… | |
… | |
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. |
13 | |
17 | |
|
|
18 | This module implements a simple, stateless and non-blocking HTTP |
|
|
19 | client. It supports GET, POST and other request methods, cookies and more, |
|
|
20 | all on a very low level. It can follow redirects supports proxies and |
|
|
21 | automatically limits the number of connections to the values specified in |
|
|
22 | the RFC. |
|
|
23 | |
|
|
24 | It should generally be a "good client" that is enough for most HTTP |
|
|
25 | tasks. Simple tasks should be simple, but complex tasks should still be |
|
|
26 | possible as the user retains control over request and response headers. |
|
|
27 | |
|
|
28 | The caller is responsible for authentication management, cookies (if |
|
|
29 | the simplistic implementation in this module doesn't suffice), referer |
|
|
30 | and other high-level protocol details for which this module offers only |
|
|
31 | limited support. |
|
|
32 | |
14 | =head2 METHODS |
33 | =head2 METHODS |
15 | |
34 | |
16 | =over 4 |
35 | =over 4 |
17 | |
36 | |
18 | =cut |
37 | =cut |
… | |
… | |
20 | package AnyEvent::HTTP; |
39 | package AnyEvent::HTTP; |
21 | |
40 | |
22 | use strict; |
41 | use strict; |
23 | no warnings; |
42 | no warnings; |
24 | |
43 | |
25 | use Carp; |
44 | use Errno (); |
26 | |
45 | |
27 | use AnyEvent (); |
46 | use AnyEvent 4.8 (); |
28 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
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 = '1.42'; |
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 $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
39 | our $MAX_REDIRECTS = 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 = 0; |
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. |
|
|
77 | |
|
|
78 | =item http_head $url, key => value..., $cb->($data, $headers) |
|
|
79 | |
|
|
80 | Executes an HTTP-HEAD request. See the http_request function for details |
|
|
81 | on additional parameters and the return value. |
|
|
82 | |
|
|
83 | =item http_post $url, $body, key => value..., $cb->($data, $headers) |
|
|
84 | |
|
|
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
|
|
86 | http_request function for details on additional parameters and the return |
|
|
87 | value. |
56 | |
88 | |
57 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
58 | |
90 | |
59 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
60 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
61 | |
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
|
|
98 | |
62 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response body data as first argument |
63 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if an error occured), and a hash-ref with response headers as |
64 | response headers as second argument. |
101 | second argument. |
65 | |
102 | |
66 | All the headers in that has are lowercased. In addition to the response |
103 | All the headers in that hash are lowercased. In addition to the response |
67 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
68 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
69 | name. |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
107 | requested URL when following redirects). |
|
|
108 | |
|
|
109 | If the server sends a header multiple times, then their contents will be |
|
|
110 | joined together with a comma (C<,>), as per the HTTP spec. |
70 | |
111 | |
71 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
72 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x> |
73 | and the C<Reason> pseudo-header will contain an error message. |
114 | (usually C<599>) and the C<Reason> pseudo-header will contain an error |
|
|
115 | message. |
|
|
116 | |
|
|
117 | A typical callback might look like this: |
|
|
118 | |
|
|
119 | sub { |
|
|
120 | my ($body, $hdr) = @_; |
|
|
121 | |
|
|
122 | if ($hdr->{Status} =~ /^2/) { |
|
|
123 | ... everything should be ok |
|
|
124 | } else { |
|
|
125 | print "error, $hdr->{Status} $hdr->{Reason}\n"; |
|
|
126 | } |
|
|
127 | } |
74 | |
128 | |
75 | Additional parameters are key-value pairs, and are fully optional. They |
129 | Additional parameters are key-value pairs, and are fully optional. They |
76 | include: |
130 | include: |
77 | |
131 | |
78 | =over 4 |
132 | =over 4 |
79 | |
133 | |
80 | =item recurse => $boolean (default: true) |
134 | =item recurse => $count (default: $MAX_RECURSE) |
81 | |
135 | |
82 | Whether to recurse requests or not, e.g. on redirects, authentication |
136 | Whether to recurse requests or not, e.g. on redirects, authentication |
83 | retries and so on. |
137 | retries and so on, and how often to do so. |
84 | |
138 | |
85 | =item headers => hashref |
139 | =item headers => hashref |
86 | |
140 | |
87 | The request headers to use. |
141 | The request headers to use. Currently, C<http_request> may provide its |
|
|
142 | own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers |
|
|
143 | and will provide defaults for C<User-Agent:> and C<Referer:> (this can be |
|
|
144 | suppressed by using C<undef> for these headers in which case they won't be |
|
|
145 | sent at all). |
88 | |
146 | |
89 | =item timeout => $seconds |
147 | =item timeout => $seconds |
90 | |
148 | |
91 | The time-out to use for various stages - each connect attempt will reset |
149 | The time-out to use for various stages - each connect attempt will reset |
92 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
150 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
… | |
… | |
94 | =item proxy => [$host, $port[, $scheme]] or undef |
152 | =item proxy => [$host, $port[, $scheme]] or undef |
95 | |
153 | |
96 | Use the given http proxy for all requests. If not specified, then the |
154 | Use the given http proxy for all requests. If not specified, then the |
97 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
155 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
98 | |
156 | |
99 | C<$scheme> must be either missing or C<http> for HTTP, or C<https> for |
157 | C<$scheme> must be either missing, C<http> for HTTP or C<https> for |
100 | HTTPS. |
158 | HTTPS. |
101 | |
159 | |
|
|
160 | =item body => $string |
|
|
161 | |
|
|
162 | The request body, usually empty. Will be-sent as-is (future versions of |
|
|
163 | this module might offer more options). |
|
|
164 | |
|
|
165 | =item cookie_jar => $hash_ref |
|
|
166 | |
|
|
167 | Passing this parameter enables (simplified) cookie-processing, loosely |
|
|
168 | based on the original netscape specification. |
|
|
169 | |
|
|
170 | The C<$hash_ref> must be an (initially empty) hash reference which will |
|
|
171 | get updated automatically. It is possible to save the cookie_jar to |
|
|
172 | persistent storage with something like JSON or Storable, but this is not |
|
|
173 | recommended, as expiry times are currently being ignored. |
|
|
174 | |
|
|
175 | Note that this cookie implementation is not of very high quality, nor |
|
|
176 | meant to be complete. If you want complete cookie management you have to |
|
|
177 | do that on your own. C<cookie_jar> is meant as a quick fix to get some |
|
|
178 | cookie-using sites working. Cookies are a privacy disaster, do not use |
|
|
179 | them unless required to. |
|
|
180 | |
|
|
181 | =item tls_ctx => $scheme | $tls_ctx |
|
|
182 | |
|
|
183 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
184 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
185 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
186 | C<high> can be specified, which give you a predefined low-security (no |
|
|
187 | verification, highest compatibility) and high-security (CA and common-name |
|
|
188 | verification) TLS context. |
|
|
189 | |
|
|
190 | The default for this option is C<low>, which could be interpreted as "give |
|
|
191 | me the page, no matter what". |
|
|
192 | |
|
|
193 | =item on_header => $callback->($headers) |
|
|
194 | |
|
|
195 | When specified, this callback will be called with the header hash as soon |
|
|
196 | as headers have been successfully received from the remote server (not on |
|
|
197 | locally-generated errors). |
|
|
198 | |
|
|
199 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
200 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
201 | the finish callback with an error code of C<598>). |
|
|
202 | |
|
|
203 | This callback is useful, among other things, to quickly reject unwanted |
|
|
204 | content, which, if it is supposed to be rare, can be faster than first |
|
|
205 | doing a C<HEAD> request. |
|
|
206 | |
|
|
207 | Example: cancel the request unless the content-type is "text/html". |
|
|
208 | |
|
|
209 | on_header => sub { |
|
|
210 | $_[0]{"content-type"} =~ /^text\/html\s*(?:;|$)/ |
|
|
211 | }, |
|
|
212 | |
|
|
213 | =item on_body => $callback->($partial_body, $headers) |
|
|
214 | |
|
|
215 | When specified, all body data will be passed to this callback instead of |
|
|
216 | to the completion callback. The completion callback will get the empty |
|
|
217 | string instead of the body data. |
|
|
218 | |
|
|
219 | It has to return either true (in which case AnyEvent::HTTP will continue), |
|
|
220 | or false, in which case AnyEvent::HTTP will cancel the download (and call |
|
|
221 | the completion callback with an error code of C<598>). |
|
|
222 | |
|
|
223 | This callback is useful when the data is too large to be held in memory |
|
|
224 | (so the callback writes it to a file) or when only some information should |
|
|
225 | be extracted, or when the body should be processed incrementally. |
|
|
226 | |
|
|
227 | It is usually preferred over doing your own body handling via |
|
|
228 | C<want_body_handle>, but in case of streaming APIs, where HTTP is |
|
|
229 | only used to create a connection, C<want_body_handle> is the better |
|
|
230 | alternative, as it allows you to install your own event handler, reducing |
|
|
231 | resource usage. |
|
|
232 | |
|
|
233 | =item want_body_handle => $enable |
|
|
234 | |
|
|
235 | When enabled (default is disabled), the behaviour of AnyEvent::HTTP |
|
|
236 | changes considerably: after parsing the headers, and instead of |
|
|
237 | downloading the body (if any), the completion callback will be |
|
|
238 | called. Instead of the C<$body> argument containing the body data, the |
|
|
239 | callback will receive the L<AnyEvent::Handle> object associated with the |
|
|
240 | connection. In error cases, C<undef> will be passed. When there is no body |
|
|
241 | (e.g. status C<304>), the empty string will be passed. |
|
|
242 | |
|
|
243 | The handle object might or might not be in TLS mode, might be connected to |
|
|
244 | a proxy, be a persistent connection etc., and configured in unspecified |
|
|
245 | ways. The user is responsible for this handle (it will not be used by this |
|
|
246 | module anymore). |
|
|
247 | |
|
|
248 | This is useful with some push-type services, where, after the initial |
|
|
249 | headers, an interactive protocol is used (typical example would be the |
|
|
250 | push-style twitter API which starts a JSON/XML stream). |
|
|
251 | |
|
|
252 | If you think you need this, first have a look at C<on_body>, to see if |
|
|
253 | that doesn't solve your problem in a better way. |
|
|
254 | |
102 | =back |
255 | =back |
103 | |
256 | |
104 | =back |
257 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
|
|
258 | |
|
|
259 | http_request GET => "http://www.nethype.de/", sub { |
|
|
260 | my ($body, $hdr) = @_; |
|
|
261 | print "$body\n"; |
|
|
262 | }; |
|
|
263 | |
|
|
264 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
|
|
265 | timeout of 30 seconds. |
|
|
266 | |
|
|
267 | http_request |
|
|
268 | GET => "https://www.google.com", |
|
|
269 | timeout => 30, |
|
|
270 | sub { |
|
|
271 | my ($body, $hdr) = @_; |
|
|
272 | use Data::Dumper; |
|
|
273 | print Dumper $hdr; |
|
|
274 | } |
|
|
275 | ; |
|
|
276 | |
|
|
277 | Example: make another simple HTTP GET request, but immediately try to |
|
|
278 | cancel it. |
|
|
279 | |
|
|
280 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
281 | my ($body, $hdr) = @_; |
|
|
282 | print "$body\n"; |
|
|
283 | }; |
|
|
284 | |
|
|
285 | undef $request; |
105 | |
286 | |
106 | =cut |
287 | =cut |
107 | |
288 | |
|
|
289 | sub _slot_schedule; |
|
|
290 | sub _slot_schedule($) { |
|
|
291 | my $host = shift; |
|
|
292 | |
|
|
293 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
|
|
294 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
|
|
295 | # somebody wants that slot |
|
|
296 | ++$CO_SLOT{$host}[0]; |
|
|
297 | ++$ACTIVE; |
|
|
298 | |
|
|
299 | $cb->(AnyEvent::Util::guard { |
|
|
300 | --$ACTIVE; |
|
|
301 | --$CO_SLOT{$host}[0]; |
|
|
302 | _slot_schedule $host; |
|
|
303 | }); |
|
|
304 | } else { |
|
|
305 | # nobody wants the slot, maybe we can forget about it |
|
|
306 | delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; |
|
|
307 | last; |
|
|
308 | } |
|
|
309 | } |
|
|
310 | } |
|
|
311 | |
|
|
312 | # wait for a free slot on host, call callback |
|
|
313 | sub _get_slot($$) { |
|
|
314 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
|
|
315 | |
|
|
316 | _slot_schedule $_[0]; |
|
|
317 | } |
|
|
318 | |
|
|
319 | our $qr_nl = qr{\015?\012}; |
|
|
320 | our $qr_nlnl = qr{(?<![^\012])\015?\012}; |
|
|
321 | |
|
|
322 | our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 }; |
|
|
323 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" }; |
|
|
324 | |
108 | sub http_request($$$;@) { |
325 | sub http_request($$@) { |
109 | my $cb = pop; |
326 | my $cb = pop; |
110 | my ($method, $url, %arg) = @_; |
327 | my ($method, $url, %arg) = @_; |
111 | |
328 | |
112 | my %hdr; |
329 | my %hdr; |
113 | |
330 | |
|
|
331 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
332 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
|
|
333 | |
|
|
334 | $method = uc $method; |
|
|
335 | |
114 | if (my $hdr = delete $arg{headers}) { |
336 | if (my $hdr = $arg{headers}) { |
115 | while (my ($k, $v) = each %$hdr) { |
337 | while (my ($k, $v) = each %$hdr) { |
116 | $hdr{lc $k} = $v; |
338 | $hdr{lc $k} = $v; |
117 | } |
339 | } |
118 | } |
340 | } |
119 | |
341 | |
|
|
342 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
|
|
343 | |
|
|
344 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
|
|
345 | if $recurse < 0; |
|
|
346 | |
120 | my $proxy = $arg{proxy} || $PROXY; |
347 | my $proxy = $arg{proxy} || $PROXY; |
121 | my $timeout = $arg{timeout} || $TIMEOUT; |
348 | my $timeout = $arg{timeout} || $TIMEOUT; |
122 | |
349 | |
123 | $hdr{"user-agent"} ||= $USERAGENT; |
350 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
|
|
351 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
124 | |
352 | |
125 | my ($host, $port, $path, $scheme); |
353 | $uscheme = lc $uscheme; |
|
|
354 | |
|
|
355 | my $uport = $uscheme eq "http" ? 80 |
|
|
356 | : $uscheme eq "https" ? 443 |
|
|
357 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url }); |
|
|
358 | |
|
|
359 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
360 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
|
|
361 | |
|
|
362 | my $uhost = $1; |
|
|
363 | $uport = $2 if defined $2; |
|
|
364 | |
|
|
365 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"; |
|
|
366 | |
|
|
367 | $uhost =~ s/^\[(.*)\]$/$1/; |
|
|
368 | $upath .= "?$query" if length $query; |
|
|
369 | |
|
|
370 | $upath =~ s%^/?%/%; |
|
|
371 | |
|
|
372 | # cookie processing |
|
|
373 | if (my $jar = $arg{cookie_jar}) { |
|
|
374 | %$jar = () if $jar->{version} != 1; |
|
|
375 | |
|
|
376 | my @cookie; |
|
|
377 | |
|
|
378 | while (my ($chost, $v) = each %$jar) { |
|
|
379 | if ($chost =~ /^\./) { |
|
|
380 | next unless $chost eq substr $uhost, -length $chost; |
|
|
381 | } elsif ($chost =~ /\./) { |
|
|
382 | next unless $chost eq $uhost; |
|
|
383 | } else { |
|
|
384 | next; |
|
|
385 | } |
|
|
386 | |
|
|
387 | while (my ($cpath, $v) = each %$v) { |
|
|
388 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
389 | |
|
|
390 | while (my ($k, $v) = each %$v) { |
|
|
391 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
392 | my $value = $v->{value}; |
|
|
393 | $value =~ s/([\\"])/\\$1/g; |
|
|
394 | push @cookie, "$k=\"$value\""; |
|
|
395 | } |
|
|
396 | } |
|
|
397 | } |
|
|
398 | |
|
|
399 | $hdr{cookie} = join "; ", @cookie |
|
|
400 | if @cookie; |
|
|
401 | } |
|
|
402 | |
|
|
403 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
126 | |
404 | |
127 | if ($proxy) { |
405 | if ($proxy) { |
128 | ($host, $port, $scheme) = @$proxy; |
406 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
129 | $path = $url; |
407 | |
|
|
408 | $rscheme = "http" unless defined $rscheme; |
|
|
409 | |
|
|
410 | # don't support https requests over https-proxy transport, |
|
|
411 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
412 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
130 | } else { |
413 | } else { |
131 | ($scheme, my $authority, $path, my $query, my $fragment) = |
414 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
132 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
133 | |
|
|
134 | $port = $scheme eq "http" ? 80 |
|
|
135 | : $scheme eq "https" ? 443 |
|
|
136 | : croak "$url: only http and https URLs supported"; |
|
|
137 | |
|
|
138 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
139 | or croak "$authority: unparsable URL"; |
|
|
140 | |
|
|
141 | $host = $1; |
|
|
142 | $port = $2 if defined $2; |
|
|
143 | |
|
|
144 | $host =~ s/^\[(.*)\]$/$1/; |
|
|
145 | $path .= "?$query" if length $query; |
|
|
146 | |
|
|
147 | $path = "/" unless $path; |
|
|
148 | |
|
|
149 | $hdr{host} = $host = lc $host; |
|
|
150 | } |
415 | } |
151 | |
416 | |
152 | $scheme = lc $scheme; |
417 | # leave out fragment and query string, just a heuristic |
|
|
418 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
|
|
419 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
153 | |
420 | |
154 | my %state; |
|
|
155 | |
|
|
156 | my $body = ""; |
|
|
157 | $state{body} = $body; |
|
|
158 | |
|
|
159 | $hdr{"content-length"} = length $body; |
421 | $hdr{"content-length"} = length $arg{body}; |
160 | |
422 | |
|
|
423 | my %state = (connect_guard => 1); |
|
|
424 | |
|
|
425 | _get_slot $uhost, sub { |
|
|
426 | $state{slot_guard} = shift; |
|
|
427 | |
|
|
428 | return unless $state{connect_guard}; |
|
|
429 | |
161 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
430 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
162 | $state{fh} = shift |
431 | $state{fh} = shift |
|
|
432 | or do { |
|
|
433 | my $err = "$!"; |
|
|
434 | %state = (); |
163 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
435 | return $cb->(undef, { Status => 599, Reason => $err, URL => $url }); |
|
|
436 | }; |
164 | |
437 | |
165 | delete $state{connect_guard}; # reduce memory usage, save a tree |
438 | pop; # free memory, save a tree |
166 | |
439 | |
|
|
440 | return unless delete $state{connect_guard}; |
|
|
441 | |
167 | # get handle |
442 | # get handle |
168 | $state{handle} = new AnyEvent::Handle |
443 | $state{handle} = new AnyEvent::Handle |
169 | fh => $state{fh}, |
444 | fh => $state{fh}, |
170 | ($scheme eq "https" ? (tls => "connect") : ()); |
445 | timeout => $timeout, |
|
|
446 | peername => $rhost, |
|
|
447 | tls_ctx => $arg{tls_ctx}; |
171 | |
448 | |
172 | # limit the number of persistent connections |
449 | # limit the number of persistent connections |
|
|
450 | # keepalive not yet supported |
173 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
451 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
174 | ++$KA_COUNT{$_[1]}; |
452 | ++$KA_COUNT{$_[1]}; |
175 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
453 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
454 | --$KA_COUNT{$_[1]} |
|
|
455 | }; |
176 | $hdr{connection} = "keep-alive"; |
456 | $hdr{connection} = "keep-alive"; |
177 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
178 | } else { |
457 | } else { |
179 | delete $hdr{connection}; |
458 | delete $hdr{connection}; |
180 | } |
459 | } |
181 | |
460 | |
182 | # (re-)configure handle |
461 | # (re-)configure handle |
183 | $state{handle}->timeout ($timeout); |
|
|
184 | $state{handle}->on_error (sub { |
462 | $state{handle}->on_error (sub { |
185 | %state = (); |
463 | %state = (); |
186 | $cb->(undef, { Status => 599, Reason => "$!" }); |
464 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
187 | }); |
465 | }); |
188 | $state{handle}->on_eof (sub { |
466 | $state{handle}->on_eof (sub { |
189 | %state = (); |
467 | %state = (); |
190 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
468 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
191 | }); |
|
|
192 | |
|
|
193 | # send request |
|
|
194 | $state{handle}->push_write ( |
|
|
195 | "\U$method\E $path HTTP/1.0\015\012" |
|
|
196 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
|
|
197 | . "\015\012" |
|
|
198 | . (delete $state{body}) |
|
|
199 | ); |
|
|
200 | |
|
|
201 | %hdr = (); # reduce memory usage, save a kitten |
|
|
202 | |
|
|
203 | # status line |
|
|
204 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
205 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
206 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
207 | |
|
|
208 | my %hdr = ( # response headers |
|
|
209 | HTTPVersion => ",$1", |
|
|
210 | Status => ",$2", |
|
|
211 | Reason => ",$3", |
|
|
212 | ); |
469 | }); |
213 | |
470 | |
|
|
471 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
472 | |
|
|
473 | # handle actual, non-tunneled, request |
|
|
474 | my $handle_actual_request = sub { |
|
|
475 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
476 | |
|
|
477 | # send request |
|
|
478 | $state{handle}->push_write ( |
|
|
479 | "$method $rpath HTTP/1.0\015\012" |
|
|
480 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
|
|
481 | . "\015\012" |
|
|
482 | . (delete $arg{body}) |
|
|
483 | ); |
|
|
484 | |
|
|
485 | %hdr = (); # reduce memory usage, save a kitten |
|
|
486 | |
|
|
487 | # status line |
|
|
488 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
489 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
490 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
491 | |
|
|
492 | my %hdr = ( # response headers |
|
|
493 | HTTPVersion => ",$1", |
|
|
494 | Status => ",$2", |
|
|
495 | Reason => ",$3", |
|
|
496 | URL => ",$url" |
|
|
497 | ); |
|
|
498 | |
214 | # headers, could be optimized a bit |
499 | # headers, could be optimized a bit |
215 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
500 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
216 | for ("$_[1]\012") { |
501 | for ("$_[1]") { |
217 | # we support spaces in field names, as lotus domino |
502 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
218 | # creates them. |
503 | |
|
|
504 | # things seen, not parsed: |
|
|
505 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
506 | |
219 | $hdr{lc $1} .= ",$2" |
507 | $hdr{lc $1} .= ",$2" |
220 | while /\G |
508 | while /\G |
221 | ([^:\000-\037]+): |
509 | ([^:\000-\037]*): |
222 | [\011\040]* |
510 | [\011\040]* |
223 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
511 | ((?: [^\012]+ | \012[\011\040] )*) |
224 | \015?\012 |
512 | \012 |
225 | /gxc; |
513 | /gxc; |
226 | |
514 | |
227 | /\G$/ |
515 | /\G$/ |
228 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
516 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
229 | } |
517 | } |
230 | |
518 | |
231 | substr $_, 0, 1, "" |
519 | substr $_, 0, 1, "" |
232 | for values %hdr; |
520 | for values %hdr; |
233 | |
521 | |
234 | if (exists $hdr{"content-length"}) { |
522 | # redirect handling |
235 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
523 | # microsoft and other shitheads don't give a shit for following standards, |
236 | # could cache persistent connection now |
524 | # try to support some common forms of broken Location headers. |
237 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
525 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
238 | # but we don't, due to misdesigns, this is annoyingly complex |
526 | $hdr{location} =~ s/^\.\/+//; |
|
|
527 | |
|
|
528 | my $url = "$rscheme://$uhost:$uport"; |
|
|
529 | |
|
|
530 | unless ($hdr{location} =~ s/^\///) { |
|
|
531 | $url .= $upath; |
|
|
532 | $url =~ s/\/[^\/]*$//; |
|
|
533 | } |
|
|
534 | |
|
|
535 | $hdr{location} = "$url/$hdr{location}"; |
|
|
536 | } |
|
|
537 | |
|
|
538 | my $redirect; |
|
|
539 | |
|
|
540 | if ($recurse) { |
|
|
541 | if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") { |
|
|
542 | # apparently, mozilla et al. just change POST to GET here |
|
|
543 | # more research is needed before we do the same |
|
|
544 | $redirect = 1; |
|
|
545 | } elsif ($hdr{Status} == 303) { |
|
|
546 | # even http/1.1 is unclear on how to mutate the method |
|
|
547 | $method = "GET" unless $method eq "HEAD"; |
|
|
548 | $redirect = 1; |
|
|
549 | } elsif ($hdr{Status} == 307 && $method =~ /^(?:GET|HEAD)$/) { |
|
|
550 | $redirect = 1; |
|
|
551 | } |
|
|
552 | } |
|
|
553 | |
|
|
554 | my $finish = sub { |
|
|
555 | $state{handle}->destroy if $state{handle}; |
|
|
556 | %state = (); |
|
|
557 | |
|
|
558 | # set-cookie processing |
|
|
559 | if ($arg{cookie_jar}) { |
|
|
560 | for ($_[1]{"set-cookie"}) { |
|
|
561 | # parse NAME=VALUE |
|
|
562 | my @kv; |
|
|
563 | |
|
|
564 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
565 | my $name = $1; |
|
|
566 | my $value = $3; |
|
|
567 | |
|
|
568 | unless ($value) { |
|
|
569 | $value = $2; |
|
|
570 | $value =~ s/\\(.)/$1/gs; |
|
|
571 | } |
|
|
572 | |
|
|
573 | push @kv, $name => $value; |
|
|
574 | |
|
|
575 | last unless /\G\s*;/gc; |
|
|
576 | } |
|
|
577 | |
|
|
578 | last unless @kv; |
|
|
579 | |
|
|
580 | my $name = shift @kv; |
|
|
581 | my %kv = (value => shift @kv, @kv); |
|
|
582 | |
|
|
583 | my $cdom; |
|
|
584 | my $cpath = (delete $kv{path}) || "/"; |
|
|
585 | |
|
|
586 | if (exists $kv{domain}) { |
|
|
587 | $cdom = delete $kv{domain}; |
|
|
588 | |
|
|
589 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
590 | |
|
|
591 | next if $cdom =~ /\.$/; |
|
|
592 | |
|
|
593 | # this is not rfc-like and not netscape-like. go figure. |
|
|
594 | my $ndots = $cdom =~ y/.//; |
|
|
595 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
596 | } else { |
|
|
597 | $cdom = $uhost; |
|
|
598 | } |
|
|
599 | |
|
|
600 | # store it |
|
|
601 | $arg{cookie_jar}{version} = 1; |
|
|
602 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
603 | |
|
|
604 | redo if /\G\s*,/gc; |
|
|
605 | } |
|
|
606 | } |
|
|
607 | |
|
|
608 | if ($redirect && exists $hdr{location}) { |
|
|
609 | # we ignore any errors, as it is very common to receive |
|
|
610 | # Content-Length != 0 but no actual body |
|
|
611 | # we also access %hdr, as $_[1] might be an erro |
|
|
612 | http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
613 | } else { |
|
|
614 | $cb->($_[0], $_[1]); |
|
|
615 | } |
239 | }; |
616 | }; |
240 | |
617 | |
|
|
618 | my $len = $hdr{"content-length"}; |
|
|
619 | |
|
|
620 | if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) { |
|
|
621 | $finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url }); |
|
|
622 | } elsif ( |
|
|
623 | $hdr{Status} =~ /^(?:1..|[23]04)$/ |
|
|
624 | or $method eq "HEAD" |
|
|
625 | or (defined $len && !$len) |
|
|
626 | ) { |
|
|
627 | # no body |
|
|
628 | $finish->("", \%hdr); |
|
|
629 | } else { |
|
|
630 | # body handling, four different code paths |
|
|
631 | # for want_body_handle, on_body (2x), normal (2x) |
|
|
632 | # we might read too much here, but it does not matter yet (no pers. connections) |
|
|
633 | if (!$redirect && $arg{want_body_handle}) { |
|
|
634 | $_[0]->on_eof (undef); |
|
|
635 | $_[0]->on_error (undef); |
|
|
636 | $_[0]->on_read (undef); |
|
|
637 | |
|
|
638 | $finish->(delete $state{handle}, \%hdr); |
|
|
639 | |
|
|
640 | } elsif ($arg{on_body}) { |
|
|
641 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
642 | if ($len) { |
|
|
643 | $_[0]->on_eof (undef); |
|
|
644 | $_[0]->on_read (sub { |
|
|
645 | $len -= length $_[0]{rbuf}; |
|
|
646 | |
|
|
647 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
648 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
649 | |
|
|
650 | $len > 0 |
|
|
651 | or $finish->("", \%hdr); |
|
|
652 | }); |
|
|
653 | } else { |
|
|
654 | $_[0]->on_eof (sub { |
|
|
655 | $finish->("", \%hdr); |
|
|
656 | }); |
|
|
657 | $_[0]->on_read (sub { |
|
|
658 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
|
|
659 | or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url }); |
|
|
660 | }); |
|
|
661 | } |
|
|
662 | } else { |
|
|
663 | $_[0]->on_eof (undef); |
|
|
664 | |
|
|
665 | if ($len) { |
|
|
666 | $_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) }); |
|
|
667 | $_[0]->on_read (sub { |
|
|
668 | $finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr) |
|
|
669 | if $len <= length $_[0]{rbuf}; |
|
|
670 | }); |
|
|
671 | } else { |
|
|
672 | $_[0]->on_error (sub { |
|
|
673 | $! == Errno::EPIPE || !$! |
|
|
674 | ? $finish->(delete $_[0]{rbuf}, \%hdr) |
|
|
675 | : $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
|
|
676 | }); |
|
|
677 | $_[0]->on_read (sub { }); |
|
|
678 | } |
|
|
679 | } |
|
|
680 | } |
|
|
681 | }); |
|
|
682 | }); |
|
|
683 | }; |
|
|
684 | |
|
|
685 | # now handle proxy-CONNECT method |
|
|
686 | if ($proxy && $uscheme eq "https") { |
|
|
687 | # oh dear, we have to wrap it into a connect request |
|
|
688 | |
|
|
689 | # maybe re-use $uauthority with patched port? |
|
|
690 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
691 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
692 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
693 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
|
|
694 | |
|
|
695 | if ($2 == 200) { |
|
|
696 | $rpath = $upath; |
|
|
697 | &$handle_actual_request; |
|
|
698 | } else { |
241 | %state = (); |
699 | %state = (); |
242 | $cb->($_[1], \%hdr); |
700 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
243 | }); |
701 | } |
244 | } else { |
|
|
245 | # too bad, need to read until we get an error or EOF, |
|
|
246 | # no way to detect winged data. |
|
|
247 | $_[0]->on_error (sub { |
|
|
248 | %state = (); |
|
|
249 | $cb->($_[0]{rbuf}, \%hdr); |
|
|
250 | }); |
|
|
251 | $_[0]->on_eof (undef); |
|
|
252 | $_[0]->on_read (sub { }); |
|
|
253 | } |
702 | }); |
|
|
703 | } else { |
|
|
704 | &$handle_actual_request; |
254 | }); |
705 | } |
|
|
706 | |
|
|
707 | }, sub { |
|
|
708 | $timeout |
255 | }); |
709 | }; |
256 | }, sub { |
|
|
257 | $timeout |
|
|
258 | }; |
710 | }; |
259 | |
711 | |
260 | defined wantarray && AnyEvent::Util::guard { %state = () } |
712 | defined wantarray && AnyEvent::Util::guard { %state = () } |
261 | } |
713 | } |
262 | |
714 | |
263 | sub http_get($$;@) { |
715 | sub http_get($@) { |
264 | unshift @_, "GET"; |
716 | unshift @_, "GET"; |
265 | &http_request |
717 | &http_request |
266 | } |
718 | } |
267 | |
719 | |
|
|
720 | sub http_head($@) { |
|
|
721 | unshift @_, "HEAD"; |
|
|
722 | &http_request |
|
|
723 | } |
|
|
724 | |
|
|
725 | sub http_post($$@) { |
|
|
726 | my $url = shift; |
|
|
727 | unshift @_, "POST", $url, "body"; |
|
|
728 | &http_request |
|
|
729 | } |
|
|
730 | |
|
|
731 | =back |
|
|
732 | |
268 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
733 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
269 | |
734 | |
270 | =over 4 |
735 | =over 4 |
271 | |
736 | |
272 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
737 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
273 | |
738 | |
274 | Sets the default proxy server to use. The proxy-url must begin with a |
739 | Sets the default proxy server to use. The proxy-url must begin with a |
275 | string of the form C<http://host:port> (optionally C<https:...>). |
740 | string of the form C<http://host:port> (optionally C<https:...>). |
276 | |
741 | |
277 | =item $AnyEvent::HTTP::MAX_REDIRECTS |
742 | =item $AnyEvent::HTTP::MAX_RECURSE |
278 | |
743 | |
279 | The default value for the C<max_redirects> request parameter |
744 | The default value for the C<recurse> request parameter (default: C<10>). |
280 | (default: C<10>). |
|
|
281 | |
745 | |
282 | =item $AnyEvent::HTTP::USERAGENT |
746 | =item $AnyEvent::HTTP::USERAGENT |
283 | |
747 | |
284 | The default value for the C<User-Agent> header (the default is |
748 | The default value for the C<User-Agent> header (the default is |
285 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
749 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
286 | |
750 | |
287 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
751 | =item $AnyEvent::HTTP::MAX_PER_HOST |
288 | |
752 | |
289 | The maximum number of persistent connections to keep open (default: 8). |
753 | The maximum number of concurrent connections to the same host (identified |
|
|
754 | by the hostname). If the limit is exceeded, then the additional requests |
|
|
755 | are queued until previous connections are closed. |
290 | |
756 | |
291 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
757 | The default value for this is C<4>, and it is highly advisable to not |
|
|
758 | increase it. |
292 | |
759 | |
293 | The maximum time to cache a persistent connection, in seconds (default: 2). |
760 | =item $AnyEvent::HTTP::ACTIVE |
|
|
761 | |
|
|
762 | The number of active connections. This is not the number of currently |
|
|
763 | running requests, but the number of currently open and non-idle TCP |
|
|
764 | connections. This number of can be useful for load-leveling. |
294 | |
765 | |
295 | =back |
766 | =back |
296 | |
767 | |
297 | =cut |
768 | =cut |
298 | |
769 | |
… | |
… | |
307 | |
778 | |
308 | L<AnyEvent>. |
779 | L<AnyEvent>. |
309 | |
780 | |
310 | =head1 AUTHOR |
781 | =head1 AUTHOR |
311 | |
782 | |
312 | Marc Lehmann <schmorp@schmorp.de> |
783 | Marc Lehmann <schmorp@schmorp.de> |
313 | http://home.schmorp.de/ |
784 | http://home.schmorp.de/ |
|
|
785 | |
|
|
786 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
787 | testcases and bugreports. |
314 | |
788 | |
315 | =cut |
789 | =cut |
316 | |
790 | |
317 | 1 |
791 | 1 |
318 | |
792 | |