… | |
… | |
39 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
40 | |
40 | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Carp; |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
|
|
49 | use AnyEvent::Handle (); |
48 | use AnyEvent::Handle (); |
50 | |
49 | |
51 | use base Exporter::; |
50 | use base Exporter::; |
52 | |
51 | |
53 | our $VERSION = '1.03'; |
52 | our $VERSION = '1.5'; |
54 | |
53 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
55 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
57 | our $MAX_RECURSE = 10; |
59 | our $MAX_PERSISTENT = 8; |
58 | our $MAX_PERSISTENT = 8; |
60 | our $PERSISTENT_TIMEOUT = 2; |
59 | our $PERSISTENT_TIMEOUT = 2; |
61 | our $TIMEOUT = 300; |
60 | our $TIMEOUT = 300; |
62 | |
61 | |
63 | # changing these is evil |
62 | # changing these is evil |
64 | our $MAX_PERSISTENT_PER_HOST = 2; |
63 | our $MAX_PERSISTENT_PER_HOST = 0; |
65 | our $MAX_PER_HOST = 4; |
64 | our $MAX_PER_HOST = 4; |
66 | |
65 | |
67 | our $PROXY; |
66 | our $PROXY; |
68 | our $ACTIVE = 0; |
67 | our $ACTIVE = 0; |
69 | |
68 | |
… | |
… | |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
70 | my %CO_SLOT; # number of open connections, and wait queue, per host |
72 | |
71 | |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
72 | =item http_get $url, key => value..., $cb->($data, $headers) |
74 | |
73 | |
75 | Executes an HTTP-GET request. See the http_request function for details on |
74 | Executes an HTTP-GET request. See the http_request function for details on |
76 | additional parameters. |
75 | additional parameters and the return value. |
77 | |
76 | |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
77 | =item http_head $url, key => value..., $cb->($data, $headers) |
79 | |
78 | |
80 | Executes an HTTP-HEAD request. See the http_request function for details on |
79 | Executes an HTTP-HEAD request. See the http_request function for details |
81 | additional parameters. |
80 | on additional parameters and the return value. |
82 | |
81 | |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
82 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
84 | |
83 | |
85 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
84 | Executes an HTTP-POST request with a request body of C<$body>. See the |
86 | http_request function for details on additional parameters. |
85 | http_request function for details on additional parameters and the return |
|
|
86 | value. |
87 | |
87 | |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | |
89 | |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | must be an absolute http or https URL. |
91 | must be an absolute http or https URL. |
92 | |
92 | |
|
|
93 | When called in void context, nothing is returned. In other contexts, |
|
|
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
95 | object at least alive until the callback get called. If the object gets |
|
|
96 | destroyed before the callback is called, the request will be cancelled. |
|
|
97 | |
93 | The callback will be called with the response data as first argument |
98 | The callback will be called with the response body data as first argument |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
99 | (or C<undef> if an error occured), and a hash-ref with response headers |
95 | response headers as second argument. |
100 | (and trailers) as second argument. |
96 | |
101 | |
97 | All the headers in that hash are lowercased. In addition to the response |
102 | All the headers in that hash are lowercased. In addition to the response |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
103 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
|
|
104 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
105 | three parts of the HTTP Status-Line of the same name. If an error occurs |
|
|
106 | during the body phase of a request, then the original C<Status> and |
|
|
107 | C<Reason> values from the header are available as C<OrigStatus> and |
|
|
108 | C<OrigReason>. |
|
|
109 | |
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
110 | The pseudo-header C<URL> contains the actual URL (which can differ from |
101 | requested URL when following redirects). |
111 | the requested URL when following redirects - for example, you might get |
|
|
112 | an error that your URL scheme is not supported even though your URL is a |
|
|
113 | valid http URL because it redirected to an ftp URL, in which case you can |
|
|
114 | look at the URL pseudo header). |
102 | |
115 | |
|
|
116 | The pseudo-header C<Redirect> only exists when the request was a result |
|
|
117 | of an internal redirect. In that case it is an array reference with |
|
|
118 | the C<($data, $headers)> from the redirect response. Note that this |
|
|
119 | response could in turn be the result of a redirect itself, and C<< |
|
|
120 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
121 | response, and so on. |
|
|
122 | |
103 | If the server sends a header multiple lines, then their contents will be |
123 | If the server sends a header multiple times, then their contents will be |
104 | joined together with C<\x00>. |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
105 | |
125 | |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
107 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be |
108 | and the C<Reason> pseudo-header will contain an error message. |
128 | C<590>-C<599> and the C<Reason> pseudo-header will contain an error |
|
|
129 | message. Currently the following status codes are used: |
|
|
130 | |
|
|
131 | =over 4 |
|
|
132 | |
|
|
133 | =item 595 - errors during connection etsbalishment, proxy handshake. |
|
|
134 | |
|
|
135 | =item 596 - errors during TLS negotiation, request sending and header processing. |
|
|
136 | |
|
|
137 | =item 597 - errors during body receiving or processing. |
|
|
138 | |
|
|
139 | =item 598 - user aborted request via C<on_header> or C<on_body>. |
|
|
140 | |
|
|
141 | =item 599 - other, usually nonretryable, errors (garbled URL etc.). |
|
|
142 | |
|
|
143 | =back |
109 | |
144 | |
110 | A typical callback might look like this: |
145 | A typical callback might look like this: |
111 | |
146 | |
112 | sub { |
147 | sub { |
113 | my ($body, $hdr) = @_; |
148 | my ($body, $hdr) = @_; |
… | |
… | |
129 | Whether to recurse requests or not, e.g. on redirects, authentication |
164 | Whether to recurse requests or not, e.g. on redirects, authentication |
130 | retries and so on, and how often to do so. |
165 | retries and so on, and how often to do so. |
131 | |
166 | |
132 | =item headers => hashref |
167 | =item headers => hashref |
133 | |
168 | |
134 | 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 |
135 | 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 |
136 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
|
|
172 | (this can be suppressed by using C<undef> for these headers in which case |
|
|
173 | they won't be sent at all). |
137 | |
174 | |
138 | =item timeout => $seconds |
175 | =item timeout => $seconds |
139 | |
176 | |
140 | The time-out to use for various stages - each connect attempt will reset |
177 | The time-out to use for various stages - each connect attempt will reset |
141 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
178 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
179 | timeout. |
|
|
180 | |
|
|
181 | Default timeout is 5 minutes. |
142 | |
182 | |
143 | =item proxy => [$host, $port[, $scheme]] or undef |
183 | =item proxy => [$host, $port[, $scheme]] or undef |
144 | |
184 | |
145 | Use the given http proxy for all requests. If not specified, then the |
185 | Use the given http proxy for all requests. If not specified, then the |
146 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
186 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
147 | |
187 | |
148 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
188 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
149 | HTTPS. |
189 | HTTPS. |
150 | |
190 | |
151 | =item body => $string |
191 | =item body => $string |
152 | |
192 | |
153 | The request body, usually empty. Will be-sent as-is (future versions of |
193 | The request body, usually empty. Will be sent as-is (future versions of |
154 | this module might offer more options). |
194 | this module might offer more options). |
155 | |
195 | |
156 | =item cookie_jar => $hash_ref |
196 | =item cookie_jar => $hash_ref |
157 | |
197 | |
158 | Passing this parameter enables (simplified) cookie-processing, loosely |
198 | Passing this parameter enables (simplified) cookie-processing, loosely |
159 | based on the original netscape specification. |
199 | based on the original netscape specification. |
160 | |
200 | |
161 | The C<$hash_ref> must be an (initially empty) hash reference which will |
201 | The C<$hash_ref> must be an (initially empty) hash reference which |
162 | get updated automatically. It is possible to save the cookie_jar to |
202 | will get updated automatically. It is possible to save the cookie jar |
163 | persistent storage with something like JSON or Storable, but this is not |
203 | to persistent storage with something like JSON or Storable - see the |
164 | recommended, as expire times are currently being ignored. |
204 | C<AnyEvent::HTTP::cookie_jar_expire> function if you wish to remove |
|
|
205 | expired or session-only cookies, and also for documentation on the format |
|
|
206 | of the cookie jar. |
165 | |
207 | |
166 | Note that this cookie implementation is not of very high quality, nor |
208 | Note that this cookie implementation is not meant to be complete. If |
167 | meant to be complete. If you want complete cookie management you have to |
209 | you want complete cookie management you have to do that on your |
168 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
210 | own. C<cookie_jar> is meant as a quick fix to get most cookie-using sites |
169 | cookie-using sites working. Cookies are a privacy disaster, do not use |
211 | working. Cookies are a privacy disaster, do not use them unless required |
170 | them unless required to. |
212 | to. |
|
|
213 | |
|
|
214 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
215 | headers will be set and handled by this module, otherwise they will be |
|
|
216 | left untouched. |
|
|
217 | |
|
|
218 | =item tls_ctx => $scheme | $tls_ctx |
|
|
219 | |
|
|
220 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
221 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
222 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
223 | C<high> can be specified, which give you a predefined low-security (no |
|
|
224 | verification, highest compatibility) and high-security (CA and common-name |
|
|
225 | verification) TLS context. |
|
|
226 | |
|
|
227 | The default for this option is C<low>, which could be interpreted as "give |
|
|
228 | me the page, no matter what". |
|
|
229 | |
|
|
230 | =item on_prepare => $callback->($fh) |
|
|
231 | |
|
|
232 | In rare cases you need to "tune" the socket before it is used to |
|
|
233 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
234 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
235 | and behaves exactly the same way (e.g. it has to provide a |
|
|
236 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
237 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
238 | |
|
|
239 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
240 | |
|
|
241 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
242 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
243 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
244 | obviously, it has to follow the same calling conventions, except that it |
|
|
245 | may always return a connection guard object. |
|
|
246 | |
|
|
247 | There are probably lots of weird uses for this function, starting from |
|
|
248 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
249 | but fast) host => IP address caching or even socks protocol support. |
|
|
250 | |
|
|
251 | =item on_header => $callback->($headers) |
|
|
252 | |
|
|
253 | When specified, this callback will be called with the header hash as soon |
|
|
254 | as headers have been successfully received from the remote server (not on |
|
|
255 | locally-generated errors). |
|
|
256 | |
|
|
257 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
258 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
259 | the finish callback with an error code of C<598>). |
|
|
260 | |
|
|
261 | This callback is useful, among other things, to quickly reject unwanted |
|
|
262 | content, which, if it is supposed to be rare, can be faster than first |
|
|
263 | doing a C<HEAD> request. |
|
|
264 | |
|
|
265 | The downside is that cancelling the request makes it impossible to re-use |
|
|
266 | the connection. Also, the C<on_header> callback will not receive any |
|
|
267 | trailer (headers sent after the response body). |
|
|
268 | |
|
|
269 | Example: cancel the request unless the content-type is "text/html". |
|
|
270 | |
|
|
271 | on_header => sub { |
|
|
272 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
273 | }, |
|
|
274 | |
|
|
275 | =item on_body => $callback->($partial_body, $headers) |
|
|
276 | |
|
|
277 | When specified, all body data will be passed to this callback instead of |
|
|
278 | to the completion callback. The completion callback will get the empty |
|
|
279 | string instead of the body data. |
|
|
280 | |
|
|
281 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
282 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
283 | the completion callback with an error code of C<598>). |
|
|
284 | |
|
|
285 | The downside to cancelling the request is that it makes it impossible to |
|
|
286 | re-use the connection. |
|
|
287 | |
|
|
288 | This callback is useful when the data is too large to be held in memory |
|
|
289 | (so the callback writes it to a file) or when only some information should |
|
|
290 | be extracted, or when the body should be processed incrementally. |
|
|
291 | |
|
|
292 | It is usually preferred over doing your own body handling via |
|
|
293 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
294 | only used to create a connection, C<want_body_handle> is the better |
|
|
295 | alternative, as it allows you to install your own event handler, reducing |
|
|
296 | resource usage. |
|
|
297 | |
|
|
298 | =item want_body_handle => $enable |
|
|
299 | |
|
|
300 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
301 | changes considerably: after parsing the headers, and instead of |
|
|
302 | downloading the body (if any), the completion callback will be |
|
|
303 | called. Instead of the C<$body> argument containing the body data, the |
|
|
304 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
305 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
306 | (e.g. status C<304>), the empty string will be passed. |
|
|
307 | |
|
|
308 | The handle object might or might not be in TLS mode, might be connected to |
|
|
309 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
310 | ways. The user is responsible for this handle (it will not be used by this |
|
|
311 | module anymore). |
|
|
312 | |
|
|
313 | This is useful with some push-type services, where, after the initial |
|
|
314 | headers, an interactive protocol is used (typical example would be the |
|
|
315 | push-style twitter API which starts a JSON/XML stream). |
|
|
316 | |
|
|
317 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
318 | that doesn't solve your problem in a better way. |
171 | |
319 | |
172 | =back |
320 | =back |
173 | |
321 | |
174 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
322 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
323 | the response body. |
175 | |
324 | |
176 | http_request GET => "http://www.nethype.de/", sub { |
325 | http_request GET => "http://www.nethype.de/", sub { |
177 | my ($body, $hdr) = @_; |
326 | my ($body, $hdr) = @_; |
178 | print "$body\n"; |
327 | print "$body\n"; |
179 | }; |
328 | }; |
180 | |
329 | |
181 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
330 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
182 | timeout of 30 seconds. |
331 | timeout of 30 seconds. |
183 | |
332 | |
184 | http_request |
333 | http_request |
185 | GET => "https://www.google.com", |
334 | GET => "https://www.google.com", |
186 | timeout => 30, |
335 | timeout => 30, |
… | |
… | |
188 | my ($body, $hdr) = @_; |
337 | my ($body, $hdr) = @_; |
189 | use Data::Dumper; |
338 | use Data::Dumper; |
190 | print Dumper $hdr; |
339 | print Dumper $hdr; |
191 | } |
340 | } |
192 | ; |
341 | ; |
|
|
342 | |
|
|
343 | Example: do another simple HTTP GET request, but immediately try to |
|
|
344 | cancel it. |
|
|
345 | |
|
|
346 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
347 | my ($body, $hdr) = @_; |
|
|
348 | print "$body\n"; |
|
|
349 | }; |
|
|
350 | |
|
|
351 | undef $request; |
193 | |
352 | |
194 | =cut |
353 | =cut |
195 | |
354 | |
196 | sub _slot_schedule; |
355 | sub _slot_schedule; |
197 | sub _slot_schedule($) { |
356 | sub _slot_schedule($) { |
… | |
… | |
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
380 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
222 | |
381 | |
223 | _slot_schedule $_[0]; |
382 | _slot_schedule $_[0]; |
224 | } |
383 | } |
225 | |
384 | |
|
|
385 | ############################################################################# |
|
|
386 | |
|
|
387 | # expire cookies |
|
|
388 | sub cookie_jar_expire($;$) { |
|
|
389 | my ($jar, $session_end) = @_; |
|
|
390 | |
|
|
391 | %$jar = () if $jar->{version} != 1; |
|
|
392 | |
|
|
393 | my $anow = AE::now; |
|
|
394 | |
|
|
395 | while (my ($chost, $paths) = each %$jar) { |
|
|
396 | next unless ref $paths; |
|
|
397 | |
|
|
398 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
399 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
400 | if (exists $kv->{_expires}) { |
|
|
401 | delete $cookies->{$cookie} |
|
|
402 | if $anow > $kv->{_expires}; |
|
|
403 | } elsif ($session_end) { |
|
|
404 | delete $cookies->{$cookie}; |
|
|
405 | } |
|
|
406 | } |
|
|
407 | |
|
|
408 | delete $paths->{$cpath} |
|
|
409 | unless %$cookies; |
|
|
410 | } |
|
|
411 | |
|
|
412 | delete $jar->{$chost} |
|
|
413 | unless %$paths; |
|
|
414 | } |
|
|
415 | } |
|
|
416 | |
|
|
417 | # extract cookies from jar |
|
|
418 | sub cookie_jar_extract($$$$) { |
|
|
419 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
420 | |
|
|
421 | %$jar = () if $jar->{version} != 1; |
|
|
422 | |
|
|
423 | my @cookies; |
|
|
424 | |
|
|
425 | while (my ($chost, $paths) = each %$jar) { |
|
|
426 | next unless ref $paths; |
|
|
427 | |
|
|
428 | if ($chost =~ /^\./) { |
|
|
429 | next unless $chost eq substr $uhost, -length $chost; |
|
|
430 | } elsif ($chost =~ /\./) { |
|
|
431 | next unless $chost eq $uhost; |
|
|
432 | } else { |
|
|
433 | next; |
|
|
434 | } |
|
|
435 | |
|
|
436 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
437 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
438 | |
|
|
439 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
440 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
441 | |
|
|
442 | if (exists $kv->{_expires} and AE::now > $kv->{_expires}) { |
|
|
443 | delete $cookies->{$cookie}; |
|
|
444 | next; |
|
|
445 | } |
|
|
446 | |
|
|
447 | my $value = $kv->{value}; |
|
|
448 | |
|
|
449 | if ($value =~ /[=;,[:space:]]/) { |
|
|
450 | $value =~ s/([\\"])/\\$1/g; |
|
|
451 | $value = "\"$value\""; |
|
|
452 | } |
|
|
453 | |
|
|
454 | push @cookies, "$cookie=$value"; |
|
|
455 | } |
|
|
456 | } |
|
|
457 | } |
|
|
458 | |
|
|
459 | \@cookies |
|
|
460 | } |
|
|
461 | |
|
|
462 | # parse set_cookie header into jar |
|
|
463 | sub cookie_jar_set_cookie($$$$) { |
|
|
464 | my ($jar, $set_cookie, $uhost, $date) = @_; |
|
|
465 | |
|
|
466 | my $anow = int AE::now; |
|
|
467 | my $snow; # server-now |
|
|
468 | |
|
|
469 | for ($set_cookie) { |
|
|
470 | # parse NAME=VALUE |
|
|
471 | my @kv; |
|
|
472 | |
|
|
473 | # expires is not http-compliant in the original cookie-spec, |
|
|
474 | # we support the official date format and some extensions |
|
|
475 | while ( |
|
|
476 | m{ |
|
|
477 | \G\s* |
|
|
478 | (?: |
|
|
479 | expires \s*=\s* ([A-Z][a-z][a-z]+,\ [^,;]+) |
|
|
480 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
|
|
481 | ) |
|
|
482 | }gcxsi |
|
|
483 | ) { |
|
|
484 | my $name = $2; |
|
|
485 | my $value = $4; |
|
|
486 | |
|
|
487 | unless (defined $name) { |
|
|
488 | # expires |
|
|
489 | $name = "expires"; |
|
|
490 | $value = $1; |
|
|
491 | } elsif (!defined $value) { |
|
|
492 | # quoted |
|
|
493 | $value = $3; |
|
|
494 | $value =~ s/\\(.)/$1/gs; |
|
|
495 | } |
|
|
496 | |
|
|
497 | push @kv, lc $name, $value; |
|
|
498 | |
|
|
499 | last unless /\G\s*;/gc; |
|
|
500 | } |
|
|
501 | |
|
|
502 | last unless @kv; |
|
|
503 | |
|
|
504 | my $name = shift @kv; |
|
|
505 | my %kv = (value => shift @kv, @kv); |
|
|
506 | |
|
|
507 | if (exists $kv{"max-age"}) { |
|
|
508 | $kv{_expires} = $anow + delete $kv{"max-age"}; |
|
|
509 | } elsif (exists $kv{expires}) { |
|
|
510 | $snow ||= parse_date ($date) || $anow; |
|
|
511 | $kv{_expires} = $anow + (parse_date (delete $kv{expires}) - $snow); |
|
|
512 | } else { |
|
|
513 | delete $kv{_expires}; |
|
|
514 | } |
|
|
515 | |
|
|
516 | my $cdom; |
|
|
517 | my $cpath = (delete $kv{path}) || "/"; |
|
|
518 | |
|
|
519 | if (exists $kv{domain}) { |
|
|
520 | $cdom = delete $kv{domain}; |
|
|
521 | |
|
|
522 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
523 | |
|
|
524 | next if $cdom =~ /\.$/; |
|
|
525 | |
|
|
526 | # this is not rfc-like and not netscape-like. go figure. |
|
|
527 | my $ndots = $cdom =~ y/.//; |
|
|
528 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
529 | } else { |
|
|
530 | $cdom = $uhost; |
|
|
531 | } |
|
|
532 | |
|
|
533 | # store it |
|
|
534 | $jar->{version} = 1; |
|
|
535 | $jar->{$cdom}{$cpath}{$name} = \%kv; |
|
|
536 | |
|
|
537 | redo if /\G\s*,/gc; |
|
|
538 | } |
|
|
539 | } |
|
|
540 | |
|
|
541 | # continue to parse $_ for headers and place them into the arg |
|
|
542 | sub parse_hdr() { |
|
|
543 | my %hdr; |
|
|
544 | |
|
|
545 | # things seen, not parsed: |
|
|
546 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
547 | |
|
|
548 | $hdr{lc $1} .= ",$2" |
|
|
549 | while /\G |
|
|
550 | ([^:\000-\037]*): |
|
|
551 | [\011\040]* |
|
|
552 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
553 | \012 |
|
|
554 | /gxc; |
|
|
555 | |
|
|
556 | /\G$/ |
|
|
557 | or return; |
|
|
558 | |
|
|
559 | # remove the "," prefix we added to all headers above |
|
|
560 | substr $_, 0, 1, "" |
|
|
561 | for values %hdr; |
|
|
562 | |
|
|
563 | \%hdr |
|
|
564 | } |
|
|
565 | |
|
|
566 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
|
|
567 | |
|
|
568 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
569 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
570 | |
226 | sub http_request($$@) { |
571 | sub http_request($$@) { |
227 | my $cb = pop; |
572 | my $cb = pop; |
228 | my ($method, $url, %arg) = @_; |
573 | my ($method, $url, %arg) = @_; |
229 | |
574 | |
230 | my %hdr; |
575 | my %hdr; |
|
|
576 | |
|
|
577 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
578 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
231 | |
579 | |
232 | $method = uc $method; |
580 | $method = uc $method; |
233 | |
581 | |
234 | if (my $hdr = $arg{headers}) { |
582 | if (my $hdr = $arg{headers}) { |
235 | while (my ($k, $v) = each %$hdr) { |
583 | while (my ($k, $v) = each %$hdr) { |
236 | $hdr{lc $k} = $v; |
584 | $hdr{lc $k} = $v; |
237 | } |
585 | } |
238 | } |
586 | } |
239 | |
587 | |
|
|
588 | # pseudo headers for all subsequent responses |
|
|
589 | my @pseudo = (URL => $url); |
|
|
590 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
591 | |
240 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
592 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
241 | |
593 | |
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
594 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
243 | if $recurse < 0; |
595 | if $recurse < 0; |
244 | |
596 | |
245 | my $proxy = $arg{proxy} || $PROXY; |
597 | my $proxy = $arg{proxy} || $PROXY; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
598 | my $timeout = $arg{timeout} || $TIMEOUT; |
247 | |
599 | |
248 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
249 | |
|
|
250 | my ($scheme, $authority, $upath, $query, $fragment) = |
600 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
251 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
601 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
252 | |
602 | |
253 | $scheme = lc $scheme; |
603 | $uscheme = lc $uscheme; |
254 | |
604 | |
255 | my $uport = $scheme eq "http" ? 80 |
605 | my $uport = $uscheme eq "http" ? 80 |
256 | : $scheme eq "https" ? 443 |
606 | : $uscheme eq "https" ? 443 |
257 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
607 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
258 | |
608 | |
259 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
|
|
260 | |
|
|
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
609 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
610 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
263 | |
611 | |
264 | my $uhost = $1; |
612 | my $uhost = $1; |
265 | $uport = $2 if defined $2; |
613 | $uport = $2 if defined $2; |
266 | |
614 | |
|
|
615 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
616 | unless exists $hdr{host}; |
|
|
617 | |
267 | $uhost =~ s/^\[(.*)\]$/$1/; |
618 | $uhost =~ s/^\[(.*)\]$/$1/; |
268 | $upath .= "?$query" if length $query; |
619 | $upath .= $query if length $query; |
269 | |
620 | |
270 | $upath =~ s%^/?%/%; |
621 | $upath =~ s%^/?%/%; |
271 | |
622 | |
272 | # cookie processing |
623 | # cookie processing |
273 | if (my $jar = $arg{cookie_jar}) { |
624 | if (my $jar = $arg{cookie_jar}) { |
274 | %$jar = () if $jar->{version} < 1; |
625 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
275 | |
626 | |
276 | my @cookie; |
|
|
277 | |
|
|
278 | while (my ($chost, $v) = each %$jar) { |
|
|
279 | next unless $chost eq substr $uhost, -length $chost; |
|
|
280 | next unless $chost =~ /^\./; |
|
|
281 | |
|
|
282 | while (my ($cpath, $v) = each %$v) { |
|
|
283 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
284 | |
|
|
285 | while (my ($k, $v) = each %$v) { |
|
|
286 | next if $scheme ne "https" && exists $v->{secure}; |
|
|
287 | push @cookie, "$k=$v->{value}"; |
|
|
288 | } |
|
|
289 | } |
|
|
290 | } |
|
|
291 | |
|
|
292 | $hdr{cookie} = join "; ", @cookie |
627 | $hdr{cookie} = join "; ", @$cookies |
293 | if @cookie; |
628 | if @$cookies; |
294 | } |
629 | } |
295 | |
630 | |
296 | my ($rhost, $rport, $rpath); # request host, port, path |
631 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
297 | |
632 | |
298 | if ($proxy) { |
633 | if ($proxy) { |
299 | ($rhost, $rport, $scheme) = @$proxy; |
634 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
300 | $rpath = $url; |
635 | |
|
|
636 | $rscheme = "http" unless defined $rscheme; |
|
|
637 | |
|
|
638 | # don't support https requests over https-proxy transport, |
|
|
639 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
640 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
301 | } else { |
641 | } else { |
302 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
642 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
303 | $hdr{host} = $uhost; |
|
|
304 | } |
643 | } |
305 | |
644 | |
|
|
645 | # leave out fragment and query string, just a heuristic |
|
|
646 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
647 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
|
|
648 | |
306 | $hdr{"content-length"} = length $arg{body}; |
649 | $hdr{"content-length"} = length $arg{body} |
|
|
650 | if length $arg{body} || $method ne "GET"; |
|
|
651 | |
|
|
652 | $hdr{connection} = "close TE"; #1.1 |
|
|
653 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
307 | |
654 | |
308 | my %state = (connect_guard => 1); |
655 | my %state = (connect_guard => 1); |
309 | |
656 | |
310 | _get_slot $uhost, sub { |
657 | _get_slot $uhost, sub { |
311 | $state{slot_guard} = shift; |
658 | $state{slot_guard} = shift; |
312 | |
659 | |
313 | return unless $state{connect_guard}; |
660 | return unless $state{connect_guard}; |
314 | |
661 | |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
662 | my $ae_error = 595; # connecting |
|
|
663 | |
|
|
664 | my $connect_cb = sub { |
316 | $state{fh} = shift |
665 | $state{fh} = shift |
|
|
666 | or do { |
|
|
667 | my $err = "$!"; |
|
|
668 | %state = (); |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
669 | return $cb->(undef, { @pseudo, Status => $ae_error, Reason => $err }); |
|
|
670 | }; |
318 | |
671 | |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
672 | return unless delete $state{connect_guard}; |
320 | |
673 | |
321 | # get handle |
674 | # get handle |
322 | $state{handle} = new AnyEvent::Handle |
675 | $state{handle} = new AnyEvent::Handle |
323 | fh => $state{fh}, |
676 | fh => $state{fh}, |
324 | ($scheme eq "https" ? (tls => "connect") : ()); |
677 | peername => $rhost, |
|
|
678 | tls_ctx => $arg{tls_ctx}, |
|
|
679 | # these need to be reconfigured on keepalive handles |
|
|
680 | timeout => $timeout, |
|
|
681 | on_error => sub { |
|
|
682 | %state = (); |
|
|
683 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => $_[2] }); |
|
|
684 | }, |
|
|
685 | on_eof => sub { |
|
|
686 | %state = (); |
|
|
687 | $cb->(undef, { @pseudo, Status => $ae_error, Reason => "Unexpected end-of-file" }); |
|
|
688 | }, |
|
|
689 | ; |
325 | |
690 | |
326 | # limit the number of persistent connections |
691 | # limit the number of persistent connections |
|
|
692 | # keepalive not yet supported |
327 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
693 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
328 | ++$KA_COUNT{$_[1]}; |
694 | # ++$KA_COUNT{$_[1]}; |
329 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
695 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
696 | # --$KA_COUNT{$_[1]} |
|
|
697 | # }; |
330 | $hdr{connection} = "keep-alive"; |
698 | # $hdr{connection} = "keep-alive"; |
331 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
332 | } else { |
|
|
333 | delete $hdr{connection}; |
|
|
334 | } |
699 | # } |
335 | |
700 | |
336 | # (re-)configure handle |
701 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
337 | $state{handle}->timeout ($timeout); |
|
|
338 | $state{handle}->on_error (sub { |
|
|
339 | my $errno = "$!"; |
|
|
340 | %state = (); |
|
|
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
|
|
342 | }); |
|
|
343 | $state{handle}->on_eof (sub { |
|
|
344 | %state = (); |
|
|
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
|
|
346 | }); |
|
|
347 | |
702 | |
|
|
703 | # handle actual, non-tunneled, request |
|
|
704 | my $handle_actual_request = sub { |
|
|
705 | $ae_error = 596; # request phase |
|
|
706 | |
|
|
707 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
708 | |
348 | # send request |
709 | # send request |
349 | $state{handle}->push_write ( |
710 | $state{handle}->push_write ( |
350 | "$method $rpath HTTP/1.0\015\012" |
711 | "$method $rpath HTTP/1.1\015\012" |
351 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
712 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
352 | . "\015\012" |
713 | . "\015\012" |
353 | . (delete $arg{body}) |
714 | . (delete $arg{body}) |
354 | ); |
|
|
355 | |
|
|
356 | %hdr = (); # reduce memory usage, save a kitten |
|
|
357 | |
|
|
358 | # status line |
|
|
359 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
360 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
361 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
|
|
362 | |
|
|
363 | my %hdr = ( # response headers |
|
|
364 | HTTPVersion => "\x00$1", |
|
|
365 | Status => "\x00$2", |
|
|
366 | Reason => "\x00$3", |
|
|
367 | URL => "\x00$url" |
|
|
368 | ); |
715 | ); |
369 | |
716 | |
370 | # headers, could be optimized a bit |
717 | # return if error occured during push_write() |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
718 | return unless %state; |
|
|
719 | |
|
|
720 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
|
|
721 | |
|
|
722 | # status line and headers |
|
|
723 | $state{read_response} = sub { |
372 | for ("$_[1]\012") { |
724 | for ("$_[1]") { |
373 | # we support spaces in field names, as lotus domino |
725 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
374 | # creates them. |
|
|
375 | $hdr{lc $1} .= "\x00$2" |
|
|
376 | while /\G |
|
|
377 | ([^:\000-\037]+): |
|
|
378 | [\011\040]* |
|
|
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
|
|
380 | \015?\012 |
|
|
381 | /gxc; |
|
|
382 | |
726 | |
|
|
727 | /^HTTP\/0*([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/gxci |
|
|
728 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
|
|
729 | |
|
|
730 | # 100 Continue handling |
|
|
731 | # should not happen as we don't send expect: 100-continue, |
|
|
732 | # but we handle it just in case. |
|
|
733 | # since we send the request body regardless, if we get an error |
|
|
734 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
735 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
736 | if $2 eq 100; |
|
|
737 | |
|
|
738 | push @pseudo, |
|
|
739 | HTTPVersion => $1, |
|
|
740 | Status => $2, |
|
|
741 | Reason => $3, |
383 | /\G$/ |
742 | ; |
|
|
743 | |
|
|
744 | my $hdr = parse_hdr |
384 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
745 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
746 | |
|
|
747 | %hdr = (%$hdr, @pseudo); |
385 | } |
748 | } |
386 | |
749 | |
387 | substr $_, 0, 1, "" |
750 | # redirect handling |
388 | for values %hdr; |
751 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
752 | # try to support some common forms of broken Location headers. |
|
|
753 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
754 | $hdr{location} =~ s/^\.\/+//; |
389 | |
755 | |
390 | my $finish = sub { |
756 | my $url = "$rscheme://$uhost:$uport"; |
|
|
757 | |
|
|
758 | unless ($hdr{location} =~ s/^\///) { |
|
|
759 | $url .= $upath; |
|
|
760 | $url =~ s/\/[^\/]*$//; |
|
|
761 | } |
|
|
762 | |
|
|
763 | $hdr{location} = "$url/$hdr{location}"; |
|
|
764 | } |
|
|
765 | |
|
|
766 | my $redirect; |
|
|
767 | |
|
|
768 | if ($recurse) { |
|
|
769 | my $status = $hdr{Status}; |
|
|
770 | |
|
|
771 | # industry standard is to redirect POST as GET for |
|
|
772 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
|
|
773 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
774 | # industry standard seems to be to simply follow. |
|
|
775 | # we go with the industry standard. |
|
|
776 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
777 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
778 | $method = "GET" unless $method eq "HEAD"; |
|
|
779 | $redirect = 1; |
|
|
780 | } elsif ($status == 307) { |
|
|
781 | $redirect = 1; |
|
|
782 | } |
|
|
783 | } |
|
|
784 | |
|
|
785 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
786 | my $may_keep_alive = $_[3]; |
|
|
787 | |
|
|
788 | $state{handle}->destroy if $state{handle}; |
391 | %state = (); |
789 | %state = (); |
392 | |
790 | |
|
|
791 | if (defined $_[1]) { |
|
|
792 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
793 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
794 | } |
|
|
795 | |
393 | # set-cookie processing |
796 | # set-cookie processing |
394 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
797 | if ($arg{cookie_jar}) { |
395 | for (split /\x00/, $hdr{"set-cookie"}) { |
798 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost, $hdr{date}; |
396 | my ($cookie, @arg) = split /;\s*/; |
799 | } |
397 | my ($name, $value) = split /=/, $cookie, 2; |
|
|
398 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
|
|
399 | |
|
|
400 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
401 | my $cpath = (delete $kv{path}) || "/"; |
|
|
402 | |
|
|
403 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
|
|
404 | |
800 | |
405 | next if $cdom =~ /\.$/; |
801 | if ($redirect && exists $hdr{location}) { |
406 | |
802 | # we ignore any errors, as it is very common to receive |
407 | # this is not rfc-like and not netscape-like. go figure. |
803 | # Content-Length != 0 but no actual body |
408 | my $ndots = $cdom =~ y/.//; |
804 | # we also access %hdr, as $_[1] might be an erro |
409 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
805 | http_request ( |
410 | |
806 | $method => $hdr{location}, |
|
|
807 | %arg, |
|
|
808 | recurse => $recurse - 1, |
|
|
809 | Redirect => [$_[0], \%hdr], |
|
|
810 | $cb); |
|
|
811 | } else { |
|
|
812 | $cb->($_[0], \%hdr); |
|
|
813 | } |
|
|
814 | }; |
|
|
815 | |
|
|
816 | $ae_error = 597; # body phase |
|
|
817 | |
|
|
818 | my $len = $hdr{"content-length"}; |
|
|
819 | |
|
|
820 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
821 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
822 | } elsif ( |
|
|
823 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
824 | or $method eq "HEAD" |
|
|
825 | or (defined $len && !$len) |
|
|
826 | ) { |
|
|
827 | # no body |
|
|
828 | $finish->("", undef, undef, 1); |
|
|
829 | } else { |
|
|
830 | # body handling, many different code paths |
|
|
831 | # - no body expected |
|
|
832 | # - want_body_handle |
|
|
833 | # - te chunked |
|
|
834 | # - 2x length known (with or without on_body) |
|
|
835 | # - 2x length not known (with or without on_body) |
|
|
836 | if (!$redirect && $arg{want_body_handle}) { |
|
|
837 | $_[0]->on_eof (undef); |
|
|
838 | $_[0]->on_error (undef); |
|
|
839 | $_[0]->on_read (undef); |
|
|
840 | |
|
|
841 | $finish->(delete $state{handle}); |
|
|
842 | |
|
|
843 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
844 | my $cl = 0; |
|
|
845 | my $body = undef; |
|
|
846 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
847 | |
|
|
848 | $state{read_chunk} = sub { |
|
|
849 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
850 | or $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
851 | |
|
|
852 | my $len = hex $1; |
|
|
853 | |
|
|
854 | if ($len) { |
|
|
855 | $cl += $len; |
|
|
856 | |
|
|
857 | $_[0]->push_read (chunk => $len, sub { |
|
|
858 | $on_body->($_[1], \%hdr) |
|
|
859 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
860 | |
|
|
861 | $_[0]->push_read (line => sub { |
|
|
862 | length $_[1] |
|
|
863 | and return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
|
|
864 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
865 | }); |
|
|
866 | }); |
411 | # store it |
867 | } else { |
412 | $arg{cookie_jar}{version} = 1; |
868 | $hdr{"content-length"} ||= $cl; |
413 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
869 | |
|
|
870 | $_[0]->push_read (line => $qr_nlnl, sub { |
|
|
871 | if (length $_[1]) { |
|
|
872 | for ("$_[1]") { |
|
|
873 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
874 | |
|
|
875 | my $hdr = parse_hdr |
|
|
876 | or return $finish->(undef, $ae_error => "Garbled response trailers"); |
|
|
877 | |
|
|
878 | %hdr = (%hdr, %$hdr); |
|
|
879 | } |
|
|
880 | } |
|
|
881 | |
|
|
882 | $finish->($body, undef, undef, 1); |
|
|
883 | }); |
|
|
884 | } |
|
|
885 | }; |
|
|
886 | |
|
|
887 | $_[0]->push_read (line => $state{read_chunk}); |
|
|
888 | |
|
|
889 | } elsif ($arg{on_body}) { |
|
|
890 | if ($len) { |
|
|
891 | $_[0]->on_read (sub { |
|
|
892 | $len -= length $_[0]{rbuf}; |
|
|
893 | |
|
|
894 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
895 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
896 | |
|
|
897 | $len > 0 |
|
|
898 | or $finish->("", undef, undef, 1); |
|
|
899 | }); |
|
|
900 | } else { |
|
|
901 | $_[0]->on_eof (sub { |
|
|
902 | $finish->(""); |
|
|
903 | }); |
|
|
904 | $_[0]->on_read (sub { |
|
|
905 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
906 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
907 | }); |
|
|
908 | } |
|
|
909 | } else { |
|
|
910 | $_[0]->on_eof (undef); |
|
|
911 | |
|
|
912 | if ($len) { |
|
|
913 | $_[0]->on_read (sub { |
|
|
914 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
915 | if $len <= length $_[0]{rbuf}; |
|
|
916 | }); |
|
|
917 | } else { |
|
|
918 | $_[0]->on_error (sub { |
|
|
919 | ($! == Errno::EPIPE || !$!) |
|
|
920 | ? $finish->(delete $_[0]{rbuf}) |
|
|
921 | : $finish->(undef, $ae_error => $_[2]); |
|
|
922 | }); |
|
|
923 | $_[0]->on_read (sub { }); |
414 | } |
924 | } |
415 | } |
925 | } |
416 | |
|
|
417 | # microsoft and other assholes don't give a shit for following standards, |
|
|
418 | # try to support a common form of broken Location header. |
|
|
419 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/% |
|
|
420 | if exists $_[1]{location}; |
|
|
421 | |
|
|
422 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
423 | # apparently, mozilla et al. just change POST to GET here |
|
|
424 | # more research is needed before we do the same |
|
|
425 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
426 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
427 | # even http/1.1 is unlear on how to mutate the method |
|
|
428 | $method = "GET" unless $method eq "HEAD"; |
|
|
429 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
430 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
431 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
432 | } else { |
|
|
433 | $cb->($_[0], $_[1]); |
|
|
434 | } |
|
|
435 | }; |
926 | } |
|
|
927 | }; |
436 | |
928 | |
437 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
929 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
438 | $finish->(undef, \%hdr); |
930 | }; |
|
|
931 | |
|
|
932 | # now handle proxy-CONNECT method |
|
|
933 | if ($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->(); |
439 | } else { |
945 | } else { |
440 | if (exists $hdr{"content-length"}) { |
946 | %state = (); |
441 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
947 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
442 | # could cache persistent connection now |
|
|
443 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
444 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
445 | }; |
|
|
446 | |
|
|
447 | $finish->($_[1], \%hdr); |
|
|
448 | }); |
|
|
449 | } else { |
|
|
450 | # too bad, need to read until we get an error or EOF, |
|
|
451 | # no way to detect winged data. |
|
|
452 | $_[0]->on_error (sub { |
|
|
453 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
454 | }); |
|
|
455 | $_[0]->on_eof (undef); |
|
|
456 | $_[0]->on_read (sub { }); |
|
|
457 | } |
|
|
458 | } |
948 | } |
459 | }); |
949 | }); |
|
|
950 | } else { |
|
|
951 | $handle_actual_request->(); |
460 | }); |
952 | } |
461 | }, sub { |
|
|
462 | $timeout |
|
|
463 | }; |
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 { $timeout }); |
|
|
959 | |
464 | }; |
960 | }; |
465 | |
961 | |
466 | defined wantarray && AnyEvent::Util::guard { %state = () } |
962 | defined wantarray && AnyEvent::Util::guard { %state = () } |
467 | } |
963 | } |
468 | |
964 | |
… | |
… | |
482 | &http_request |
978 | &http_request |
483 | } |
979 | } |
484 | |
980 | |
485 | =back |
981 | =back |
486 | |
982 | |
|
|
983 | =head2 DNS CACHING |
|
|
984 | |
|
|
985 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
986 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
987 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
988 | on its own. If you want DNS caching, you currently have to provide |
|
|
989 | your own default resolver (by storing a suitable resolver object in |
|
|
990 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
991 | |
487 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
992 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
488 | |
993 | |
489 | =over 4 |
994 | =over 4 |
490 | |
995 | |
491 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
996 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
492 | |
997 | |
493 | Sets the default proxy server to use. The proxy-url must begin with a |
998 | Sets the default proxy server to use. The proxy-url must begin with a |
494 | string of the form C<http://host:port> (optionally C<https:...>). |
999 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
1000 | otherwise. |
|
|
1001 | |
|
|
1002 | To clear an already-set proxy, use C<undef>. |
|
|
1003 | |
|
|
1004 | =item AnyEvent::HTTP::cookie_jar_expire $jar[, $session_end] |
|
|
1005 | |
|
|
1006 | Remove all cookies from the cookie jar that have been expired. If |
|
|
1007 | C<$session_end> is given and true, then additionally remove all session |
|
|
1008 | cookies. |
|
|
1009 | |
|
|
1010 | You should call this function (with a true C<$session_end>) before you |
|
|
1011 | save cookies to disk, and you should call this function after loading them |
|
|
1012 | again. If you have a long-running program you can additonally call this |
|
|
1013 | function from time to time. |
|
|
1014 | |
|
|
1015 | A cookie jar is initially an empty hash-reference that is managed by this |
|
|
1016 | module. It's format is subject to change, but currently it is like this: |
|
|
1017 | |
|
|
1018 | The key C<version> has to contain C<1>, otherwise the hash gets |
|
|
1019 | emptied. All other keys are hostnames or IP addresses pointing to |
|
|
1020 | hash-references. The key for these inner hash references is the |
|
|
1021 | server path for which this cookie is meant, and the values are again |
|
|
1022 | hash-references. The keys of those hash-references is the cookie name, and |
|
|
1023 | the value, you guessed it, is another hash-reference, this time with the |
|
|
1024 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
|
|
1025 | which have been replaced by a C<_expires> key that contains the cookie |
|
|
1026 | expiry timestamp. |
|
|
1027 | |
|
|
1028 | Here is an example of a cookie jar with a single cookie, so you have a |
|
|
1029 | chance of understanding the above paragraph: |
|
|
1030 | |
|
|
1031 | { |
|
|
1032 | version => 1, |
|
|
1033 | "10.0.0.1" => { |
|
|
1034 | "/" => { |
|
|
1035 | "mythweb_id" => { |
|
|
1036 | _expires => 1293917923, |
|
|
1037 | value => "ooRung9dThee3ooyXooM1Ohm", |
|
|
1038 | }, |
|
|
1039 | }, |
|
|
1040 | }, |
|
|
1041 | } |
|
|
1042 | |
|
|
1043 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
1044 | |
|
|
1045 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
1046 | Date (RFC 2616). |
|
|
1047 | |
|
|
1048 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
1049 | |
|
|
1050 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) or a |
|
|
1051 | bunch of minor variations of those, and returns the corresponding POSIX |
|
|
1052 | timestamp, or C<undef> if the date cannot be parsed. |
495 | |
1053 | |
496 | =item $AnyEvent::HTTP::MAX_RECURSE |
1054 | =item $AnyEvent::HTTP::MAX_RECURSE |
497 | |
1055 | |
498 | The default value for the C<recurse> request parameter (default: C<10>). |
1056 | The default value for the C<recurse> request parameter (default: C<10>). |
499 | |
1057 | |
500 | =item $AnyEvent::HTTP::USERAGENT |
1058 | =item $AnyEvent::HTTP::USERAGENT |
501 | |
1059 | |
502 | The default value for the C<User-Agent> header (the default is |
1060 | The default value for the C<User-Agent> header (the default is |
503 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1061 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
504 | |
1062 | |
505 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
1063 | =item $AnyEvent::HTTP::MAX_PER_HOST |
506 | |
1064 | |
507 | The maximum number of persistent connections to keep open (default: 8). |
1065 | The maximum number of concurrent connections to the same host (identified |
|
|
1066 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
1067 | are queued until previous connections are closed. |
508 | |
1068 | |
509 | Not implemented currently. |
1069 | The default value for this is C<4>, and it is highly advisable to not |
510 | |
1070 | increase it. |
511 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
512 | |
|
|
513 | The maximum time to cache a persistent connection, in seconds (default: 2). |
|
|
514 | |
|
|
515 | Not implemented currently. |
|
|
516 | |
1071 | |
517 | =item $AnyEvent::HTTP::ACTIVE |
1072 | =item $AnyEvent::HTTP::ACTIVE |
518 | |
1073 | |
519 | The number of active connections. This is not the number of currently |
1074 | The number of active connections. This is not the number of currently |
520 | running requests, but the number of currently open and non-idle TCP |
1075 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
522 | |
1077 | |
523 | =back |
1078 | =back |
524 | |
1079 | |
525 | =cut |
1080 | =cut |
526 | |
1081 | |
|
|
1082 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
1083 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
1084 | |
|
|
1085 | sub format_date($) { |
|
|
1086 | my ($time) = @_; |
|
|
1087 | |
|
|
1088 | # RFC 822/1123 format |
|
|
1089 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
1090 | |
|
|
1091 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
1092 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
1093 | $H, $M, $S; |
|
|
1094 | } |
|
|
1095 | |
|
|
1096 | sub parse_date($) { |
|
|
1097 | my ($date) = @_; |
|
|
1098 | |
|
|
1099 | my ($d, $m, $y, $H, $M, $S); |
|
|
1100 | |
|
|
1101 | if ($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$/) { |
|
|
1102 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1103 | # cookie dates (with "-") |
|
|
1104 | |
|
|
1105 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
1106 | |
|
|
1107 | } elsif ($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$/) { |
|
|
1108 | # RFC 850 |
|
|
1109 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
1110 | |
|
|
1111 | } elsif ($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])$/) { |
|
|
1112 | # ISO C's asctime |
|
|
1113 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
1114 | } |
|
|
1115 | # other formats fail in the loop below |
|
|
1116 | |
|
|
1117 | for (0..11) { |
|
|
1118 | if ($m eq $month[$_]) { |
|
|
1119 | require Time::Local; |
|
|
1120 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
1121 | } |
|
|
1122 | } |
|
|
1123 | |
|
|
1124 | undef |
|
|
1125 | } |
|
|
1126 | |
527 | sub set_proxy($) { |
1127 | sub set_proxy($) { |
|
|
1128 | if (length $_[0]) { |
528 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
1129 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
1130 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
1131 | $PROXY = [$2, $3 || 3128, $1] |
|
|
1132 | } else { |
|
|
1133 | undef $PROXY; |
|
|
1134 | } |
529 | } |
1135 | } |
530 | |
1136 | |
531 | # initialise proxy from environment |
1137 | # initialise proxy from environment |
|
|
1138 | eval { |
532 | set_proxy $ENV{http_proxy}; |
1139 | set_proxy $ENV{http_proxy}; |
|
|
1140 | }; |
|
|
1141 | |
|
|
1142 | =head2 SOCKS PROXIES |
|
|
1143 | |
|
|
1144 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
1145 | compile your perl to support socks, or use an external program such as |
|
|
1146 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
1147 | transparently. |
|
|
1148 | |
|
|
1149 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
1150 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
1151 | that works with socks4a proxies: |
|
|
1152 | |
|
|
1153 | use Errno; |
|
|
1154 | use AnyEvent::Util; |
|
|
1155 | use AnyEvent::Socket; |
|
|
1156 | use AnyEvent::Handle; |
|
|
1157 | |
|
|
1158 | # host, port and username of/for your socks4a proxy |
|
|
1159 | my $socks_host = "10.0.0.23"; |
|
|
1160 | my $socks_port = 9050; |
|
|
1161 | my $socks_user = ""; |
|
|
1162 | |
|
|
1163 | sub socks4a_connect { |
|
|
1164 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
1165 | |
|
|
1166 | my $hdl = new AnyEvent::Handle |
|
|
1167 | connect => [$socks_host, $socks_port], |
|
|
1168 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
1169 | on_error => sub { $connect_cb->() }, |
|
|
1170 | ; |
|
|
1171 | |
|
|
1172 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1173 | |
|
|
1174 | $hdl->push_read (chunk => 8, sub { |
|
|
1175 | my ($hdl, $chunk) = @_; |
|
|
1176 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1177 | |
|
|
1178 | if ($status == 0x5a) { |
|
|
1179 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1180 | } else { |
|
|
1181 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1182 | } |
|
|
1183 | }); |
|
|
1184 | |
|
|
1185 | $hdl |
|
|
1186 | } |
|
|
1187 | |
|
|
1188 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1189 | possibly after switching off other proxy types: |
|
|
1190 | |
|
|
1191 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1192 | |
|
|
1193 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1194 | my ($data, $headers) = @_; |
|
|
1195 | ... |
|
|
1196 | }; |
533 | |
1197 | |
534 | =head1 SEE ALSO |
1198 | =head1 SEE ALSO |
535 | |
1199 | |
536 | L<AnyEvent>. |
1200 | L<AnyEvent>. |
537 | |
1201 | |
538 | =head1 AUTHOR |
1202 | =head1 AUTHOR |
539 | |
1203 | |
540 | Marc Lehmann <schmorp@schmorp.de> |
1204 | Marc Lehmann <schmorp@schmorp.de> |
541 | http://home.schmorp.de/ |
1205 | http://home.schmorp.de/ |
542 | |
1206 | |
|
|
1207 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
1208 | testcases and bugreports. |
|
|
1209 | |
543 | =cut |
1210 | =cut |
544 | |
1211 | |
545 | 1 |
1212 | 1 |
546 | |
1213 | |