… | |
… | |
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 = 2.24; |
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; |
… | |
… | |
157 | =item recurse => $count (default: $MAX_RECURSE) |
157 | =item recurse => $count (default: $MAX_RECURSE) |
158 | |
158 | |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
159 | Whether to recurse requests or not, e.g. on redirects, authentication and |
160 | other retries and so on, and how often to do so. |
160 | other retries and so on, and how often to do so. |
161 | |
161 | |
|
|
162 | Only redirects to http and https URLs are supported. While most common |
|
|
163 | redirection forms are handled entirely within this module, some require |
|
|
164 | the use of the optional L<URI> module. If it is required but missing, then |
|
|
165 | the request will fail with an error. |
|
|
166 | |
162 | =item headers => hashref |
167 | =item headers => hashref |
163 | |
168 | |
164 | The request headers to use. Currently, C<http_request> may provide its own |
169 | The request headers to use. Currently, C<http_request> may provide its own |
165 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
170 | C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and |
166 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
171 | will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:> |
… | |
… | |
189 | |
194 | |
190 | C<$scheme> must be either missing or must be C<http> for HTTP. |
195 | C<$scheme> must be either missing or must be C<http> for HTTP. |
191 | |
196 | |
192 | If not specified, then the default proxy is used (see |
197 | If not specified, then the default proxy is used (see |
193 | C<AnyEvent::HTTP::set_proxy>). |
198 | C<AnyEvent::HTTP::set_proxy>). |
|
|
199 | |
|
|
200 | Currently, if your proxy requires authorization, you have to specify an |
|
|
201 | appropriate "Proxy-Authorization" header in every request. |
194 | |
202 | |
195 | =item body => $string |
203 | =item body => $string |
196 | |
204 | |
197 | The request body, usually empty. Will be sent as-is (future versions of |
205 | The request body, usually empty. Will be sent as-is (future versions of |
198 | this module might offer more options). |
206 | this module might offer more options). |
… | |
… | |
255 | In even rarer cases you want total control over how AnyEvent::HTTP |
263 | In even rarer cases you want total control over how AnyEvent::HTTP |
256 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
264 | establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect> |
257 | to do this, but you can provide your own C<tcp_connect> function - |
265 | to do this, but you can provide your own C<tcp_connect> function - |
258 | obviously, it has to follow the same calling conventions, except that it |
266 | obviously, it has to follow the same calling conventions, except that it |
259 | may always return a connection guard object. |
267 | may always return a connection guard object. |
|
|
268 | |
|
|
269 | The connections made by this hook will be treated as equivalent to |
|
|
270 | connecitons made the built-in way, specifically, they will be put into |
|
|
271 | and taken from the persistent conneciton cache. If your C<$tcp_connect> |
|
|
272 | function is incompatible with this kind of re-use, consider switching off |
|
|
273 | C<persistent> connections and/or providing a C<session> identifier. |
260 | |
274 | |
261 | There are probably lots of weird uses for this function, starting from |
275 | There are probably lots of weird uses for this function, starting from |
262 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
276 | tracing the hosts C<http_request> actually tries to connect, to (inexact |
263 | but fast) host => IP address caching or even socks protocol support. |
277 | but fast) host => IP address caching or even socks protocol support. |
264 | |
278 | |
… | |
… | |
334 | =item persistent => $boolean |
348 | =item persistent => $boolean |
335 | |
349 | |
336 | Try to create/reuse a persistent connection. When this flag is set |
350 | Try to create/reuse a persistent connection. When this flag is set |
337 | (default: true for idempotent requests, false for all others), then |
351 | (default: true for idempotent requests, false for all others), then |
338 | C<http_request> tries to re-use an existing (previously-created) |
352 | C<http_request> tries to re-use an existing (previously-created) |
339 | persistent connection to the host and, failing that, tries to create a new |
353 | persistent connection to same host (i.e. identical URL scheme, hostname, |
340 | one. |
354 | port and session) and, failing that, tries to create a new one. |
341 | |
355 | |
342 | Requests failing in certain ways will be automatically retried once, which |
356 | Requests failing in certain ways will be automatically retried once, which |
343 | is dangerous for non-idempotent requests, which is why it defaults to off |
357 | is dangerous for non-idempotent requests, which is why it defaults to off |
344 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
358 | for them. The reason for this is because the bozos who designed HTTP/1.1 |
345 | made it impossible to distinguish between a fatal error and a normal |
359 | made it impossible to distinguish between a fatal error and a normal |
… | |
… | |
446 | |
460 | |
447 | # expire cookies |
461 | # expire cookies |
448 | sub cookie_jar_expire($;$) { |
462 | sub cookie_jar_expire($;$) { |
449 | my ($jar, $session_end) = @_; |
463 | my ($jar, $session_end) = @_; |
450 | |
464 | |
451 | %$jar = () if $jar->{version} != 1; |
465 | %$jar = () if $jar->{version} != 2; |
452 | |
466 | |
453 | my $anow = AE::now; |
467 | my $anow = AE::now; |
454 | |
468 | |
455 | while (my ($chost, $paths) = each %$jar) { |
469 | while (my ($chost, $paths) = each %$jar) { |
456 | next unless ref $paths; |
470 | next unless ref $paths; |
… | |
… | |
476 | |
490 | |
477 | # extract cookies from jar |
491 | # extract cookies from jar |
478 | sub cookie_jar_extract($$$$) { |
492 | sub cookie_jar_extract($$$$) { |
479 | my ($jar, $scheme, $host, $path) = @_; |
493 | my ($jar, $scheme, $host, $path) = @_; |
480 | |
494 | |
481 | %$jar = () if $jar->{version} != 1; |
495 | %$jar = () if $jar->{version} != 2; |
|
|
496 | |
|
|
497 | $host = AnyEvent::Util::idn_to_ascii $host |
|
|
498 | if $host =~ /[^\x00-\x7f]/; |
482 | |
499 | |
483 | my @cookies; |
500 | my @cookies; |
484 | |
501 | |
485 | while (my ($chost, $paths) = each %$jar) { |
502 | while (my ($chost, $paths) = each %$jar) { |
486 | next unless ref $paths; |
503 | next unless ref $paths; |
487 | |
504 | |
488 | if ($chost =~ /^\./) { |
505 | # exact match or suffix including . match |
489 | next unless $chost eq substr $host, -length $chost; |
506 | $chost eq $host or ".$chost" eq substr $host, -1 - length $chost |
490 | } elsif ($chost =~ /\./) { |
|
|
491 | next unless $chost eq $host; |
|
|
492 | } else { |
|
|
493 | next; |
507 | or next; |
494 | } |
|
|
495 | |
508 | |
496 | while (my ($cpath, $cookies) = each %$paths) { |
509 | while (my ($cpath, $cookies) = each %$paths) { |
497 | next unless $cpath eq substr $path, 0, length $cpath; |
510 | next unless $cpath eq substr $path, 0, length $cpath; |
498 | |
511 | |
499 | while (my ($cookie, $kv) = each %$cookies) { |
512 | while (my ($cookie, $kv) = each %$cookies) { |
… | |
… | |
520 | } |
533 | } |
521 | |
534 | |
522 | # parse set_cookie header into jar |
535 | # parse set_cookie header into jar |
523 | sub cookie_jar_set_cookie($$$$) { |
536 | sub cookie_jar_set_cookie($$$$) { |
524 | my ($jar, $set_cookie, $host, $date) = @_; |
537 | my ($jar, $set_cookie, $host, $date) = @_; |
|
|
538 | |
|
|
539 | %$jar = () if $jar->{version} != 2; |
525 | |
540 | |
526 | my $anow = int AE::now; |
541 | my $anow = int AE::now; |
527 | my $snow; # server-now |
542 | my $snow; # server-now |
528 | |
543 | |
529 | for ($set_cookie) { |
544 | for ($set_cookie) { |
… | |
… | |
575 | |
590 | |
576 | my $cdom; |
591 | my $cdom; |
577 | my $cpath = (delete $kv{path}) || "/"; |
592 | my $cpath = (delete $kv{path}) || "/"; |
578 | |
593 | |
579 | if (exists $kv{domain}) { |
594 | if (exists $kv{domain}) { |
580 | $cdom = delete $kv{domain}; |
595 | $cdom = $kv{domain}; |
581 | |
596 | |
582 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
597 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
583 | |
598 | |
584 | next if $cdom =~ /\.$/; |
599 | next if $cdom =~ /\.$/; |
585 | |
600 | |
586 | # this is not rfc-like and not netscape-like. go figure. |
601 | # this is not rfc-like and not netscape-like. go figure. |
587 | my $ndots = $cdom =~ y/.//; |
602 | my $ndots = $cdom =~ y/.//; |
588 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
603 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
|
|
604 | |
|
|
605 | $cdom = substr $cdom, 1; # remove initial . |
589 | } else { |
606 | } else { |
590 | $cdom = $host; |
607 | $cdom = $host; |
591 | } |
608 | } |
592 | |
609 | |
593 | # store it |
610 | # store it |
594 | $jar->{version} = 1; |
611 | $jar->{version} = 2; |
595 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
612 | $jar->{lc $cdom}{$cpath}{$name} = \%kv; |
596 | |
613 | |
597 | redo if /\G\s*,/gc; |
614 | redo if /\G\s*,/gc; |
598 | } |
615 | } |
599 | } |
616 | } |
… | |
… | |
765 | |
782 | |
766 | my $uport = $uscheme eq "http" ? 80 |
783 | my $uport = $uscheme eq "http" ? 80 |
767 | : $uscheme eq "https" ? 443 |
784 | : $uscheme eq "https" ? 443 |
768 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
785 | : return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" }); |
769 | |
786 | |
770 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
787 | $uauthority =~ /^(?: .*\@ )? ([^\@]+?) (?: : (\d+) )?$/x |
771 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
788 | or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" }); |
772 | |
789 | |
773 | my $uhost = lc $1; |
790 | my $uhost = lc $1; |
774 | $uport = $2 if defined $2; |
791 | $uport = $2 if defined $2; |
775 | |
792 | |
… | |
… | |
841 | # send request |
858 | # send request |
842 | $hdl->push_write ( |
859 | $hdl->push_write ( |
843 | "$method $rpath HTTP/1.1\015\012" |
860 | "$method $rpath HTTP/1.1\015\012" |
844 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
861 | . (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr) |
845 | . "\015\012" |
862 | . "\015\012" |
846 | . (delete $arg{body}) |
863 | . $arg{body} |
847 | ); |
864 | ); |
848 | |
865 | |
849 | # return if error occurred during push_write() |
866 | # return if error occurred during push_write() |
850 | return unless %state; |
867 | return unless %state; |
851 | |
868 | |
… | |
… | |
881 | |
898 | |
882 | %hdr = (%$hdr, @pseudo); |
899 | %hdr = (%$hdr, @pseudo); |
883 | } |
900 | } |
884 | |
901 | |
885 | # redirect handling |
902 | # redirect handling |
886 | # microsoft and other shitheads don't give a shit for following standards, |
903 | # relative uri handling forced by microsoft and other shitheads. |
887 | # try to support some common forms of broken Location headers. |
904 | # we give our best and fall back to URI if available. |
888 | if ($hdr{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
905 | if (exists $hdr{location}) { |
|
|
906 | my $loc = $hdr{location}; |
|
|
907 | |
|
|
908 | if ($loc =~ m%^//%) { # // |
|
|
909 | $loc = "$uscheme:$loc"; |
|
|
910 | |
|
|
911 | } elsif ($loc eq "") { |
|
|
912 | $loc = $url; |
|
|
913 | |
|
|
914 | } elsif ($loc !~ /^(?: $ | [^:\/?\#]+ : )/x) { # anything "simple" |
889 | $hdr{location} =~ s/^\.\/+//; |
915 | $loc =~ s/^\.\/+//; |
890 | |
916 | |
891 | my $url = "$rscheme://$uhost:$uport"; |
917 | if ($loc !~ m%^[.?#]%) { |
|
|
918 | my $prefix = "$uscheme://$uauthority"; |
892 | |
919 | |
893 | unless ($hdr{location} =~ s/^\///) { |
920 | unless ($loc =~ s/^\///) { |
894 | $url .= $upath; |
921 | $prefix .= $upath; |
895 | $url =~ s/\/[^\/]*$//; |
922 | $prefix =~ s/\/[^\/]*$//; |
|
|
923 | } |
|
|
924 | |
|
|
925 | $loc = "$prefix/$loc"; |
|
|
926 | |
|
|
927 | } elsif (eval { require URI }) { # uri |
|
|
928 | $loc = URI->new_abs ($loc, $url)->as_string; |
|
|
929 | |
|
|
930 | } else { |
|
|
931 | return _error %state, $cb, { @pseudo, Status => 599, Reason => "Cannot parse Location (URI module missing)" }; |
|
|
932 | #$hdr{Status} = 599; |
|
|
933 | #$hdr{Reason} = "Unparsable Redirect (URI module missing)"; |
|
|
934 | #$recurse = 0; |
|
|
935 | } |
896 | } |
936 | } |
897 | |
937 | |
898 | $hdr{location} = "$url/$hdr{location}"; |
938 | $hdr{location} = $loc; |
899 | } |
939 | } |
900 | |
940 | |
901 | my $redirect; |
941 | my $redirect; |
902 | |
942 | |
903 | if ($recurse) { |
943 | if ($recurse) { |
… | |
… | |
905 | |
945 | |
906 | # industry standard is to redirect POST as GET for |
946 | # industry standard is to redirect POST as GET for |
907 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
947 | # 301, 302 and 303, in contrast to HTTP/1.0 and 1.1. |
908 | # also, the UA should ask the user for 301 and 307 and POST, |
948 | # also, the UA should ask the user for 301 and 307 and POST, |
909 | # industry standard seems to be to simply follow. |
949 | # industry standard seems to be to simply follow. |
910 | # we go with the industry standard. |
950 | # we go with the industry standard. 308 is defined |
|
|
951 | # by rfc7538 |
911 | if ($status == 301 or $status == 302 or $status == 303) { |
952 | if ($status == 301 or $status == 302 or $status == 303) { |
|
|
953 | $redirect = 1; |
912 | # HTTP/1.1 is unclear on how to mutate the method |
954 | # HTTP/1.1 is unclear on how to mutate the method |
913 | $method = "GET" unless $method eq "HEAD"; |
955 | unless ($method eq "HEAD") { |
914 | $redirect = 1; |
956 | $method = "GET"; |
|
|
957 | delete $arg{body}; |
|
|
958 | } |
915 | } elsif ($status == 307) { |
959 | } elsif ($status == 307 or $status == 308) { |
916 | $redirect = 1; |
960 | $redirect = 1; |
917 | } |
961 | } |
918 | } |
962 | } |
919 | |
963 | |
920 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
964 | my $finish = sub { # ($data, $err_status, $err_reason[, $persistent]) |
… | |
… | |
996 | $finish->(delete $state{handle}); |
1040 | $finish->(delete $state{handle}); |
997 | |
1041 | |
998 | } elsif ($chunked) { |
1042 | } elsif ($chunked) { |
999 | my $cl = 0; |
1043 | my $cl = 0; |
1000 | my $body = ""; |
1044 | my $body = ""; |
1001 | my $on_body = $arg{on_body} || sub { $body .= shift; 1 }; |
1045 | my $on_body = (!$redirect && $arg{on_body}) || sub { $body .= shift; 1 }; |
1002 | |
1046 | |
1003 | $state{read_chunk} = sub { |
1047 | $state{read_chunk} = sub { |
1004 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1048 | $_[1] =~ /^([0-9a-fA-F]+)/ |
1005 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1049 | or return $finish->(undef, $ae_error => "Garbled chunked transfer encoding"); |
1006 | |
1050 | |
… | |
… | |
1039 | } |
1083 | } |
1040 | }; |
1084 | }; |
1041 | |
1085 | |
1042 | $_[0]->push_read (line => $state{read_chunk}); |
1086 | $_[0]->push_read (line => $state{read_chunk}); |
1043 | |
1087 | |
1044 | } elsif ($arg{on_body}) { |
1088 | } elsif (!$redirect && $arg{on_body}) { |
1045 | if (defined $len) { |
1089 | if (defined $len) { |
1046 | $_[0]->on_read (sub { |
1090 | $_[0]->on_read (sub { |
1047 | $len -= length $_[0]{rbuf}; |
1091 | $len -= length $_[0]{rbuf}; |
1048 | |
1092 | |
1049 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
1093 | $arg{on_body}(delete $_[0]{rbuf}, \%hdr) |
… | |
… | |
1088 | _destroy_state %state; |
1132 | _destroy_state %state; |
1089 | |
1133 | |
1090 | %state = (); |
1134 | %state = (); |
1091 | $state{recurse} = |
1135 | $state{recurse} = |
1092 | http_request ( |
1136 | http_request ( |
1093 | $method => $url, |
1137 | $method => $url, |
1094 | %arg, |
1138 | %arg, |
1095 | recurse => $recurse - 1, |
1139 | recurse => $recurse - 1, |
1096 | keepalive => 0, |
1140 | persistent => 0, |
1097 | sub { |
1141 | sub { |
1098 | %state = (); |
1142 | %state = (); |
1099 | &$cb |
1143 | &$cb |
1100 | } |
1144 | } |
1101 | ); |
1145 | ); |
… | |
… | |
1147 | |
1191 | |
1148 | # now handle proxy-CONNECT method |
1192 | # now handle proxy-CONNECT method |
1149 | if ($proxy && $uscheme eq "https") { |
1193 | if ($proxy && $uscheme eq "https") { |
1150 | # oh dear, we have to wrap it into a connect request |
1194 | # oh dear, we have to wrap it into a connect request |
1151 | |
1195 | |
|
|
1196 | my $auth = exists $hdr{"proxy-authorization"} |
|
|
1197 | ? "proxy-authorization: " . (delete $hdr{"proxy-authorization"}) . "\015\012" |
|
|
1198 | : ""; |
|
|
1199 | |
1152 | # maybe re-use $uauthority with patched port? |
1200 | # maybe re-use $uauthority with patched port? |
1153 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012\015\012"); |
1201 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012$auth\015\012"); |
1154 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1202 | $state{handle}->push_read (line => $qr_nlnl, sub { |
1155 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1203 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
1156 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1204 | or return _error %state, $cb, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }; |
1157 | |
1205 | |
1158 | if ($2 == 200) { |
1206 | if ($2 == 200) { |
… | |
… | |
1161 | } else { |
1209 | } else { |
1162 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1210 | _error %state, $cb, { @pseudo, Status => $2, Reason => $3 }; |
1163 | } |
1211 | } |
1164 | }); |
1212 | }); |
1165 | } else { |
1213 | } else { |
|
|
1214 | delete $hdr{"proxy-authorization"} unless $proxy; |
|
|
1215 | |
1166 | $handle_actual_request->(); |
1216 | $handle_actual_request->(); |
1167 | } |
1217 | } |
1168 | }; |
1218 | }; |
1169 | |
1219 | |
1170 | _get_slot $uhost, sub { |
1220 | _get_slot $uhost, sub { |
… | |
… | |
1176 | # on a keepalive request (in theory, this should be a separate config option). |
1226 | # on a keepalive request (in theory, this should be a separate config option). |
1177 | if ($persistent && $KA_CACHE{$ka_key}) { |
1227 | if ($persistent && $KA_CACHE{$ka_key}) { |
1178 | $was_persistent = 1; |
1228 | $was_persistent = 1; |
1179 | |
1229 | |
1180 | $state{handle} = ka_fetch $ka_key; |
1230 | $state{handle} = ka_fetch $ka_key; |
1181 | $state{handle}->destroyed |
1231 | # $state{handle}->destroyed |
1182 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1232 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (1), please report.";#d# |
1183 | $prepare_handle->(); |
1233 | $prepare_handle->(); |
1184 | $state{handle}->destroyed |
1234 | # $state{handle}->destroyed |
1185 | and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1235 | # and die "AnyEvent::HTTP: unexpectedly got a destructed handle (2), please report.";#d# |
1186 | $handle_actual_request->(); |
1236 | $handle_actual_request->(); |
1187 | |
1237 | |
1188 | } else { |
1238 | } else { |
1189 | my $tcp_connect = $arg{tcp_connect} |
1239 | my $tcp_connect = $arg{tcp_connect} |
1190 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
1240 | || do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect }; |
… | |
… | |
1248 | save cookies to disk, and you should call this function after loading them |
1298 | save cookies to disk, and you should call this function after loading them |
1249 | again. If you have a long-running program you can additionally call this |
1299 | again. If you have a long-running program you can additionally call this |
1250 | function from time to time. |
1300 | function from time to time. |
1251 | |
1301 | |
1252 | A cookie jar is initially an empty hash-reference that is managed by this |
1302 | 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: |
1303 | module. Its format is subject to change, but currently it is as follows: |
1254 | |
1304 | |
1255 | The key C<version> has to contain C<1>, otherwise the hash gets |
1305 | The key C<version> has to contain C<2>, otherwise the hash gets |
1256 | emptied. All other keys are hostnames or IP addresses pointing to |
1306 | cleared. All other keys are hostnames or IP addresses pointing to |
1257 | hash-references. The key for these inner hash references is the |
1307 | hash-references. The key for these inner hash references is the |
1258 | server path for which this cookie is meant, and the values are again |
1308 | server path for which this cookie is meant, and the values are again |
1259 | hash-references. Each key of those hash-references is a cookie name, and |
1309 | hash-references. Each key of those hash-references is a cookie name, and |
1260 | the value, you guessed it, is another hash-reference, this time with the |
1310 | the value, you guessed it, is another hash-reference, this time with the |
1261 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
1311 | key-value pairs from the cookie, except for C<expires> and C<max-age>, |
… | |
… | |
1265 | |
1315 | |
1266 | Here is an example of a cookie jar with a single cookie, so you have a |
1316 | Here is an example of a cookie jar with a single cookie, so you have a |
1267 | chance of understanding the above paragraph: |
1317 | chance of understanding the above paragraph: |
1268 | |
1318 | |
1269 | { |
1319 | { |
1270 | version => 1, |
1320 | version => 2, |
1271 | "10.0.0.1" => { |
1321 | "10.0.0.1" => { |
1272 | "/" => { |
1322 | "/" => { |
1273 | "mythweb_id" => { |
1323 | "mythweb_id" => { |
1274 | _expires => 1293917923, |
1324 | _expires => 1293917923, |
1275 | value => "ooRung9dThee3ooyXooM1Ohm", |
1325 | value => "ooRung9dThee3ooyXooM1Ohm", |
… | |
… | |
1303 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1353 | C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>). |
1304 | |
1354 | |
1305 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1355 | =item $AnyEvent::HTTP::MAX_PER_HOST |
1306 | |
1356 | |
1307 | The maximum number of concurrent connections to the same host (identified |
1357 | The maximum number of concurrent connections to the same host (identified |
1308 | by the hostname). If the limit is exceeded, then the additional requests |
1358 | by the hostname). If the limit is exceeded, then additional requests |
1309 | are queued until previous connections are closed. Both persistent and |
1359 | are queued until previous connections are closed. Both persistent and |
1310 | non-persistent connections are counted in this limit. |
1360 | non-persistent connections are counted in this limit. |
1311 | |
1361 | |
1312 | The default value for this is C<4>, and it is highly advisable to not |
1362 | The default value for this is C<4>, and it is highly advisable to not |
1313 | increase it much. |
1363 | increase it much. |
… | |
… | |
1420 | or die "$file: $!"; |
1470 | or die "$file: $!"; |
1421 | |
1471 | |
1422 | my %hdr; |
1472 | my %hdr; |
1423 | my $ofs = 0; |
1473 | my $ofs = 0; |
1424 | |
1474 | |
1425 | warn stat $fh; |
|
|
1426 | warn -s _; |
|
|
1427 | if (stat $fh and -s _) { |
1475 | if (stat $fh and -s _) { |
1428 | $ofs = -s _; |
1476 | $ofs = -s _; |
1429 | warn "-s is ", $ofs; |
1477 | warn "-s is ", $ofs; |
1430 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1478 | $hdr{"if-unmodified-since"} = AnyEvent::HTTP::format_date +(stat _)[9]; |
1431 | $hdr{"range"} = "bytes=$ofs-"; |
1479 | $hdr{"range"} = "bytes=$ofs-"; |
… | |
… | |
1459 | my (undef, $hdr) = @_; |
1507 | my (undef, $hdr) = @_; |
1460 | |
1508 | |
1461 | my $status = $hdr->{Status}; |
1509 | my $status = $hdr->{Status}; |
1462 | |
1510 | |
1463 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1511 | if (my $time = AnyEvent::HTTP::parse_date $hdr->{"last-modified"}) { |
1464 | utime $fh, $time, $time; |
1512 | utime $time, $time, $fh; |
1465 | } |
1513 | } |
1466 | |
1514 | |
1467 | if ($status == 200 || $status == 206 || $status == 416) { |
1515 | if ($status == 200 || $status == 206 || $status == 416) { |
1468 | # download ok || resume ok || file already fully downloaded |
1516 | # download ok || resume ok || file already fully downloaded |
1469 | $cb->(1, $hdr); |
1517 | $cb->(1, $hdr); |