody else on the planet. |
|
|
1360 | |
|
|
1361 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
1362 | |
|
|
1363 | The time after which idle persistent connections get closed by |
|
|
1364 | AnyEvent::HTTP (default: C<3>). |
844 | |
1365 | |
845 | =item $AnyEvent::HTTP::ACTIVE |
1366 | =item $AnyEvent::HTTP::ACTIVE |
846 | |
1367 | |
847 | The number of active connections. This is not the number of currently |
1368 | The number of active connections. This is not the number of currently |
848 | running requests, but the number of currently open and non-idle TCP |
1369 | running requests, but the number of currently open and non-idle TCP |
849 | connections. This number of can be useful for load-leveling. |
1370 | connections. This number can be useful for load-leveling. |
850 | |
1371 | |
851 | =back |
1372 | =back |
852 | |
1373 | |
853 | =cut |
1374 | =cut |
854 | |
1375 | |
… | |
… | |
869 | sub parse_date($) { |
1390 | sub parse_date($) { |
870 | my ($date) = @_; |
1391 | my ($date) = @_; |
871 | |
1392 | |
872 | my ($d, $m, $y, $H, $M, $S); |
1393 | my ($d, $m, $y, $H, $M, $S); |
873 | |
1394 | |
874 | 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$/) { |
1395 | 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$/) { |
875 | # RFC 822/1123, required by RFC 2616 |
1396 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1397 | # cookie dates (with "-") |
|
|
1398 | |
876 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
1399 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
877 | |
1400 | |
878 | } 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$/) { |
1401 | } 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$/) { |
879 | # RFC 850 |
1402 | # RFC 850 |
880 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
1403 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
881 | |
1404 | |
882 | } 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])$/) { |
1405 | } 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])$/) { |
883 | # ISO C's asctime |
1406 | # ISO C's asctime |
884 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
1407 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
885 | } |
1408 | } |
886 | # other formats fail in the loop below |
1409 | # other formats fail in the loop below |
887 | |
1410 | |
888 | for (0..11) { |
1411 | for (0..11) { |
889 | if ($m eq $month[$_]) { |
1412 | if ($m eq $month[$_]) { |
890 | require Time::Local; |
1413 | require Time::Local; |
891 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
1414 | return eval { Time::Local::timegm ($S, $M, $H, $d, $_, $y) }; |
892 | } |
1415 | } |
893 | } |
1416 | } |
894 | |
1417 | |
895 | undef |
1418 | undef |
896 | } |
1419 | } |
897 | |
1420 | |
898 | sub set_proxy($) { |
1421 | sub set_proxy($) { |
899 | if (length $_[0]) { |
1422 | if (length $_[0]) { |
900 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
1423 | $_[0] =~ m%^(http):// ([^:/]+) (?: : (\d*) )?%ix |
901 | or Carp::croak "$_[0]: invalid proxy URL"; |
1424 | or Carp::croak "$_[0]: invalid proxy URL"; |
902 | $PROXY = [$2, $3 || 3128, $1] |
1425 | $PROXY = [$2, $3 || 3128, $1] |
903 | } else { |
1426 | } else { |
904 | undef $PROXY; |
1427 | undef $PROXY; |
905 | } |
1428 | } |
… | |
… | |
908 | # initialise proxy from environment |
1431 | # initialise proxy from environment |
909 | eval { |
1432 | eval { |
910 | set_proxy $ENV{http_proxy}; |
1433 | set_proxy $ENV{http_proxy}; |
911 | }; |
1434 | }; |
912 | |
1435 | |
|
|
1436 | =head2 SHOWCASE |
|
|
1437 | |
|
|
1438 | This section contains some more elaborate "real-world" examples or code |
|
|
1439 | snippets. |
|
|
1440 | |
|
|
1441 | =head2 HTTP/1.1 FILE DOWNLOAD |
|
|
1442 | |
|
|
1443 | Downloading files with HTTP can be quite tricky, especially when something |
|
|
1444 | goes wrong and you want to resume. |
|
|
1445 | |
|
|
1446 | Here is a function that initiates and resumes a download. It uses the |
|
|
1447 | last modified time to check for file content changes, and works with many |
|
|
1448 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
|
|
1449 | on older servers. |
|
|
1450 | |
|
|
1451 | It calls the completion callback with either C<undef>, which means a |
|
|
1452 | nonretryable error occurred, C<0> when the download was partial and should |
|
|
1453 | be retried, and C<1> if it was successful. |
|
|
1454 | |
|
|
1455 | use AnyEvent::HTTP; |
|
|
1456 | |
|
|
1457 | sub download($$$) { |
|
|
1458 | my ($url, $file, $cb) = @_; |
|
|
1459 | |
|
|
1460 | open my $fh, "+<", $file |
|
|
1461 | or die "$file: $!"; |
|
|
1462 | |
|
|
1463 | my %hdr; |
|
|
1464 | my $ofs = 0; |
|
|
1465 | |
|
|
1466 | warn stat $fh; |
|
|
1467 | warn -s _; |
|
|
1468 | if (stat $fh and -s _) { |
|
|
1469 | $ofs = -s _; |
|
|
1470 | warn "-s is ", $ofs; |
|
|
1471 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
|
|
1472 | $hdr{"range"} = "bytes=$ofs-"; |
|
|
1473 | } |
|
|
1474 | |
|
|
1475 | http_get $url, |
|
|
1476 | headers => \%hdr, |
|
|
1477 | on_header => sub { |
|
|
1478 | my ($hdr) = @_; |
|
|
1479 | |
|
|
1480 | if ($hdr->{Status} == 200 && $ofs) { |
|
|
1481 | # resume failed |
|
|
1482 | truncate $fh, $ofs = 0; |
|
|
1483 | } |
|
|
1484 | |
|
|
1485 | sysseek $fh, $ofs, 0; |
|
|
1486 | |
|
|
1487 | 1 |
|
|
1488 | }, |
|
|
1489 | on_body => sub { |
|
|
1490 | my ($data, $hdr) = @_; |
|
|
1491 | |
|
|
1492 | if ($hdr->{Status} =~ /^2/) { |
|
|
1493 | length $data == syswrite $fh, $data |
|
|
1494 | or return; # abort on write errors |
|
|
1495 | } |
|
|
1496 | |
|
|
1497 | 1 |
|
|
1498 | }, |
|
|
1499 | sub { |
|
|
1500 | my (undef, $hdr) = @_; |
|
|
1501 | |
|
|
1502 | my $status = $hdr->{Status}; |
|
|
1503 | |
|
|
1504 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
|
|
1505 | utime $fh, $time, $time; |
|
|
1506 | } |
|
|
1507 | |
|
|
1508 | if ($status == 200 || $status == 206 || $status == 416) { |
|
|
1509 | # download ok || resume ok || file already fully downloaded |
|
|
1510 | $cb->(1, $hdr); |
|
|
1511 | |
|
|
1512 | } elsif ($status == 412) { |
|
|
1513 | # file has changed while resuming, delete and retry |
|
|
1514 | unlink $file; |
|
|
1515 | $cb->(0, $hdr); |
|
|
1516 | |
|
|
1517 | } elsif ($status == 500 or $status == 503 or $status =~ /^59/) { |
|
|
1518 | # retry later |
|
|
1519 | $cb->(0, $hdr); |
|
|
1520 | |
|
|
1521 | } else { |
|
|
1522 | $cb->(undef, $hdr); |
|
|
1523 | } |
|
|
1524 | } |
|
|
1525 | ; |
|
|
1526 | } |
|
|
1527 | |
|
|
1528 | download "http://server/somelargefile", "/tmp/somelargefile", sub { |
|
|
1529 | if ($_[0]) { |
|
|
1530 | print "OK!\n"; |
|
|
1531 | } elsif (defined $_[0]) { |
|
|
1532 | print "please retry later\n"; |
|
|
1533 | } else { |
|
|
1534 | print "ERROR\n"; |
|
|
1535 | } |
|
|
1536 | }; |
|
|
1537 | |
913 | =head2 SOCKS PROXIES |
1538 | =head3 SOCKS PROXIES |
914 | |
1539 | |
915 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
1540 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
916 | compile your perl to support socks, or use an external program such as |
1541 | compile your perl to support socks, or use an external program such as |
917 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
1542 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
918 | transparently. |
1543 | transparently. |