| … | |
… | |
| 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 |
| … | |
… | |
| 22 | use strict; |
41 | use strict; |
| 23 | no warnings; |
42 | no warnings; |
| 24 | |
43 | |
| 25 | use Carp; |
44 | use Carp; |
| 26 | |
45 | |
| 27 | use AnyEvent (); |
46 | use AnyEvent 4.452 (); |
| 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 = '1.12'; |
| 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_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<$method> (e.g. C<GET>, C<POST>). The URL |
| 70 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
|
|
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
| 71 | |
98 | |
| 72 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response data as first argument |
| 73 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
| 74 | response headers as second argument. |
101 | response headers as second argument. |
| 75 | |
102 | |
| 76 | All the headers in that hash are lowercased. In addition to the response |
103 | All the headers in that hash are lowercased. In addition to the response |
| 77 | headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
| 78 | C<Reason> contain the three parts of the HTTP Status-Line of the same |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
| 79 | name. |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
|
|
107 | requested URL when following redirects). |
|
|
108 | |
|
|
109 | If the server sends a header multiple times, then their contents will be |
|
|
110 | joined together with a comma (C<,>), as per the HTTP spec. |
| 80 | |
111 | |
| 81 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
| 82 | then C<$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. |
| … | |
… | |
| 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). |
| 128 | |
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 expiry 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. |
|
|
177 | |
|
|
178 | =item tls_ctx => $scheme | $tls_ctx |
|
|
179 | |
|
|
180 | Specifies the AnyEvent::TLS context to be used for https connections. This |
|
|
181 | parameter follows the same rules as the C<tls_ctx> parameter to |
|
|
182 | L<AnyEvent::Handle>, but additionally, the two strings C<low> or |
|
|
183 | C<high> can be specified, which give you a predefined low-security (no |
|
|
184 | verification, highest compatibility) and high-security (CA and common-name |
|
|
185 | verification) TLS context. |
|
|
186 | |
|
|
187 | The default for this option is C<low>, which could be interpreted as "give |
|
|
188 | me the page, no matter what". |
|
|
189 | |
| 129 | =back |
190 | =back |
| 130 | |
191 | |
| 131 | =back |
192 | Example: make a simple HTTP GET request for http://www.nethype.de/ |
|
|
193 | |
|
|
194 | http_request GET => "http://www.nethype.de/", sub { |
|
|
195 | my ($body, $hdr) = @_; |
|
|
196 | print "$body\n"; |
|
|
197 | }; |
|
|
198 | |
|
|
199 | Example: make a HTTP HEAD request on https://www.google.com/, use a |
|
|
200 | timeout of 30 seconds. |
|
|
201 | |
|
|
202 | http_request |
|
|
203 | GET => "https://www.google.com", |
|
|
204 | timeout => 30, |
|
|
205 | sub { |
|
|
206 | my ($body, $hdr) = @_; |
|
|
207 | use Data::Dumper; |
|
|
208 | print Dumper $hdr; |
|
|
209 | } |
|
|
210 | ; |
|
|
211 | |
|
|
212 | Example: make another simple HTTP GET request, but immediately try to |
|
|
213 | cancel it. |
|
|
214 | |
|
|
215 | my $request = http_request GET => "http://www.nethype.de/", sub { |
|
|
216 | my ($body, $hdr) = @_; |
|
|
217 | print "$body\n"; |
|
|
218 | }; |
|
|
219 | |
|
|
220 | undef $request; |
| 132 | |
221 | |
| 133 | =cut |
222 | =cut |
| 134 | |
223 | |
|
|
224 | sub _slot_schedule; |
|
|
225 | sub _slot_schedule($) { |
|
|
226 | my $host = shift; |
|
|
227 | |
|
|
228 | while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { |
|
|
229 | if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { |
|
|
230 | # somebody wants that slot |
|
|
231 | ++$CO_SLOT{$host}[0]; |
|
|
232 | ++$ACTIVE; |
|
|
233 | |
|
|
234 | $cb->(AnyEvent::Util::guard { |
|
|
235 | --$ACTIVE; |
|
|
236 | --$CO_SLOT{$host}[0]; |
|
|
237 | _slot_schedule $host; |
|
|
238 | }); |
|
|
239 | } else { |
|
|
240 | # nobody wants the slot, maybe we can forget about it |
|
|
241 | delete $CO_SLOT{$host} unless $CO_SLOT{$host}[0]; |
|
|
242 | last; |
|
|
243 | } |
|
|
244 | } |
|
|
245 | } |
|
|
246 | |
|
|
247 | # wait for a free slot on host, call callback |
|
|
248 | sub _get_slot($$) { |
|
|
249 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
|
|
250 | |
|
|
251 | _slot_schedule $_[0]; |
|
|
252 | } |
|
|
253 | |
|
|
254 | our $qr_nl = qr<\015?\012>; |
|
|
255 | our $qr_nlnl = qr<\015?\012\015?\012>; |
|
|
256 | |
|
|
257 | our $TLS_CTX_LOW = { cache => 1, dh => undef, sslv2 => 1 }; |
|
|
258 | our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_cn => "https", dh => "skip4096" }; |
|
|
259 | |
| 135 | sub http_request($$$;@) { |
260 | sub http_request($$@) { |
| 136 | my $cb = pop; |
261 | my $cb = pop; |
| 137 | my ($method, $url, %arg) = @_; |
262 | my ($method, $url, %arg) = @_; |
| 138 | |
263 | |
| 139 | my %hdr; |
264 | my %hdr; |
| 140 | |
265 | |
|
|
266 | $arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" || !exists $arg{tls_ctx}; |
|
|
267 | $arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high"; |
|
|
268 | |
| 141 | $method = uc $method; |
269 | $method = uc $method; |
| 142 | |
270 | |
| 143 | if (my $hdr = delete $arg{headers}) { |
271 | if (my $hdr = $arg{headers}) { |
| 144 | while (my ($k, $v) = each %$hdr) { |
272 | while (my ($k, $v) = each %$hdr) { |
| 145 | $hdr{lc $k} = $v; |
273 | $hdr{lc $k} = $v; |
| 146 | } |
274 | } |
| 147 | } |
275 | } |
| 148 | |
276 | |
|
|
277 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
|
|
278 | |
|
|
279 | return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url }) |
|
|
280 | if $recurse < 0; |
|
|
281 | |
| 149 | my $proxy = $arg{proxy} || $PROXY; |
282 | my $proxy = $arg{proxy} || $PROXY; |
| 150 | my $timeout = $arg{timeout} || $TIMEOUT; |
283 | my $timeout = $arg{timeout} || $TIMEOUT; |
| 151 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
|
|
| 152 | |
284 | |
| 153 | $hdr{"user-agent"} ||= $USERAGENT; |
285 | $hdr{"user-agent"} ||= $USERAGENT; |
| 154 | |
286 | |
| 155 | my ($host, $port, $path, $scheme); |
287 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
|
|
288 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
289 | |
|
|
290 | $uscheme = lc $uscheme; |
|
|
291 | |
|
|
292 | my $uport = $uscheme eq "http" ? 80 |
|
|
293 | : $uscheme eq "https" ? 443 |
|
|
294 | : return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported (not '$uscheme')", URL => $url }); |
|
|
295 | |
|
|
296 | $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic |
|
|
297 | |
|
|
298 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
299 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
|
|
300 | |
|
|
301 | my $uhost = $1; |
|
|
302 | $uport = $2 if defined $2; |
|
|
303 | |
|
|
304 | $uhost =~ s/^\[(.*)\]$/$1/; |
|
|
305 | $upath .= "?$query" if length $query; |
|
|
306 | |
|
|
307 | $upath =~ s%^/?%/%; |
|
|
308 | |
|
|
309 | # cookie processing |
|
|
310 | if (my $jar = $arg{cookie_jar}) { |
|
|
311 | %$jar = () if $jar->{version} != 1; |
|
|
312 | |
|
|
313 | my @cookie; |
|
|
314 | |
|
|
315 | while (my ($chost, $v) = each %$jar) { |
|
|
316 | if ($chost =~ /^\./) { |
|
|
317 | next unless $chost eq substr $uhost, -length $chost; |
|
|
318 | } elsif ($chost =~ /\./) { |
|
|
319 | next unless $chost eq $uhost; |
|
|
320 | } else { |
|
|
321 | next; |
|
|
322 | } |
|
|
323 | |
|
|
324 | while (my ($cpath, $v) = each %$v) { |
|
|
325 | next unless $cpath eq substr $upath, 0, length $cpath; |
|
|
326 | |
|
|
327 | while (my ($k, $v) = each %$v) { |
|
|
328 | next if $uscheme ne "https" && exists $v->{secure}; |
|
|
329 | my $value = $v->{value}; |
|
|
330 | $value =~ s/([\\"])/\\$1/g; |
|
|
331 | push @cookie, "$k=\"$value\""; |
|
|
332 | } |
|
|
333 | } |
|
|
334 | } |
|
|
335 | |
|
|
336 | $hdr{cookie} = join "; ", @cookie |
|
|
337 | if @cookie; |
|
|
338 | } |
|
|
339 | |
|
|
340 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
| 156 | |
341 | |
| 157 | if ($proxy) { |
342 | if ($proxy) { |
| 158 | ($host, $port, $scheme) = @$proxy; |
343 | ($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy); |
| 159 | $path = $url; |
344 | |
|
|
345 | # don't support https requests over https-proxy transport, |
|
|
346 | # can't be done with tls as spec'ed, unless you double-encrypt. |
|
|
347 | $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https"; |
| 160 | } else { |
348 | } else { |
| 161 | ($scheme, my $authority, $path, my $query, my $fragment) = |
349 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
| 162 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
|
|
| 163 | |
|
|
| 164 | $port = $scheme eq "http" ? 80 |
|
|
| 165 | : $scheme eq "https" ? 443 |
|
|
| 166 | : croak "$url: only http and https URLs supported"; |
|
|
| 167 | |
|
|
| 168 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
|
|
| 169 | or croak "$authority: unparsable URL"; |
|
|
| 170 | |
|
|
| 171 | $host = $1; |
|
|
| 172 | $port = $2 if defined $2; |
|
|
| 173 | |
|
|
| 174 | $host =~ s/^\[(.*)\]$/$1/; |
|
|
| 175 | $path .= "?$query" if length $query; |
|
|
| 176 | |
|
|
| 177 | $path = "/" unless $path; |
|
|
| 178 | |
|
|
| 179 | $hdr{host} = $host = lc $host; |
|
|
| 180 | } |
350 | } |
| 181 | |
351 | |
| 182 | $scheme = lc $scheme; |
352 | $hdr{host} = $uhost; |
| 183 | |
|
|
| 184 | my %state; |
|
|
| 185 | |
|
|
| 186 | $state{body} = delete $arg{body}; |
|
|
| 187 | |
|
|
| 188 | $hdr{"content-length"} = length $state{body}; |
353 | $hdr{"content-length"} = length $arg{body}; |
| 189 | |
354 | |
|
|
355 | my %state = (connect_guard => 1); |
|
|
356 | |
|
|
357 | _get_slot $uhost, sub { |
|
|
358 | $state{slot_guard} = shift; |
|
|
359 | |
|
|
360 | return unless $state{connect_guard}; |
|
|
361 | |
| 190 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { |
362 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
| 191 | $state{fh} = shift |
363 | $state{fh} = shift |
| 192 | or return $cb->(undef, { Status => 599, Reason => "$!" }); |
364 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url })); |
|
|
365 | pop; # free memory, save a tree |
| 193 | |
366 | |
| 194 | delete $state{connect_guard}; # reduce memory usage, save a tree |
367 | return unless delete $state{connect_guard}; |
| 195 | |
368 | |
| 196 | # get handle |
369 | # get handle |
| 197 | $state{handle} = new AnyEvent::Handle |
370 | $state{handle} = new AnyEvent::Handle |
| 198 | fh => $state{fh}, |
371 | fh => $state{fh}, |
| 199 | ($scheme eq "https" ? (tls => "connect") : ()); |
372 | timeout => $timeout, |
|
|
373 | peername => $rhost, |
|
|
374 | tls_ctx => $arg{tls_ctx}; |
| 200 | |
375 | |
| 201 | # limit the number of persistent connections |
376 | # limit the number of persistent connections |
|
|
377 | # keepalive not yet supported |
| 202 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
378 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
| 203 | ++$KA_COUNT{$_[1]}; |
379 | ++$KA_COUNT{$_[1]}; |
| 204 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
380 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
381 | --$KA_COUNT{$_[1]} |
|
|
382 | }; |
| 205 | $hdr{connection} = "keep-alive"; |
383 | $hdr{connection} = "keep-alive"; |
| 206 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
| 207 | } else { |
384 | } else { |
| 208 | delete $hdr{connection}; |
385 | delete $hdr{connection}; |
| 209 | } |
386 | } |
| 210 | |
387 | |
| 211 | # (re-)configure handle |
388 | # (re-)configure handle |
| 212 | $state{handle}->timeout ($timeout); |
|
|
| 213 | $state{handle}->on_error (sub { |
389 | $state{handle}->on_error (sub { |
| 214 | %state = (); |
390 | %state = (); |
| 215 | $cb->(undef, { Status => 599, Reason => "$!" }); |
391 | $cb->(undef, { Status => 599, Reason => $_[2], URL => $url }); |
| 216 | }); |
392 | }); |
| 217 | $state{handle}->on_eof (sub { |
393 | $state{handle}->on_eof (sub { |
| 218 | %state = (); |
394 | %state = (); |
| 219 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); |
395 | $cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url }); |
| 220 | }); |
|
|
| 221 | |
|
|
| 222 | # send request |
|
|
| 223 | $state{handle}->push_write ( |
|
|
| 224 | "$method $path HTTP/1.0\015\012" |
|
|
| 225 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
|
|
| 226 | . "\015\012" |
|
|
| 227 | . (delete $state{body}) |
|
|
| 228 | ); |
|
|
| 229 | |
|
|
| 230 | %hdr = (); # reduce memory usage, save a kitten |
|
|
| 231 | |
|
|
| 232 | # status line |
|
|
| 233 | $state{handle}->push_read (line => qr/\015?\012/, sub { |
|
|
| 234 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix |
|
|
| 235 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); |
|
|
| 236 | |
|
|
| 237 | my %hdr = ( # response headers |
|
|
| 238 | HTTPVersion => ",$1", |
|
|
| 239 | Status => ",$2", |
|
|
| 240 | Reason => ",$3", |
|
|
| 241 | ); |
396 | }); |
| 242 | |
397 | |
|
|
398 | $state{handle}->starttls ("connect") if $rscheme eq "https"; |
|
|
399 | |
|
|
400 | # handle actual, non-tunneled, request |
|
|
401 | my $handle_actual_request = sub { |
|
|
402 | $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls}; |
|
|
403 | |
|
|
404 | # send request |
|
|
405 | $state{handle}->push_write ( |
|
|
406 | "$method $rpath HTTP/1.0\015\012" |
|
|
407 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
|
|
408 | . "\015\012" |
|
|
409 | . (delete $arg{body}) |
|
|
410 | ); |
|
|
411 | |
|
|
412 | %hdr = (); # reduce memory usage, save a kitten |
|
|
413 | |
|
|
414 | # status line |
|
|
415 | $state{handle}->push_read (line => $qr_nl, sub { |
|
|
416 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
417 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url })); |
|
|
418 | |
|
|
419 | my %hdr = ( # response headers |
|
|
420 | HTTPVersion => ",$1", |
|
|
421 | Status => ",$2", |
|
|
422 | Reason => ",$3", |
|
|
423 | URL => ",$url" |
|
|
424 | ); |
|
|
425 | |
| 243 | # headers, could be optimized a bit |
426 | # headers, could be optimized a bit |
| 244 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
427 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
| 245 | for ("$_[1]\012") { |
428 | for ("$_[1]\012") { |
| 246 | # we support spaces in field names, as lotus domino |
429 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
| 247 | # creates them. |
430 | |
|
|
431 | # things seen, not parsed: |
|
|
432 | # p3pP="NON CUR OTPi OUR NOR UNI" |
|
|
433 | |
| 248 | $hdr{lc $1} .= ",$2" |
434 | $hdr{lc $1} .= ",$2" |
| 249 | while /\G |
435 | while /\G |
| 250 | ([^:\000-\037]+): |
436 | ([^:\000-\037]+): |
| 251 | [\011\040]* |
437 | [\011\040]* |
| 252 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
438 | ((?: [^\012]+ | \012[\011\040] )*) |
| 253 | \015?\012 |
439 | \012 |
| 254 | /gxc; |
440 | /gxc; |
| 255 | |
441 | |
| 256 | /\G$/ |
442 | /\G$/ |
| 257 | or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); |
443 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url })); |
| 258 | } |
444 | } |
| 259 | |
445 | |
| 260 | substr $_, 0, 1, "" |
446 | substr $_, 0, 1, "" |
| 261 | for values %hdr; |
447 | for values %hdr; |
| 262 | |
448 | |
| 263 | if ($method eq "HEAD") { |
449 | my $finish = sub { |
| 264 | %state = (); |
450 | $state{handle}->destroy; |
| 265 | $cb->(undef, \%hdr); |
|
|
| 266 | } else { |
|
|
| 267 | if (exists $hdr{"content-length"}) { |
|
|
| 268 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
| 269 | # could cache persistent connection now |
|
|
| 270 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
| 271 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
| 272 | }; |
|
|
| 273 | |
|
|
| 274 | %state = (); |
451 | %state = (); |
|
|
452 | |
|
|
453 | # set-cookie processing |
|
|
454 | if ($arg{cookie_jar}) { |
|
|
455 | for ($hdr{"set-cookie"}) { |
|
|
456 | # parse NAME=VALUE |
|
|
457 | my @kv; |
|
|
458 | |
|
|
459 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
|
|
460 | my $name = $1; |
|
|
461 | my $value = $3; |
|
|
462 | |
|
|
463 | unless ($value) { |
|
|
464 | $value = $2; |
|
|
465 | $value =~ s/\\(.)/$1/gs; |
|
|
466 | } |
|
|
467 | |
|
|
468 | push @kv, $name => $value; |
|
|
469 | |
|
|
470 | last unless /\G\s*;/gc; |
|
|
471 | } |
|
|
472 | |
|
|
473 | last unless @kv; |
|
|
474 | |
|
|
475 | my $name = shift @kv; |
|
|
476 | my %kv = (value => shift @kv, @kv); |
|
|
477 | |
|
|
478 | my $cdom; |
|
|
479 | my $cpath = (delete $kv{path}) || "/"; |
|
|
480 | |
|
|
481 | if (exists $kv{domain}) { |
|
|
482 | $cdom = delete $kv{domain}; |
|
|
483 | |
|
|
484 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
|
|
485 | |
|
|
486 | next if $cdom =~ /\.$/; |
|
|
487 | |
|
|
488 | # this is not rfc-like and not netscape-like. go figure. |
|
|
489 | my $ndots = $cdom =~ y/.//; |
|
|
490 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
491 | } else { |
|
|
492 | $cdom = $uhost; |
|
|
493 | } |
|
|
494 | |
|
|
495 | # store it |
|
|
496 | $arg{cookie_jar}{version} = 1; |
|
|
497 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
498 | |
|
|
499 | redo if /\G\s*,/gc; |
|
|
500 | } |
|
|
501 | } |
|
|
502 | |
|
|
503 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
504 | # try to support some common forms of broken Location headers. |
|
|
505 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
506 | $_[1]{location} =~ s/^\.\/+//; |
|
|
507 | |
|
|
508 | my $url = "$rscheme://$uhost:$uport"; |
|
|
509 | |
|
|
510 | unless ($_[1]{location} =~ s/^\///) { |
|
|
511 | $url .= $upath; |
|
|
512 | $url =~ s/\/[^\/]*$//; |
|
|
513 | } |
|
|
514 | |
|
|
515 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
516 | } |
|
|
517 | |
|
|
518 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
519 | # apparently, mozilla et al. just change POST to GET here |
|
|
520 | # more research is needed before we do the same |
|
|
521 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
522 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
523 | # even http/1.1 is unclear on how to mutate the method |
|
|
524 | $method = "GET" unless $method eq "HEAD"; |
|
|
525 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
526 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
527 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
528 | } else { |
| 275 | $cb->($_[1], \%hdr); |
529 | $cb->($_[0], $_[1]); |
|
|
530 | } |
| 276 | }); |
531 | }; |
|
|
532 | |
|
|
533 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
534 | $finish->(undef, \%hdr); |
|
|
535 | } else { |
|
|
536 | if (exists $hdr{"content-length"}) { |
|
|
537 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
538 | # could cache persistent connection now |
|
|
539 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
540 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
541 | }; |
|
|
542 | |
|
|
543 | $finish->($_[1], \%hdr); |
|
|
544 | }); |
|
|
545 | } else { |
|
|
546 | # too bad, need to read until we get an error or EOF, |
|
|
547 | # no way to detect winged data. |
|
|
548 | $_[0]->on_error (sub { |
|
|
549 | # delete ought to be more efficient, as we would have to make |
|
|
550 | # a copy otherwise as $_[0] gets destroyed. |
|
|
551 | $finish->(delete $_[0]{rbuf}, \%hdr); |
|
|
552 | }); |
|
|
553 | $_[0]->on_eof (undef); |
|
|
554 | $_[0]->on_read (sub { }); |
|
|
555 | } |
|
|
556 | } |
|
|
557 | }); |
|
|
558 | }); |
|
|
559 | }; |
|
|
560 | |
|
|
561 | # now handle proxy-CONNECT method |
|
|
562 | if ($proxy && $uscheme eq "https") { |
|
|
563 | # oh dear, we have to wrap it into a connect request |
|
|
564 | |
|
|
565 | # maybe re-use $uauthority with patched port? |
|
|
566 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
567 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
568 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
569 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url })); |
|
|
570 | |
|
|
571 | if ($2 == 200) { |
|
|
572 | $rpath = $upath; |
|
|
573 | &$handle_actual_request; |
| 277 | } else { |
574 | } else { |
| 278 | # too bad, need to read until we get an error or EOF, |
|
|
| 279 | # no way to detect winged data. |
|
|
| 280 | $_[0]->on_error (sub { |
|
|
| 281 | %state = (); |
575 | %state = (); |
| 282 | $cb->($_[0]{rbuf}, \%hdr); |
576 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
| 283 | }); |
|
|
| 284 | $_[0]->on_eof (undef); |
|
|
| 285 | $_[0]->on_read (sub { }); |
|
|
| 286 | } |
577 | } |
| 287 | } |
578 | }); |
|
|
579 | } else { |
|
|
580 | &$handle_actual_request; |
| 288 | }); |
581 | } |
|
|
582 | |
|
|
583 | }, sub { |
|
|
584 | $timeout |
| 289 | }); |
585 | }; |
| 290 | }, sub { |
|
|
| 291 | $timeout |
|
|
| 292 | }; |
586 | }; |
| 293 | |
587 | |
| 294 | defined wantarray && AnyEvent::Util::guard { %state = () } |
588 | defined wantarray && AnyEvent::Util::guard { %state = () } |
| 295 | } |
589 | } |
| 296 | |
590 | |
| 297 | sub http_get($$;@) { |
591 | sub http_get($@) { |
| 298 | unshift @_, "GET"; |
592 | unshift @_, "GET"; |
| 299 | &http_request |
593 | &http_request |
| 300 | } |
594 | } |
| 301 | |
595 | |
| 302 | sub http_head($$;@) { |
596 | sub http_head($@) { |
| 303 | unshift @_, "HEAD"; |
597 | unshift @_, "HEAD"; |
| 304 | &http_request |
598 | &http_request |
| 305 | } |
599 | } |
| 306 | |
600 | |
| 307 | sub http_post($$$;@) { |
601 | sub http_post($$@) { |
|
|
602 | my $url = shift; |
| 308 | unshift @_, "POST", "body"; |
603 | unshift @_, "POST", $url, "body"; |
| 309 | &http_request |
604 | &http_request |
| 310 | } |
605 | } |
| 311 | |
606 | |
|
|
607 | =back |
|
|
608 | |
| 312 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
609 | =head2 GLOBAL FUNCTIONS AND VARIABLES |
| 313 | |
610 | |
| 314 | =over 4 |
611 | =over 4 |
| 315 | |
612 | |
| 316 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
613 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
| … | |
… | |
| 323 | The default value for the C<recurse> request parameter (default: C<10>). |
620 | The default value for the C<recurse> request parameter (default: C<10>). |
| 324 | |
621 | |
| 325 | =item $AnyEvent::HTTP::USERAGENT |
622 | =item $AnyEvent::HTTP::USERAGENT |
| 326 | |
623 | |
| 327 | The default value for the C<User-Agent> header (the default is |
624 | The default value for the C<User-Agent> header (the default is |
| 328 | C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
625 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
| 329 | |
626 | |
| 330 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
627 | =item $AnyEvent::HTTP::MAX_PERSISTENT |
| 331 | |
628 | |
| 332 | The maximum number of persistent connections to keep open (default: 8). |
629 | The maximum number of persistent connections to keep open (default: 8). |
| 333 | |
630 | |
| … | |
… | |
| 336 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
633 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
| 337 | |
634 | |
| 338 | The maximum time to cache a persistent connection, in seconds (default: 2). |
635 | The maximum time to cache a persistent connection, in seconds (default: 2). |
| 339 | |
636 | |
| 340 | Not implemented currently. |
637 | Not implemented currently. |
|
|
638 | |
|
|
639 | =item $AnyEvent::HTTP::ACTIVE |
|
|
640 | |
|
|
641 | The number of active connections. This is not the number of currently |
|
|
642 | running requests, but the number of currently open and non-idle TCP |
|
|
643 | connections. This number of can be useful for load-leveling. |
| 341 | |
644 | |
| 342 | =back |
645 | =back |
| 343 | |
646 | |
| 344 | =cut |
647 | =cut |
| 345 | |
648 | |
| … | |
… | |
| 354 | |
657 | |
| 355 | L<AnyEvent>. |
658 | L<AnyEvent>. |
| 356 | |
659 | |
| 357 | =head1 AUTHOR |
660 | =head1 AUTHOR |
| 358 | |
661 | |
| 359 | Marc Lehmann <schmorp@schmorp.de> |
662 | Marc Lehmann <schmorp@schmorp.de> |
| 360 | http://home.schmorp.de/ |
663 | http://home.schmorp.de/ |
|
|
664 | |
|
|
665 | With many thanks to Дмитрий Шалашов, who provided countless |
|
|
666 | testcases and bugreports. |
| 361 | |
667 | |
| 362 | =cut |
668 | =cut |
| 363 | |
669 | |
| 364 | 1 |
670 | 1 |
| 365 | |
671 | |
