1 |
root |
1.1 |
=head1 NAME |
2 |
|
|
|
3 |
|
|
AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client |
4 |
|
|
|
5 |
|
|
=head1 SYNOPSIS |
6 |
|
|
|
7 |
|
|
use AnyEvent::HTTP; |
8 |
|
|
|
9 |
root |
1.17 |
http_get "http://www.nethype.de/", sub { print $_[1] }; |
10 |
|
|
|
11 |
|
|
# ... do something else here |
12 |
|
|
|
13 |
root |
1.1 |
=head1 DESCRIPTION |
14 |
|
|
|
15 |
|
|
This module is an L<AnyEvent> user, you need to make sure that you use and |
16 |
|
|
run a supported event loop. |
17 |
|
|
|
18 |
root |
1.11 |
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 |
|
|
|
33 |
root |
1.1 |
=head2 METHODS |
34 |
|
|
|
35 |
|
|
=over 4 |
36 |
|
|
|
37 |
|
|
=cut |
38 |
|
|
|
39 |
|
|
package AnyEvent::HTTP; |
40 |
|
|
|
41 |
|
|
use strict; |
42 |
|
|
no warnings; |
43 |
|
|
|
44 |
|
|
use Carp; |
45 |
|
|
|
46 |
|
|
use AnyEvent (); |
47 |
|
|
use AnyEvent::Util (); |
48 |
|
|
use AnyEvent::Socket (); |
49 |
|
|
use AnyEvent::Handle (); |
50 |
|
|
|
51 |
|
|
use base Exporter::; |
52 |
|
|
|
53 |
root |
1.28 |
our $VERSION = '1.05'; |
54 |
root |
1.1 |
|
55 |
root |
1.17 |
our @EXPORT = qw(http_get http_post http_head http_request); |
56 |
root |
1.1 |
|
57 |
|
|
our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 |
root |
1.3 |
our $MAX_RECURSE = 10; |
59 |
root |
1.2 |
our $MAX_PERSISTENT = 8; |
60 |
|
|
our $PERSISTENT_TIMEOUT = 2; |
61 |
|
|
our $TIMEOUT = 300; |
62 |
root |
1.1 |
|
63 |
|
|
# changing these is evil |
64 |
|
|
our $MAX_PERSISTENT_PER_HOST = 2; |
65 |
root |
1.11 |
our $MAX_PER_HOST = 4; |
66 |
root |
1.1 |
|
67 |
root |
1.2 |
our $PROXY; |
68 |
root |
1.14 |
our $ACTIVE = 0; |
69 |
root |
1.2 |
|
70 |
root |
1.1 |
my %KA_COUNT; # number of open keep-alive connections per host |
71 |
root |
1.11 |
my %CO_SLOT; # number of open connections, and wait queue, per host |
72 |
root |
1.1 |
|
73 |
|
|
=item http_get $url, key => value..., $cb->($data, $headers) |
74 |
|
|
|
75 |
|
|
Executes an HTTP-GET request. See the http_request function for details on |
76 |
root |
1.29 |
additional parameters and the return value. |
77 |
root |
1.1 |
|
78 |
root |
1.5 |
=item http_head $url, key => value..., $cb->($data, $headers) |
79 |
|
|
|
80 |
root |
1.29 |
Executes an HTTP-HEAD request. See the http_request function for details |
81 |
|
|
on additional parameters and the return value. |
82 |
root |
1.5 |
|
83 |
|
|
=item http_post $url, $body, key => value..., $cb->($data, $headers) |
84 |
root |
1.3 |
|
85 |
root |
1.26 |
Executes an HTTP-POST request with a request body of C<$body>. See the |
86 |
root |
1.29 |
http_request function for details on additional parameters and the return |
87 |
|
|
value. |
88 |
root |
1.3 |
|
89 |
root |
1.1 |
=item http_request $method => $url, key => value..., $cb->($data, $headers) |
90 |
|
|
|
91 |
|
|
Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
92 |
|
|
must be an absolute http or https URL. |
93 |
|
|
|
94 |
root |
1.29 |
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. |
98 |
|
|
|
99 |
root |
1.2 |
The callback will be called with the response data as first argument |
100 |
|
|
(or C<undef> if it wasn't available due to errors), and a hash-ref with |
101 |
|
|
response headers as second argument. |
102 |
|
|
|
103 |
root |
1.7 |
All the headers in that hash are lowercased. In addition to the response |
104 |
root |
1.20 |
headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
105 |
|
|
contain the three parts of the HTTP Status-Line of the same name. The |
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 lines, then their contents will be |
110 |
|
|
joined together with C<\x00>. |
111 |
root |
1.2 |
|
112 |
|
|
If an internal error occurs, such as not being able to resolve a hostname, |
113 |
|
|
then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
114 |
|
|
and the C<Reason> pseudo-header will contain an error message. |
115 |
|
|
|
116 |
root |
1.6 |
A typical callback might look like this: |
117 |
|
|
|
118 |
|
|
sub { |
119 |
|
|
my ($body, $hdr) = @_; |
120 |
|
|
|
121 |
|
|
if ($hdr->{Status} =~ /^2/) { |
122 |
|
|
... everything should be ok |
123 |
|
|
} else { |
124 |
|
|
print "error, $hdr->{Status} $hdr->{Reason}\n"; |
125 |
|
|
} |
126 |
|
|
} |
127 |
|
|
|
128 |
root |
1.1 |
Additional parameters are key-value pairs, and are fully optional. They |
129 |
|
|
include: |
130 |
|
|
|
131 |
|
|
=over 4 |
132 |
|
|
|
133 |
root |
1.3 |
=item recurse => $count (default: $MAX_RECURSE) |
134 |
root |
1.1 |
|
135 |
|
|
Whether to recurse requests or not, e.g. on redirects, authentication |
136 |
root |
1.3 |
retries and so on, and how often to do so. |
137 |
root |
1.1 |
|
138 |
|
|
=item headers => hashref |
139 |
|
|
|
140 |
root |
1.12 |
The request headers to use. Currently, C<http_request> may provide its |
141 |
|
|
own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
142 |
|
|
and will provide defaults for C<User-Agent:> and C<Referer:>. |
143 |
root |
1.1 |
|
144 |
|
|
=item timeout => $seconds |
145 |
|
|
|
146 |
|
|
The time-out to use for various stages - each connect attempt will reset |
147 |
root |
1.2 |
the timeout, as will read or write activity. Default timeout is 5 minutes. |
148 |
|
|
|
149 |
|
|
=item proxy => [$host, $port[, $scheme]] or undef |
150 |
|
|
|
151 |
|
|
Use the given http proxy for all requests. If not specified, then the |
152 |
|
|
default proxy (as specified by C<$ENV{http_proxy}>) is used. |
153 |
|
|
|
154 |
|
|
C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
155 |
|
|
HTTPS. |
156 |
root |
1.1 |
|
157 |
root |
1.3 |
=item body => $string |
158 |
|
|
|
159 |
|
|
The request body, usually empty. Will be-sent as-is (future versions of |
160 |
|
|
this module might offer more options). |
161 |
|
|
|
162 |
root |
1.10 |
=item cookie_jar => $hash_ref |
163 |
|
|
|
164 |
|
|
Passing this parameter enables (simplified) cookie-processing, loosely |
165 |
|
|
based on the original netscape specification. |
166 |
|
|
|
167 |
|
|
The C<$hash_ref> must be an (initially empty) hash reference which will |
168 |
|
|
get updated automatically. It is possible to save the cookie_jar to |
169 |
|
|
persistent storage with something like JSON or Storable, but this is not |
170 |
|
|
recommended, as expire times are currently being ignored. |
171 |
|
|
|
172 |
|
|
Note that this cookie implementation is not of very high quality, nor |
173 |
|
|
meant to be complete. If you want complete cookie management you have to |
174 |
|
|
do that on your own. C<cookie_jar> is meant as a quick fix to get some |
175 |
|
|
cookie-using sites working. Cookies are a privacy disaster, do not use |
176 |
|
|
them unless required to. |
177 |
|
|
|
178 |
root |
1.1 |
=back |
179 |
|
|
|
180 |
root |
1.9 |
Example: make a simple HTTP GET request for http://www.nethype.de/ |
181 |
|
|
|
182 |
|
|
http_request GET => "http://www.nethype.de/", sub { |
183 |
|
|
my ($body, $hdr) = @_; |
184 |
|
|
print "$body\n"; |
185 |
|
|
}; |
186 |
|
|
|
187 |
|
|
Example: make a HTTP HEAD request on https://www.google.com/, use a |
188 |
|
|
timeout of 30 seconds. |
189 |
|
|
|
190 |
|
|
http_request |
191 |
|
|
GET => "https://www.google.com", |
192 |
|
|
timeout => 30, |
193 |
|
|
sub { |
194 |
|
|
my ($body, $hdr) = @_; |
195 |
|
|
use Data::Dumper; |
196 |
|
|
print Dumper $hdr; |
197 |
|
|
} |
198 |
|
|
; |
199 |
root |
1.1 |
|
200 |
root |
1.29 |
Example: make another simple HTTP GET request, but immediately try to |
201 |
|
|
cancel it. |
202 |
|
|
|
203 |
|
|
my $request = http_request GET => "http://www.nethype.de/", sub { |
204 |
|
|
my ($body, $hdr) = @_; |
205 |
|
|
print "$body\n"; |
206 |
|
|
}; |
207 |
|
|
|
208 |
|
|
undef $request; |
209 |
|
|
|
210 |
root |
1.1 |
=cut |
211 |
|
|
|
212 |
root |
1.12 |
sub _slot_schedule; |
213 |
root |
1.11 |
sub _slot_schedule($) { |
214 |
|
|
my $host = shift; |
215 |
|
|
|
216 |
|
|
while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
217 |
|
|
if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
218 |
root |
1.12 |
# somebody wants that slot |
219 |
root |
1.11 |
++$CO_SLOT{$host}[0]; |
220 |
root |
1.14 |
++$ACTIVE; |
221 |
root |
1.11 |
|
222 |
|
|
$cb->(AnyEvent::Util::guard { |
223 |
root |
1.14 |
--$ACTIVE; |
224 |
root |
1.11 |
--$CO_SLOT{$host}[0]; |
225 |
|
|
_slot_schedule $host; |
226 |
|
|
}); |
227 |
|
|
} else { |
228 |
|
|
# nobody wants the slot, maybe we can forget about it |
229 |
|
|
delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; |
230 |
|
|
last; |
231 |
|
|
} |
232 |
|
|
} |
233 |
|
|
} |
234 |
|
|
|
235 |
|
|
# wait for a free slot on host, call callback |
236 |
|
|
sub _get_slot($$) { |
237 |
|
|
push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
238 |
|
|
|
239 |
|
|
_slot_schedule $_[0]; |
240 |
|
|
} |
241 |
|
|
|
242 |
elmex |
1.15 |
sub http_request($$@) { |
243 |
root |
1.1 |
my $cb = pop; |
244 |
|
|
my ($method, $url, %arg) = @_; |
245 |
|
|
|
246 |
|
|
my %hdr; |
247 |
|
|
|
248 |
root |
1.3 |
$method = uc $method; |
249 |
|
|
|
250 |
root |
1.8 |
if (my $hdr = $arg{headers}) { |
251 |
root |
1.1 |
while (my ($k, $v) = each %$hdr) { |
252 |
|
|
$hdr{lc $k} = $v; |
253 |
|
|
} |
254 |
|
|
} |
255 |
|
|
|
256 |
root |
1.23 |
my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
257 |
root |
1.8 |
|
258 |
elmex |
1.19 |
return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
259 |
root |
1.8 |
if $recurse < 0; |
260 |
|
|
|
261 |
root |
1.2 |
my $proxy = $arg{proxy} || $PROXY; |
262 |
root |
1.1 |
my $timeout = $arg{timeout} || $TIMEOUT; |
263 |
|
|
|
264 |
|
|
$hdr{"user-agent"} ||= $USERAGENT; |
265 |
|
|
|
266 |
root |
1.10 |
my ($scheme, $authority, $upath, $query, $fragment) = |
267 |
|
|
$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
268 |
root |
1.2 |
|
269 |
root |
1.10 |
$scheme = lc $scheme; |
270 |
root |
1.1 |
|
271 |
root |
1.10 |
my $uport = $scheme eq "http" ? 80 |
272 |
|
|
: $scheme eq "https" ? 443 |
273 |
elmex |
1.19 |
: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
274 |
root |
1.10 |
|
275 |
root |
1.13 |
$hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
276 |
|
|
|
277 |
root |
1.10 |
$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
278 |
elmex |
1.19 |
or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
279 |
root |
1.10 |
|
280 |
|
|
my $uhost = $1; |
281 |
|
|
$uport = $2 if defined $2; |
282 |
|
|
|
283 |
|
|
$uhost =~ s/^\[(.*)\]$/$1/; |
284 |
|
|
$upath .= "?$query" if length $query; |
285 |
|
|
|
286 |
|
|
$upath =~ s%^/?%/%; |
287 |
|
|
|
288 |
|
|
# cookie processing |
289 |
|
|
if (my $jar = $arg{cookie_jar}) { |
290 |
|
|
%$jar = () if $jar->{version} < 1; |
291 |
|
|
|
292 |
|
|
my @cookie; |
293 |
|
|
|
294 |
|
|
while (my ($chost, $v) = each %$jar) { |
295 |
|
|
next unless $chost eq substr $uhost, -length $chost; |
296 |
|
|
next unless $chost =~ /^\./; |
297 |
|
|
|
298 |
|
|
while (my ($cpath, $v) = each %$v) { |
299 |
|
|
next unless $cpath eq substr $upath, 0, length $cpath; |
300 |
|
|
|
301 |
|
|
while (my ($k, $v) = each %$v) { |
302 |
|
|
next if $scheme ne "https" && exists $v->{secure}; |
303 |
|
|
push @cookie, "$k=$v->{value}"; |
304 |
|
|
} |
305 |
|
|
} |
306 |
|
|
} |
307 |
|
|
|
308 |
|
|
$hdr{cookie} = join "; ", @cookie |
309 |
|
|
if @cookie; |
310 |
|
|
} |
311 |
root |
1.1 |
|
312 |
root |
1.10 |
my ($rhost, $rport, $rpath); # request host, port, path |
313 |
root |
1.2 |
|
314 |
root |
1.10 |
if ($proxy) { |
315 |
|
|
($rhost, $rport, $scheme) = @$proxy; |
316 |
|
|
$rpath = $url; |
317 |
|
|
} else { |
318 |
|
|
($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
319 |
|
|
$hdr{host} = $uhost; |
320 |
root |
1.2 |
} |
321 |
|
|
|
322 |
root |
1.10 |
$hdr{"content-length"} = length $arg{body}; |
323 |
root |
1.1 |
|
324 |
root |
1.11 |
my %state = (connect_guard => 1); |
325 |
|
|
|
326 |
|
|
_get_slot $uhost, sub { |
327 |
|
|
$state{slot_guard} = shift; |
328 |
root |
1.1 |
|
329 |
root |
1.11 |
return unless $state{connect_guard}; |
330 |
root |
1.1 |
|
331 |
root |
1.11 |
$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
332 |
|
|
$state{fh} = shift |
333 |
elmex |
1.19 |
or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
334 |
root |
1.11 |
|
335 |
|
|
delete $state{connect_guard}; # reduce memory usage, save a tree |
336 |
|
|
|
337 |
|
|
# get handle |
338 |
|
|
$state{handle} = new AnyEvent::Handle |
339 |
|
|
fh => $state{fh}, |
340 |
|
|
($scheme eq "https" ? (tls => "connect") : ()); |
341 |
|
|
|
342 |
|
|
# limit the number of persistent connections |
343 |
|
|
if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
344 |
|
|
++$KA_COUNT{$_[1]}; |
345 |
|
|
$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
346 |
|
|
$hdr{connection} = "keep-alive"; |
347 |
|
|
delete $hdr{connection}; # keep-alive not yet supported |
348 |
|
|
} else { |
349 |
|
|
delete $hdr{connection}; |
350 |
|
|
} |
351 |
root |
1.1 |
|
352 |
root |
1.11 |
# (re-)configure handle |
353 |
|
|
$state{handle}->timeout ($timeout); |
354 |
|
|
$state{handle}->on_error (sub { |
355 |
root |
1.14 |
my $errno = "$!"; |
356 |
root |
1.11 |
%state = (); |
357 |
elmex |
1.19 |
$cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
358 |
root |
1.11 |
}); |
359 |
|
|
$state{handle}->on_eof (sub { |
360 |
|
|
%state = (); |
361 |
elmex |
1.19 |
$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
362 |
root |
1.11 |
}); |
363 |
root |
1.1 |
|
364 |
root |
1.11 |
# send request |
365 |
|
|
$state{handle}->push_write ( |
366 |
|
|
"$method $rpath HTTP/1.0\015\012" |
367 |
|
|
. (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
368 |
|
|
. "\015\012" |
369 |
|
|
. (delete $arg{body}) |
370 |
|
|
); |
371 |
root |
1.1 |
|
372 |
root |
1.11 |
%hdr = (); # reduce memory usage, save a kitten |
373 |
root |
1.1 |
|
374 |
root |
1.11 |
# status line |
375 |
|
|
$state{handle}->push_read (line => qr/\015?\012/, sub { |
376 |
root |
1.25 |
$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
377 |
elmex |
1.19 |
or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
378 |
root |
1.11 |
|
379 |
|
|
my %hdr = ( # response headers |
380 |
|
|
HTTPVersion => "\x00$1", |
381 |
|
|
Status => "\x00$2", |
382 |
|
|
Reason => "\x00$3", |
383 |
elmex |
1.19 |
URL => "\x00$url" |
384 |
root |
1.11 |
); |
385 |
|
|
|
386 |
|
|
# headers, could be optimized a bit |
387 |
|
|
$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
388 |
|
|
for ("$_[1]\012") { |
389 |
|
|
# we support spaces in field names, as lotus domino |
390 |
|
|
# creates them. |
391 |
|
|
$hdr{lc $1} .= "\x00$2" |
392 |
|
|
while /\G |
393 |
|
|
([^:\000-\037]+): |
394 |
|
|
[\011\040]* |
395 |
|
|
((?: [^\015\012]+ | \015?\012[\011\040] )*) |
396 |
|
|
\015?\012 |
397 |
|
|
/gxc; |
398 |
root |
1.10 |
|
399 |
root |
1.11 |
/\G$/ |
400 |
elmex |
1.19 |
or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
401 |
root |
1.10 |
} |
402 |
|
|
|
403 |
root |
1.11 |
substr $_, 0, 1, "" |
404 |
|
|
for values %hdr; |
405 |
|
|
|
406 |
|
|
my $finish = sub { |
407 |
|
|
%state = (); |
408 |
root |
1.10 |
|
409 |
root |
1.11 |
# set-cookie processing |
410 |
|
|
if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
411 |
|
|
for (split /\x00/, $hdr{"set-cookie"}) { |
412 |
|
|
my ($cookie, @arg) = split /;\s*/; |
413 |
|
|
my ($name, $value) = split /=/, $cookie, 2; |
414 |
|
|
my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
415 |
|
|
|
416 |
|
|
my $cdom = (delete $kv{domain}) || $uhost; |
417 |
|
|
my $cpath = (delete $kv{path}) || "/"; |
418 |
|
|
|
419 |
root |
1.28 |
$cdom =~ s/^\.?/./; # make sure it starts with a "." |
420 |
root |
1.11 |
|
421 |
|
|
next if $cdom =~ /\.$/; |
422 |
|
|
|
423 |
|
|
# this is not rfc-like and not netscape-like. go figure. |
424 |
|
|
my $ndots = $cdom =~ y/.//; |
425 |
|
|
next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
426 |
|
|
|
427 |
|
|
# store it |
428 |
|
|
$arg{cookie_jar}{version} = 1; |
429 |
|
|
$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
430 |
|
|
} |
431 |
|
|
} |
432 |
root |
1.8 |
|
433 |
root |
1.25 |
# microsoft and other shitheads don't give a shit for following standards, |
434 |
|
|
# try to support some common forms of broken Location headers. |
435 |
|
|
if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
436 |
|
|
$_[1]{location} =~ s/^\.\/+//; |
437 |
|
|
|
438 |
|
|
my $url = "$scheme://$uhost:$uport"; |
439 |
|
|
|
440 |
|
|
unless ($_[1]{location} =~ s/^\///) { |
441 |
|
|
$url .= $upath; |
442 |
|
|
$url =~ s/\/[^\/]*$//; |
443 |
|
|
} |
444 |
|
|
|
445 |
|
|
$_[1]{location} = "$url/$_[1]{location}"; |
446 |
|
|
} |
447 |
root |
1.24 |
|
448 |
root |
1.23 |
if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
449 |
|
|
# apparently, mozilla et al. just change POST to GET here |
450 |
|
|
# more research is needed before we do the same |
451 |
root |
1.11 |
http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
452 |
root |
1.23 |
} elsif ($_[1]{Status} == 303 && $recurse) { |
453 |
root |
1.24 |
# even http/1.1 is unlear on how to mutate the method |
454 |
|
|
$method = "GET" unless $method eq "HEAD"; |
455 |
|
|
http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
456 |
|
|
} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
457 |
|
|
http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
458 |
root |
1.11 |
} else { |
459 |
|
|
$cb->($_[0], $_[1]); |
460 |
|
|
} |
461 |
|
|
}; |
462 |
root |
1.3 |
|
463 |
root |
1.11 |
if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
464 |
|
|
$finish->(undef, \%hdr); |
465 |
root |
1.3 |
} else { |
466 |
root |
1.11 |
if (exists $hdr{"content-length"}) { |
467 |
|
|
$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
468 |
|
|
# could cache persistent connection now |
469 |
|
|
if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
470 |
|
|
# but we don't, due to misdesigns, this is annoyingly complex |
471 |
|
|
}; |
472 |
|
|
|
473 |
|
|
$finish->($_[1], \%hdr); |
474 |
|
|
}); |
475 |
|
|
} else { |
476 |
|
|
# too bad, need to read until we get an error or EOF, |
477 |
|
|
# no way to detect winged data. |
478 |
|
|
$_[0]->on_error (sub { |
479 |
|
|
$finish->($_[0]{rbuf}, \%hdr); |
480 |
|
|
}); |
481 |
|
|
$_[0]->on_eof (undef); |
482 |
|
|
$_[0]->on_read (sub { }); |
483 |
|
|
} |
484 |
root |
1.3 |
} |
485 |
root |
1.11 |
}); |
486 |
root |
1.1 |
}); |
487 |
root |
1.11 |
}, sub { |
488 |
|
|
$timeout |
489 |
|
|
}; |
490 |
root |
1.1 |
}; |
491 |
|
|
|
492 |
|
|
defined wantarray && AnyEvent::Util::guard { %state = () } |
493 |
|
|
} |
494 |
|
|
|
495 |
elmex |
1.15 |
sub http_get($@) { |
496 |
root |
1.1 |
unshift @_, "GET"; |
497 |
|
|
&http_request |
498 |
|
|
} |
499 |
|
|
|
500 |
elmex |
1.15 |
sub http_head($@) { |
501 |
root |
1.4 |
unshift @_, "HEAD"; |
502 |
|
|
&http_request |
503 |
|
|
} |
504 |
|
|
|
505 |
elmex |
1.15 |
sub http_post($$@) { |
506 |
root |
1.22 |
my $url = shift; |
507 |
|
|
unshift @_, "POST", $url, "body"; |
508 |
root |
1.3 |
&http_request |
509 |
|
|
} |
510 |
|
|
|
511 |
root |
1.9 |
=back |
512 |
|
|
|
513 |
root |
1.2 |
=head2 GLOBAL FUNCTIONS AND VARIABLES |
514 |
root |
1.1 |
|
515 |
|
|
=over 4 |
516 |
|
|
|
517 |
root |
1.2 |
=item AnyEvent::HTTP::set_proxy "proxy-url" |
518 |
|
|
|
519 |
|
|
Sets the default proxy server to use. The proxy-url must begin with a |
520 |
|
|
string of the form C<http://host:port> (optionally C<https:...>). |
521 |
|
|
|
522 |
root |
1.3 |
=item $AnyEvent::HTTP::MAX_RECURSE |
523 |
root |
1.1 |
|
524 |
root |
1.3 |
The default value for the C<recurse> request parameter (default: C<10>). |
525 |
root |
1.1 |
|
526 |
|
|
=item $AnyEvent::HTTP::USERAGENT |
527 |
|
|
|
528 |
|
|
The default value for the C<User-Agent> header (the default is |
529 |
|
|
C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
530 |
|
|
|
531 |
|
|
=item $AnyEvent::HTTP::MAX_PERSISTENT |
532 |
|
|
|
533 |
|
|
The maximum number of persistent connections to keep open (default: 8). |
534 |
|
|
|
535 |
root |
1.3 |
Not implemented currently. |
536 |
|
|
|
537 |
root |
1.1 |
=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
538 |
|
|
|
539 |
root |
1.2 |
The maximum time to cache a persistent connection, in seconds (default: 2). |
540 |
root |
1.1 |
|
541 |
root |
1.3 |
Not implemented currently. |
542 |
|
|
|
543 |
root |
1.14 |
=item $AnyEvent::HTTP::ACTIVE |
544 |
|
|
|
545 |
|
|
The number of active connections. This is not the number of currently |
546 |
|
|
running requests, but the number of currently open and non-idle TCP |
547 |
|
|
connections. This number of can be useful for load-leveling. |
548 |
|
|
|
549 |
root |
1.1 |
=back |
550 |
|
|
|
551 |
|
|
=cut |
552 |
|
|
|
553 |
root |
1.2 |
sub set_proxy($) { |
554 |
|
|
$PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
555 |
|
|
} |
556 |
|
|
|
557 |
|
|
# initialise proxy from environment |
558 |
|
|
set_proxy $ENV{http_proxy}; |
559 |
|
|
|
560 |
root |
1.1 |
=head1 SEE ALSO |
561 |
|
|
|
562 |
|
|
L<AnyEvent>. |
563 |
|
|
|
564 |
|
|
=head1 AUTHOR |
565 |
|
|
|
566 |
root |
1.18 |
Marc Lehmann <schmorp@schmorp.de> |
567 |
|
|
http://home.schmorp.de/ |
568 |
root |
1.1 |
|
569 |
|
|
=cut |
570 |
|
|
|
571 |
|
|
1 |
572 |
|
|
|