… | |
… | |
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 = '1.03'; |
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. |
56 | |
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 on |
|
|
81 | additional parameters. |
|
|
82 | |
57 | =item http_get $url, $body, key => value..., $cb->($data, $headers) |
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
58 | |
84 | |
59 | Executes an HTTP-POST request with a requets body of C<$bod>. See the |
85 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
60 | http_request function for details on additional parameters. |
86 | http_request function for details on additional parameters. |
61 | |
87 | |
62 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
63 | |
89 | |
64 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
… | |
… | |
66 | |
92 | |
67 | The callback will be called with the response data as first argument |
93 | The callback will be called with the response data as first argument |
68 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
69 | response headers as second argument. |
95 | response headers as second argument. |
70 | |
96 | |
71 | All the headers in that has are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
72 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
73 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
74 | name. |
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
101 | requested URL when following redirects). |
|
|
102 | |
|
|
103 | If the server sends a header multiple lines, then their contents will be |
|
|
104 | joined together with C<\x00>. |
75 | |
105 | |
76 | If an internal error occurs, such as not being able to resolve a hostname, |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
77 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
107 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
78 | and the C<Reason> pseudo-header will contain an error message. |
108 | and the C<Reason> pseudo-header will contain an error message. |
79 | |
109 | |
|
|
110 | A typical callback might look like this: |
|
|
111 | |
|
|
112 | sub { |
|
|
113 | my ($body, $hdr) = @_; |
|
|
114 | |
|
|
115 | if ($hdr->{Status} =~ /^2/) { |
|
|
116 | ... everything should be ok |
|
|
117 | } else { |
|
|
118 | print "error, $hdr->{Status} $hdr->{Reason}\n"; |
|
|
119 | } |
|
|
120 | } |
|
|
121 | |
80 | Additional parameters are key-value pairs, and are fully optional. They |
122 | Additional parameters are key-value pairs, and are fully optional. They |
81 | include: |
123 | include: |
82 | |
124 | |
83 | =over 4 |
125 | =over 4 |
84 | |
126 | |
… | |
… | |
87 | Whether to recurse requests or not, e.g. on redirects, authentication |
129 | Whether to recurse requests or not, e.g. on redirects, authentication |
88 | retries and so on, and how often to do so. |
130 | retries and so on, and how often to do so. |
89 | |
131 | |
90 | =item headers => hashref |
132 | =item headers => hashref |
91 | |
133 | |
92 | The request headers to use. |
134 | The request headers to use. Currently, C<http_request> may provide its |
|
|
135 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
|
|
136 | and will provide defaults for C<User-Agent:> and C<Referer:>. |
93 | |
137 | |
94 | =item timeout => $seconds |
138 | =item timeout => $seconds |
95 | |
139 | |
96 | The time-out to use for various stages - each connect attempt will reset |
140 | The time-out to use for various stages - each connect attempt will reset |
97 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
141 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
… | |
… | |
107 | =item body => $string |
151 | =item body => $string |
108 | |
152 | |
109 | The request body, usually empty. Will be-sent as-is (future versions of |
153 | The request body, usually empty. Will be-sent as-is (future versions of |
110 | this module might offer more options). |
154 | this module might offer more options). |
111 | |
155 | |
|
|
156 | =item cookie_jar => $hash_ref |
|
|
157 | |
|
|
158 | Passing this parameter enables (simplified) cookie-processing, loosely |
|
|
159 | based on the original netscape specification. |
|
|
160 | |
|
|
161 | The C<$hash_ref> must be an (initially empty) hash reference which will |
|
|
162 | get updated automatically. It is possible to save the cookie_jar to |
|
|
163 | persistent storage with something like JSON or Storable, but this is not |
|
|
164 | recommended, as expire times are currently being ignored. |
|
|
165 | |
|
|
166 | 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 |
|
|
168 | 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 |
|
|
170 | them unless required to. |
|
|
171 | |
112 | =back |
172 | =back |
113 | |
173 | |
114 | =back |
174 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
|
|
175 | |
|
|
176 | http_request GET => "http://www.nethype.de/", sub { |
|
|
177 | my ($body, $hdr) = @_; |
|
|
178 | print "$body\n"; |
|
|
179 | }; |
|
|
180 | |
|
|
181 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
|
|
182 | timeout of 30 seconds. |
|
|
183 | |
|
|
184 | http_request |
|
|
185 | GET => "https://www.google.com", |
|
|
186 | timeout => 30, |
|
|
187 | sub { |
|
|
188 | my ($body, $hdr) = @_; |
|
|
189 | use Data::Dumper; |
|
|
190 | print Dumper $hdr; |
|
|
191 | } |
|
|
192 | ; |
115 | |
193 | |
116 | =cut |
194 | =cut |
117 | |
195 | |
|
|
196 | sub _slot_schedule; |
|
|
197 | sub _slot_schedule($) { |
|
|
198 | my $host = shift; |
|
|
199 | |
|
|
200 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
|
|
201 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
|
|
202 | # somebody wants that slot |
|
|
203 | ++$CO_SLOT{$host}[0]; |
|
|
204 | ++$ACTIVE; |
|
|
205 | |
|
|
206 | $cb->(AnyEvent::Util::guard { |
|
|
207 | --$ACTIVE; |
|
|
208 | --$CO_SLOT{$host}[0]; |
|
|
209 | _slot_schedule $host; |
|
|
210 | }); |
|
|
211 | } else { |
|
|
212 | # nobody wants the slot, maybe we can forget about it |
|
|
213 | delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; |
|
|
214 | last; |
|
|
215 | } |
|
|
216 | } |
|
|
217 | } |
|
|
218 | |
|
|
219 | # wait for a free slot on host, call callback |
|
|
220 | sub _get_slot($$) { |
|
|
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
|
|
222 | |
|
|
223 | _slot_schedule $_[0]; |
|
|
224 | } |
|
|
225 | |
118 | sub http_request($$$;@) { |
226 | sub http_request($$@) { |
119 | my $cb = pop; |
227 | my $cb = pop; |
120 | my ($method, $url, %arg) = @_; |
228 | my ($method, $url, %arg) = @_; |
121 | |
229 | |
122 | my %hdr; |
230 | my %hdr; |
123 | |
231 | |
124 | $method = uc $method; |
232 | $method = uc $method; |
125 | |
233 | |
126 | if (my $hdr = delete $arg{headers}) { |
234 | if (my $hdr = $arg{headers}) { |
127 | while (my ($k, $v) = each %$hdr) { |
235 | while (my ($k, $v) = each %$hdr) { |
128 | $hdr{lc $k} = $v; |
236 | $hdr{lc $k} = $v; |
129 | } |
237 | } |
130 | } |
238 | } |
131 | |
239 | |
|
|
240 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
|
|
241 | |
|
|
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
|
|
243 | if $recurse < 0; |
|
|
244 | |
132 | my $proxy = $arg{proxy} || $PROXY; |
245 | my $proxy = $arg{proxy} || $PROXY; |
133 | my $timeout = $arg{timeout} || $TIMEOUT; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
134 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
|
|
135 | |
247 | |
136 | $hdr{"user-agent"} ||= $USERAGENT; |
248 | $hdr{"user-agent"} ||= $USERAGENT; |
137 | |
249 | |
138 | my ($host, $port, $path, $scheme); |
250 | my ($scheme, $authority, $upath, $query, $fragment) = |
|
|
251 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
252 | |
|
|
253 | $scheme = lc $scheme; |
|
|
254 | |
|
|
255 | my $uport = $scheme eq "http" ? 80 |
|
|
256 | : $scheme eq "https" ? 443 |
|
|
257 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
|
|
258 | |
|
|
259 | $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic |
|
|
260 | |
|
|
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
|
|
263 | |
|
|
264 | my $uhost = $1; |
|
|
265 | $uport = $2 if defined $2; |
|
|
266 | |
|
|
267 | $uhost =~ s/^\[(.*)\]$/$1/; |
|
|
268 | $upath .= "?$query" if length $query; |
|
|
269 | |
|
|
270 | $upath =~ s%^/?%/%; |
|
|
271 | |
|
|
272 | # cookie processing |
|
|
273 | if (my $jar = $arg{cookie_jar}) { |
|
|
274 | %$jar = () if $jar->{version} < 1; |
|
|
275 | |
|
|
276 | my @cookie; |
|
|
277 | |
|
|
278 | while (my ($chost, $v) = each %$jar) { |
|
|
279 | next unless $chost eq substr $uhost, -length $chost; |
|
|
280 | next unless $chost =~ /^\./; |
|
|
281 | |
|
|
282 | while (my ($cpath, $v) = each %$v) { |
|
|
283 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
284 | |
|
|
285 | while (my ($k, $v) = each %$v) { |
|
|
286 | next if $scheme ne "https" && exists $v->{secure}; |
|
|
287 | push @cookie, "$k=$v->{value}"; |
|
|
288 | } |
|
|
289 | } |
|
|
290 | } |
|
|
291 | |
|
|
292 | $hdr{cookie} = join "; ", @cookie |
|
|
293 | if @cookie; |
|
|
294 | } |
|
|
295 | |
|
|
296 | my ($rhost, $rport, $rpath); # request host, port, path |
139 | |
297 | |
140 | if ($proxy) { |
298 | if ($proxy) { |
141 | ($host, $port, $scheme) = @$proxy; |
299 | ($rhost, $rport, $scheme) = @$proxy; |
142 | $path = $url; |
300 | $rpath = $url; |
143 | } else { |
301 | } else { |
144 | ($scheme, my $authority, $path, my $query, my $fragment) = |
302 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
145 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
146 | |
|
|
147 | $port = $scheme eq "http" ? 80 |
|
|
148 | : $scheme eq "https" ? 443 |
|
|
149 | : croak "$url: only http and https URLs supported"; |
|
|
150 | |
|
|
151 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
152 | or croak "$authority: unparsable URL"; |
|
|
153 | |
|
|
154 | $host = $1; |
|
|
155 | $port = $2 if defined $2; |
|
|
156 | |
|
|
157 | $host =~ s/^\[(.*)\]$/$1/; |
|
|
158 | $path .= "?$query" if length $query; |
|
|
159 | |
|
|
160 | $path = "/" unless $path; |
|
|
161 | |
|
|
162 | $hdr{host} = $host = lc $host; |
303 | $hdr{host} = $uhost; |
163 | } |
304 | } |
164 | |
305 | |
165 | $scheme = lc $scheme; |
|
|
166 | |
|
|
167 | my %state; |
|
|
168 | |
|
|
169 | $state{body} = delete $arg{body}; |
|
|
170 | |
|
|
171 | $hdr{"content-length"} = length $state{body}; |
306 | $hdr{"content-length"} = length $arg{body}; |
172 | |
307 | |
|
|
308 | my %state = (connect_guard => 1); |
|
|
309 | |
|
|
310 | _get_slot $uhost, sub { |
|
|
311 | $state{slot_guard} = shift; |
|
|
312 | |
|
|
313 | return unless $state{connect_guard}; |
|
|
314 | |
173 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
174 | $state{fh} = shift |
316 | $state{fh} = shift |
175 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
176 | |
318 | |
177 | delete $state{connect_guard}; # reduce memory usage, save a tree |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
178 | |
320 | |
179 | # get handle |
321 | # get handle |
180 | $state{handle} = new AnyEvent::Handle |
322 | $state{handle} = new AnyEvent::Handle |
181 | fh => $state{fh}, |
323 | fh => $state{fh}, |
182 | ($scheme eq "https" ? (tls => "connect") : ()); |
324 | ($scheme eq "https" ? (tls => "connect") : ()); |
183 | |
325 | |
184 | # limit the number of persistent connections |
326 | # limit the number of persistent connections |
185 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
327 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
186 | ++$KA_COUNT{$_[1]}; |
328 | ++$KA_COUNT{$_[1]}; |
187 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
329 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
188 | $hdr{connection} = "keep-alive"; |
330 | $hdr{connection} = "keep-alive"; |
189 | delete $hdr{connection}; # keep-alive not yet supported |
331 | delete $hdr{connection}; # keep-alive not yet supported |
190 | } else { |
332 | } else { |
191 | delete $hdr{connection}; |
333 | delete $hdr{connection}; |
192 | } |
334 | } |
193 | |
335 | |
194 | # (re-)configure handle |
336 | # (re-)configure handle |
195 | $state{handle}->timeout ($timeout); |
337 | $state{handle}->timeout ($timeout); |
196 | $state{handle}->on_error (sub { |
338 | $state{handle}->on_error (sub { |
|
|
339 | my $errno = "$!"; |
197 | %state = (); |
340 | %state = (); |
198 | $cb->(undef, { Status => 599, Reason => "$!" }); |
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
199 | }); |
342 | }); |
200 | $state{handle}->on_eof (sub { |
343 | $state{handle}->on_eof (sub { |
201 | %state = (); |
344 | %state = (); |
202 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
203 | }); |
346 | }); |
204 | |
347 | |
205 | # send request |
348 | # send request |
206 | $state{handle}->push_write ( |
349 | $state{handle}->push_write ( |
207 | "$method $path HTTP/1.0\015\012" |
350 | "$method $rpath HTTP/1.0\015\012" |
208 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
351 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
209 | . "\015\012" |
352 | . "\015\012" |
210 | . (delete $state{body}) |
353 | . (delete $arg{body}) |
211 | ); |
|
|
212 | |
|
|
213 | %hdr = (); # reduce memory usage, save a kitten |
|
|
214 | |
|
|
215 | # status line |
|
|
216 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
217 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
218 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
219 | |
|
|
220 | my %hdr = ( # response headers |
|
|
221 | HTTPVersion => ",$1", |
|
|
222 | Status => ",$2", |
|
|
223 | Reason => ",$3", |
|
|
224 | ); |
354 | ); |
225 | |
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 | ); |
|
|
369 | |
226 | # headers, could be optimized a bit |
370 | # headers, could be optimized a bit |
227 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
228 | for ("$_[1]\012") { |
372 | for ("$_[1]\012") { |
229 | # we support spaces in field names, as lotus domino |
373 | # we support spaces in field names, as lotus domino |
230 | # creates them. |
374 | # creates them. |
231 | $hdr{lc $1} .= ",$2" |
375 | $hdr{lc $1} .= "\x00$2" |
232 | while /\G |
376 | while /\G |
233 | ([^:\000-\037]+): |
377 | ([^:\000-\037]+): |
234 | [\011\040]* |
378 | [\011\040]* |
235 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
236 | \015?\012 |
380 | \015?\012 |
237 | /gxc; |
381 | /gxc; |
238 | |
382 | |
239 | /\G$/ |
383 | /\G$/ |
240 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
384 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
241 | } |
385 | } |
242 | |
386 | |
243 | substr $_, 0, 1, "" |
387 | substr $_, 0, 1, "" |
244 | for values %hdr; |
388 | for values %hdr; |
245 | |
389 | |
246 | if ($method ne "HEAD") { |
390 | my $finish = sub { |
247 | if (exists $hdr{"content-length"}) { |
391 | %state = (); |
248 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
392 | |
249 | # could cache persistent connection now |
393 | # set-cookie processing |
250 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
394 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
251 | # but we don't, due to misdesigns, this is annoyingly complex |
395 | for (split /\x00/, $hdr{"set-cookie"}) { |
|
|
396 | my ($cookie, @arg) = split /;\s*/; |
|
|
397 | my ($name, $value) = split /=/, $cookie, 2; |
|
|
398 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
|
|
399 | |
|
|
400 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
401 | my $cpath = (delete $kv{path}) || "/"; |
|
|
402 | |
|
|
403 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
|
|
404 | |
|
|
405 | next if $cdom =~ /\.$/; |
|
|
406 | |
|
|
407 | # this is not rfc-like and not netscape-like. go figure. |
|
|
408 | my $ndots = $cdom =~ y/.//; |
|
|
409 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
410 | |
|
|
411 | # store it |
|
|
412 | $arg{cookie_jar}{version} = 1; |
|
|
413 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
252 | }; |
414 | } |
253 | |
|
|
254 | %state = (); |
|
|
255 | $cb->($_[1], \%hdr); |
|
|
256 | }); |
415 | } |
|
|
416 | |
|
|
417 | # microsoft and other assholes don't give a shit for following standards, |
|
|
418 | # try to support a common form of broken Location header. |
|
|
419 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/% |
|
|
420 | if exists $_[1]{location}; |
|
|
421 | |
|
|
422 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
423 | # apparently, mozilla et al. just change POST to GET here |
|
|
424 | # more research is needed before we do the same |
|
|
425 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
426 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
427 | # even http/1.1 is unlear on how to mutate the method |
|
|
428 | $method = "GET" unless $method eq "HEAD"; |
|
|
429 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
430 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
431 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
432 | } else { |
|
|
433 | $cb->($_[0], $_[1]); |
|
|
434 | } |
|
|
435 | }; |
|
|
436 | |
|
|
437 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
438 | $finish->(undef, \%hdr); |
257 | } else { |
439 | } else { |
|
|
440 | if (exists $hdr{"content-length"}) { |
|
|
441 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
442 | # could cache persistent connection now |
|
|
443 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
444 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
445 | }; |
|
|
446 | |
|
|
447 | $finish->($_[1], \%hdr); |
|
|
448 | }); |
|
|
449 | } else { |
258 | # too bad, need to read until we get an error or EOF, |
450 | # too bad, need to read until we get an error or EOF, |
259 | # no way to detect winged data. |
451 | # no way to detect winged data. |
260 | $_[0]->on_error (sub { |
452 | $_[0]->on_error (sub { |
261 | %state = (); |
|
|
262 | $cb->($_[0]{rbuf}, \%hdr); |
453 | $finish->($_[0]{rbuf}, \%hdr); |
263 | }); |
454 | }); |
264 | $_[0]->on_eof (undef); |
455 | $_[0]->on_eof (undef); |
265 | $_[0]->on_read (sub { }); |
456 | $_[0]->on_read (sub { }); |
|
|
457 | } |
266 | } |
458 | } |
267 | } |
459 | }); |
268 | }); |
460 | }); |
|
|
461 | }, sub { |
|
|
462 | $timeout |
269 | }); |
463 | }; |
270 | }, sub { |
|
|
271 | $timeout |
|
|
272 | }; |
464 | }; |
273 | |
465 | |
274 | defined wantarray && AnyEvent::Util::guard { %state = () } |
466 | defined wantarray && AnyEvent::Util::guard { %state = () } |
275 | } |
467 | } |
276 | |
468 | |
277 | sub http_get($$;@) { |
469 | sub http_get($@) { |
278 | unshift @_, "GET"; |
470 | unshift @_, "GET"; |
279 | &http_request |
471 | &http_request |
280 | } |
472 | } |
281 | |
473 | |
282 | sub http_post($$$;@) { |
474 | sub http_head($@) { |
283 | unshift @_, "POST", "body"; |
475 | unshift @_, "HEAD"; |
284 | &http_request |
476 | &http_request |
285 | } |
477 | } |
|
|
478 | |
|
|
479 | sub http_post($$@) { |
|
|
480 | my $url = shift; |
|
|
481 | unshift @_, "POST", $url, "body"; |
|
|
482 | &http_request |
|
|
483 | } |
|
|
484 | |
|
|
485 | =back |
286 | |
486 | |
287 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
487 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
288 | |
488 | |
289 | =over 4 |
489 | =over 4 |
290 | |
490 | |
… | |
… | |
312 | |
512 | |
313 | The maximum time to cache a persistent connection, in seconds (default: 2). |
513 | The maximum time to cache a persistent connection, in seconds (default: 2). |
314 | |
514 | |
315 | Not implemented currently. |
515 | Not implemented currently. |
316 | |
516 | |
|
|
517 | =item $AnyEvent::HTTP::ACTIVE |
|
|
518 | |
|
|
519 | The number of active connections. This is not the number of currently |
|
|
520 | running requests, but the number of currently open and non-idle TCP |
|
|
521 | connections. This number of can be useful for load-leveling. |
|
|
522 | |
317 | =back |
523 | =back |
318 | |
524 | |
319 | =cut |
525 | =cut |
320 | |
526 | |
321 | sub set_proxy($) { |
527 | sub set_proxy($) { |
… | |
… | |
329 | |
535 | |
330 | L<AnyEvent>. |
536 | L<AnyEvent>. |
331 | |
537 | |
332 | =head1 AUTHOR |
538 | =head1 AUTHOR |
333 | |
539 | |
334 | Marc Lehmann <schmorp@schmorp.de> |
540 | Marc Lehmann <schmorp@schmorp.de> |
335 | http://home.schmorp.de/ |
541 | http://home.schmorp.de/ |
336 | |
542 | |
337 | =cut |
543 | =cut |
338 | |
544 | |
339 | 1 |
545 | 1 |
340 | |
546 | |