… | |
… | |
52 | =item http_get $url, key => value..., $cb->($data, $headers) |
52 | =item http_get $url, key => value..., $cb->($data, $headers) |
53 | |
53 | |
54 | Executes an HTTP-GET request. See the http_request function for details on |
54 | Executes an HTTP-GET request. See the http_request function for details on |
55 | additional parameters. |
55 | additional parameters. |
56 | |
56 | |
|
|
57 | =item http_head $url, key => value..., $cb->($data, $headers) |
|
|
58 | |
|
|
59 | Executes an HTTP-HEAD request. See the http_request function for details on |
|
|
60 | additional parameters. |
|
|
61 | |
57 | =item http_get $url, $body, key => value..., $cb->($data, $headers) |
62 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
58 | |
63 | |
59 | Executes an HTTP-POST request with a requets body of C<$bod>. See the |
64 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
60 | http_request function for details on additional parameters. |
65 | http_request function for details on additional parameters. |
61 | |
66 | |
62 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
67 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
63 | |
68 | |
64 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
69 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
… | |
… | |
66 | |
71 | |
67 | The callback will be called with the response data as first argument |
72 | The callback will be called with the response data as first argument |
68 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
73 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
69 | response headers as second argument. |
74 | response headers as second argument. |
70 | |
75 | |
71 | All the headers in that has are lowercased. In addition to the response |
76 | All the headers in that hash are lowercased. In addition to the response |
72 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
77 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
73 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
78 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
74 | name. |
79 | name. If the server sends a header multiple lines, then their contents |
|
|
80 | will be joined together with C<\x00>. |
75 | |
81 | |
76 | If an internal error occurs, such as not being able to resolve a hostname, |
82 | If an internal error occurs, such as not being able to resolve a hostname, |
77 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
83 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
78 | and the C<Reason> pseudo-header will contain an error message. |
84 | and the C<Reason> pseudo-header will contain an error message. |
79 | |
85 | |
|
|
86 | A typical callback might look like this: |
|
|
87 | |
|
|
88 | sub { |
|
|
89 | my ($body, $hdr) = @_; |
|
|
90 | |
|
|
91 | if ($hdr->{Status} =~ /^2/) { |
|
|
92 | ... everything should be ok |
|
|
93 | } else { |
|
|
94 | print "error, $hdr->{Status} $hdr->{Reason}\n"; |
|
|
95 | } |
|
|
96 | } |
|
|
97 | |
80 | Additional parameters are key-value pairs, and are fully optional. They |
98 | Additional parameters are key-value pairs, and are fully optional. They |
81 | include: |
99 | include: |
82 | |
100 | |
83 | =over 4 |
101 | =over 4 |
84 | |
102 | |
… | |
… | |
107 | =item body => $string |
125 | =item body => $string |
108 | |
126 | |
109 | The request body, usually empty. Will be-sent as-is (future versions of |
127 | The request body, usually empty. Will be-sent as-is (future versions of |
110 | this module might offer more options). |
128 | this module might offer more options). |
111 | |
129 | |
|
|
130 | =item cookie_jar => $hash_ref |
|
|
131 | |
|
|
132 | Passing this parameter enables (simplified) cookie-processing, loosely |
|
|
133 | based on the original netscape specification. |
|
|
134 | |
|
|
135 | The C<$hash_ref> must be an (initially empty) hash reference which will |
|
|
136 | get updated automatically. It is possible to save the cookie_jar to |
|
|
137 | persistent storage with something like JSON or Storable, but this is not |
|
|
138 | recommended, as expire times are currently being ignored. |
|
|
139 | |
|
|
140 | Note that this cookie implementation is not of very high quality, nor |
|
|
141 | meant to be complete. If you want complete cookie management you have to |
|
|
142 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
|
|
143 | cookie-using sites working. Cookies are a privacy disaster, do not use |
|
|
144 | them unless required to. |
|
|
145 | |
112 | =back |
146 | =back |
113 | |
147 | |
114 | =back |
148 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
|
|
149 | |
|
|
150 | http_request GET => "http://www.nethype.de/", sub { |
|
|
151 | my ($body, $hdr) = @_; |
|
|
152 | print "$body\n"; |
|
|
153 | }; |
|
|
154 | |
|
|
155 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
|
|
156 | timeout of 30 seconds. |
|
|
157 | |
|
|
158 | http_request |
|
|
159 | GET => "https://www.google.com", |
|
|
160 | timeout => 30, |
|
|
161 | sub { |
|
|
162 | my ($body, $hdr) = @_; |
|
|
163 | use Data::Dumper; |
|
|
164 | print Dumper $hdr; |
|
|
165 | } |
|
|
166 | ; |
115 | |
167 | |
116 | =cut |
168 | =cut |
117 | |
169 | |
118 | sub http_request($$$;@) { |
170 | sub http_request($$$;@) { |
119 | my $cb = pop; |
171 | my $cb = pop; |
… | |
… | |
121 | |
173 | |
122 | my %hdr; |
174 | my %hdr; |
123 | |
175 | |
124 | $method = uc $method; |
176 | $method = uc $method; |
125 | |
177 | |
126 | if (my $hdr = delete $arg{headers}) { |
178 | if (my $hdr = $arg{headers}) { |
127 | while (my ($k, $v) = each %$hdr) { |
179 | while (my ($k, $v) = each %$hdr) { |
128 | $hdr{lc $k} = $v; |
180 | $hdr{lc $k} = $v; |
129 | } |
181 | } |
130 | } |
182 | } |
131 | |
183 | |
|
|
184 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
|
|
185 | |
|
|
186 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) |
|
|
187 | if $recurse < 0; |
|
|
188 | |
132 | my $proxy = $arg{proxy} || $PROXY; |
189 | my $proxy = $arg{proxy} || $PROXY; |
133 | my $timeout = $arg{timeout} || $TIMEOUT; |
190 | my $timeout = $arg{timeout} || $TIMEOUT; |
134 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
|
|
135 | |
191 | |
136 | $hdr{"user-agent"} ||= $USERAGENT; |
192 | $hdr{"user-agent"} ||= $USERAGENT; |
137 | |
193 | |
138 | my ($host, $port, $path, $scheme); |
194 | my ($scheme, $authority, $upath, $query, $fragment) = |
|
|
195 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
196 | |
|
|
197 | $scheme = lc $scheme; |
|
|
198 | |
|
|
199 | my $uport = $scheme eq "http" ? 80 |
|
|
200 | : $scheme eq "https" ? 443 |
|
|
201 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); |
|
|
202 | |
|
|
203 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
204 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); |
|
|
205 | |
|
|
206 | my $uhost = $1; |
|
|
207 | $uport = $2 if defined $2; |
|
|
208 | |
|
|
209 | $uhost =~ s/^\[(.*)\]$/$1/; |
|
|
210 | $upath .= "?$query" if length $query; |
|
|
211 | |
|
|
212 | $upath =~ s%^/?%/%; |
|
|
213 | |
|
|
214 | # cookie processing |
|
|
215 | if (my $jar = $arg{cookie_jar}) { |
|
|
216 | %$jar = () if $jar->{version} < 1; |
|
|
217 | |
|
|
218 | my @cookie; |
|
|
219 | |
|
|
220 | while (my ($chost, $v) = each %$jar) { |
|
|
221 | next unless $chost eq substr $uhost, -length $chost; |
|
|
222 | next unless $chost =~ /^\./; |
|
|
223 | |
|
|
224 | while (my ($cpath, $v) = each %$v) { |
|
|
225 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
226 | |
|
|
227 | while (my ($k, $v) = each %$v) { |
|
|
228 | next if $scheme ne "https" && exists $v->{secure}; |
|
|
229 | push @cookie, "$k=$v->{value}"; |
|
|
230 | } |
|
|
231 | } |
|
|
232 | } |
|
|
233 | |
|
|
234 | $hdr{cookie} = join "; ", @cookie |
|
|
235 | if @cookie; |
|
|
236 | } |
|
|
237 | |
|
|
238 | my ($rhost, $rport, $rpath); # request host, port, path |
139 | |
239 | |
140 | if ($proxy) { |
240 | if ($proxy) { |
141 | ($host, $port, $scheme) = @$proxy; |
241 | ($rhost, $rport, $scheme) = @$proxy; |
142 | $path = $url; |
242 | $rpath = $url; |
143 | } else { |
243 | } else { |
144 | ($scheme, my $authority, $path, my $query, my $fragment) = |
244 | ($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; |
245 | $hdr{host} = $uhost; |
163 | } |
246 | } |
164 | |
247 | |
165 | $scheme = lc $scheme; |
248 | $hdr{"content-length"} = length $arg{body}; |
166 | |
249 | |
167 | my %state; |
250 | my %state; |
168 | |
251 | |
169 | $state{body} = delete $arg{body}; |
|
|
170 | |
|
|
171 | $hdr{"content-length"} = length $state{body}; |
|
|
172 | |
|
|
173 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
252 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
174 | $state{fh} = shift |
253 | $state{fh} = shift |
175 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
254 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
176 | |
255 | |
177 | delete $state{connect_guard}; # reduce memory usage, save a tree |
256 | delete $state{connect_guard}; # reduce memory usage, save a tree |
178 | |
257 | |
… | |
… | |
202 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
281 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
203 | }); |
282 | }); |
204 | |
283 | |
205 | # send request |
284 | # send request |
206 | $state{handle}->push_write ( |
285 | $state{handle}->push_write ( |
207 | "$method $path HTTP/1.0\015\012" |
286 | "$method $rpath HTTP/1.0\015\012" |
208 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
287 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
209 | . "\015\012" |
288 | . "\015\012" |
210 | . (delete $state{body}) |
289 | . (delete $arg{body}) |
211 | ); |
290 | ); |
212 | |
291 | |
213 | %hdr = (); # reduce memory usage, save a kitten |
292 | %hdr = (); # reduce memory usage, save a kitten |
214 | |
293 | |
215 | # status line |
294 | # status line |
216 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
295 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
217 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
296 | $_[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])" })); |
297 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
219 | |
298 | |
220 | my %hdr = ( # response headers |
299 | my %hdr = ( # response headers |
221 | HTTPVersion => ",$1", |
300 | HTTPVersion => "\x00$1", |
222 | Status => ",$2", |
301 | Status => "\x00$2", |
223 | Reason => ",$3", |
302 | Reason => "\x00$3", |
224 | ); |
303 | ); |
225 | |
304 | |
226 | # headers, could be optimized a bit |
305 | # headers, could be optimized a bit |
227 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
306 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
228 | for ("$_[1]\012") { |
307 | for ("$_[1]\012") { |
229 | # we support spaces in field names, as lotus domino |
308 | # we support spaces in field names, as lotus domino |
230 | # creates them. |
309 | # creates them. |
231 | $hdr{lc $1} .= ",$2" |
310 | $hdr{lc $1} .= "\x00$2" |
232 | while /\G |
311 | while /\G |
233 | ([^:\000-\037]+): |
312 | ([^:\000-\037]+): |
234 | [\011\040]* |
313 | [\011\040]* |
235 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
314 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
236 | \015?\012 |
315 | \015?\012 |
237 | /gxc; |
316 | /gxc; |
238 | |
317 | |
239 | /\G$/ |
318 | /\G$/ |
240 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
319 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); |
241 | } |
320 | } |
242 | |
321 | |
243 | substr $_, 0, 1, "" |
322 | substr $_, 0, 1, "" |
244 | for values %hdr; |
323 | for values %hdr; |
245 | |
324 | |
246 | if ($method ne "HEAD") { |
325 | my $finish = sub { |
|
|
326 | %state = (); |
|
|
327 | |
|
|
328 | # set-cookie processing |
|
|
329 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
|
|
330 | for (split /\x00/, $hdr{"set-cookie"}) { |
|
|
331 | my ($cookie, @arg) = split /;\s*/; |
|
|
332 | my ($name, $value) = split /=/, $cookie, 2; |
|
|
333 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
|
|
334 | |
|
|
335 | my $cdom = (delete $kv{domain}) || $uhost; |
|
|
336 | my $cpath = (delete $kv{path}) || "/"; |
|
|
337 | |
|
|
338 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
|
|
339 | |
|
|
340 | my $ndots = $cdom =~ y/.//; |
|
|
341 | next if $ndots < ($cdom =~ /[^.]{3}$/ ? 2 : 3); |
|
|
342 | |
|
|
343 | # store it |
|
|
344 | $arg{cookie_jar}{version} = 1; |
|
|
345 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
346 | } |
|
|
347 | } |
|
|
348 | |
|
|
349 | if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) { |
|
|
350 | # microsoft and other assholes don't give a shit for following standards, |
|
|
351 | # try to support a common form of broken Location header. |
|
|
352 | $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; |
|
|
353 | |
|
|
354 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
355 | } else { |
|
|
356 | $cb->($_[0], $_[1]); |
|
|
357 | } |
|
|
358 | }; |
|
|
359 | |
|
|
360 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
361 | $finish->(undef, \%hdr); |
|
|
362 | } else { |
247 | if (exists $hdr{"content-length"}) { |
363 | if (exists $hdr{"content-length"}) { |
248 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
364 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
249 | # could cache persistent connection now |
365 | # could cache persistent connection now |
250 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
366 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
251 | # but we don't, due to misdesigns, this is annoyingly complex |
367 | # but we don't, due to misdesigns, this is annoyingly complex |
252 | }; |
368 | }; |
253 | |
369 | |
254 | %state = (); |
|
|
255 | $cb->($_[1], \%hdr); |
370 | $finish->($_[1], \%hdr); |
256 | }); |
371 | }); |
257 | } else { |
372 | } else { |
258 | # too bad, need to read until we get an error or EOF, |
373 | # too bad, need to read until we get an error or EOF, |
259 | # no way to detect winged data. |
374 | # no way to detect winged data. |
260 | $_[0]->on_error (sub { |
375 | $_[0]->on_error (sub { |
261 | %state = (); |
|
|
262 | $cb->($_[0]{rbuf}, \%hdr); |
376 | $finish->($_[0]{rbuf}, \%hdr); |
263 | }); |
377 | }); |
264 | $_[0]->on_eof (undef); |
378 | $_[0]->on_eof (undef); |
265 | $_[0]->on_read (sub { }); |
379 | $_[0]->on_read (sub { }); |
266 | } |
380 | } |
267 | } |
381 | } |
… | |
… | |
277 | sub http_get($$;@) { |
391 | sub http_get($$;@) { |
278 | unshift @_, "GET"; |
392 | unshift @_, "GET"; |
279 | &http_request |
393 | &http_request |
280 | } |
394 | } |
281 | |
395 | |
|
|
396 | sub http_head($$;@) { |
|
|
397 | unshift @_, "HEAD"; |
|
|
398 | &http_request |
|
|
399 | } |
|
|
400 | |
282 | sub http_post($$$;@) { |
401 | sub http_post($$$;@) { |
283 | unshift @_, "POST", "body"; |
402 | unshift @_, "POST", "body"; |
284 | &http_request |
403 | &http_request |
285 | } |
404 | } |
286 | |
405 | |
|
|
406 | =back |
|
|
407 | |
287 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
408 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
288 | |
409 | |
289 | =over 4 |
410 | =over 4 |
290 | |
411 | |
291 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
412 | =item AnyEvent::HTTP::set_proxy "proxy-url" |