… | |
… | |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
3 | AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
4 | |
4 | |
5 | =head1 SYNOPSIS |
5 | =head1 SYNOPSIS |
6 | |
6 | |
7 | use AnyEvent::HTTP; |
7 | use AnyEvent::HTTP; |
|
|
8 | |
|
|
9 | http_get "http://www.nethype.de/", sub { print $_[1] }; |
|
|
10 | |
|
|
11 | # ... do something else here |
8 | |
12 | |
9 | =head1 DESCRIPTION |
13 | =head1 DESCRIPTION |
10 | |
14 | |
11 | This module is an L<AnyEvent> user, you need to make sure that you use and |
15 | This module is an L<AnyEvent> user, you need to make sure that you use and |
12 | run a supported event loop. |
16 | run a supported event loop. |
13 | |
17 | |
|
|
18 | This module implements a simple, stateless and non-blocking HTTP |
|
|
19 | client. It supports GET, POST and other request methods, cookies and more, |
|
|
20 | all on a very low level. It can follow redirects supports proxies and |
|
|
21 | automatically limits the number of connections to the values specified in |
|
|
22 | the RFC. |
|
|
23 | |
|
|
24 | It should generally be a "good client" that is enough for most HTTP |
|
|
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
|
|
26 | possible as the user retains control over request and response headers. |
|
|
27 | |
|
|
28 | The caller is responsible for authentication management, cookies (if |
|
|
29 | the simplistic implementation in this module doesn't suffice), referer |
|
|
30 | and other high-level protocol details for which this module offers only |
|
|
31 | limited support. |
|
|
32 | |
14 | =head2 METHODS |
33 | =head2 METHODS |
15 | |
34 | |
16 | =over 4 |
35 | =over 4 |
17 | |
36 | |
18 | =cut |
37 | =cut |
… | |
… | |
20 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
21 | |
40 | |
22 | use strict; |
41 | use strict; |
23 | no warnings; |
42 | no warnings; |
24 | |
43 | |
25 | use Carp; |
44 | use Errno (); |
26 | |
45 | |
27 | use AnyEvent (); |
46 | use AnyEvent 4.452 (); |
28 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
29 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
30 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
31 | |
50 | |
32 | use base Exporter::; |
51 | use base Exporter::; |
33 | |
52 | |
34 | our $VERSION = '1.0'; |
53 | our $VERSION = '1.12'; |
35 | |
54 | |
36 | our @EXPORT = qw(http_get http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
37 | |
56 | |
38 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
39 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
40 | our $MAX_PERSISTENT = 8; |
59 | our $MAX_PERSISTENT = 8; |
41 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $PERSISTENT_TIMEOUT = 2; |
42 | our $TIMEOUT = 300; |
61 | our $TIMEOUT = 300; |
43 | |
62 | |
44 | # changing these is evil |
63 | # changing these is evil |
45 | our $MAX_PERSISTENT_PER_HOST = 2; |
64 | our $MAX_PERSISTENT_PER_HOST = 2; |
46 | our $MAX_PER_HOST = 4; # not respected yet :( |
65 | our $MAX_PER_HOST = 4; |
47 | |
66 | |
48 | our $PROXY; |
67 | our $PROXY; |
|
|
68 | our $ACTIVE = 0; |
49 | |
69 | |
50 | my %KA_COUNT; # number of open keep-alive connections per host |
70 | my %KA_COUNT; # number of open keep-alive connections per host |
|
|
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
51 | |
72 | |
52 | =item http_get $url, key => value..., $cb->($data, $headers) |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
53 | |
74 | |
54 | Executes an HTTP-GET request. See the http_request function for details on |
75 | Executes an HTTP-GET request. See the http_request function for details on |
55 | additional parameters. |
76 | additional parameters and the return value. |
56 | |
77 | |
57 | =item http_head $url, key => value..., $cb->($data, $headers) |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
58 | |
79 | |
59 | Executes an HTTP-HEAD request. See the http_request function for details on |
80 | Executes an HTTP-HEAD request. See the http_request function for details |
60 | additional parameters. |
81 | on additional parameters and the return value. |
61 | |
82 | |
62 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
63 | |
84 | |
64 | Executes an HTTP-POST request with a requets body of C<$bod>. See the |
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
65 | http_request function for details on additional parameters. |
86 | http_request function for details on additional parameters and the return |
|
|
87 | value. |
66 | |
88 | |
67 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
68 | |
90 | |
69 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
70 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
|
|
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
71 | |
98 | |
72 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response data as first argument |
73 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
74 | response headers as second argument. |
101 | response headers as second argument. |
75 | |
102 | |
76 | All the headers in that has are lowercased. In addition to the response |
103 | All the headers in that hash are lowercased. In addition to the response |
77 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
78 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
79 | name. |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
107 | requested URL when following redirects). |
|
|
108 | |
|
|
109 | If the server sends a header multiple times, then their contents will be |
|
|
110 | joined together with a comma (C<,>), as per the HTTP spec. |
80 | |
111 | |
81 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
82 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
83 | and the C<Reason> pseudo-header will contain an error message. |
114 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
|
|
115 | message. |
84 | |
116 | |
85 | A typical callback might look like this: |
117 | A typical callback might look like this: |
86 | |
118 | |
87 | sub { |
119 | sub { |
88 | my ($body, $hdr) = @_; |
120 | my ($body, $hdr) = @_; |
… | |
… | |
104 | Whether to recurse requests or not, e.g. on redirects, authentication |
136 | Whether to recurse requests or not, e.g. on redirects, authentication |
105 | retries and so on, and how often to do so. |
137 | retries and so on, and how often to do so. |
106 | |
138 | |
107 | =item headers => hashref |
139 | =item headers => hashref |
108 | |
140 | |
109 | The request headers to use. |
141 | The request headers to use. Currently, C<http_request> may provide its |
|
|
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
|
|
143 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
110 | |
144 | |
111 | =item timeout => $seconds |
145 | =item timeout => $seconds |
112 | |
146 | |
113 | The time-out to use for various stages - each connect attempt will reset |
147 | The time-out to use for various stages - each connect attempt will reset |
114 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
148 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
… | |
… | |
124 | =item body => $string |
158 | =item body => $string |
125 | |
159 | |
126 | The request body, usually empty. Will be-sent as-is (future versions of |
160 | The request body, usually empty. Will be-sent as-is (future versions of |
127 | this module might offer more options). |
161 | this module might offer more options). |
128 | |
162 | |
|
|
163 | =item cookie_jar => $hash_ref |
|
|
164 | |
|
|
165 | Passing this parameter enables (simplified) cookie-processing, loosely |
|
|
166 | based on the original netscape specification. |
|
|
167 | |
|
|
168 | The C<$hash_ref> must be an (initially empty) hash reference which will |
|
|
169 | get updated automatically. It is possible to save the cookie_jar to |
|
|
170 | persistent storage with something like JSON or Storable, but this is not |
|
|
171 | recommended, as expiry times are currently being ignored. |
|
|
172 | |
|
|
173 | Note that this cookie implementation is not of very high quality, nor |
|
|
174 | meant to be complete. If you want complete cookie management you have to |
|
|
175 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
|
|
176 | cookie-using sites working. Cookies are a privacy disaster, do not use |
|
|
177 | them unless required to. |
|
|
178 | |
|
|
179 | =item tls_ctx => $scheme | $tls_ctx |
|
|
180 | |
|
|
181 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
182 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
183 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
184 | C<high> can be specified, which give you a predefined low-security (no |
|
|
185 | verification, highest compatibility) and high-security (CA and common-name |
|
|
186 | verification) TLS context. |
|
|
187 | |
|
|
188 | The default for this option is C<low>, which could be interpreted as "give |
|
|
189 | me the page, no matter what". |
|
|
190 | |
|
|
191 | =item on_header => $callback->($hdr) |
|
|
192 | |
|
|
193 | When specified, this callback will be called with the header hash as soon |
|
|
194 | as headers have been successfully received from the remote server (not on |
|
|
195 | locally-generated errors). |
|
|
196 | |
|
|
197 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
198 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
199 | the finish callback with an error code of C<598>). |
|
|
200 | |
|
|
201 | This callback is useful, among other things, to quickly reject unwanted |
|
|
202 | content, which, if it is supposed to be rare, can be faster than first |
|
|
203 | doing a C<HEAD> request. |
|
|
204 | |
|
|
205 | =item on_body => $callback->($data, $hdr) |
|
|
206 | |
|
|
207 | When specified, all body data will be "filtered" through this callback. |
|
|
208 | |
|
|
209 | The callback will incrementally receive body data, and is supposed to |
|
|
210 | return it or a modified version of it (empty strings are valid returns). |
|
|
211 | |
|
|
212 | If the callback returns C<undef>, then the request will be cancelled. |
|
|
213 | |
|
|
214 | This callback is useful when you want to do some processing on the data, |
|
|
215 | or the data is too large to be held in memory (so the callback writes it |
|
|
216 | to a file and returns the empty string) and so on. |
|
|
217 | |
|
|
218 | It is usually preferred over doing your own body handling via |
|
|
219 | C<want_body_handle>. |
|
|
220 | |
|
|
221 | =item want_body_handle => $enable |
|
|
222 | |
|
|
223 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
224 | changes considerably: after parsing the headers, and instead of |
|
|
225 | downloading the body (if any), the completion callback will be |
|
|
226 | called. Instead of the C<$body> argument containing the body data, the |
|
|
227 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
228 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
229 | (e.g. status C<304>), the empty string will be passed. |
|
|
230 | |
|
|
231 | The handle object might or might not be in TLS mode, might be connected to |
|
|
232 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
233 | ways. The user is responsible for this handle (it will not be used by this |
|
|
234 | module anymore). |
|
|
235 | |
|
|
236 | This is useful with some push-type services, where, after the initial |
|
|
237 | headers, an interactive protocol is used (typical example would be the |
|
|
238 | push-style twitter API which starts a JSON/XML stream). |
|
|
239 | |
|
|
240 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
241 | that doesn'T solve your problem in a better way. |
|
|
242 | |
129 | =back |
243 | =back |
130 | |
244 | |
131 | =back |
245 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
|
|
246 | |
|
|
247 | http_request GET => "http://www.nethype.de/", sub { |
|
|
248 | my ($body, $hdr) = @_; |
|
|
249 | print "$body\n"; |
|
|
250 | }; |
|
|
251 | |
|
|
252 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
|
|
253 | timeout of 30 seconds. |
|
|
254 | |
|
|
255 | http_request |
|
|
256 | GET => "https://www.google.com", |
|
|
257 | timeout => 30, |
|
|
258 | sub { |
|
|
259 | my ($body, $hdr) = @_; |
|
|
260 | use Data::Dumper; |
|
|
261 | print Dumper $hdr; |
|
|
262 | } |
|
|
263 | ; |
|
|
264 | |
|
|
265 | Example: make another simple HTTP GET request, but immediately try to |
|
|
266 | cancel it. |
|
|
267 | |
|
|
268 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
269 | my ($body, $hdr) = @_; |
|
|
270 | print "$body\n"; |
|
|
271 | }; |
|
|
272 | |
|
|
273 | undef $request; |
132 | |
274 | |
133 | =cut |
275 | =cut |
134 | |
276 | |
|
|
277 | sub _slot_schedule; |
|
|
278 | sub _slot_schedule($) { |
|
|
279 | my $host = shift; |
|
|
280 | |
|
|
281 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
|
|
282 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
|
|
283 | # somebody wants that slot |
|
|
284 | ++$CO_SLOT{$host}[0]; |
|
|
285 | ++$ACTIVE; |
|
|
286 | |
|
|
287 | $cb->(AnyEvent::Util::guard { |
|
|
288 | --$ACTIVE; |
|
|
289 | --$CO_SLOT{$host}[0]; |
|
|
290 | _slot_schedule $host; |
|
|
291 | }); |
|
|
292 | } else { |
|
|
293 | # nobody wants the slot, maybe we can forget about it |
|
|
294 | delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; |
|
|
295 | last; |
|
|
296 | } |
|
|
297 | } |
|
|
298 | } |
|
|
299 | |
|
|
300 | # wait for a free slot on host, call callback |
|
|
301 | sub _get_slot($$) { |
|
|
302 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
|
|
303 | |
|
|
304 | _slot_schedule $_[0]; |
|
|
305 | } |
|
|
306 | |
|
|
307 | our $qr_nl = qr<\015?\012>; |
|
|
308 | our $qr_nlnl = qr<\015?\012\015?\012>; |
|
|
309 | |
|
|
310 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
311 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
312 | |
135 | sub http_request($$$;@) { |
313 | sub http_request($$@) { |
136 | my $cb = pop; |
314 | my $cb = pop; |
137 | my ($method, $url, %arg) = @_; |
315 | my ($method, $url, %arg) = @_; |
138 | |
316 | |
139 | my %hdr; |
317 | my %hdr; |
140 | |
318 | |
|
|
319 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
320 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
|
|
321 | |
141 | $method = uc $method; |
322 | $method = uc $method; |
142 | |
323 | |
143 | if (my $hdr = delete $arg{headers}) { |
324 | if (my $hdr = $arg{headers}) { |
144 | while (my ($k, $v) = each %$hdr) { |
325 | while (my ($k, $v) = each %$hdr) { |
145 | $hdr{lc $k} = $v; |
326 | $hdr{lc $k} = $v; |
146 | } |
327 | } |
147 | } |
328 | } |
148 | |
329 | |
|
|
330 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
|
|
331 | |
|
|
332 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
|
|
333 | if $recurse < 0; |
|
|
334 | |
149 | my $proxy = $arg{proxy} || $PROXY; |
335 | my $proxy = $arg{proxy} || $PROXY; |
150 | my $timeout = $arg{timeout} || $TIMEOUT; |
336 | my $timeout = $arg{timeout} || $TIMEOUT; |
151 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
337 | |
|
|
338 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
|
|
339 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
340 | |
|
|
341 | $uscheme = lc $uscheme; |
|
|
342 | |
|
|
343 | my $uport = $uscheme eq "http" ? 80 |
|
|
344 | : $uscheme eq "https" ? 443 |
|
|
345 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
|
|
346 | |
|
|
347 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
348 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
|
|
349 | |
|
|
350 | my $uhost = $1; |
|
|
351 | $uport = $2 if defined $2; |
|
|
352 | |
|
|
353 | $uhost =~ s/^\[(.*)\]$/$1/; |
|
|
354 | $upath .= "?$query" if length $query; |
|
|
355 | |
|
|
356 | $upath =~ s%^/?%/%; |
|
|
357 | |
|
|
358 | # cookie processing |
|
|
359 | if (my $jar = $arg{cookie_jar}) { |
|
|
360 | %$jar = () if $jar->{version} != 1; |
|
|
361 | |
|
|
362 | my @cookie; |
|
|
363 | |
|
|
364 | while (my ($chost, $v) = each %$jar) { |
|
|
365 | if ($chost =~ /^\./) { |
|
|
366 | next unless $chost eq substr $uhost, -length $chost; |
|
|
367 | } elsif ($chost =~ /\./) { |
|
|
368 | next unless $chost eq $uhost; |
|
|
369 | } else { |
|
|
370 | next; |
|
|
371 | } |
|
|
372 | |
|
|
373 | while (my ($cpath, $v) = each %$v) { |
|
|
374 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
375 | |
|
|
376 | while (my ($k, $v) = each %$v) { |
|
|
377 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
378 | my $value = $v->{value}; |
|
|
379 | $value =~ s/([\\"])/\\$1/g; |
|
|
380 | push @cookie, "$k=\"$value\""; |
|
|
381 | } |
|
|
382 | } |
|
|
383 | } |
|
|
384 | |
|
|
385 | $hdr{cookie} = join "; ", @cookie |
|
|
386 | if @cookie; |
|
|
387 | } |
|
|
388 | |
|
|
389 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
|
|
390 | |
|
|
391 | if ($proxy) { |
|
|
392 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
|
|
393 | |
|
|
394 | # don't support https requests over https-proxy transport, |
|
|
395 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
396 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
|
|
397 | } else { |
|
|
398 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
|
|
399 | } |
152 | |
400 | |
153 | $hdr{"user-agent"} ||= $USERAGENT; |
401 | $hdr{"user-agent"} ||= $USERAGENT; |
|
|
402 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
154 | |
403 | |
155 | my ($host, $port, $path, $scheme); |
404 | $hdr{host} = "$uhost:$uport"; |
156 | |
|
|
157 | if ($proxy) { |
|
|
158 | ($host, $port, $scheme) = @$proxy; |
|
|
159 | $path = $url; |
|
|
160 | } else { |
|
|
161 | ($scheme, my $authority, $path, my $query, my $fragment) = |
|
|
162 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
163 | |
|
|
164 | $port = $scheme eq "http" ? 80 |
|
|
165 | : $scheme eq "https" ? 443 |
|
|
166 | : croak "$url: only http and https URLs supported"; |
|
|
167 | |
|
|
168 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
169 | or croak "$authority: unparsable URL"; |
|
|
170 | |
|
|
171 | $host = $1; |
|
|
172 | $port = $2 if defined $2; |
|
|
173 | |
|
|
174 | $host =~ s/^\[(.*)\]$/$1/; |
|
|
175 | $path .= "?$query" if length $query; |
|
|
176 | |
|
|
177 | $path = "/" unless $path; |
|
|
178 | |
|
|
179 | $hdr{host} = $host = lc $host; |
|
|
180 | } |
|
|
181 | |
|
|
182 | $scheme = lc $scheme; |
|
|
183 | |
|
|
184 | my %state; |
|
|
185 | |
|
|
186 | $state{body} = delete $arg{body}; |
|
|
187 | |
|
|
188 | $hdr{"content-length"} = length $state{body}; |
405 | $hdr{"content-length"} = length $arg{body}; |
189 | |
406 | |
|
|
407 | my %state = (connect_guard => 1); |
|
|
408 | |
|
|
409 | _get_slot $uhost, sub { |
|
|
410 | $state{slot_guard} = shift; |
|
|
411 | |
|
|
412 | return unless $state{connect_guard}; |
|
|
413 | |
190 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
414 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
191 | $state{fh} = shift |
415 | $state{fh} = shift |
192 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
416 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url })); |
|
|
417 | pop; # free memory, save a tree |
193 | |
418 | |
194 | delete $state{connect_guard}; # reduce memory usage, save a tree |
419 | return unless delete $state{connect_guard}; |
195 | |
420 | |
196 | # get handle |
421 | # get handle |
197 | $state{handle} = new AnyEvent::Handle |
422 | $state{handle} = new AnyEvent::Handle |
198 | fh => $state{fh}, |
423 | fh => $state{fh}, |
199 | ($scheme eq "https" ? (tls => "connect") : ()); |
424 | timeout => $timeout, |
|
|
425 | peername => $rhost, |
|
|
426 | tls_ctx => $arg{tls_ctx}; |
200 | |
427 | |
201 | # limit the number of persistent connections |
428 | # limit the number of persistent connections |
|
|
429 | # keepalive not yet supported |
202 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
430 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
203 | ++$KA_COUNT{$_[1]}; |
431 | ++$KA_COUNT{$_[1]}; |
204 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
432 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
433 | --$KA_COUNT{$_[1]} |
|
|
434 | }; |
205 | $hdr{connection} = "keep-alive"; |
435 | $hdr{connection} = "keep-alive"; |
206 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
207 | } else { |
436 | } else { |
208 | delete $hdr{connection}; |
437 | delete $hdr{connection}; |
209 | } |
438 | } |
210 | |
439 | |
211 | # (re-)configure handle |
440 | # (re-)configure handle |
212 | $state{handle}->timeout ($timeout); |
|
|
213 | $state{handle}->on_error (sub { |
441 | $state{handle}->on_error (sub { |
214 | %state = (); |
442 | %state = (); |
215 | $cb->(undef, { Status => 599, Reason => "$!" }); |
443 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
216 | }); |
444 | }); |
217 | $state{handle}->on_eof (sub { |
445 | $state{handle}->on_eof (sub { |
218 | %state = (); |
446 | %state = (); |
219 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
447 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
220 | }); |
|
|
221 | |
|
|
222 | # send request |
|
|
223 | $state{handle}->push_write ( |
|
|
224 | "$method $path HTTP/1.0\015\012" |
|
|
225 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
|
|
226 | . "\015\012" |
|
|
227 | . (delete $state{body}) |
|
|
228 | ); |
|
|
229 | |
|
|
230 | %hdr = (); # reduce memory usage, save a kitten |
|
|
231 | |
|
|
232 | # status line |
|
|
233 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
234 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
235 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
236 | |
|
|
237 | my %hdr = ( # response headers |
|
|
238 | HTTPVersion => ",$1", |
|
|
239 | Status => ",$2", |
|
|
240 | Reason => ",$3", |
|
|
241 | ); |
448 | }); |
242 | |
449 | |
|
|
450 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
451 | |
|
|
452 | # handle actual, non-tunneled, request |
|
|
453 | my $handle_actual_request = sub { |
|
|
454 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
455 | |
|
|
456 | # send request |
|
|
457 | $state{handle}->push_write ( |
|
|
458 | "$method $rpath HTTP/1.0\015\012" |
|
|
459 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
|
|
460 | . "\015\012" |
|
|
461 | . (delete $arg{body}) |
|
|
462 | ); |
|
|
463 | |
|
|
464 | %hdr = (); # reduce memory usage, save a kitten |
|
|
465 | |
|
|
466 | # status line |
|
|
467 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
468 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
469 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
470 | |
|
|
471 | my %hdr = ( # response headers |
|
|
472 | HTTPVersion => ",$1", |
|
|
473 | Status => ",$2", |
|
|
474 | Reason => ",$3", |
|
|
475 | URL => ",$url" |
|
|
476 | ); |
|
|
477 | |
243 | # headers, could be optimized a bit |
478 | # headers, could be optimized a bit |
244 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
479 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
245 | for ("$_[1]\012") { |
480 | for ("$_[1]\012") { |
246 | # we support spaces in field names, as lotus domino |
481 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
247 | # creates them. |
482 | |
|
|
483 | # things seen, not parsed: |
|
|
484 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
485 | |
248 | $hdr{lc $1} .= ",$2" |
486 | $hdr{lc $1} .= ",$2" |
249 | while /\G |
487 | while /\G |
250 | ([^:\000-\037]+): |
488 | ([^:\000-\037]+): |
251 | [\011\040]* |
489 | [\011\040]* |
252 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
490 | ((?: [^\012]+ | \012[\011\040] )*) |
253 | \015?\012 |
491 | \012 |
254 | /gxc; |
492 | /gxc; |
255 | |
493 | |
256 | /\G$/ |
494 | /\G$/ |
257 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
495 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
258 | } |
496 | } |
259 | |
497 | |
260 | substr $_, 0, 1, "" |
498 | substr $_, 0, 1, "" |
261 | for values %hdr; |
499 | for values %hdr; |
262 | |
500 | |
263 | if ($method eq "HEAD") { |
501 | # redirect handling |
264 | %state = (); |
502 | # microsoft and other shitheads don't give a shit for following standards, |
265 | $cb->(undef, \%hdr); |
503 | # try to support some common forms of broken Location headers. |
266 | } else { |
504 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
267 | if (exists $hdr{"content-length"}) { |
505 | $hdr{location} =~ s/^\.\/+//; |
268 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
506 | |
269 | # could cache persistent connection now |
507 | my $url = "$rscheme://$uhost:$uport"; |
270 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
508 | |
271 | # but we don't, due to misdesigns, this is annoyingly complex |
509 | unless ($hdr{location} =~ s/^\///) { |
|
|
510 | $url .= $upath; |
|
|
511 | $url =~ s/\/[^\/]*$//; |
272 | }; |
512 | } |
273 | |
513 | |
|
|
514 | $hdr{location} = "$url/$hdr{location}"; |
|
|
515 | } |
|
|
516 | |
|
|
517 | my $redirect; |
|
|
518 | |
|
|
519 | if ($recurse) { |
|
|
520 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
|
|
521 | # apparently, mozilla et al. just change POST to GET here |
|
|
522 | # more research is needed before we do the same |
|
|
523 | $redirect = 1; |
|
|
524 | } elsif ($hdr{Status} == 303) { |
|
|
525 | # even http/1.1 is unclear on how to mutate the method |
|
|
526 | $method = "GET" unless $method eq "HEAD"; |
|
|
527 | $redirect = 1; |
|
|
528 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
|
|
529 | $redirect = 1; |
|
|
530 | } |
|
|
531 | } |
|
|
532 | |
|
|
533 | my $finish = sub { |
|
|
534 | $state{handle}->destroy if $state{handle}; |
274 | %state = (); |
535 | %state = (); |
|
|
536 | |
|
|
537 | # set-cookie processing |
|
|
538 | if ($arg{cookie_jar}) { |
|
|
539 | for ($_[1]{"set-cookie"}) { |
|
|
540 | # parse NAME=VALUE |
|
|
541 | my @kv; |
|
|
542 | |
|
|
543 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
544 | my $name = $1; |
|
|
545 | my $value = $3; |
|
|
546 | |
|
|
547 | unless ($value) { |
|
|
548 | $value = $2; |
|
|
549 | $value =~ s/\\(.)/$1/gs; |
|
|
550 | } |
|
|
551 | |
|
|
552 | push @kv, $name => $value; |
|
|
553 | |
|
|
554 | last unless /\G\s*;/gc; |
|
|
555 | } |
|
|
556 | |
|
|
557 | last unless @kv; |
|
|
558 | |
|
|
559 | my $name = shift @kv; |
|
|
560 | my %kv = (value => shift @kv, @kv); |
|
|
561 | |
|
|
562 | my $cdom; |
|
|
563 | my $cpath = (delete $kv{path}) || "/"; |
|
|
564 | |
|
|
565 | if (exists $kv{domain}) { |
|
|
566 | $cdom = delete $kv{domain}; |
|
|
567 | |
|
|
568 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
569 | |
|
|
570 | next if $cdom =~ /\.$/; |
|
|
571 | |
|
|
572 | # this is not rfc-like and not netscape-like. go figure. |
|
|
573 | my $ndots = $cdom =~ y/.//; |
|
|
574 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
575 | } else { |
|
|
576 | $cdom = $uhost; |
|
|
577 | } |
|
|
578 | |
|
|
579 | # store it |
|
|
580 | $arg{cookie_jar}{version} = 1; |
|
|
581 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
582 | |
|
|
583 | redo if /\G\s*,/gc; |
|
|
584 | } |
|
|
585 | } |
|
|
586 | |
|
|
587 | if ($redirect) { |
|
|
588 | # we ignore any errors, as it is very common to receive |
|
|
589 | # Content-Length != 0 but no actual body |
|
|
590 | # we also access %hdr, as $_[1] might be an erro |
|
|
591 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
592 | } else { |
275 | $cb->($_[1], \%hdr); |
593 | $cb->($_[0], $_[1]); |
|
|
594 | } |
276 | }); |
595 | }; |
|
|
596 | |
|
|
597 | my $len = $hdr{"content-length"}; |
|
|
598 | |
|
|
599 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
600 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
|
|
601 | } elsif ( |
|
|
602 | $hdr{Status} =~ /^(?:1..|204|304)$/ |
|
|
603 | or $method eq "HEAD" |
|
|
604 | or (defined $len && !$len) |
|
|
605 | ) { |
|
|
606 | # no body |
|
|
607 | $finish->("", \%hdr); |
|
|
608 | } else { |
|
|
609 | # body handling, four different code paths |
|
|
610 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
611 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
612 | if (!$redirect && $arg{want_body_handle}) { |
|
|
613 | $_[0]->on_eof (undef); |
|
|
614 | $_[0]->on_error (undef); |
|
|
615 | $_[0]->on_read (undef); |
|
|
616 | |
|
|
617 | $finish->(delete $state{handle}, \%hdr); |
|
|
618 | |
|
|
619 | } elsif ($arg{on_body}) { |
|
|
620 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
621 | if ($len) { |
|
|
622 | $_[0]->on_eof (undef); |
|
|
623 | $_[0]->on_read (sub { |
|
|
624 | $len -= length $_[0]{rbuf}; |
|
|
625 | |
|
|
626 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
627 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
628 | |
|
|
629 | $len > 0 |
|
|
630 | or $finish->("", \%hdr); |
|
|
631 | }); |
|
|
632 | } else { |
|
|
633 | $_[0]->on_eof (sub { |
|
|
634 | $finish->("", \%hdr); |
|
|
635 | }); |
|
|
636 | $_[0]->on_read (sub { |
|
|
637 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
638 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
639 | }); |
|
|
640 | } |
|
|
641 | } else { |
|
|
642 | $_[0]->on_eof (undef); |
|
|
643 | |
|
|
644 | if ($len) { |
|
|
645 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
646 | $_[0]->on_read (sub { |
|
|
647 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
648 | if $len <= length $_[0]{rbuf}; |
|
|
649 | }); |
|
|
650 | } else { |
|
|
651 | $_[0]->on_error (sub { |
|
|
652 | $! == Errno::EPIPE |
|
|
653 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
|
|
654 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
655 | }); |
|
|
656 | $_[0]->on_read (sub { }); |
|
|
657 | } |
|
|
658 | } |
|
|
659 | } |
|
|
660 | }); |
|
|
661 | }); |
|
|
662 | }; |
|
|
663 | |
|
|
664 | # now handle proxy-CONNECT method |
|
|
665 | if ($proxy && $uscheme eq "https") { |
|
|
666 | # oh dear, we have to wrap it into a connect request |
|
|
667 | |
|
|
668 | # maybe re-use $uauthority with patched port? |
|
|
669 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
670 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
671 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
672 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
|
|
673 | |
|
|
674 | if ($2 == 200) { |
|
|
675 | $rpath = $upath; |
|
|
676 | &$handle_actual_request; |
277 | } else { |
677 | } else { |
278 | # too bad, need to read until we get an error or EOF, |
|
|
279 | # no way to detect winged data. |
|
|
280 | $_[0]->on_error (sub { |
|
|
281 | %state = (); |
678 | %state = (); |
282 | $cb->($_[0]{rbuf}, \%hdr); |
679 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
283 | }); |
|
|
284 | $_[0]->on_eof (undef); |
|
|
285 | $_[0]->on_read (sub { }); |
|
|
286 | } |
680 | } |
287 | } |
681 | }); |
|
|
682 | } else { |
|
|
683 | &$handle_actual_request; |
288 | }); |
684 | } |
|
|
685 | |
|
|
686 | }, sub { |
|
|
687 | $timeout |
289 | }); |
688 | }; |
290 | }, sub { |
|
|
291 | $timeout |
|
|
292 | }; |
689 | }; |
293 | |
690 | |
294 | defined wantarray && AnyEvent::Util::guard { %state = () } |
691 | defined wantarray && AnyEvent::Util::guard { %state = () } |
295 | } |
692 | } |
296 | |
693 | |
297 | sub http_get($$;@) { |
694 | sub http_get($@) { |
298 | unshift @_, "GET"; |
695 | unshift @_, "GET"; |
299 | &http_request |
696 | &http_request |
300 | } |
697 | } |
301 | |
698 | |
302 | sub http_head($$;@) { |
699 | sub http_head($@) { |
303 | unshift @_, "HEAD"; |
700 | unshift @_, "HEAD"; |
304 | &http_request |
701 | &http_request |
305 | } |
702 | } |
306 | |
703 | |
307 | sub http_post($$$;@) { |
704 | sub http_post($$@) { |
|
|
705 | my $url = shift; |
308 | unshift @_, "POST", "body"; |
706 | unshift @_, "POST", $url, "body"; |
309 | &http_request |
707 | &http_request |
310 | } |
708 | } |
311 | |
709 | |
|
|
710 | =back |
|
|
711 | |
312 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
712 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
313 | |
713 | |
314 | =over 4 |
714 | =over 4 |
315 | |
715 | |
316 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
716 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
… | |
… | |
323 | The default value for the C<recurse> request parameter (default: C<10>). |
723 | The default value for the C<recurse> request parameter (default: C<10>). |
324 | |
724 | |
325 | =item $AnyEvent::HTTP::USERAGENT |
725 | =item $AnyEvent::HTTP::USERAGENT |
326 | |
726 | |
327 | The default value for the C<User-Agent> header (the default is |
727 | The default value for the C<User-Agent> header (the default is |
328 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
728 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
329 | |
729 | |
330 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
730 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
331 | |
731 | |
332 | The maximum number of persistent connections to keep open (default: 8). |
732 | The maximum number of persistent connections to keep open (default: 8). |
333 | |
733 | |
… | |
… | |
336 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
736 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
337 | |
737 | |
338 | The maximum time to cache a persistent connection, in seconds (default: 2). |
738 | The maximum time to cache a persistent connection, in seconds (default: 2). |
339 | |
739 | |
340 | Not implemented currently. |
740 | Not implemented currently. |
|
|
741 | |
|
|
742 | =item $AnyEvent::HTTP::ACTIVE |
|
|
743 | |
|
|
744 | The number of active connections. This is not the number of currently |
|
|
745 | running requests, but the number of currently open and non-idle TCP |
|
|
746 | connections. This number of can be useful for load-leveling. |
341 | |
747 | |
342 | =back |
748 | =back |
343 | |
749 | |
344 | =cut |
750 | =cut |
345 | |
751 | |
… | |
… | |
354 | |
760 | |
355 | L<AnyEvent>. |
761 | L<AnyEvent>. |
356 | |
762 | |
357 | =head1 AUTHOR |
763 | =head1 AUTHOR |
358 | |
764 | |
359 | Marc Lehmann <schmorp@schmorp.de> |
765 | Marc Lehmann <schmorp@schmorp.de> |
360 | http://home.schmorp.de/ |
766 | http://home.schmorp.de/ |
|
|
767 | |
|
|
768 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
769 | testcases and bugreports. |
361 | |
770 | |
362 | =cut |
771 | =cut |
363 | |
772 | |
364 | 1 |
773 | 1 |
365 | |
774 | |