… | |
… | |
41 | use strict; |
41 | use strict; |
42 | no warnings; |
42 | no warnings; |
43 | |
43 | |
44 | use Errno (); |
44 | use Errno (); |
45 | |
45 | |
46 | use AnyEvent 4.8 (); |
46 | use AnyEvent 5.0 (); |
47 | use AnyEvent::Util (); |
47 | use AnyEvent::Util (); |
48 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
49 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
50 | |
50 | |
51 | use base Exporter::; |
51 | use base Exporter::; |
52 | |
52 | |
53 | our $VERSION = '1.42'; |
53 | our $VERSION = '1.44'; |
54 | |
54 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
56 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
… | |
… | |
145 | sent at all). |
145 | sent at all). |
146 | |
146 | |
147 | =item timeout => $seconds |
147 | =item timeout => $seconds |
148 | |
148 | |
149 | The time-out to use for various stages - each connect attempt will reset |
149 | The time-out to use for various stages - each connect attempt will reset |
150 | the timeout, as will read or write activity. Default timeout is 5 minutes. |
150 | the timeout, as will read or write activity, i.e. this is not an overall |
|
|
151 | timeout. |
|
|
152 | |
|
|
153 | Default timeout is 5 minutes. |
151 | |
154 | |
152 | =item proxy => [$host, $port[, $scheme]] or undef |
155 | =item proxy => [$host, $port[, $scheme]] or undef |
153 | |
156 | |
154 | Use the given http proxy for all requests. If not specified, then the |
157 | Use the given http proxy for all requests. If not specified, then the |
155 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
158 | default proxy (as specified by C<$ENV{http_proxy}>) is used. |
… | |
… | |
187 | verification, highest compatibility) and high-security (CA and common-name |
190 | verification, highest compatibility) and high-security (CA and common-name |
188 | verification) TLS context. |
191 | verification) TLS context. |
189 | |
192 | |
190 | The default for this option is C<low>, which could be interpreted as "give |
193 | The default for this option is C<low>, which could be interpreted as "give |
191 | me the page, no matter what". |
194 | me the page, no matter what". |
|
|
195 | |
|
|
196 | =item on_prepare => $callback->($fh) |
|
|
197 | |
|
|
198 | In rare cases you need to "tune" the socket before it is used to |
|
|
199 | connect (for exmaple, to bind it on a given IP address). This parameter |
|
|
200 | overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect> |
|
|
201 | and behaves exactly the same way (e.g. it has to provide a |
|
|
202 | timeout). See the description for the C<$prepare_cb> argument of |
|
|
203 | C<AnyEvent::Socket::tcp_connect> for details. |
192 | |
204 | |
193 | =item on_header => $callback->($headers) |
205 | =item on_header => $callback->($headers) |
194 | |
206 | |
195 | When specified, this callback will be called with the header hash as soon |
207 | 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 |
208 | as headers have been successfully received from the remote server (not on |
… | |
… | |
360 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
372 | or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url }); |
361 | |
373 | |
362 | my $uhost = $1; |
374 | my $uhost = $1; |
363 | $uport = $2 if defined $2; |
375 | $uport = $2 if defined $2; |
364 | |
376 | |
365 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"; |
377 | $hdr{host} = defined $2 ? "$uhost:$2" : "$uhost" |
|
|
378 | unless exists $hdr{host}; |
366 | |
379 | |
367 | $uhost =~ s/^\[(.*)\]$/$1/; |
380 | $uhost =~ s/^\[(.*)\]$/$1/; |
368 | $upath .= "?$query" if length $query; |
381 | $upath .= "?$query" if length $query; |
369 | |
382 | |
370 | $upath =~ s%^/?%/%; |
383 | $upath =~ s%^/?%/%; |
… | |
… | |
416 | |
429 | |
417 | # leave out fragment and query string, just a heuristic |
430 | # leave out fragment and query string, just a heuristic |
418 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
431 | $hdr{referer} ||= "$uscheme://$uauthority$upath" unless exists $hdr{referer}; |
419 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
432 | $hdr{"user-agent"} ||= $USERAGENT unless exists $hdr{"user-agent"}; |
420 | |
433 | |
421 | $hdr{"content-length"} = length $arg{body}; |
434 | $hdr{"content-length"} = length $arg{body} |
|
|
435 | if length $arg{body} || $method ne "GET"; |
422 | |
436 | |
423 | my %state = (connect_guard => 1); |
437 | my %state = (connect_guard => 1); |
424 | |
438 | |
425 | _get_slot $uhost, sub { |
439 | _get_slot $uhost, sub { |
426 | $state{slot_guard} = shift; |
440 | $state{slot_guard} = shift; |
… | |
… | |
733 | =over 4 |
747 | =over 4 |
734 | |
748 | |
735 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
749 | =item AnyEvent::HTTP::set_proxy "proxy-url" |
736 | |
750 | |
737 | Sets the default proxy server to use. The proxy-url must begin with a |
751 | Sets the default proxy server to use. The proxy-url must begin with a |
738 | string of the form C<http://host:port> (optionally C<https:...>). |
752 | string of the form C<http://host:port> (optionally C<https:...>), croaks |
|
|
753 | otherwise. |
|
|
754 | |
|
|
755 | To clear an already-set proxy, use C<undef>. |
739 | |
756 | |
740 | =item $AnyEvent::HTTP::MAX_RECURSE |
757 | =item $AnyEvent::HTTP::MAX_RECURSE |
741 | |
758 | |
742 | The default value for the C<recurse> request parameter (default: C<10>). |
759 | The default value for the C<recurse> request parameter (default: C<10>). |
743 | |
760 | |
… | |
… | |
764 | =back |
781 | =back |
765 | |
782 | |
766 | =cut |
783 | =cut |
767 | |
784 | |
768 | sub set_proxy($) { |
785 | sub set_proxy($) { |
|
|
786 | if (length $_[0]) { |
769 | $PROXY = [$2, $3 || 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix; |
787 | $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix |
|
|
788 | or Carp::croak "$_[0]: invalid proxy URL"; |
|
|
789 | $PROXY = [$2, $3 || 3128, $1] |
|
|
790 | } else { |
|
|
791 | undef $PROXY; |
|
|
792 | } |
770 | } |
793 | } |
771 | |
794 | |
772 | # initialise proxy from environment |
795 | # initialise proxy from environment |
|
|
796 | eval { |
773 | set_proxy $ENV{http_proxy}; |
797 | set_proxy $ENV{http_proxy}; |
|
|
798 | }; |
774 | |
799 | |
775 | =head1 SEE ALSO |
800 | =head1 SEE ALSO |
776 | |
801 | |
777 | L<AnyEvent>. |
802 | L<AnyEvent>. |
778 | |
803 | |