… | |
… | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Carp; |
44 | use Carp; |
45 | |
45 | |
46 | use AnyEvent (); |
46 | use AnyEvent 4.452 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
49 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
50 | |
50 | |
51 | use base Exporter::; |
51 | use base Exporter::; |
52 | |
52 | |
53 | our $VERSION = '1.03'; |
53 | our $VERSION = '1.12'; |
54 | |
54 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
56 | |
57 | 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)"; |
58 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
59 | our $MAX_PERSISTENT = 8; |
59 | our $MAX_PERSISTENT = 8; |
60 | our $PERSISTENT_TIMEOUT = 2; |
60 | our $PERSISTENT_TIMEOUT = 2; |
61 | our $TIMEOUT = 300; |
61 | our $TIMEOUT = 300; |
62 | |
62 | |
… | |
… | |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
72 | |
72 | |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
73 | =item http_get $url, key => value..., $cb->($data, $headers) |
74 | |
74 | |
75 | 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 |
76 | additional parameters. |
76 | additional parameters and the return value. |
77 | |
77 | |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
79 | |
79 | |
80 | 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 |
81 | additional parameters. |
81 | on additional parameters and the return value. |
82 | |
82 | |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
84 | |
84 | |
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
86 | http_request function for details on additional parameters. |
86 | http_request function for details on additional parameters and the return |
|
|
87 | value. |
87 | |
88 | |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | |
90 | |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
|
|
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
92 | |
98 | |
93 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response data as first argument |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
95 | response headers as second argument. |
101 | response headers as second argument. |
96 | |
102 | |
… | |
… | |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
101 | requested URL when following redirects). |
107 | requested URL when following redirects). |
102 | |
108 | |
103 | If the server sends a header multiple lines, then their contents will be |
109 | If the server sends a header multiple times, then their contents will be |
104 | joined together with C<\x00>. |
110 | joined together with a comma (C<,>), as per the HTTP spec. |
105 | |
111 | |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
107 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
108 | and the C<Reason> pseudo-header will contain an error message. |
114 | and the C<Reason> pseudo-header will contain an error message. |
109 | |
115 | |
… | |
… | |
159 | based on the original netscape specification. |
165 | based on the original netscape specification. |
160 | |
166 | |
161 | The C<$hash_ref> must be an (initially empty) hash reference which will |
167 | The C<$hash_ref> must be an (initially empty) hash reference which will |
162 | get updated automatically. It is possible to save the cookie_jar to |
168 | get updated automatically. It is possible to save the cookie_jar to |
163 | persistent storage with something like JSON or Storable, but this is not |
169 | persistent storage with something like JSON or Storable, but this is not |
164 | recommended, as expire times are currently being ignored. |
170 | recommended, as expiry times are currently being ignored. |
165 | |
171 | |
166 | Note that this cookie implementation is not of very high quality, nor |
172 | Note that this cookie implementation is not of very high quality, nor |
167 | meant to be complete. If you want complete cookie management you have to |
173 | meant to be complete. If you want complete cookie management you have to |
168 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
174 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
169 | cookie-using sites working. Cookies are a privacy disaster, do not use |
175 | cookie-using sites working. Cookies are a privacy disaster, do not use |
170 | them unless required to. |
176 | them unless required to. |
|
|
177 | |
|
|
178 | =item tls_ctx => $scheme | $tls_ctx |
|
|
179 | |
|
|
180 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
181 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
182 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
183 | C<high> can be specified, which give you a predefined low-security (no |
|
|
184 | verification, highest compatibility) and high-security (CA and common-name |
|
|
185 | verification) TLS context. |
|
|
186 | |
|
|
187 | The default for this option is C<low>, which could be interpreted as "give |
|
|
188 | me the page, no matter what". |
171 | |
189 | |
172 | =back |
190 | =back |
173 | |
191 | |
174 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
192 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
175 | |
193 | |
… | |
… | |
188 | my ($body, $hdr) = @_; |
206 | my ($body, $hdr) = @_; |
189 | use Data::Dumper; |
207 | use Data::Dumper; |
190 | print Dumper $hdr; |
208 | print Dumper $hdr; |
191 | } |
209 | } |
192 | ; |
210 | ; |
|
|
211 | |
|
|
212 | Example: make another simple HTTP GET request, but immediately try to |
|
|
213 | cancel it. |
|
|
214 | |
|
|
215 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
216 | my ($body, $hdr) = @_; |
|
|
217 | print "$body\n"; |
|
|
218 | }; |
|
|
219 | |
|
|
220 | undef $request; |
193 | |
221 | |
194 | =cut |
222 | =cut |
195 | |
223 | |
196 | sub _slot_schedule; |
224 | sub _slot_schedule; |
197 | sub _slot_schedule($) { |
225 | sub _slot_schedule($) { |
… | |
… | |
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
249 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
222 | |
250 | |
223 | _slot_schedule $_[0]; |
251 | _slot_schedule $_[0]; |
224 | } |
252 | } |
225 | |
253 | |
|
|
254 | our $qr_nl = qr<\015?\012>; |
|
|
255 | our $qr_nlnl = qr<\015?\012\015?\012>; |
|
|
256 | |
|
|
257 | our $TLS_CTX_LOW = { cache => 1, dh => undef, sslv2 => 1 }; |
|
|
258 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_cn => "https", dh => "skip4096" }; |
|
|
259 | |
226 | sub http_request($$@) { |
260 | sub http_request($$@) { |
227 | my $cb = pop; |
261 | my $cb = pop; |
228 | my ($method, $url, %arg) = @_; |
262 | my ($method, $url, %arg) = @_; |
229 | |
263 | |
230 | my %hdr; |
264 | my %hdr; |
|
|
265 | |
|
|
266 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
267 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
231 | |
268 | |
232 | $method = uc $method; |
269 | $method = uc $method; |
233 | |
270 | |
234 | if (my $hdr = $arg{headers}) { |
271 | if (my $hdr = $arg{headers}) { |
235 | while (my ($k, $v) = each %$hdr) { |
272 | while (my ($k, $v) = each %$hdr) { |
… | |
… | |
237 | } |
274 | } |
238 | } |
275 | } |
239 | |
276 | |
240 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
277 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
241 | |
278 | |
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
279 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
243 | if $recurse < 0; |
280 | if $recurse < 0; |
244 | |
281 | |
245 | my $proxy = $arg{proxy} || $PROXY; |
282 | my $proxy = $arg{proxy} || $PROXY; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
283 | my $timeout = $arg{timeout} || $TIMEOUT; |
247 | |
284 | |
248 | $hdr{"user-agent"} ||= $USERAGENT; |
285 | $hdr{"user-agent"} ||= $USERAGENT; |
249 | |
286 | |
250 | my ($scheme, $authority, $upath, $query, $fragment) = |
287 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
251 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
288 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
252 | |
289 | |
253 | $scheme = lc $scheme; |
290 | $uscheme = lc $uscheme; |
254 | |
291 | |
255 | my $uport = $scheme eq "http" ? 80 |
292 | my $uport = $uscheme eq "http" ? 80 |
256 | : $scheme eq "https" ? 443 |
293 | : $uscheme eq "https" ? 443 |
257 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
294 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported (not '$uscheme')", URL => $url }); |
258 | |
295 | |
259 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
296 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
260 | |
297 | |
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
298 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
299 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
263 | |
300 | |
264 | my $uhost = $1; |
301 | my $uhost = $1; |
265 | $uport = $2 if defined $2; |
302 | $uport = $2 if defined $2; |
266 | |
303 | |
267 | $uhost =~ s/^\[(.*)\]$/$1/; |
304 | $uhost =~ s/^\[(.*)\]$/$1/; |
… | |
… | |
269 | |
306 | |
270 | $upath =~ s%^/?%/%; |
307 | $upath =~ s%^/?%/%; |
271 | |
308 | |
272 | # cookie processing |
309 | # cookie processing |
273 | if (my $jar = $arg{cookie_jar}) { |
310 | if (my $jar = $arg{cookie_jar}) { |
274 | %$jar = () if $jar->{version} < 1; |
311 | %$jar = () if $jar->{version} != 1; |
275 | |
312 | |
276 | my @cookie; |
313 | my @cookie; |
277 | |
314 | |
278 | while (my ($chost, $v) = each %$jar) { |
315 | while (my ($chost, $v) = each %$jar) { |
|
|
316 | if ($chost =~ /^\./) { |
279 | next unless $chost eq substr $uhost, -length $chost; |
317 | next unless $chost eq substr $uhost, -length $chost; |
280 | next unless $chost =~ /^\./; |
318 | } elsif ($chost =~ /\./) { |
|
|
319 | next unless $chost eq $uhost; |
|
|
320 | } else { |
|
|
321 | next; |
|
|
322 | } |
281 | |
323 | |
282 | while (my ($cpath, $v) = each %$v) { |
324 | while (my ($cpath, $v) = each %$v) { |
283 | next unless $cpath eq substr $upath, 0, length $cpath; |
325 | next unless $cpath eq substr $upath, 0, length $cpath; |
284 | |
326 | |
285 | while (my ($k, $v) = each %$v) { |
327 | while (my ($k, $v) = each %$v) { |
286 | next if $scheme ne "https" && exists $v->{secure}; |
328 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
329 | my $value = $v->{value}; |
|
|
330 | $value =~ s/([\\"])/\\$1/g; |
287 | push @cookie, "$k=$v->{value}"; |
331 | push @cookie, "$k=\"$value\""; |
288 | } |
332 | } |
289 | } |
333 | } |
290 | } |
334 | } |
291 | |
335 | |
292 | $hdr{cookie} = join "; ", @cookie |
336 | $hdr{cookie} = join "; ", @cookie |
293 | if @cookie; |
337 | if @cookie; |
294 | } |
338 | } |
295 | |
339 | |
296 | my ($rhost, $rport, $rpath); # request host, port, path |
340 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
297 | |
341 | |
298 | if ($proxy) { |
342 | if ($proxy) { |
299 | ($rhost, $rport, $scheme) = @$proxy; |
343 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
300 | $rpath = $url; |
344 | |
|
|
345 | # don't support https requests over https-proxy transport, |
|
|
346 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
347 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
301 | } else { |
348 | } else { |
302 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
349 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
303 | $hdr{host} = $uhost; |
|
|
304 | } |
350 | } |
305 | |
351 | |
|
|
352 | $hdr{host} = $uhost; |
306 | $hdr{"content-length"} = length $arg{body}; |
353 | $hdr{"content-length"} = length $arg{body}; |
307 | |
354 | |
308 | my %state = (connect_guard => 1); |
355 | my %state = (connect_guard => 1); |
309 | |
356 | |
310 | _get_slot $uhost, sub { |
357 | _get_slot $uhost, sub { |
… | |
… | |
312 | |
359 | |
313 | return unless $state{connect_guard}; |
360 | return unless $state{connect_guard}; |
314 | |
361 | |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
362 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
316 | $state{fh} = shift |
363 | $state{fh} = shift |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
364 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url })); |
|
|
365 | pop; # free memory, save a tree |
318 | |
366 | |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
367 | return unless delete $state{connect_guard}; |
320 | |
368 | |
321 | # get handle |
369 | # get handle |
322 | $state{handle} = new AnyEvent::Handle |
370 | $state{handle} = new AnyEvent::Handle |
323 | fh => $state{fh}, |
371 | fh => $state{fh}, |
324 | ($scheme eq "https" ? (tls => "connect") : ()); |
372 | timeout => $timeout, |
|
|
373 | peername => $rhost, |
|
|
374 | tls_ctx => $arg{tls_ctx}; |
325 | |
375 | |
326 | # limit the number of persistent connections |
376 | # limit the number of persistent connections |
|
|
377 | # keepalive not yet supported |
327 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
378 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
328 | ++$KA_COUNT{$_[1]}; |
379 | ++$KA_COUNT{$_[1]}; |
329 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
380 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
381 | --$KA_COUNT{$_[1]} |
|
|
382 | }; |
330 | $hdr{connection} = "keep-alive"; |
383 | $hdr{connection} = "keep-alive"; |
331 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
332 | } else { |
384 | } else { |
333 | delete $hdr{connection}; |
385 | delete $hdr{connection}; |
334 | } |
386 | } |
335 | |
387 | |
336 | # (re-)configure handle |
388 | # (re-)configure handle |
337 | $state{handle}->timeout ($timeout); |
|
|
338 | $state{handle}->on_error (sub { |
389 | $state{handle}->on_error (sub { |
339 | my $errno = "$!"; |
|
|
340 | %state = (); |
390 | %state = (); |
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
391 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
342 | }); |
392 | }); |
343 | $state{handle}->on_eof (sub { |
393 | $state{handle}->on_eof (sub { |
344 | %state = (); |
394 | %state = (); |
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
395 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
346 | }); |
396 | }); |
347 | |
397 | |
|
|
398 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
399 | |
|
|
400 | # handle actual, non-tunneled, request |
|
|
401 | my $handle_actual_request = sub { |
|
|
402 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
403 | |
348 | # send request |
404 | # send request |
349 | $state{handle}->push_write ( |
405 | $state{handle}->push_write ( |
350 | "$method $rpath HTTP/1.0\015\012" |
406 | "$method $rpath HTTP/1.0\015\012" |
351 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
407 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
352 | . "\015\012" |
408 | . "\015\012" |
353 | . (delete $arg{body}) |
409 | . (delete $arg{body}) |
354 | ); |
|
|
355 | |
|
|
356 | %hdr = (); # reduce memory usage, save a kitten |
|
|
357 | |
|
|
358 | # status line |
|
|
359 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
360 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
361 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
|
|
362 | |
|
|
363 | my %hdr = ( # response headers |
|
|
364 | HTTPVersion => "\x00$1", |
|
|
365 | Status => "\x00$2", |
|
|
366 | Reason => "\x00$3", |
|
|
367 | URL => "\x00$url" |
|
|
368 | ); |
410 | ); |
369 | |
411 | |
|
|
412 | %hdr = (); # reduce memory usage, save a kitten |
|
|
413 | |
|
|
414 | # status line |
|
|
415 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
416 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
417 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
418 | |
|
|
419 | my %hdr = ( # response headers |
|
|
420 | HTTPVersion => ",$1", |
|
|
421 | Status => ",$2", |
|
|
422 | Reason => ",$3", |
|
|
423 | URL => ",$url" |
|
|
424 | ); |
|
|
425 | |
370 | # headers, could be optimized a bit |
426 | # headers, could be optimized a bit |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
427 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
372 | for ("$_[1]\012") { |
428 | for ("$_[1]\012") { |
373 | # we support spaces in field names, as lotus domino |
429 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
374 | # creates them. |
430 | |
|
|
431 | # things seen, not parsed: |
|
|
432 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
433 | |
375 | $hdr{lc $1} .= "\x00$2" |
434 | $hdr{lc $1} .= ",$2" |
376 | while /\G |
435 | while /\G |
377 | ([^:\000-\037]+): |
436 | ([^:\000-\037]+): |
378 | [\011\040]* |
437 | [\011\040]* |
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
438 | ((?: [^\012]+ | \012[\011\040] )*) |
380 | \015?\012 |
439 | \012 |
381 | /gxc; |
440 | /gxc; |
382 | |
441 | |
383 | /\G$/ |
442 | /\G$/ |
384 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
443 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
385 | } |
444 | } |
386 | |
445 | |
387 | substr $_, 0, 1, "" |
446 | substr $_, 0, 1, "" |
388 | for values %hdr; |
447 | for values %hdr; |
389 | |
448 | |
390 | my $finish = sub { |
449 | my $finish = sub { |
|
|
450 | $state{handle}->destroy; |
391 | %state = (); |
451 | %state = (); |
392 | |
452 | |
393 | # set-cookie processing |
453 | # set-cookie processing |
394 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
454 | if ($arg{cookie_jar}) { |
395 | for (split /\x00/, $hdr{"set-cookie"}) { |
455 | for ($hdr{"set-cookie"}) { |
396 | my ($cookie, @arg) = split /;\s*/; |
456 | # parse NAME=VALUE |
397 | my ($name, $value) = split /=/, $cookie, 2; |
457 | my @kv; |
398 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
458 | |
399 | |
459 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
400 | my $cdom = (delete $kv{domain}) || $uhost; |
460 | my $name = $1; |
|
|
461 | my $value = $3; |
|
|
462 | |
|
|
463 | unless ($value) { |
|
|
464 | $value = $2; |
|
|
465 | $value =~ s/\\(.)/$1/gs; |
|
|
466 | } |
|
|
467 | |
|
|
468 | push @kv, $name => $value; |
|
|
469 | |
|
|
470 | last unless /\G\s*;/gc; |
|
|
471 | } |
|
|
472 | |
|
|
473 | last unless @kv; |
|
|
474 | |
|
|
475 | my $name = shift @kv; |
|
|
476 | my %kv = (value => shift @kv, @kv); |
|
|
477 | |
|
|
478 | my $cdom; |
401 | my $cpath = (delete $kv{path}) || "/"; |
479 | my $cpath = (delete $kv{path}) || "/"; |
402 | |
480 | |
|
|
481 | if (exists $kv{domain}) { |
|
|
482 | $cdom = delete $kv{domain}; |
|
|
483 | |
403 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
484 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
404 | |
485 | |
405 | next if $cdom =~ /\.$/; |
486 | next if $cdom =~ /\.$/; |
406 | |
487 | |
407 | # this is not rfc-like and not netscape-like. go figure. |
488 | # this is not rfc-like and not netscape-like. go figure. |
408 | my $ndots = $cdom =~ y/.//; |
489 | my $ndots = $cdom =~ y/.//; |
409 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
490 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
410 | |
491 | } else { |
|
|
492 | $cdom = $uhost; |
|
|
493 | } |
|
|
494 | |
411 | # store it |
495 | # store it |
412 | $arg{cookie_jar}{version} = 1; |
496 | $arg{cookie_jar}{version} = 1; |
413 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
497 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
498 | |
|
|
499 | redo if /\G\s*,/gc; |
|
|
500 | } |
|
|
501 | } |
|
|
502 | |
|
|
503 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
504 | # try to support some common forms of broken Location headers. |
|
|
505 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
506 | $_[1]{location} =~ s/^\.\/+//; |
|
|
507 | |
|
|
508 | my $url = "$rscheme://$uhost:$uport"; |
|
|
509 | |
|
|
510 | unless ($_[1]{location} =~ s/^\///) { |
|
|
511 | $url .= $upath; |
|
|
512 | $url =~ s/\/[^\/]*$//; |
|
|
513 | } |
|
|
514 | |
|
|
515 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
516 | } |
|
|
517 | |
|
|
518 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
519 | # apparently, mozilla et al. just change POST to GET here |
|
|
520 | # more research is needed before we do the same |
|
|
521 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
522 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
523 | # even http/1.1 is unclear on how to mutate the method |
|
|
524 | $method = "GET" unless $method eq "HEAD"; |
|
|
525 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
526 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
527 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
528 | } else { |
|
|
529 | $cb->($_[0], $_[1]); |
|
|
530 | } |
|
|
531 | }; |
|
|
532 | |
|
|
533 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
534 | $finish->(undef, \%hdr); |
|
|
535 | } else { |
|
|
536 | if (exists $hdr{"content-length"}) { |
|
|
537 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
538 | # could cache persistent connection now |
|
|
539 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
540 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
541 | }; |
|
|
542 | |
|
|
543 | $finish->($_[1], \%hdr); |
|
|
544 | }); |
|
|
545 | } else { |
|
|
546 | # too bad, need to read until we get an error or EOF, |
|
|
547 | # no way to detect winged data. |
|
|
548 | $_[0]->on_error (sub { |
|
|
549 | # delete ought to be more efficient, as we would have to make |
|
|
550 | # a copy otherwise as $_[0] gets destroyed. |
|
|
551 | $finish->(delete $_[0]{rbuf}, \%hdr); |
|
|
552 | }); |
|
|
553 | $_[0]->on_eof (undef); |
|
|
554 | $_[0]->on_read (sub { }); |
414 | } |
555 | } |
415 | } |
556 | } |
416 | |
|
|
417 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
418 | # try to support some common forms of broken Location headers. |
|
|
419 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
420 | $_[1]{location} =~ s/^\.\/+//; |
|
|
421 | |
|
|
422 | my $url = "$scheme://$uhost:$uport"; |
|
|
423 | |
|
|
424 | unless ($_[1]{location} =~ s/^\///) { |
|
|
425 | $url .= $upath; |
|
|
426 | $url =~ s/\/[^\/]*$//; |
|
|
427 | } |
|
|
428 | |
|
|
429 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
430 | } |
|
|
431 | |
|
|
432 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
433 | # apparently, mozilla et al. just change POST to GET here |
|
|
434 | # more research is needed before we do the same |
|
|
435 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
436 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
437 | # even http/1.1 is unlear on how to mutate the method |
|
|
438 | $method = "GET" unless $method eq "HEAD"; |
|
|
439 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
440 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
441 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
442 | } else { |
|
|
443 | $cb->($_[0], $_[1]); |
|
|
444 | } |
|
|
445 | }; |
557 | }); |
|
|
558 | }); |
|
|
559 | }; |
446 | |
560 | |
447 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
561 | # now handle proxy-CONNECT method |
448 | $finish->(undef, \%hdr); |
562 | if ($proxy && $uscheme eq "https") { |
|
|
563 | # oh dear, we have to wrap it into a connect request |
|
|
564 | |
|
|
565 | # maybe re-use $uauthority with patched port? |
|
|
566 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
567 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
568 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
569 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
|
|
570 | |
|
|
571 | if ($2 == 200) { |
|
|
572 | $rpath = $upath; |
|
|
573 | &$handle_actual_request; |
449 | } else { |
574 | } else { |
450 | if (exists $hdr{"content-length"}) { |
575 | %state = (); |
451 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
576 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
452 | # could cache persistent connection now |
|
|
453 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
454 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
455 | }; |
|
|
456 | |
|
|
457 | $finish->($_[1], \%hdr); |
|
|
458 | }); |
|
|
459 | } else { |
|
|
460 | # too bad, need to read until we get an error or EOF, |
|
|
461 | # no way to detect winged data. |
|
|
462 | $_[0]->on_error (sub { |
|
|
463 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
464 | }); |
|
|
465 | $_[0]->on_eof (undef); |
|
|
466 | $_[0]->on_read (sub { }); |
|
|
467 | } |
|
|
468 | } |
577 | } |
469 | }); |
578 | }); |
|
|
579 | } else { |
|
|
580 | &$handle_actual_request; |
470 | }); |
581 | } |
|
|
582 | |
471 | }, sub { |
583 | }, sub { |
472 | $timeout |
584 | $timeout |
473 | }; |
585 | }; |
474 | }; |
586 | }; |
475 | |
587 | |
… | |
… | |
508 | The default value for the C<recurse> request parameter (default: C<10>). |
620 | The default value for the C<recurse> request parameter (default: C<10>). |
509 | |
621 | |
510 | =item $AnyEvent::HTTP::USERAGENT |
622 | =item $AnyEvent::HTTP::USERAGENT |
511 | |
623 | |
512 | The default value for the C<User-Agent> header (the default is |
624 | The default value for the C<User-Agent> header (the default is |
513 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
625 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
514 | |
626 | |
515 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
627 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
516 | |
628 | |
517 | The maximum number of persistent connections to keep open (default: 8). |
629 | The maximum number of persistent connections to keep open (default: 8). |
518 | |
630 | |
… | |
… | |
548 | =head1 AUTHOR |
660 | =head1 AUTHOR |
549 | |
661 | |
550 | Marc Lehmann <schmorp@schmorp.de> |
662 | Marc Lehmann <schmorp@schmorp.de> |
551 | http://home.schmorp.de/ |
663 | http://home.schmorp.de/ |
552 | |
664 | |
|
|
665 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
666 | testcases and bugreports. |
|
|
667 | |
553 | =cut |
668 | =cut |
554 | |
669 | |
555 | 1 |
670 | 1 |
556 | |
671 | |