… | |
… | |
46 | use AnyEvent::Util (); |
46 | use AnyEvent::Util (); |
47 | use AnyEvent::Handle (); |
47 | use AnyEvent::Handle (); |
48 | |
48 | |
49 | use base Exporter::; |
49 | use base Exporter::; |
50 | |
50 | |
51 | our $VERSION = '2.15'; |
51 | our $VERSION = 2.2; |
52 | |
52 | |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
53 | our @EXPORT = qw(http_get http_post http_head http_request); |
54 | |
54 | |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
55 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
56 | our $MAX_RECURSE = 10; |
56 | our $MAX_RECURSE = 10; |
… | |
… | |
89 | C<http_request> returns a "cancellation guard" - you have to keep the |
89 | C<http_request> returns a "cancellation guard" - you have to keep the |
90 | object at least alive until the callback get called. If the object gets |
90 | object at least alive until the callback get called. If the object gets |
91 | destroyed before the callback is called, the request will be cancelled. |
91 | destroyed before the callback is called, the request will be cancelled. |
92 | |
92 | |
93 | The callback will be called with the response body data as first argument |
93 | The callback will be called with the response body data as first argument |
94 | (or C<undef> if an error occured), and a hash-ref with response headers |
94 | (or C<undef> if an error occurred), and a hash-ref with response headers |
95 | (and trailers) as second argument. |
95 | (and trailers) as second argument. |
96 | |
96 | |
97 | All the headers in that hash are lowercased. In addition to the response |
97 | All the headers in that hash are lowercased. In addition to the response |
98 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
98 | headers, the "pseudo-headers" (uppercase to avoid clashing with possible |
99 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
99 | response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the |
… | |
… | |
157 | =item recurse => $count (default: $MAX_RECURSE) |
157 | =item recurse => $count (default: $MAX_RECURSE) |
158 | |
158 | |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
160 | other retries and so on, and how often to do so. |
160 | other retries and so on, and how often to do so. |
161 | |
161 | |
|
|
162 | Only redirects to http and https URLs are supported. While most common |
|
|
163 | redirection forms are handled entirely within this module, some require |
|
|
164 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
165 | the request will fail with an error. |
|
|
166 | |
162 | =item headers => hashref |
167 | =item headers => hashref |
163 | |
168 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
169 | The request headers to use. Currently, C<http_request> may provide its own |
165 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
166 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
… | |
… | |
242 | context) - only connections using the same unique ID will be reused. |
247 | context) - only connections using the same unique ID will be reused. |
243 | |
248 | |
244 | =item on_prepare => $callback->($fh) |
249 | =item on_prepare => $callback->($fh) |
245 | |
250 | |
246 | In rare cases you need to "tune" the socket before it is used to |
251 | In rare cases you need to "tune" the socket before it is used to |
247 | connect (for exmaple, to bind it on a given IP address). This parameter |
252 | connect (for example, to bind it on a given IP address). This parameter |
248 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
253 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
249 | and behaves exactly the same way (e.g. it has to provide a |
254 | and behaves exactly the same way (e.g. it has to provide a |
250 | timeout). See the description for the C<$prepare_cb> argument of |
255 | timeout). See the description for the C<$prepare_cb> argument of |
251 | C<AnyEvent::Socket::tcp_connect> for details. |
256 | C<AnyEvent::Socket::tcp_connect> for details. |
252 | |
257 | |
… | |
… | |
821 | my $was_persistent; # true if this is actually a recycled connection |
826 | my $was_persistent; # true if this is actually a recycled connection |
822 | |
827 | |
823 | # the key to use in the keepalive cache |
828 | # the key to use in the keepalive cache |
824 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
829 | my $ka_key = "$uscheme\x00$uhost\x00$uport\x00$arg{sessionid}"; |
825 | |
830 | |
826 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive " : "" : "close ") . "Te"; #1.1 |
831 | $hdr{connection} = ($persistent ? $keepalive ? "keep-alive, " : "" : "close, ") . "Te"; #1.1 |
827 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
832 | $hdr{te} = "trailers" unless exists $hdr{te}; #1.1 |
828 | |
833 | |
829 | my %state = (connect_guard => 1); |
834 | my %state = (connect_guard => 1); |
830 | |
835 | |
831 | my $ae_error = 595; # connecting |
836 | my $ae_error = 595; # connecting |
… | |
… | |
844 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
849 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
845 | . "\015\012" |
850 | . "\015\012" |
846 | . (delete $arg{body}) |
851 | . (delete $arg{body}) |
847 | ); |
852 | ); |
848 | |
853 | |
849 | # return if error occured during push_write() |
854 | # return if error occurred during push_write() |
850 | return unless %state; |
855 | return unless %state; |
851 | |
856 | |
852 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
857 | # reduce memory usage, save a kitten, also re-use it for the response headers. |
853 | %hdr = (); |
858 | %hdr = (); |
854 | |
859 | |
… | |
… | |
881 | |
886 | |
882 | %hdr = (%$hdr, @pseudo); |
887 | %hdr = (%$hdr, @pseudo); |
883 | } |
888 | } |
884 | |
889 | |
885 | # redirect handling |
890 | # redirect handling |
886 | # microsoft and other shitheads don't give a shit for following standards, |
891 | # relative uri handling forced by microsoft and other shitheads. |
887 | # try to support some common forms of broken Location headers. |
892 | # we give our best and fall back to URI if available. |
888 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
893 | if (exists $hdr{location}) { |
|
|
894 | my $loc = $hdr{location}; |
|
|
895 | |
|
|
896 | if ($loc =~ m%^//%) { # // |
|
|
897 | $loc = "$rscheme:$loc"; |
|
|
898 | |
|
|
899 | } elsif ($loc eq "") { |
|
|
900 | $loc = $url; |
|
|
901 | |
|
|
902 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
889 | $hdr{location} =~ s/^\.\/+//; |
903 | $loc =~ s/^\.\/+//; |
890 | |
904 | |
|
|
905 | if ($loc !~ m%^[.?#]%) { |
891 | my $url = "$rscheme://$uhost:$uport"; |
906 | my $prefix = "$rscheme://$uhost:$uport"; |
892 | |
907 | |
893 | unless ($hdr{location} =~ s/^\///) { |
908 | unless ($loc =~ s/^\///) { |
894 | $url .= $upath; |
909 | $prefix .= $upath; |
895 | $url =~ s/\/[^\/]*$//; |
910 | $prefix =~ s/\/[^\/]*$//; |
|
|
911 | } |
|
|
912 | |
|
|
913 | $loc = "$prefix/$loc"; |
|
|
914 | |
|
|
915 | } elsif (eval { require URI }) { # uri |
|
|
916 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
917 | |
|
|
918 | } else { |
|
|
919 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
920 | #$hdr{Status} = 599; |
|
|
921 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
922 | #$recurse = 0; |
|
|
923 | } |
896 | } |
924 | } |
897 | |
925 | |
898 | $hdr{location} = "$url/$hdr{location}"; |
926 | $hdr{location} = $loc; |
899 | } |
927 | } |
900 | |
928 | |
901 | my $redirect; |
929 | my $redirect; |
902 | |
930 | |
903 | if ($recurse) { |
931 | if ($recurse) { |
… | |
… | |
905 | |
933 | |
906 | # industry standard is to redirect POST as GET for |
934 | # industry standard is to redirect POST as GET for |
907 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
935 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
908 | # also, the UA should ask the user for 301 and 307 and POST, |
936 | # also, the UA should ask the user for 301 and 307 and POST, |
909 | # industry standard seems to be to simply follow. |
937 | # industry standard seems to be to simply follow. |
910 | # we go with the industry standard. |
938 | # we go with the industry standard. 308 is defined |
|
|
939 | # by rfc7238 |
911 | if ($status == 301 or $status == 302 or $status == 303) { |
940 | if ($status == 301 or $status == 302 or $status == 303) { |
912 | # HTTP/1.1 is unclear on how to mutate the method |
941 | # HTTP/1.1 is unclear on how to mutate the method |
913 | $method = "GET" unless $method eq "HEAD"; |
942 | $method = "GET" unless $method eq "HEAD"; |
914 | $redirect = 1; |
943 | $redirect = 1; |
915 | } elsif ($status == 307) { |
944 | } elsif ($status == 307 or $status == 308) { |
916 | $redirect = 1; |
945 | $redirect = 1; |
917 | } |
946 | } |
918 | } |
947 | } |
919 | |
948 | |
920 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
949 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
… | |
… | |
1244 | C<$session_end> is given and true, then additionally remove all session |
1273 | C<$session_end> is given and true, then additionally remove all session |
1245 | cookies. |
1274 | cookies. |
1246 | |
1275 | |
1247 | You should call this function (with a true C<$session_end>) before you |
1276 | You should call this function (with a true C<$session_end>) before you |
1248 | save cookies to disk, and you should call this function after loading them |
1277 | save cookies to disk, and you should call this function after loading them |
1249 | again. If you have a long-running program you can additonally call this |
1278 | again. If you have a long-running program you can additionally call this |
1250 | function from time to time. |
1279 | function from time to time. |
1251 | |
1280 | |
1252 | A cookie jar is initially an empty hash-reference that is managed by this |
1281 | A cookie jar is initially an empty hash-reference that is managed by this |
1253 | module. It's format is subject to change, but currently it is like this: |
1282 | module. It's format is subject to change, but currently it is like this: |
1254 | |
1283 | |
… | |
… | |
1311 | |
1340 | |
1312 | The default value for this is C<4>, and it is highly advisable to not |
1341 | The default value for this is C<4>, and it is highly advisable to not |
1313 | increase it much. |
1342 | increase it much. |
1314 | |
1343 | |
1315 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1344 | For comparison: the RFC's recommend 4 non-persistent or 2 persistent |
1316 | connections, older browsers used 2, newers (such as firefox 3) typically |
1345 | connections, older browsers used 2, newer ones (such as firefox 3) |
1317 | use 6, and Opera uses 8 because like, they have the fastest browser and |
1346 | typically use 6, and Opera uses 8 because like, they have the fastest |
1318 | give a shit for everybody else on the planet. |
1347 | browser and give a shit for everybody else on the planet. |
1319 | |
1348 | |
1320 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1349 | =item $AnyEvent::HTTP::PERSISTENT_TIMEOUT |
1321 | |
1350 | |
1322 | The time after which idle persistent connections get closed by |
1351 | The time after which idle persistent connections get closed by |
1323 | AnyEvent::HTTP (default: C<3>). |
1352 | AnyEvent::HTTP (default: C<3>). |
… | |
… | |
1392 | set_proxy $ENV{http_proxy}; |
1421 | set_proxy $ENV{http_proxy}; |
1393 | }; |
1422 | }; |
1394 | |
1423 | |
1395 | =head2 SHOWCASE |
1424 | =head2 SHOWCASE |
1396 | |
1425 | |
1397 | This section contaisn some more elaborate "real-world" examples or code |
1426 | This section contains some more elaborate "real-world" examples or code |
1398 | snippets. |
1427 | snippets. |
1399 | |
1428 | |
1400 | =head2 HTTP/1.1 FILE DOWNLOAD |
1429 | =head2 HTTP/1.1 FILE DOWNLOAD |
1401 | |
1430 | |
1402 | Downloading files with HTTP can be quite tricky, especially when something |
1431 | Downloading files with HTTP can be quite tricky, especially when something |
… | |
… | |
1406 | last modified time to check for file content changes, and works with many |
1435 | last modified time to check for file content changes, and works with many |
1407 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1436 | HTTP/1.0 servers as well, and usually falls back to a complete re-download |
1408 | on older servers. |
1437 | on older servers. |
1409 | |
1438 | |
1410 | It calls the completion callback with either C<undef>, which means a |
1439 | It calls the completion callback with either C<undef>, which means a |
1411 | nonretryable error occured, C<0> when the download was partial and should |
1440 | nonretryable error occurred, C<0> when the download was partial and should |
1412 | be retried, and C<1> if it was successful. |
1441 | be retried, and C<1> if it was successful. |
1413 | |
1442 | |
1414 | use AnyEvent::HTTP; |
1443 | use AnyEvent::HTTP; |
1415 | |
1444 | |
1416 | sub download($$$) { |
1445 | sub download($$$) { |