| 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 |
http_get "http://www.nethype.de/", sub { print $_[1] }; |
| 10 |
|
| 11 |
# ... do something else here |
| 12 |
|
| 13 |
=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 |
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 |
=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 |
our $VERSION = '1.05'; |
| 54 |
|
| 55 |
our @EXPORT = qw(http_get http_post http_head http_request); |
| 56 |
|
| 57 |
our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
| 58 |
our $MAX_RECURSE = 10; |
| 59 |
our $MAX_PERSISTENT = 8; |
| 60 |
our $PERSISTENT_TIMEOUT = 2; |
| 61 |
our $TIMEOUT = 300; |
| 62 |
|
| 63 |
# changing these is evil |
| 64 |
our $MAX_PERSISTENT_PER_HOST = 2; |
| 65 |
our $MAX_PER_HOST = 4; |
| 66 |
|
| 67 |
our $PROXY; |
| 68 |
our $ACTIVE = 0; |
| 69 |
|
| 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 |
| 72 |
|
| 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 |
additional parameters and the return value. |
| 77 |
|
| 78 |
=item http_head $url, key => value..., $cb->($data, $headers) |
| 79 |
|
| 80 |
Executes an HTTP-HEAD request. See the http_request function for details |
| 81 |
on additional parameters and the return value. |
| 82 |
|
| 83 |
=item http_post $url, $body, key => value..., $cb->($data, $headers) |
| 84 |
|
| 85 |
Executes an HTTP-POST request with a request body of C<$body>. See the |
| 86 |
http_request function for details on additional parameters and the return |
| 87 |
value. |
| 88 |
|
| 89 |
=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 |
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 |
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 |
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> |
| 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 times, then their contents will be |
| 110 |
joined together with a comma (C<,>), as per the HTTP spec. |
| 111 |
|
| 112 |
If an internal error occurs, such as not being able to resolve a hostname, |
| 113 |
then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
| 114 |
and the C<Reason> pseudo-header will contain an error message. |
| 115 |
|
| 116 |
A typical callback might look like this: |
| 117 |
|
| 118 |
sub { |
| 119 |
my ($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 |
Additional parameters are key-value pairs, and are fully optional. They |
| 129 |
include: |
| 130 |
|
| 131 |
=over 4 |
| 132 |
|
| 133 |
=item recurse => $count (default: $MAX_RECURSE) |
| 134 |
|
| 135 |
Whether to recurse requests or not, e.g. on redirects, authentication |
| 136 |
retries and so on, and how often to do so. |
| 137 |
|
| 138 |
=item headers => hashref |
| 139 |
|
| 140 |
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 |
|
| 144 |
=item timeout => $seconds |
| 145 |
|
| 146 |
The time-out to use for various stages - each connect attempt will reset |
| 147 |
the timeout, as will read or write activity. Default timeout is 5 minutes. |
| 148 |
|
| 149 |
=item proxy => [$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 |
|
| 157 |
=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 |
=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 |
=back |
| 179 |
|
| 180 |
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 |
|
| 200 |
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 $request; |
| 209 |
|
| 210 |
=cut |
| 211 |
|
| 212 |
sub _slot_schedule; |
| 213 |
sub _slot_schedule($) { |
| 214 |
my $host = shift; |
| 215 |
|
| 216 |
while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
| 217 |
if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
| 218 |
# somebody wants that slot |
| 219 |
++$CO_SLOT{$host}[0]; |
| 220 |
++$ACTIVE; |
| 221 |
|
| 222 |
$cb->(AnyEvent::Util::guard { |
| 223 |
--$ACTIVE; |
| 224 |
--$CO_SLOT{$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($$) { |
| 237 |
push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
| 238 |
|
| 239 |
_slot_schedule $_[0]; |
| 240 |
} |
| 241 |
|
| 242 |
our $qr_nl = qr<\015?\012>; |
| 243 |
our $qr_nlnl = qr<\015?\012\015?\012>; |
| 244 |
|
| 245 |
sub http_request($$@) { |
| 246 |
my $cb = pop; |
| 247 |
my ($method, $url, %arg) = @_; |
| 248 |
|
| 249 |
my %hdr; |
| 250 |
|
| 251 |
$method = uc $method; |
| 252 |
|
| 253 |
if (my $hdr = $arg{headers}) { |
| 254 |
while (my ($k, $v) = each %$hdr) { |
| 255 |
$hdr{lc $k} = $v; |
| 256 |
} |
| 257 |
} |
| 258 |
|
| 259 |
my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
| 260 |
|
| 261 |
return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
| 262 |
if $recurse < 0; |
| 263 |
|
| 264 |
my $proxy = $arg{proxy} || $PROXY; |
| 265 |
my $timeout = $arg{timeout} || $TIMEOUT; |
| 266 |
|
| 267 |
$hdr{"user-agent"} ||= $USERAGENT; |
| 268 |
|
| 269 |
my ($uscheme, $uauthority, $upath, $query, $fragment) = |
| 270 |
$url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
| 271 |
|
| 272 |
$uscheme = lc $uscheme; |
| 273 |
|
| 274 |
my $uport = $uscheme eq "http" ? 80 |
| 275 |
: $uscheme eq "https" ? 443 |
| 276 |
: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
| 277 |
|
| 278 |
$hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
| 279 |
|
| 280 |
$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
| 281 |
or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
| 282 |
|
| 283 |
my $uhost = $1; |
| 284 |
$uport = $2 if defined $2; |
| 285 |
|
| 286 |
$uhost =~ s/^\[(.*)\]$/$1/; |
| 287 |
$upath .= "?$query" if length $query; |
| 288 |
|
| 289 |
$upath =~ s%^/?%/%; |
| 290 |
|
| 291 |
# cookie processing |
| 292 |
if (my $jar = $arg{cookie_jar}) { |
| 293 |
%$jar = () if $jar->{version} != 1; |
| 294 |
|
| 295 |
my @cookie; |
| 296 |
|
| 297 |
while (my ($chost, $v) = each %$jar) { |
| 298 |
if ($chost =~ /^\./) { |
| 299 |
next unless $chost eq substr $uhost, -length $chost; |
| 300 |
} elsif ($chost =~ /\./) { |
| 301 |
next unless $chost eq $uhost; |
| 302 |
} else { |
| 303 |
next; |
| 304 |
} |
| 305 |
|
| 306 |
while (my ($cpath, $v) = each %$v) { |
| 307 |
next unless $cpath eq substr $upath, 0, length $cpath; |
| 308 |
|
| 309 |
while (my ($k, $v) = each %$v) { |
| 310 |
next if $uscheme ne "https" && exists $v->{secure}; |
| 311 |
my $value = $v->{value}; |
| 312 |
$value =~ s/([\\"])/\\$1/g; |
| 313 |
push @cookie, "$k=\"$value\""; |
| 314 |
} |
| 315 |
} |
| 316 |
} |
| 317 |
|
| 318 |
$hdr{cookie} = join "; ", @cookie |
| 319 |
if @cookie; |
| 320 |
} |
| 321 |
|
| 322 |
my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
| 323 |
|
| 324 |
if ($proxy) { |
| 325 |
($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url); |
| 326 |
|
| 327 |
# don't support https requests over https-proxy transport, |
| 328 |
# can't be done with tls as spec'ed. |
| 329 |
$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
| 330 |
} else { |
| 331 |
($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
| 332 |
} |
| 333 |
|
| 334 |
$hdr{host} = $uhost; |
| 335 |
$hdr{"content-length"} = length $arg{body}; |
| 336 |
|
| 337 |
my %state = (connect_guard => 1); |
| 338 |
|
| 339 |
_get_slot $uhost, sub { |
| 340 |
$state{slot_guard} = shift; |
| 341 |
|
| 342 |
return unless $state{connect_guard}; |
| 343 |
|
| 344 |
$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
| 345 |
$state{fh} = shift |
| 346 |
or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
| 347 |
pop; # free memory, save a tree |
| 348 |
|
| 349 |
return unless delete $state{connect_guard}; |
| 350 |
|
| 351 |
# get handle |
| 352 |
$state{handle} = new AnyEvent::Handle |
| 353 |
fh => $state{fh}, |
| 354 |
timeout => $timeout; |
| 355 |
|
| 356 |
# limit the number of persistent connections |
| 357 |
# keepalive not yet supported |
| 358 |
if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
| 359 |
++$KA_COUNT{$_[1]}; |
| 360 |
$state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
| 361 |
--$KA_COUNT{$_[1]} |
| 362 |
}; |
| 363 |
$hdr{connection} = "keep-alive"; |
| 364 |
} else { |
| 365 |
delete $hdr{connection}; |
| 366 |
} |
| 367 |
|
| 368 |
# (re-)configure handle |
| 369 |
$state{handle}->on_error (sub { |
| 370 |
my $errno = "$!"; |
| 371 |
%state = (); |
| 372 |
$cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
| 373 |
}); |
| 374 |
$state{handle}->on_eof (sub { |
| 375 |
%state = (); |
| 376 |
$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
| 377 |
}); |
| 378 |
|
| 379 |
$state{handle}->starttls ("connect") if $rscheme eq "https"; |
| 380 |
|
| 381 |
# handle actual, non-tunneled, request |
| 382 |
my $handle_actual_request = sub { |
| 383 |
$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
| 384 |
|
| 385 |
# send request |
| 386 |
$state{handle}->push_write ( |
| 387 |
"$method $rpath HTTP/1.0\015\012" |
| 388 |
. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
| 389 |
. "\015\012" |
| 390 |
. (delete $arg{body}) |
| 391 |
); |
| 392 |
|
| 393 |
%hdr = (); # reduce memory usage, save a kitten |
| 394 |
|
| 395 |
# status line |
| 396 |
$state{handle}->push_read (line => $qr_nl, sub { |
| 397 |
$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
| 398 |
or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
| 399 |
|
| 400 |
my %hdr = ( # response headers |
| 401 |
HTTPVersion => ",$1", |
| 402 |
Status => ",$2", |
| 403 |
Reason => ",$3", |
| 404 |
URL => ",$url" |
| 405 |
); |
| 406 |
|
| 407 |
# headers, could be optimized a bit |
| 408 |
$state{handle}->unshift_read (line => $qr_nlnl, sub { |
| 409 |
for ("$_[1]\012") { |
| 410 |
y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
| 411 |
|
| 412 |
# we support spaces in field names, as lotus domino |
| 413 |
# creates them (actually spaces around seperators |
| 414 |
# are strictly allowed in http, they are a security issue). |
| 415 |
$hdr{lc $1} .= ",$2" |
| 416 |
while /\G |
| 417 |
([^:\000-\037]+): |
| 418 |
[\011\040]* |
| 419 |
((?: [^\012]+ | \012[\011\040] )*) |
| 420 |
\012 |
| 421 |
/gxc; |
| 422 |
|
| 423 |
/\G$/ |
| 424 |
or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
| 425 |
} |
| 426 |
|
| 427 |
substr $_, 0, 1, "" |
| 428 |
for values %hdr; |
| 429 |
|
| 430 |
my $finish = sub { |
| 431 |
# TODO: use destroy method, when/if available |
| 432 |
#$state{handle}->destroy; |
| 433 |
$state{handle}->on_eof (undef); |
| 434 |
$state{handle}->on_error (undef); |
| 435 |
%state = (); |
| 436 |
|
| 437 |
# set-cookie processing |
| 438 |
if ($arg{cookie_jar}) { |
| 439 |
for ($hdr{"set-cookie"}) { |
| 440 |
# parse NAME=VALUE |
| 441 |
my @kv; |
| 442 |
|
| 443 |
while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
| 444 |
my $name = $1; |
| 445 |
my $value = $3; |
| 446 |
|
| 447 |
unless ($value) { |
| 448 |
$value = $2; |
| 449 |
$value =~ s/\\(.)/$1/gs; |
| 450 |
} |
| 451 |
|
| 452 |
push @kv, $name => $value; |
| 453 |
|
| 454 |
last unless /\G\s*;/gc; |
| 455 |
} |
| 456 |
|
| 457 |
last unless @kv; |
| 458 |
|
| 459 |
my $name = shift @kv; |
| 460 |
my %kv = (value => shift @kv, @kv); |
| 461 |
|
| 462 |
my $cdom; |
| 463 |
my $cpath = (delete $kv{path}) || "/"; |
| 464 |
|
| 465 |
if (exists $kv{domain}) { |
| 466 |
$cdom = delete $kv{domain}; |
| 467 |
|
| 468 |
$cdom =~ s/^\.?/./; # make sure it starts with a "." |
| 469 |
|
| 470 |
next if $cdom =~ /\.$/; |
| 471 |
|
| 472 |
# this is not rfc-like and not netscape-like. go figure. |
| 473 |
my $ndots = $cdom =~ y/.//; |
| 474 |
next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
| 475 |
} else { |
| 476 |
$cdom = $uhost; |
| 477 |
} |
| 478 |
|
| 479 |
# store it |
| 480 |
$arg{cookie_jar}{version} = 1; |
| 481 |
$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
| 482 |
|
| 483 |
redo if /\G\s*,/gc; |
| 484 |
} |
| 485 |
} |
| 486 |
|
| 487 |
# microsoft and other shitheads don't give a shit for following standards, |
| 488 |
# try to support some common forms of broken Location headers. |
| 489 |
if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
| 490 |
$_[1]{location} =~ s/^\.\/+//; |
| 491 |
|
| 492 |
my $url = "$rscheme://$uhost:$uport"; |
| 493 |
|
| 494 |
unless ($_[1]{location} =~ s/^\///) { |
| 495 |
$url .= $upath; |
| 496 |
$url =~ s/\/[^\/]*$//; |
| 497 |
} |
| 498 |
|
| 499 |
$_[1]{location} = "$url/$_[1]{location}"; |
| 500 |
} |
| 501 |
|
| 502 |
if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
| 503 |
# apparently, mozilla et al. just change POST to GET here |
| 504 |
# more research is needed before we do the same |
| 505 |
http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
| 506 |
} elsif ($_[1]{Status} == 303 && $recurse) { |
| 507 |
# even http/1.1 is unclear on how to mutate the method |
| 508 |
$method = "GET" unless $method eq "HEAD"; |
| 509 |
http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
| 510 |
} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
| 511 |
http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
| 512 |
} else { |
| 513 |
$cb->($_[0], $_[1]); |
| 514 |
} |
| 515 |
}; |
| 516 |
|
| 517 |
if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
| 518 |
$finish->(undef, \%hdr); |
| 519 |
} else { |
| 520 |
if (exists $hdr{"content-length"}) { |
| 521 |
$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
| 522 |
# could cache persistent connection now |
| 523 |
if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
| 524 |
# but we don't, due to misdesigns, this is annoyingly complex |
| 525 |
}; |
| 526 |
|
| 527 |
$finish->($_[1], \%hdr); |
| 528 |
}); |
| 529 |
} else { |
| 530 |
# too bad, need to read until we get an error or EOF, |
| 531 |
# no way to detect winged data. |
| 532 |
$_[0]->on_error (sub { |
| 533 |
$finish->($_[0]{rbuf}, \%hdr); |
| 534 |
}); |
| 535 |
$_[0]->on_eof (undef); |
| 536 |
$_[0]->on_read (sub { }); |
| 537 |
} |
| 538 |
} |
| 539 |
}); |
| 540 |
}); |
| 541 |
}; |
| 542 |
|
| 543 |
# now handle proxy-CONNECT method |
| 544 |
if ($proxy && $uscheme eq "https") { |
| 545 |
# oh dear, we have to wrap it into a connect request |
| 546 |
|
| 547 |
# maybe re-use $uauthority with patched port? |
| 548 |
$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
| 549 |
$state{handle}->push_read (line => $qr_nlnl, sub { |
| 550 |
$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
| 551 |
or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url })); |
| 552 |
|
| 553 |
if ($2 == 200) { |
| 554 |
$rpath = $upath; |
| 555 |
&$handle_actual_request; |
| 556 |
} else { |
| 557 |
%state = (); |
| 558 |
$cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
| 559 |
} |
| 560 |
}); |
| 561 |
} else { |
| 562 |
&$handle_actual_request; |
| 563 |
} |
| 564 |
|
| 565 |
}, sub { |
| 566 |
$timeout |
| 567 |
}; |
| 568 |
}; |
| 569 |
|
| 570 |
defined wantarray && AnyEvent::Util::guard { %state = () } |
| 571 |
} |
| 572 |
|
| 573 |
sub http_get($@) { |
| 574 |
unshift @_, "GET"; |
| 575 |
&http_request |
| 576 |
} |
| 577 |
|
| 578 |
sub http_head($@) { |
| 579 |
unshift @_, "HEAD"; |
| 580 |
&http_request |
| 581 |
} |
| 582 |
|
| 583 |
sub http_post($$@) { |
| 584 |
my $url = shift; |
| 585 |
unshift @_, "POST", $url, "body"; |
| 586 |
&http_request |
| 587 |
} |
| 588 |
|
| 589 |
=back |
| 590 |
|
| 591 |
=head2 GLOBAL FUNCTIONS AND VARIABLES |
| 592 |
|
| 593 |
=over 4 |
| 594 |
|
| 595 |
=item AnyEvent::HTTP::set_proxy "proxy-url" |
| 596 |
|
| 597 |
Sets the default proxy server to use. The proxy-url must begin with a |
| 598 |
string of the form C<http://host:port> (optionally C<https:...>). |
| 599 |
|
| 600 |
=item $AnyEvent::HTTP::MAX_RECURSE |
| 601 |
|
| 602 |
The default value for the C<recurse> request parameter (default: C<10>). |
| 603 |
|
| 604 |
=item $AnyEvent::HTTP::USERAGENT |
| 605 |
|
| 606 |
The default value for the C<User-Agent> header (the default is |
| 607 |
C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
| 608 |
|
| 609 |
=item $AnyEvent::HTTP::MAX_PERSISTENT |
| 610 |
|
| 611 |
The maximum number of persistent connections to keep open (default: 8). |
| 612 |
|
| 613 |
Not implemented currently. |
| 614 |
|
| 615 |
=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
| 616 |
|
| 617 |
The maximum time to cache a persistent connection, in seconds (default: 2). |
| 618 |
|
| 619 |
Not implemented currently. |
| 620 |
|
| 621 |
=item $AnyEvent::HTTP::ACTIVE |
| 622 |
|
| 623 |
The number of active connections. This is not the number of currently |
| 624 |
running requests, but the number of currently open and non-idle TCP |
| 625 |
connections. This number of can be useful for load-leveling. |
| 626 |
|
| 627 |
=back |
| 628 |
|
| 629 |
=cut |
| 630 |
|
| 631 |
sub set_proxy($) { |
| 632 |
$PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
| 633 |
} |
| 634 |
|
| 635 |
# initialise proxy from environment |
| 636 |
set_proxy $ENV{http_proxy}; |
| 637 |
|
| 638 |
=head1 SEE ALSO |
| 639 |
|
| 640 |
L<AnyEvent>. |
| 641 |
|
| 642 |
=head1 AUTHOR |
| 643 |
|
| 644 |
Marc Lehmann <schmorp@schmorp.de> |
| 645 |
http://home.schmorp.de/ |
| 646 |
|
| 647 |
=cut |
| 648 |
|
| 649 |
1 |
| 650 |
|
