… | |
… | |
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. |
|
|
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. |
13 | |
32 | |
14 | =head2 METHODS |
33 | =head2 METHODS |
15 | |
34 | |
16 | =over 4 |
35 | =over 4 |
17 | |
36 | |
… | |
… | |
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 = '1.05'; |
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 $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$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, $headers) |
63 | |
84 | |
64 | Executes an HTTP-POST request with a request body of C<$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<$method> (e.g. C<GET>, C<POST>). The URL |
70 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
|
|
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
71 | |
98 | |
72 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response data as first argument |
73 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
74 | response headers as second argument. |
101 | response headers as second argument. |
75 | |
102 | |
76 | All the headers in that hash are lowercased. In addition to the response |
103 | All the headers in that hash are lowercased. In addition to the response |
77 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
78 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
79 | name. |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
107 | requested URL when following redirects). |
|
|
108 | |
|
|
109 | If the server sends a header multiple lines, then their contents will be |
|
|
110 | joined together with a command (C<,>). |
80 | |
111 | |
81 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
82 | then C<$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<599> |
83 | and the C<Reason> pseudo-header will contain an error message. |
114 | and the C<Reason> pseudo-header will contain an error message. |
84 | |
115 | |
… | |
… | |
104 | Whether to recurse requests or not, e.g. on redirects, authentication |
135 | Whether to recurse requests or not, e.g. on redirects, authentication |
105 | retries and so on, and how often to do so. |
136 | retries and so on, and how often to do so. |
106 | |
137 | |
107 | =item headers => hashref |
138 | =item headers => hashref |
108 | |
139 | |
109 | The request headers to use. |
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:>. |
110 | |
143 | |
111 | =item timeout => $seconds |
144 | =item timeout => $seconds |
112 | |
145 | |
113 | The time-out to use for various stages - each connect attempt will reset |
146 | 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. |
147 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
… | |
… | |
123 | |
156 | |
124 | =item body => $string |
157 | =item body => $string |
125 | |
158 | |
126 | The request body, usually empty. Will be-sent as-is (future versions of |
159 | The request body, usually empty. Will be-sent as-is (future versions of |
127 | this module might offer more options). |
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. |
128 | |
177 | |
129 | =back |
178 | =back |
130 | |
179 | |
131 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
180 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
132 | |
181 | |
… | |
… | |
146 | use Data::Dumper; |
195 | use Data::Dumper; |
147 | print Dumper $hdr; |
196 | print Dumper $hdr; |
148 | } |
197 | } |
149 | ; |
198 | ; |
150 | |
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 $request; |
|
|
209 | |
151 | =cut |
210 | =cut |
152 | |
211 | |
|
|
212 | sub _slot_schedule; |
|
|
213 | sub _slot_schedule($) { |
|
|
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($$) { |
|
|
237 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
|
|
238 | |
|
|
239 | _slot_schedule $_[0]; |
|
|
240 | } |
|
|
241 | |
153 | sub http_request($$$;@) { |
242 | sub http_request($$@) { |
154 | my $cb = pop; |
243 | my $cb = pop; |
155 | my ($method, $url, %arg) = @_; |
244 | my ($method, $url, %arg) = @_; |
156 | |
245 | |
157 | my %hdr; |
246 | my %hdr; |
158 | |
247 | |
… | |
… | |
162 | while (my ($k, $v) = each %$hdr) { |
251 | while (my ($k, $v) = each %$hdr) { |
163 | $hdr{lc $k} = $v; |
252 | $hdr{lc $k} = $v; |
164 | } |
253 | } |
165 | } |
254 | } |
166 | |
255 | |
167 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
256 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
168 | |
257 | |
169 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
258 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
170 | if $recurse < 0; |
259 | if $recurse < 0; |
171 | |
260 | |
172 | my $proxy = $arg{proxy} || $PROXY; |
261 | my $proxy = $arg{proxy} || $PROXY; |
173 | my $timeout = $arg{timeout} || $TIMEOUT; |
262 | my $timeout = $arg{timeout} || $TIMEOUT; |
174 | |
263 | |
175 | $hdr{"user-agent"} ||= $USERAGENT; |
264 | $hdr{"user-agent"} ||= $USERAGENT; |
176 | |
265 | |
177 | my ($host, $port, $path, $scheme); |
266 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
|
|
267 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
268 | |
|
|
269 | $uscheme = lc $uscheme; |
|
|
270 | |
|
|
271 | my $uport = $uscheme eq "http" ? 80 |
|
|
272 | : $uscheme eq "https" ? 443 |
|
|
273 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
|
|
274 | |
|
|
275 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
|
|
276 | |
|
|
277 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
278 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
|
|
279 | |
|
|
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 | if ($chost =~ /^\./) { |
|
|
296 | next unless $chost eq substr $uhost, -length $chost; |
|
|
297 | } elsif ($chost =~ /\./) { |
|
|
298 | next unless $chost eq $uhost; |
|
|
299 | } else { |
|
|
300 | next; |
|
|
301 | } |
|
|
302 | |
|
|
303 | while (my ($cpath, $v) = each %$v) { |
|
|
304 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
305 | |
|
|
306 | while (my ($k, $v) = each %$v) { |
|
|
307 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
308 | my $value = $v->{value}; |
|
|
309 | $value =~ s/([\\"])/\\$1/g; |
|
|
310 | push @cookie, "$k=\"$value\""; |
|
|
311 | } |
|
|
312 | } |
|
|
313 | } |
|
|
314 | |
|
|
315 | $hdr{cookie} = join "; ", @cookie |
|
|
316 | if @cookie; |
|
|
317 | } |
|
|
318 | |
|
|
319 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
178 | |
320 | |
179 | if ($proxy) { |
321 | if ($proxy) { |
180 | ($host, $port, $scheme) = @$proxy; |
322 | ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url); |
181 | $path = $url; |
323 | |
|
|
324 | # don't support https requests over https-proxy transport, |
|
|
325 | # can't be done with tls as spec'ed. |
|
|
326 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
182 | } else { |
327 | } else { |
183 | ($scheme, my $authority, $path, my $query, my $fragment) = |
328 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
184 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
185 | |
|
|
186 | $port = $scheme eq "http" ? 80 |
|
|
187 | : $scheme eq "https" ? 443 |
|
|
188 | : return $cb->(undef, { Status => 599, Reason => "$url: only http and https URLs supported" }); |
|
|
189 | |
|
|
190 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
191 | or return $cb->(undef, { Status => 599, Reason => "$url: unparsable URL" }); |
|
|
192 | |
|
|
193 | $host = $1; |
|
|
194 | $port = $2 if defined $2; |
|
|
195 | |
|
|
196 | $host =~ s/^\[(.*)\]$/$1/; |
|
|
197 | $path .= "?$query" if length $query; |
|
|
198 | |
|
|
199 | $path = "/" unless $path; |
|
|
200 | |
|
|
201 | $hdr{host} = $host = lc $host; |
|
|
202 | } |
329 | } |
203 | |
330 | |
204 | $scheme = lc $scheme; |
331 | $hdr{host} = $uhost; |
205 | |
|
|
206 | my %state; |
|
|
207 | |
|
|
208 | $hdr{"content-length"} = length $arg{body}; |
332 | $hdr{"content-length"} = length $arg{body}; |
209 | |
333 | |
|
|
334 | my %state = (connect_guard => 1); |
|
|
335 | |
|
|
336 | _get_slot $uhost, sub { |
|
|
337 | $state{slot_guard} = shift; |
|
|
338 | |
|
|
339 | return unless $state{connect_guard}; |
|
|
340 | |
210 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
341 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
211 | $state{fh} = shift |
342 | $state{fh} = shift |
212 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
343 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
213 | |
344 | |
214 | delete $state{connect_guard}; # reduce memory usage, save a tree |
345 | delete $state{connect_guard}; # reduce memory usage, save a tree |
215 | |
346 | |
216 | # get handle |
347 | # get handle |
217 | $state{handle} = new AnyEvent::Handle |
348 | $state{handle} = new AnyEvent::Handle |
218 | fh => $state{fh}, |
349 | fh => $state{fh}; |
219 | ($scheme eq "https" ? (tls => "connect") : ()); |
|
|
220 | |
350 | |
221 | # limit the number of persistent connections |
351 | # limit the number of persistent connections |
222 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
352 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
223 | ++$KA_COUNT{$_[1]}; |
353 | ++$KA_COUNT{$_[1]}; |
224 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
354 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
225 | $hdr{connection} = "keep-alive"; |
355 | $hdr{connection} = "keep-alive"; |
226 | delete $hdr{connection}; # keep-alive not yet supported |
356 | delete $hdr{connection}; # keep-alive not yet supported |
227 | } else { |
357 | } else { |
228 | delete $hdr{connection}; |
358 | delete $hdr{connection}; |
229 | } |
359 | } |
230 | |
360 | |
231 | # (re-)configure handle |
361 | # (re-)configure handle |
232 | $state{handle}->timeout ($timeout); |
362 | $state{handle}->timeout ($timeout); |
233 | $state{handle}->on_error (sub { |
363 | $state{handle}->on_error (sub { |
|
|
364 | my $errno = "$!"; |
234 | %state = (); |
365 | %state = (); |
235 | $cb->(undef, { Status => 599, Reason => "$!" }); |
366 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
236 | }); |
367 | }); |
237 | $state{handle}->on_eof (sub { |
368 | $state{handle}->on_eof (sub { |
238 | %state = (); |
369 | %state = (); |
239 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
370 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
240 | }); |
|
|
241 | |
|
|
242 | # send request |
|
|
243 | $state{handle}->push_write ( |
|
|
244 | "$method $path HTTP/1.0\015\012" |
|
|
245 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
|
|
246 | . "\015\012" |
|
|
247 | . (delete $arg{body}) |
|
|
248 | ); |
|
|
249 | |
|
|
250 | %hdr = (); # reduce memory usage, save a kitten |
|
|
251 | |
|
|
252 | # status line |
|
|
253 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
254 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
255 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
256 | |
|
|
257 | my %hdr = ( # response headers |
|
|
258 | HTTPVersion => ",$1", |
|
|
259 | Status => ",$2", |
|
|
260 | Reason => ",$3", |
|
|
261 | ); |
371 | }); |
262 | |
372 | |
|
|
373 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
374 | |
|
|
375 | # handle actual, non-tunneled, request |
|
|
376 | my $handle_actual_request = sub { |
|
|
377 | # $state{handle}->starttls ("connect") if $uscheme eq "https"; |
|
|
378 | |
|
|
379 | # send request |
|
|
380 | $state{handle}->push_write ( |
|
|
381 | "$method $rpath HTTP/1.0\015\012" |
|
|
382 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
|
|
383 | . "\015\012" |
|
|
384 | . (delete $arg{body}) |
|
|
385 | ); |
|
|
386 | |
|
|
387 | %hdr = (); # reduce memory usage, save a kitten |
|
|
388 | |
|
|
389 | # status line |
|
|
390 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
391 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
392 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); |
|
|
393 | |
|
|
394 | my %hdr = ( # response headers |
|
|
395 | HTTPVersion => ",$1", |
|
|
396 | Status => ",$2", |
|
|
397 | Reason => ",$3", |
|
|
398 | URL => ",$url" |
|
|
399 | ); |
|
|
400 | |
263 | # headers, could be optimized a bit |
401 | # headers, could be optimized a bit |
264 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
402 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
265 | for ("$_[1]\012") { |
403 | for ("$_[1]\012") { |
|
|
404 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
405 | |
266 | # we support spaces in field names, as lotus domino |
406 | # we support spaces in field names, as lotus domino |
267 | # creates them. |
407 | # creates them (actually spaces around seperators |
|
|
408 | # are strictly allowed in http, they are a security issue). |
268 | $hdr{lc $1} .= ",$2" |
409 | $hdr{lc $1} .= ",$2" |
269 | while /\G |
410 | while /\G |
270 | ([^:\000-\037]+): |
411 | ([^:\000-\037]+): |
271 | [\011\040]* |
412 | [\011\040]* |
272 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
413 | ((?: [^\012]+ | \012[\011\040] )*) |
273 | \015?\012 |
414 | \012 |
274 | /gxc; |
415 | /gxc; |
275 | |
416 | |
276 | /\G$/ |
417 | /\G$/ |
277 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
418 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
278 | } |
419 | } |
279 | |
420 | |
280 | substr $_, 0, 1, "" |
421 | substr $_, 0, 1, "" |
281 | for values %hdr; |
422 | for values %hdr; |
282 | |
423 | |
283 | my $finish = sub { |
424 | my $finish = sub { |
|
|
425 | # TODO: use destroy method, when/if available |
|
|
426 | #$state{handle}->destroy; |
|
|
427 | $state{handle}->on_eof (undef); |
|
|
428 | $state{handle}->on_error (undef); |
|
|
429 | %state = (); |
|
|
430 | |
|
|
431 | # set-cookie processing |
|
|
432 | if ($arg{cookie_jar}) { |
|
|
433 | for ($hdr{"set-cookie"}) { |
|
|
434 | # parse NAME=VALUE |
|
|
435 | my @kv; |
|
|
436 | |
|
|
437 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
438 | my $name = $1; |
|
|
439 | my $value = $3; |
|
|
440 | |
|
|
441 | unless ($value) { |
|
|
442 | $value = $2; |
|
|
443 | $value =~ s/\\(.)/$1/gs; |
|
|
444 | } |
|
|
445 | |
|
|
446 | push @kv, $name => $value; |
|
|
447 | |
|
|
448 | last unless /\G\s*;/gc; |
|
|
449 | } |
|
|
450 | |
|
|
451 | last unless @kv; |
|
|
452 | |
|
|
453 | my $name = shift @kv; |
|
|
454 | my %kv = (value => shift @kv, @kv); |
|
|
455 | |
|
|
456 | my $cdom; |
|
|
457 | my $cpath = (delete $kv{path}) || "/"; |
|
|
458 | |
|
|
459 | if (exists $kv{domain}) { |
|
|
460 | $cdom = delete $kv{domain}; |
|
|
461 | |
|
|
462 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
463 | |
|
|
464 | next if $cdom =~ /\.$/; |
|
|
465 | |
|
|
466 | # this is not rfc-like and not netscape-like. go figure. |
|
|
467 | my $ndots = $cdom =~ y/.//; |
|
|
468 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
469 | } else { |
|
|
470 | $cdom = $uhost; |
|
|
471 | } |
|
|
472 | |
|
|
473 | # store it |
|
|
474 | $arg{cookie_jar}{version} = 1; |
|
|
475 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
476 | |
|
|
477 | redo if /\G\s*,/gc; |
|
|
478 | } |
|
|
479 | } |
|
|
480 | |
|
|
481 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
482 | # try to support some common forms of broken Location headers. |
|
|
483 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
484 | $_[1]{location} =~ s/^\.\/+//; |
|
|
485 | |
|
|
486 | my $url = "$rscheme://$uhost:$uport"; |
|
|
487 | |
|
|
488 | unless ($_[1]{location} =~ s/^\///) { |
|
|
489 | $url .= $upath; |
|
|
490 | $url =~ s/\/[^\/]*$//; |
|
|
491 | } |
|
|
492 | |
|
|
493 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
494 | } |
|
|
495 | |
284 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { |
496 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
497 | # apparently, mozilla et al. just change POST to GET here |
|
|
498 | # more research is needed before we do the same |
285 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
499 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
500 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
501 | # even http/1.1 is unclear on how to mutate the method |
|
|
502 | $method = "GET" unless $method eq "HEAD"; |
|
|
503 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
504 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
505 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
506 | } else { |
|
|
507 | $cb->($_[0], $_[1]); |
|
|
508 | } |
|
|
509 | }; |
|
|
510 | |
|
|
511 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
512 | $finish->(undef, \%hdr); |
|
|
513 | } else { |
|
|
514 | if (exists $hdr{"content-length"}) { |
|
|
515 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
516 | # could cache persistent connection now |
|
|
517 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
518 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
519 | }; |
|
|
520 | |
|
|
521 | $finish->($_[1], \%hdr); |
|
|
522 | }); |
|
|
523 | } else { |
|
|
524 | # too bad, need to read until we get an error or EOF, |
|
|
525 | # no way to detect winged data. |
|
|
526 | $_[0]->on_error (sub { |
|
|
527 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
528 | }); |
|
|
529 | $_[0]->on_eof (undef); |
|
|
530 | $_[0]->on_read (sub { }); |
|
|
531 | } |
|
|
532 | } |
|
|
533 | }); |
|
|
534 | }); |
|
|
535 | }; |
|
|
536 | |
|
|
537 | # now handle proxy-CONNECT method |
|
|
538 | if ($proxy && $uscheme eq "https") { |
|
|
539 | # oh dear, we have to wrap it into a connect request |
|
|
540 | |
|
|
541 | # maybe re-use $uauthority with patched port? |
|
|
542 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
543 | $state{handle}->push_read (line => qr/\015?\012\015?\012/, sub { |
|
|
544 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
545 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url })); |
|
|
546 | |
|
|
547 | if ($2 == 200) { |
|
|
548 | $rpath = $upath; |
|
|
549 | &$handle_actual_request; |
286 | } else { |
550 | } else { |
287 | $cb->($_[0], $_[1]); |
551 | %state = (); |
|
|
552 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
288 | } |
553 | } |
289 | }; |
554 | }); |
290 | |
|
|
291 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
292 | %state = (); |
|
|
293 | $finish->(undef, \%hdr); |
|
|
294 | } else { |
555 | } else { |
295 | if (exists $hdr{"content-length"}) { |
556 | &$handle_actual_request; |
296 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
297 | # could cache persistent connection now |
|
|
298 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
299 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
300 | }; |
|
|
301 | |
|
|
302 | %state = (); |
|
|
303 | $finish->($_[1], \%hdr); |
|
|
304 | }); |
|
|
305 | } else { |
|
|
306 | # too bad, need to read until we get an error or EOF, |
|
|
307 | # no way to detect winged data. |
|
|
308 | $_[0]->on_error (sub { |
|
|
309 | %state = (); |
|
|
310 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
311 | }); |
|
|
312 | $_[0]->on_eof (undef); |
|
|
313 | $_[0]->on_read (sub { }); |
|
|
314 | } |
|
|
315 | } |
|
|
316 | }); |
557 | } |
|
|
558 | |
|
|
559 | }, sub { |
|
|
560 | $timeout |
317 | }); |
561 | }; |
318 | }, sub { |
|
|
319 | $timeout |
|
|
320 | }; |
562 | }; |
321 | |
563 | |
322 | defined wantarray && AnyEvent::Util::guard { %state = () } |
564 | defined wantarray && AnyEvent::Util::guard { %state = () } |
323 | } |
565 | } |
324 | |
566 | |
325 | sub http_get($$;@) { |
567 | sub http_get($@) { |
326 | unshift @_, "GET"; |
568 | unshift @_, "GET"; |
327 | &http_request |
569 | &http_request |
328 | } |
570 | } |
329 | |
571 | |
330 | sub http_head($$;@) { |
572 | sub http_head($@) { |
331 | unshift @_, "HEAD"; |
573 | unshift @_, "HEAD"; |
332 | &http_request |
574 | &http_request |
333 | } |
575 | } |
334 | |
576 | |
335 | sub http_post($$$;@) { |
577 | sub http_post($$@) { |
|
|
578 | my $url = shift; |
336 | unshift @_, "POST", "body"; |
579 | unshift @_, "POST", $url, "body"; |
337 | &http_request |
580 | &http_request |
338 | } |
581 | } |
339 | |
582 | |
340 | =back |
583 | =back |
341 | |
584 | |
… | |
… | |
366 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
609 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
367 | |
610 | |
368 | The maximum time to cache a persistent connection, in seconds (default: 2). |
611 | The maximum time to cache a persistent connection, in seconds (default: 2). |
369 | |
612 | |
370 | Not implemented currently. |
613 | Not implemented currently. |
|
|
614 | |
|
|
615 | =item $AnyEvent::HTTP::ACTIVE |
|
|
616 | |
|
|
617 | The number of active connections. This is not the number of currently |
|
|
618 | running requests, but the number of currently open and non-idle TCP |
|
|
619 | connections. This number of can be useful for load-leveling. |
371 | |
620 | |
372 | =back |
621 | =back |
373 | |
622 | |
374 | =cut |
623 | =cut |
375 | |
624 | |
… | |
… | |
384 | |
633 | |
385 | L<AnyEvent>. |
634 | L<AnyEvent>. |
386 | |
635 | |
387 | =head1 AUTHOR |
636 | =head1 AUTHOR |
388 | |
637 | |
389 | Marc Lehmann <schmorp@schmorp.de> |
638 | Marc Lehmann <schmorp@schmorp.de> |
390 | http://home.schmorp.de/ |
639 | http://home.schmorp.de/ |
391 | |
640 | |
392 | =cut |
641 | =cut |
393 | |
642 | |
394 | 1 |
643 | 1 |
395 | |
644 | |