… | |
… | |
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 = '1.05'; |
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 | |
… | |
… | |
92 | must be an absolute http or https URL. |
91 | must be an absolute http or https URL. |
93 | |
92 | |
94 | When called in void context, nothing is returned. In other contexts, |
93 | When called in void context, nothing is returned. In other contexts, |
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
94 | C<http_request> returns a "cancellation guard" - you have to keep the |
96 | object at least alive until the callback get called. If the object gets |
95 | object at least alive until the callback get called. If the object gets |
97 | destroyed before the callbakc is called, the request will be cancelled. |
96 | destroyed before the callback is called, the request will be cancelled. |
98 | |
97 | |
99 | 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 |
100 | (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 |
101 | response headers as second argument. |
100 | (and trailers) as second argument. |
102 | |
101 | |
103 | 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 |
104 | 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 |
105 | 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 | |
106 | 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 |
107 | 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). |
108 | |
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 | $headers->{Redirect}[1]{Redirect} >> will then contain the original |
|
|
121 | response, and so on. |
|
|
122 | |
109 | If the server sends a header multiple lines, then their contents will be |
123 | If the server sends a header multiple times, then their contents will be |
110 | joined together with a command (C<,>). |
124 | joined together with a comma (C<,>), as per the HTTP spec. |
111 | |
125 | |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
126 | If an internal error occurs, such as not being able to resolve a hostname, |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
127 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
114 | and the C<Reason> pseudo-header will contain an error message. |
128 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
|
|
129 | message. |
115 | |
130 | |
116 | A typical callback might look like this: |
131 | A typical callback might look like this: |
117 | |
132 | |
118 | sub { |
133 | sub { |
119 | my ($body, $hdr) = @_; |
134 | my ($body, $hdr) = @_; |
… | |
… | |
135 | Whether to recurse requests or not, e.g. on redirects, authentication |
150 | Whether to recurse requests or not, e.g. on redirects, authentication |
136 | retries and so on, and how often to do so. |
151 | retries and so on, and how often to do so. |
137 | |
152 | |
138 | =item headers => hashref |
153 | =item headers => hashref |
139 | |
154 | |
140 | The request headers to use. Currently, C<http_request> may provide its |
155 | The request headers to use. Currently, C<http_request> may provide its own |
141 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
156 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
142 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
157 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
|
|
158 | (this can be suppressed by using C<undef> for these headers in which case |
|
|
159 | they won't be sent at all). |
143 | |
160 | |
144 | =item timeout => $seconds |
161 | =item timeout => $seconds |
145 | |
162 | |
146 | The time-out to use for various stages - each connect attempt will reset |
163 | The time-out to use for various stages - each connect attempt will reset |
147 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
164 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
165 | timeout. |
|
|
166 | |
|
|
167 | Default timeout is 5 minutes. |
148 | |
168 | |
149 | =item proxy => [$host, $port[, $scheme]] or undef |
169 | =item proxy => [$host, $port[, $scheme]] or undef |
150 | |
170 | |
151 | Use the given http proxy for all requests. If not specified, then the |
171 | Use the given http proxy for all requests. If not specified, then the |
152 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
172 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
153 | |
173 | |
154 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
174 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
155 | HTTPS. |
175 | HTTPS. |
156 | |
176 | |
157 | =item body => $string |
177 | =item body => $string |
158 | |
178 | |
159 | The request body, usually empty. Will be-sent as-is (future versions of |
179 | The request body, usually empty. Will be sent as-is (future versions of |
160 | this module might offer more options). |
180 | this module might offer more options). |
161 | |
181 | |
162 | =item cookie_jar => $hash_ref |
182 | =item cookie_jar => $hash_ref |
163 | |
183 | |
164 | Passing this parameter enables (simplified) cookie-processing, loosely |
184 | Passing this parameter enables (simplified) cookie-processing, loosely |
165 | based on the original netscape specification. |
185 | based on the original netscape specification. |
166 | |
186 | |
167 | The C<$hash_ref> must be an (initially empty) hash reference which will |
187 | The C<$hash_ref> must be an (initially empty) hash reference which will |
168 | get updated automatically. It is possible to save the cookie_jar to |
188 | get updated automatically. It is possible to save the cookie jar to |
169 | persistent storage with something like JSON or Storable, but this is not |
189 | persistent storage with something like JSON or Storable, but this is not |
170 | recommended, as expire times are currently being ignored. |
190 | recommended, as session-only cookies might survive longer than expected. |
171 | |
191 | |
172 | Note that this cookie implementation is not of very high quality, nor |
192 | Note that this cookie implementation is not meant to be complete. If |
173 | meant to be complete. If you want complete cookie management you have to |
193 | you want complete cookie management you have to do that on your |
174 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
194 | own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites |
175 | cookie-using sites working. Cookies are a privacy disaster, do not use |
195 | working. Cookies are a privacy disaster, do not use them unless required |
176 | them unless required to. |
196 | to. |
|
|
197 | |
|
|
198 | When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:> |
|
|
199 | headers will be set and handled by this module, otherwise they will be |
|
|
200 | left untouched. |
|
|
201 | |
|
|
202 | =item tls_ctx => $scheme | $tls_ctx |
|
|
203 | |
|
|
204 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
205 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
206 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
207 | C<high> can be specified, which give you a predefined low-security (no |
|
|
208 | verification, highest compatibility) and high-security (CA and common-name |
|
|
209 | verification) TLS context. |
|
|
210 | |
|
|
211 | The default for this option is C<low>, which could be interpreted as "give |
|
|
212 | me the page, no matter what". |
|
|
213 | |
|
|
214 | =item on_prepare => $callback->($fh) |
|
|
215 | |
|
|
216 | In rare cases you need to "tune" the socket before it is used to |
|
|
217 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
218 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
219 | and behaves exactly the same way (e.g. it has to provide a |
|
|
220 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
221 | C<AnyEvent::Socket::tcp_connect> for details. |
|
|
222 | |
|
|
223 | =item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb) |
|
|
224 | |
|
|
225 | In even rarer cases you want total control over how AnyEvent::HTTP |
|
|
226 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
|
|
227 | to do this, but you can provide your own C<tcp_connect> function - |
|
|
228 | obviously, it has to follow the same calling conventions, except that it |
|
|
229 | may always return a connection guard object. |
|
|
230 | |
|
|
231 | There are probably lots of weird uses for this function, starting from |
|
|
232 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
|
|
233 | but fast) host => IP address caching or even socks protocol support. |
|
|
234 | |
|
|
235 | =item on_header => $callback->($headers) |
|
|
236 | |
|
|
237 | When specified, this callback will be called with the header hash as soon |
|
|
238 | as headers have been successfully received from the remote server (not on |
|
|
239 | locally-generated errors). |
|
|
240 | |
|
|
241 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
242 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
243 | the finish callback with an error code of C<598>). |
|
|
244 | |
|
|
245 | This callback is useful, among other things, to quickly reject unwanted |
|
|
246 | content, which, if it is supposed to be rare, can be faster than first |
|
|
247 | doing a C<HEAD> request. |
|
|
248 | |
|
|
249 | The downside is that cancelling the request makes it impossible to re-use |
|
|
250 | the connection. Also, the C<on_header> callback will not receive any |
|
|
251 | trailer (headers sent after the response body). |
|
|
252 | |
|
|
253 | Example: cancel the request unless the content-type is "text/html". |
|
|
254 | |
|
|
255 | on_header => sub { |
|
|
256 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
257 | }, |
|
|
258 | |
|
|
259 | =item on_body => $callback->($partial_body, $headers) |
|
|
260 | |
|
|
261 | When specified, all body data will be passed to this callback instead of |
|
|
262 | to the completion callback. The completion callback will get the empty |
|
|
263 | string instead of the body data. |
|
|
264 | |
|
|
265 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
266 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
267 | the completion callback with an error code of C<598>). |
|
|
268 | |
|
|
269 | The downside to cancelling the request is that it makes it impossible to |
|
|
270 | re-use the connection. |
|
|
271 | |
|
|
272 | This callback is useful when the data is too large to be held in memory |
|
|
273 | (so the callback writes it to a file) or when only some information should |
|
|
274 | be extracted, or when the body should be processed incrementally. |
|
|
275 | |
|
|
276 | It is usually preferred over doing your own body handling via |
|
|
277 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
278 | only used to create a connection, C<want_body_handle> is the better |
|
|
279 | alternative, as it allows you to install your own event handler, reducing |
|
|
280 | resource usage. |
|
|
281 | |
|
|
282 | =item want_body_handle => $enable |
|
|
283 | |
|
|
284 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
285 | changes considerably: after parsing the headers, and instead of |
|
|
286 | downloading the body (if any), the completion callback will be |
|
|
287 | called. Instead of the C<$body> argument containing the body data, the |
|
|
288 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
289 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
290 | (e.g. status C<304>), the empty string will be passed. |
|
|
291 | |
|
|
292 | The handle object might or might not be in TLS mode, might be connected to |
|
|
293 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
294 | ways. The user is responsible for this handle (it will not be used by this |
|
|
295 | module anymore). |
|
|
296 | |
|
|
297 | This is useful with some push-type services, where, after the initial |
|
|
298 | headers, an interactive protocol is used (typical example would be the |
|
|
299 | push-style twitter API which starts a JSON/XML stream). |
|
|
300 | |
|
|
301 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
302 | that doesn't solve your problem in a better way. |
177 | |
303 | |
178 | =back |
304 | =back |
179 | |
305 | |
180 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
306 | Example: do a simple HTTP GET request for http://www.nethype.de/ and print |
|
|
307 | the response body. |
181 | |
308 | |
182 | http_request GET => "http://www.nethype.de/", sub { |
309 | http_request GET => "http://www.nethype.de/", sub { |
183 | my ($body, $hdr) = @_; |
310 | my ($body, $hdr) = @_; |
184 | print "$body\n"; |
311 | print "$body\n"; |
185 | }; |
312 | }; |
186 | |
313 | |
187 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
314 | Example: do a HTTP HEAD request on https://www.google.com/, use a |
188 | timeout of 30 seconds. |
315 | timeout of 30 seconds. |
189 | |
316 | |
190 | http_request |
317 | http_request |
191 | GET => "https://www.google.com", |
318 | GET => "https://www.google.com", |
192 | timeout => 30, |
319 | timeout => 30, |
… | |
… | |
195 | use Data::Dumper; |
322 | use Data::Dumper; |
196 | print Dumper $hdr; |
323 | print Dumper $hdr; |
197 | } |
324 | } |
198 | ; |
325 | ; |
199 | |
326 | |
200 | Example: make another simple HTTP GET request, but immediately try to |
327 | Example: do another simple HTTP GET request, but immediately try to |
201 | cancel it. |
328 | cancel it. |
202 | |
329 | |
203 | my $request = http_request GET => "http://www.nethype.de/", sub { |
330 | my $request = http_request GET => "http://www.nethype.de/", sub { |
204 | my ($body, $hdr) = @_; |
331 | my ($body, $hdr) = @_; |
205 | print "$body\n"; |
332 | print "$body\n"; |
… | |
… | |
237 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
364 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
238 | |
365 | |
239 | _slot_schedule $_[0]; |
366 | _slot_schedule $_[0]; |
240 | } |
367 | } |
241 | |
368 | |
|
|
369 | # extract cookies from jar |
|
|
370 | sub cookie_jar_extract($$$$) { |
|
|
371 | my ($jar, $uscheme, $uhost, $upath) = @_; |
|
|
372 | |
|
|
373 | %$jar = () if $jar->{version} != 1; |
|
|
374 | |
|
|
375 | my @cookies; |
|
|
376 | |
|
|
377 | while (my ($chost, $paths) = each %$jar) { |
|
|
378 | next unless ref $paths; |
|
|
379 | |
|
|
380 | if ($chost =~ /^\./) { |
|
|
381 | next unless $chost eq substr $uhost, -length $chost; |
|
|
382 | } elsif ($chost =~ /\./) { |
|
|
383 | next unless $chost eq $uhost; |
|
|
384 | } else { |
|
|
385 | next; |
|
|
386 | } |
|
|
387 | |
|
|
388 | while (my ($cpath, $cookies) = each %$paths) { |
|
|
389 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
390 | |
|
|
391 | while (my ($cookie, $kv) = each %$cookies) { |
|
|
392 | next if $uscheme ne "https" && exists $kv->{secure}; |
|
|
393 | |
|
|
394 | if (exists $kv->{expires}) { |
|
|
395 | if (AE::now > parse_date ($kv->{expires})) { |
|
|
396 | delete $cookies->{$cookie}; |
|
|
397 | next; |
|
|
398 | } |
|
|
399 | } |
|
|
400 | |
|
|
401 | my $value = $kv->{value}; |
|
|
402 | |
|
|
403 | if ($value =~ /[=;,[:space:]]/) { |
|
|
404 | $value =~ s/([\\"])/\\$1/g; |
|
|
405 | $value = "\"$value\""; |
|
|
406 | } |
|
|
407 | |
|
|
408 | push @cookies, "$cookie=$value"; |
|
|
409 | } |
|
|
410 | } |
|
|
411 | } |
|
|
412 | |
|
|
413 | \@cookies |
|
|
414 | } |
|
|
415 | |
|
|
416 | # parse set_cookie header into jar |
|
|
417 | sub cookie_jar_set_cookie($$) { |
|
|
418 | my ($jar, $set_cookie) = @_; |
|
|
419 | |
|
|
420 | for ($set_cookie) { |
|
|
421 | # parse NAME=VALUE |
|
|
422 | my @kv; |
|
|
423 | |
|
|
424 | while ( |
|
|
425 | m{ |
|
|
426 | \G\s* |
|
|
427 | (?: |
|
|
428 | expires \s*=\s* ([A-Z][a-z][a-z],\ [^,;]+) |
|
|
429 | | ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) ) |
|
|
430 | ) |
|
|
431 | }gcxsi |
|
|
432 | ) { |
|
|
433 | my $name = $2; |
|
|
434 | my $value = $4; |
|
|
435 | |
|
|
436 | unless (defined $name) { |
|
|
437 | # expires |
|
|
438 | $name = "expires"; |
|
|
439 | $value = $1; |
|
|
440 | } elsif (!defined $value) { |
|
|
441 | # quoted |
|
|
442 | $value = $3; |
|
|
443 | $value =~ s/\\(.)/$1/gs; |
|
|
444 | } |
|
|
445 | |
|
|
446 | push @kv, lc $name, $value; |
|
|
447 | |
|
|
448 | last unless /\G\s*;/gc; |
|
|
449 | } |
|
|
450 | |
|
|
451 | last unless @kv; |
|
|
452 | |
|
|
453 | my $name = shift @kv; |
|
|
454 | my %kv = (value => shift @kv, @kv); |
|
|
455 | |
|
|
456 | $kv{expires} ||= format_date (AE::now + $kv{"max-age"}) |
|
|
457 | if exists $kv{"max-age"}; |
|
|
458 | |
|
|
459 | my $cdom; |
|
|
460 | my $cpath = (delete $kv{path}) || "/"; |
|
|
461 | |
|
|
462 | if (exists $kv{domain}) { |
|
|
463 | $cdom = delete $kv{domain}; |
|
|
464 | |
|
|
465 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
466 | |
|
|
467 | next if $cdom =~ /\.$/; |
|
|
468 | |
|
|
469 | # this is not rfc-like and not netscape-like. go figure. |
|
|
470 | my $ndots = $cdom =~ y/.//; |
|
|
471 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
472 | } else { |
|
|
473 | $cdom = $uhost; |
|
|
474 | } |
|
|
475 | |
|
|
476 | # store it |
|
|
477 | $arg{cookie_jar}{version} = 1; |
|
|
478 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
479 | |
|
|
480 | redo if /\G\s*,/gc; |
|
|
481 | } |
|
|
482 | } |
|
|
483 | } |
|
|
484 | |
|
|
485 | # continue to parse $_ for headers and place them into the arg |
|
|
486 | sub parse_hdr() { |
|
|
487 | my %hdr; |
|
|
488 | |
|
|
489 | # things seen, not parsed: |
|
|
490 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
491 | |
|
|
492 | $hdr{lc $1} .= ",$2" |
|
|
493 | while /\G |
|
|
494 | ([^:\000-\037]*): |
|
|
495 | [\011\040]* |
|
|
496 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
497 | \012 |
|
|
498 | /gxc; |
|
|
499 | |
|
|
500 | /\G$/ |
|
|
501 | or return; |
|
|
502 | |
|
|
503 | # remove the "," prefix we added to all headers above |
|
|
504 | substr $_, 0, 1, "" |
|
|
505 | for values %hdr; |
|
|
506 | |
|
|
507 | \%hdr |
|
|
508 | } |
|
|
509 | |
|
|
510 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
|
|
511 | |
|
|
512 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
513 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
514 | |
242 | sub http_request($$@) { |
515 | sub http_request($$@) { |
243 | my $cb = pop; |
516 | my $cb = pop; |
244 | my ($method, $url, %arg) = @_; |
517 | my ($method, $url, %arg) = @_; |
245 | |
518 | |
246 | my %hdr; |
519 | my %hdr; |
|
|
520 | |
|
|
521 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
522 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
247 | |
523 | |
248 | $method = uc $method; |
524 | $method = uc $method; |
249 | |
525 | |
250 | if (my $hdr = $arg{headers}) { |
526 | if (my $hdr = $arg{headers}) { |
251 | while (my ($k, $v) = each %$hdr) { |
527 | while (my ($k, $v) = each %$hdr) { |
252 | $hdr{lc $k} = $v; |
528 | $hdr{lc $k} = $v; |
253 | } |
529 | } |
254 | } |
530 | } |
255 | |
531 | |
|
|
532 | # pseudo headers for all subsequent responses |
|
|
533 | my @pseudo = (URL => $url); |
|
|
534 | push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect}; |
|
|
535 | |
256 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
536 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
257 | |
537 | |
258 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
538 | return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" }) |
259 | if $recurse < 0; |
539 | if $recurse < 0; |
260 | |
540 | |
261 | my $proxy = $arg{proxy} || $PROXY; |
541 | my $proxy = $arg{proxy} || $PROXY; |
262 | my $timeout = $arg{timeout} || $TIMEOUT; |
542 | my $timeout = $arg{timeout} || $TIMEOUT; |
263 | |
543 | |
264 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
265 | |
|
|
266 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
544 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
267 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
545 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:(\?[^#]*))?(?:#(.*))?|; |
268 | |
546 | |
269 | $uscheme = lc $uscheme; |
547 | $uscheme = lc $uscheme; |
270 | |
548 | |
271 | my $uport = $uscheme eq "http" ? 80 |
549 | my $uport = $uscheme eq "http" ? 80 |
272 | : $uscheme eq "https" ? 443 |
550 | : $uscheme eq "https" ? 443 |
273 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
551 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
274 | |
|
|
275 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
|
|
276 | |
552 | |
277 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
553 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
278 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
554 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
279 | |
555 | |
280 | my $uhost = $1; |
556 | my $uhost = $1; |
281 | $uport = $2 if defined $2; |
557 | $uport = $2 if defined $2; |
282 | |
558 | |
|
|
559 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
560 | unless exists $hdr{host}; |
|
|
561 | |
283 | $uhost =~ s/^\[(.*)\]$/$1/; |
562 | $uhost =~ s/^\[(.*)\]$/$1/; |
284 | $upath .= "?$query" if length $query; |
563 | $upath .= $query if length $query; |
285 | |
564 | |
286 | $upath =~ s%^/?%/%; |
565 | $upath =~ s%^/?%/%; |
287 | |
566 | |
288 | # cookie processing |
567 | # cookie processing |
289 | if (my $jar = $arg{cookie_jar}) { |
568 | if (my $jar = $arg{cookie_jar}) { |
290 | %$jar = () if $jar->{version} != 1; |
569 | my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath; |
291 | |
570 | |
292 | my @cookie; |
|
|
293 | |
|
|
294 | while (my ($chost, $v) = each %$jar) { |
|
|
295 | if ($chost =~ /^\./) { |
|
|
296 | next unless $chost eq substr $uhost, -length $chost; |
|
|
297 | } elsif ($chost =~ /\./) { |
|
|
298 | next unless $chost eq $uhost; |
|
|
299 | } else { |
|
|
300 | next; |
|
|
301 | } |
|
|
302 | |
|
|
303 | while (my ($cpath, $v) = each %$v) { |
|
|
304 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
305 | |
|
|
306 | while (my ($k, $v) = each %$v) { |
|
|
307 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
308 | my $value = $v->{value}; |
|
|
309 | $value =~ s/([\\"])/\\$1/g; |
|
|
310 | push @cookie, "$k=\"$value\""; |
|
|
311 | } |
|
|
312 | } |
|
|
313 | } |
|
|
314 | |
|
|
315 | $hdr{cookie} = join "; ", @cookie |
571 | $hdr{cookie} = join "; ", @$cookies |
316 | if @cookie; |
572 | if @$cookies; |
317 | } |
573 | } |
318 | |
574 | |
319 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
575 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
320 | |
576 | |
321 | if ($proxy) { |
577 | if ($proxy) { |
322 | ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url); |
578 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
|
|
579 | |
|
|
580 | $rscheme = "http" unless defined $rscheme; |
323 | |
581 | |
324 | # don't support https requests over https-proxy transport, |
582 | # don't support https requests over https-proxy transport, |
325 | # can't be done with tls as spec'ed. |
583 | # can't be done with tls as spec'ed, unless you double-encrypt. |
326 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
584 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
327 | } else { |
585 | } else { |
328 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
586 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
329 | } |
587 | } |
330 | |
588 | |
331 | $hdr{host} = $uhost; |
589 | # leave out fragment and query string, just a heuristic |
|
|
590 | $hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
591 | $hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"}; |
|
|
592 | |
332 | $hdr{"content-length"} = length $arg{body}; |
593 | $hdr{"content-length"} = length $arg{body} |
|
|
594 | if length $arg{body} || $method ne "GET"; |
|
|
595 | |
|
|
596 | $hdr{connection} = "close TE"; #1.1 |
|
|
597 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
333 | |
598 | |
334 | my %state = (connect_guard => 1); |
599 | my %state = (connect_guard => 1); |
335 | |
600 | |
336 | _get_slot $uhost, sub { |
601 | _get_slot $uhost, sub { |
337 | $state{slot_guard} = shift; |
602 | $state{slot_guard} = shift; |
338 | |
603 | |
339 | return unless $state{connect_guard}; |
604 | return unless $state{connect_guard}; |
340 | |
605 | |
341 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
606 | my $connect_cb = sub { |
342 | $state{fh} = shift |
607 | $state{fh} = shift |
|
|
608 | or do { |
|
|
609 | my $err = "$!"; |
|
|
610 | %state = (); |
343 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
611 | return $cb->(undef, { @pseudo, Status => 599, Reason => $err }); |
|
|
612 | }; |
344 | |
613 | |
345 | delete $state{connect_guard}; # reduce memory usage, save a tree |
614 | pop; # free memory, save a tree |
|
|
615 | |
|
|
616 | return unless delete $state{connect_guard}; |
346 | |
617 | |
347 | # get handle |
618 | # get handle |
348 | $state{handle} = new AnyEvent::Handle |
619 | $state{handle} = new AnyEvent::Handle |
349 | fh => $state{fh}; |
620 | fh => $state{fh}, |
|
|
621 | peername => $rhost, |
|
|
622 | tls_ctx => $arg{tls_ctx}, |
|
|
623 | # these need to be reconfigured on keepalive handles |
|
|
624 | timeout => $timeout, |
|
|
625 | on_error => sub { |
|
|
626 | %state = (); |
|
|
627 | $cb->(undef, { @pseudo, Status => 599, Reason => $_[2] }); |
|
|
628 | }, |
|
|
629 | on_eof => sub { |
|
|
630 | %state = (); |
|
|
631 | $cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" }); |
|
|
632 | }, |
|
|
633 | ; |
350 | |
634 | |
351 | # limit the number of persistent connections |
635 | # limit the number of persistent connections |
|
|
636 | # keepalive not yet supported |
352 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
637 | # if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
353 | ++$KA_COUNT{$_[1]}; |
638 | # ++$KA_COUNT{$_[1]}; |
354 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
639 | # $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
640 | # --$KA_COUNT{$_[1]} |
|
|
641 | # }; |
355 | $hdr{connection} = "keep-alive"; |
642 | # $hdr{connection} = "keep-alive"; |
356 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
357 | } else { |
|
|
358 | delete $hdr{connection}; |
|
|
359 | } |
643 | # } |
360 | |
|
|
361 | # (re-)configure handle |
|
|
362 | $state{handle}->timeout ($timeout); |
|
|
363 | $state{handle}->on_error (sub { |
|
|
364 | my $errno = "$!"; |
|
|
365 | %state = (); |
|
|
366 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
|
|
367 | }); |
|
|
368 | $state{handle}->on_eof (sub { |
|
|
369 | %state = (); |
|
|
370 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
|
|
371 | }); |
|
|
372 | |
644 | |
373 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
645 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
374 | |
646 | |
375 | # handle actual, non-tunneled, request |
647 | # handle actual, non-tunneled, request |
376 | my $handle_actual_request = sub { |
648 | my $handle_actual_request = sub { |
377 | # $state{handle}->starttls ("connect") if $uscheme eq "https"; |
649 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
378 | |
650 | |
379 | # send request |
651 | # send request |
380 | $state{handle}->push_write ( |
652 | $state{handle}->push_write ( |
381 | "$method $rpath HTTP/1.0\015\012" |
653 | "$method $rpath HTTP/1.1\015\012" |
382 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
654 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
383 | . "\015\012" |
655 | . "\015\012" |
384 | . (delete $arg{body}) |
656 | . (delete $arg{body}) |
385 | ); |
657 | ); |
386 | |
658 | |
|
|
659 | # return if error occured during push_write() |
|
|
660 | return unless %state; |
|
|
661 | |
387 | %hdr = (); # reduce memory usage, save a kitten |
662 | %hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use |
388 | |
663 | |
389 | # status line |
664 | # status line and headers |
390 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
665 | $state{read_response} = sub { |
391 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
392 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
|
|
393 | |
|
|
394 | my %hdr = ( # response headers |
|
|
395 | HTTPVersion => ",$1", |
|
|
396 | Status => ",$2", |
|
|
397 | Reason => ",$3", |
|
|
398 | URL => ",$url" |
|
|
399 | ); |
|
|
400 | |
|
|
401 | # headers, could be optimized a bit |
|
|
402 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
|
|
403 | for ("$_[1]\012") { |
666 | for ("$_[1]") { |
404 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
667 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
405 | |
668 | |
406 | # we support spaces in field names, as lotus domino |
669 | /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc |
407 | # creates them (actually spaces around seperators |
670 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" })); |
408 | # are strictly allowed in http, they are a security issue). |
|
|
409 | $hdr{lc $1} .= ",$2" |
|
|
410 | while /\G |
|
|
411 | ([^:\000-\037]+): |
|
|
412 | [\011\040]* |
|
|
413 | ((?: [^\012]+ | \012[\011\040] )*) |
|
|
414 | \012 |
|
|
415 | /gxc; |
|
|
416 | |
671 | |
|
|
672 | # 100 Continue handling |
|
|
673 | # should not happen as we don't send expect: 100-continue, |
|
|
674 | # but we handle it just in case. |
|
|
675 | # since we send the request body regardless, if we get an error |
|
|
676 | # we are out of-sync, which we currently do NOT handle correctly. |
|
|
677 | return $state{handle}->push_read (line => $qr_nlnl, $state{read_response}) |
|
|
678 | if $2 eq 100; |
|
|
679 | |
|
|
680 | push @pseudo, |
|
|
681 | HTTPVersion => $1, |
|
|
682 | Status => $2, |
|
|
683 | Reason => $3, |
417 | /\G$/ |
684 | ; |
|
|
685 | |
|
|
686 | my $hdr = parse_hdr |
418 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
687 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" })); |
|
|
688 | |
|
|
689 | %hdr = (%$hdr, @pseudo); |
|
|
690 | } |
|
|
691 | |
|
|
692 | # redirect handling |
|
|
693 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
694 | # try to support some common forms of broken Location headers. |
|
|
695 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
696 | $hdr{location} =~ s/^\.\/+//; |
|
|
697 | |
|
|
698 | my $url = "$rscheme://$uhost:$uport"; |
|
|
699 | |
|
|
700 | unless ($hdr{location} =~ s/^\///) { |
|
|
701 | $url .= $upath; |
|
|
702 | $url =~ s/\/[^\/]*$//; |
419 | } |
703 | } |
420 | |
704 | |
421 | substr $_, 0, 1, "" |
705 | $hdr{location} = "$url/$hdr{location}"; |
422 | for values %hdr; |
706 | } |
423 | |
707 | |
424 | my $finish = sub { |
708 | my $redirect; |
425 | # TODO: use destroy method, when/if available |
709 | |
|
|
710 | if ($recurse) { |
|
|
711 | my $status = $hdr{Status}; |
|
|
712 | |
|
|
713 | # industry standard is to redirect POST as GET for |
|
|
714 | # 301, 302 and 303, in contrast to http/1.0 and 1.1. |
|
|
715 | # also, the UA should ask the user for 301 and 307 and POST, |
|
|
716 | # industry standard seems to be to simply follow. |
|
|
717 | # we go with the industry standard. |
|
|
718 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
719 | # HTTP/1.1 is unclear on how to mutate the method |
|
|
720 | $method = "GET" unless $method eq "HEAD"; |
|
|
721 | $redirect = 1; |
|
|
722 | } elsif ($status == 307) { |
|
|
723 | $redirect = 1; |
|
|
724 | } |
|
|
725 | } |
|
|
726 | |
|
|
727 | my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive]) |
|
|
728 | my $keepalive = pop; |
|
|
729 | |
426 | #$state{handle}->destroy; |
730 | $state{handle}->destroy if $state{handle}; |
427 | $state{handle}->on_eof (undef); |
|
|
428 | $state{handle}->on_error (undef); |
|
|
429 | %state = (); |
731 | %state = (); |
430 | |
732 | |
|
|
733 | if (defined $_[1]) { |
|
|
734 | $hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1]; |
|
|
735 | $hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2]; |
|
|
736 | } |
|
|
737 | |
431 | # set-cookie processing |
738 | # set-cookie processing |
432 | if ($arg{cookie_jar}) { |
739 | if ($arg{cookie_jar}) { |
433 | for ($hdr{"set-cookie"}) { |
740 | cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}; |
434 | # parse NAME=VALUE |
741 | |
|
|
742 | if ($redirect && exists $hdr{location}) { |
|
|
743 | # we ignore any errors, as it is very common to receive |
|
|
744 | # Content-Length != 0 but no actual body |
|
|
745 | # we also access %hdr, as $_[1] might be an erro |
|
|
746 | http_request ( |
|
|
747 | $method => $hdr{location}, |
|
|
748 | %arg, |
|
|
749 | recurse => $recurse - 1, |
|
|
750 | Redirect => [$_[0], \%hdr], |
|
|
751 | $cb); |
|
|
752 | } else { |
|
|
753 | $cb->($_[0], \%hdr); |
|
|
754 | } |
|
|
755 | }; |
|
|
756 | |
|
|
757 | my $len = $hdr{"content-length"}; |
|
|
758 | |
|
|
759 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
760 | $finish->(undef, 598 => "Request cancelled by on_header"); |
|
|
761 | } elsif ( |
|
|
762 | $hdr{Status} =~ /^(?:1..|204|205|304)$/ |
|
|
763 | or $method eq "HEAD" |
|
|
764 | or (defined $len && !$len) |
|
|
765 | ) { |
|
|
766 | # no body |
|
|
767 | $finish->("", undef, undef, 1); |
|
|
768 | } else { |
|
|
769 | # body handling, many different code paths |
|
|
770 | # - no body expected |
|
|
771 | # - want_body_handle |
|
|
772 | # - te chunked |
|
|
773 | # - 2x length known (with or without on_body) |
|
|
774 | # - 2x length not known (with or without on_body) |
|
|
775 | if (!$redirect && $arg{want_body_handle}) { |
|
|
776 | $_[0]->on_eof (undef); |
|
|
777 | $_[0]->on_error (undef); |
|
|
778 | $_[0]->on_read (undef); |
|
|
779 | |
|
|
780 | $finish->(delete $state{handle}); |
|
|
781 | |
|
|
782 | } elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) { |
|
|
783 | my $cl = 0; |
|
|
784 | my $body = undef; |
|
|
785 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
|
|
786 | |
|
|
787 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
788 | |
|
|
789 | my $read_chunk; $read_chunk = sub { |
|
|
790 | $_[1] =~ /^([0-9a-fA-F]+)/ |
|
|
791 | or $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
792 | |
|
|
793 | my $len = hex $1; |
|
|
794 | |
|
|
795 | if ($len) { |
|
|
796 | $cl += $len; |
|
|
797 | |
|
|
798 | $_[0]->push_read (chunk => $len, sub { |
|
|
799 | $on_body->($_[1], \%hdr) |
|
|
800 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
801 | |
|
|
802 | $_[0]->push_read (line => sub { |
|
|
803 | length $_[1] |
|
|
804 | and return $finish->(undef, 599 => "Garbled chunked transfer encoding"); |
|
|
805 | $_[0]->push_read (line => $read_chunk); |
|
|
806 | }); |
435 | my @kv; |
807 | }); |
|
|
808 | } else { |
|
|
809 | $hdr{"content-length"} ||= $cl; |
436 | |
810 | |
437 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
811 | $_[0]->push_read (line => $qr_nlnl, sub { |
438 | my $name = $1; |
812 | if (length $_[1]) { |
439 | my $value = $3; |
|
|
440 | |
|
|
441 | unless ($value) { |
813 | for ("$_[1]") { |
|
|
814 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
815 | |
|
|
816 | my $hdr = parse_hdr |
|
|
817 | or return $finish->(undef, 599 => "Garbled response trailers"); |
|
|
818 | |
|
|
819 | %hdr = (%hdr, %$hdr); |
442 | $value = $2; |
820 | } |
443 | $value =~ s/\\(.)/$1/gs; |
|
|
444 | } |
821 | } |
445 | |
822 | |
446 | push @kv, $name => $value; |
823 | $finish->($body, undef, undef, 1); |
447 | |
|
|
448 | last unless /\G\s*;/gc; |
|
|
449 | } |
824 | }); |
450 | |
|
|
451 | last unless @kv; |
|
|
452 | |
|
|
453 | my $name = shift @kv; |
|
|
454 | my %kv = (value => shift @kv, @kv); |
|
|
455 | |
|
|
456 | my $cdom; |
|
|
457 | my $cpath = (delete $kv{path}) || "/"; |
|
|
458 | |
|
|
459 | if (exists $kv{domain}) { |
|
|
460 | $cdom = delete $kv{domain}; |
|
|
461 | |
|
|
462 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
463 | |
|
|
464 | next if $cdom =~ /\.$/; |
|
|
465 | |
|
|
466 | # this is not rfc-like and not netscape-like. go figure. |
|
|
467 | my $ndots = $cdom =~ y/.//; |
|
|
468 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
469 | } else { |
|
|
470 | $cdom = $uhost; |
|
|
471 | } |
|
|
472 | |
|
|
473 | # store it |
|
|
474 | $arg{cookie_jar}{version} = 1; |
|
|
475 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
476 | |
|
|
477 | redo if /\G\s*,/gc; |
|
|
478 | } |
825 | } |
479 | } |
826 | }; |
480 | |
827 | |
481 | # microsoft and other shitheads don't give a shit for following standards, |
828 | $_[0]->push_read (line => $read_chunk); |
482 | # try to support some common forms of broken Location headers. |
|
|
483 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
484 | $_[1]{location} =~ s/^\.\/+//; |
|
|
485 | |
829 | |
486 | my $url = "$rscheme://$uhost:$uport"; |
830 | } elsif ($arg{on_body}) { |
|
|
831 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
487 | |
832 | |
488 | unless ($_[1]{location} =~ s/^\///) { |
|
|
489 | $url .= $upath; |
|
|
490 | $url =~ s/\/[^\/]*$//; |
|
|
491 | } |
|
|
492 | |
|
|
493 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
494 | } |
|
|
495 | |
|
|
496 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
497 | # apparently, mozilla et al. just change POST to GET here |
|
|
498 | # more research is needed before we do the same |
|
|
499 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
500 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
501 | # even http/1.1 is unclear on how to mutate the method |
|
|
502 | $method = "GET" unless $method eq "HEAD"; |
|
|
503 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
504 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
505 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
506 | } else { |
833 | if ($len) { |
507 | $cb->($_[0], $_[1]); |
834 | $_[0]->on_read (sub { |
508 | } |
835 | $len -= length $_[0]{rbuf}; |
509 | }; |
|
|
510 | |
836 | |
511 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
837 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
512 | $finish->(undef, \%hdr); |
838 | or return $finish->(undef, 598 => "Request cancelled by on_body"); |
513 | } else { |
839 | |
514 | if (exists $hdr{"content-length"}) { |
|
|
515 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
516 | # could cache persistent connection now |
|
|
517 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
518 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
519 | }; |
840 | $len > 0 |
520 | |
841 | or $finish->("", undef, undef, 1); |
521 | $finish->($_[1], \%hdr); |
|
|
522 | }); |
842 | }); |
523 | } else { |
843 | } else { |
524 | # too bad, need to read until we get an error or EOF, |
844 | $_[0]->on_eof (sub { |
525 | # no way to detect winged data. |
845 | $finish->(""); |
|
|
846 | }); |
|
|
847 | $_[0]->on_read (sub { |
|
|
848 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
849 | or $finish->(undef, 598 => "Request cancelled by on_body"); |
|
|
850 | }); |
|
|
851 | } |
|
|
852 | } else { |
|
|
853 | $_[0]->on_eof (undef); |
|
|
854 | |
|
|
855 | if ($len) { |
|
|
856 | $_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) }); |
|
|
857 | $_[0]->on_read (sub { |
|
|
858 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1) |
|
|
859 | if $len <= length $_[0]{rbuf}; |
|
|
860 | }); |
|
|
861 | } else { |
526 | $_[0]->on_error (sub { |
862 | $_[0]->on_error (sub { |
|
|
863 | ($! == Errno::EPIPE || !$!) |
527 | $finish->($_[0]{rbuf}, \%hdr); |
864 | ? $finish->(delete $_[0]{rbuf}) |
|
|
865 | : $finish->(undef, 599 => $_[2]); |
528 | }); |
866 | }); |
529 | $_[0]->on_eof (undef); |
|
|
530 | $_[0]->on_read (sub { }); |
867 | $_[0]->on_read (sub { }); |
531 | } |
868 | } |
532 | } |
869 | } |
533 | }); |
870 | } |
534 | }); |
871 | }; |
|
|
872 | |
|
|
873 | $state{handle}->push_read (line => $qr_nlnl, $state{read_response}); |
535 | }; |
874 | }; |
536 | |
875 | |
537 | # now handle proxy-CONNECT method |
876 | # now handle proxy-CONNECT method |
538 | if ($proxy && $uscheme eq "https") { |
877 | if ($proxy && $uscheme eq "https") { |
539 | # oh dear, we have to wrap it into a connect request |
878 | # oh dear, we have to wrap it into a connect request |
540 | |
879 | |
541 | # maybe re-use $uauthority with patched port? |
880 | # maybe re-use $uauthority with patched port? |
542 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
881 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
543 | $state{handle}->push_read (line => qr/\015?\012\015?\012/, sub { |
882 | $state{handle}->push_read (line => $qr_nlnl, sub { |
544 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
883 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
545 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url })); |
884 | or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" })); |
546 | |
885 | |
547 | if ($2 == 200) { |
886 | if ($2 == 200) { |
548 | $rpath = $upath; |
887 | $rpath = $upath; |
549 | &$handle_actual_request; |
888 | &$handle_actual_request; |
550 | } else { |
889 | } else { |
551 | %state = (); |
890 | %state = (); |
552 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
891 | $cb->(undef, { @pseudo, Status => $2, Reason => $3 }); |
553 | } |
892 | } |
554 | }); |
893 | }); |
555 | } else { |
894 | } else { |
556 | &$handle_actual_request; |
895 | &$handle_actual_request; |
557 | } |
896 | } |
558 | |
|
|
559 | }, sub { |
|
|
560 | $timeout |
|
|
561 | }; |
897 | }; |
|
|
898 | |
|
|
899 | my $tcp_connect = $arg{tcp_connect} |
|
|
900 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
|
|
901 | |
|
|
902 | $state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} || sub { $timeout }); |
|
|
903 | |
562 | }; |
904 | }; |
563 | |
905 | |
564 | defined wantarray && AnyEvent::Util::guard { %state = () } |
906 | defined wantarray && AnyEvent::Util::guard { %state = () } |
565 | } |
907 | } |
566 | |
908 | |
… | |
… | |
580 | &http_request |
922 | &http_request |
581 | } |
923 | } |
582 | |
924 | |
583 | =back |
925 | =back |
584 | |
926 | |
|
|
927 | =head2 DNS CACHING |
|
|
928 | |
|
|
929 | AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for |
|
|
930 | the actual connection, which in turn uses AnyEvent::DNS to resolve |
|
|
931 | hostnames. The latter is a simple stub resolver and does no caching |
|
|
932 | on its own. If you want DNS caching, you currently have to provide |
|
|
933 | your own default resolver (by storing a suitable resolver object in |
|
|
934 | C<$AnyEvent::DNS::RESOLVER>). |
|
|
935 | |
585 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
936 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
586 | |
937 | |
587 | =over 4 |
938 | =over 4 |
588 | |
939 | |
589 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
940 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
590 | |
941 | |
591 | Sets the default proxy server to use. The proxy-url must begin with a |
942 | Sets the default proxy server to use. The proxy-url must begin with a |
592 | string of the form C<http://host:port> (optionally C<https:...>). |
943 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
944 | otherwise. |
|
|
945 | |
|
|
946 | To clear an already-set proxy, use C<undef>. |
|
|
947 | |
|
|
948 | =item $date = AnyEvent::HTTP::format_date $timestamp |
|
|
949 | |
|
|
950 | Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP |
|
|
951 | Date (RFC 2616). |
|
|
952 | |
|
|
953 | =item $timestamp = AnyEvent::HTTP::parse_date $date |
|
|
954 | |
|
|
955 | Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and |
|
|
956 | returns the corresponding POSIX timestamp, or C<undef> if the date cannot |
|
|
957 | be parsed. |
593 | |
958 | |
594 | =item $AnyEvent::HTTP::MAX_RECURSE |
959 | =item $AnyEvent::HTTP::MAX_RECURSE |
595 | |
960 | |
596 | The default value for the C<recurse> request parameter (default: C<10>). |
961 | The default value for the C<recurse> request parameter (default: C<10>). |
597 | |
962 | |
598 | =item $AnyEvent::HTTP::USERAGENT |
963 | =item $AnyEvent::HTTP::USERAGENT |
599 | |
964 | |
600 | The default value for the C<User-Agent> header (the default is |
965 | The default value for the C<User-Agent> header (the default is |
601 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
966 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
602 | |
967 | |
603 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
968 | =item $AnyEvent::HTTP::MAX_PER_HOST |
604 | |
969 | |
605 | The maximum number of persistent connections to keep open (default: 8). |
970 | The maximum number of concurrent connections to the same host (identified |
|
|
971 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
972 | are queued until previous connections are closed. |
606 | |
973 | |
607 | Not implemented currently. |
974 | The default value for this is C<4>, and it is highly advisable to not |
608 | |
975 | increase it. |
609 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
|
|
610 | |
|
|
611 | The maximum time to cache a persistent connection, in seconds (default: 2). |
|
|
612 | |
|
|
613 | Not implemented currently. |
|
|
614 | |
976 | |
615 | =item $AnyEvent::HTTP::ACTIVE |
977 | =item $AnyEvent::HTTP::ACTIVE |
616 | |
978 | |
617 | The number of active connections. This is not the number of currently |
979 | The number of active connections. This is not the number of currently |
618 | running requests, but the number of currently open and non-idle TCP |
980 | running requests, but the number of currently open and non-idle TCP |
… | |
… | |
620 | |
982 | |
621 | =back |
983 | =back |
622 | |
984 | |
623 | =cut |
985 | =cut |
624 | |
986 | |
|
|
987 | our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); |
|
|
988 | our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat); |
|
|
989 | |
|
|
990 | sub format_date($) { |
|
|
991 | my ($time) = @_; |
|
|
992 | |
|
|
993 | # RFC 822/1123 format |
|
|
994 | my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time; |
|
|
995 | |
|
|
996 | sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT", |
|
|
997 | $weekday[$wday], $mday, $month[$mon], $year + 1900, |
|
|
998 | $H, $M, $S; |
|
|
999 | } |
|
|
1000 | |
|
|
1001 | sub parse_date($) { |
|
|
1002 | my ($date) = @_; |
|
|
1003 | |
|
|
1004 | my ($d, $m, $y, $H, $M, $S); |
|
|
1005 | |
|
|
1006 | if ($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$/) { |
|
|
1007 | # RFC 822/1123, required by RFC 2616 (with " ") |
|
|
1008 | # cookie dates (with "-") |
|
|
1009 | |
|
|
1010 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6); |
|
|
1011 | |
|
|
1012 | } elsif ($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$/) { |
|
|
1013 | # RFC 850 |
|
|
1014 | ($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6); |
|
|
1015 | |
|
|
1016 | } elsif ($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])$/) { |
|
|
1017 | # ISO C's asctime |
|
|
1018 | ($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5); |
|
|
1019 | } |
|
|
1020 | # other formats fail in the loop below |
|
|
1021 | |
|
|
1022 | for (0..11) { |
|
|
1023 | if ($m eq $month[$_]) { |
|
|
1024 | require Time::Local; |
|
|
1025 | return Time::Local::timegm ($S, $M, $H, $d, $_, $y); |
|
|
1026 | } |
|
|
1027 | } |
|
|
1028 | |
|
|
1029 | undef |
|
|
1030 | } |
|
|
1031 | |
625 | sub set_proxy($) { |
1032 | sub set_proxy($) { |
|
|
1033 | if (length $_[0]) { |
626 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
1034 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
1035 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
1036 | $PROXY = [$2, $3 || 3128, $1] |
|
|
1037 | } else { |
|
|
1038 | undef $PROXY; |
|
|
1039 | } |
627 | } |
1040 | } |
628 | |
1041 | |
629 | # initialise proxy from environment |
1042 | # initialise proxy from environment |
|
|
1043 | eval { |
630 | set_proxy $ENV{http_proxy}; |
1044 | set_proxy $ENV{http_proxy}; |
|
|
1045 | }; |
|
|
1046 | |
|
|
1047 | =head2 SOCKS PROXIES |
|
|
1048 | |
|
|
1049 | Socks proxies are not directly supported by AnyEvent::HTTP. You can |
|
|
1050 | compile your perl to support socks, or use an external program such as |
|
|
1051 | F<socksify> (dante) or F<tsocks> to make your program use a socks proxy |
|
|
1052 | transparently. |
|
|
1053 | |
|
|
1054 | Alternatively, for AnyEvent::HTTP only, you can use your own |
|
|
1055 | C<tcp_connect> function that does the proxy handshake - here is an example |
|
|
1056 | that works with socks4a proxies: |
|
|
1057 | |
|
|
1058 | use Errno; |
|
|
1059 | use AnyEvent::Util; |
|
|
1060 | use AnyEvent::Socket; |
|
|
1061 | use AnyEvent::Handle; |
|
|
1062 | |
|
|
1063 | # host, port and username of/for your socks4a proxy |
|
|
1064 | my $socks_host = "10.0.0.23"; |
|
|
1065 | my $socks_port = 9050; |
|
|
1066 | my $socks_user = ""; |
|
|
1067 | |
|
|
1068 | sub socks4a_connect { |
|
|
1069 | my ($host, $port, $connect_cb, $prepare_cb) = @_; |
|
|
1070 | |
|
|
1071 | my $hdl = new AnyEvent::Handle |
|
|
1072 | connect => [$socks_host, $socks_port], |
|
|
1073 | on_prepare => sub { $prepare_cb->($_[0]{fh}) }, |
|
|
1074 | on_error => sub { $connect_cb->() }, |
|
|
1075 | ; |
|
|
1076 | |
|
|
1077 | $hdl->push_write (pack "CCnNZ*Z*", 4, 1, $port, 1, $socks_user, $host); |
|
|
1078 | |
|
|
1079 | $hdl->push_read (chunk => 8, sub { |
|
|
1080 | my ($hdl, $chunk) = @_; |
|
|
1081 | my ($status, $port, $ipn) = unpack "xCna4", $chunk; |
|
|
1082 | |
|
|
1083 | if ($status == 0x5a) { |
|
|
1084 | $connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port"); |
|
|
1085 | } else { |
|
|
1086 | $! = Errno::ENXIO; $connect_cb->(); |
|
|
1087 | } |
|
|
1088 | }); |
|
|
1089 | |
|
|
1090 | $hdl |
|
|
1091 | } |
|
|
1092 | |
|
|
1093 | Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s, |
|
|
1094 | possibly after switching off other proxy types: |
|
|
1095 | |
|
|
1096 | AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies |
|
|
1097 | |
|
|
1098 | http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub { |
|
|
1099 | my ($data, $headers) = @_; |
|
|
1100 | ... |
|
|
1101 | }; |
631 | |
1102 | |
632 | =head1 SEE ALSO |
1103 | =head1 SEE ALSO |
633 | |
1104 | |
634 | L<AnyEvent>. |
1105 | L<AnyEvent>. |
635 | |
1106 | |
636 | =head1 AUTHOR |
1107 | =head1 AUTHOR |
637 | |
1108 | |
638 | Marc Lehmann <schmorp@schmorp.de> |
1109 | Marc Lehmann <schmorp@schmorp.de> |
639 | http://home.schmorp.de/ |
1110 | http://home.schmorp.de/ |
640 | |
1111 | |
|
|
1112 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
1113 | testcases and bugreports. |
|
|
1114 | |
641 | =cut |
1115 | =cut |
642 | |
1116 | |
643 | 1 |
1117 | 1 |
644 | |
1118 | |