--- AnyEvent-HTTP/HTTP.pm 2008/06/04 11:58:36 1.3 +++ AnyEvent-HTTP/HTTP.pm 2008/06/05 13:06:43 1.10 @@ -54,9 +54,14 @@ Executes an HTTP-GET request. See the http_request function for details on additional parameters. -=item http_get $url, $body, key => value..., $cb->($data, $headers) +=item http_head $url, key => value..., $cb->($data, $headers) -Executes an HTTP-POST request with a requets body of C<$bod>. See the +Executes an HTTP-HEAD request. See the http_request function for details on +additional parameters. + +=item http_post $url, $body, key => value..., $cb->($data, $headers) + +Executes an HTTP-POST request with a request body of C<$bod>. See the http_request function for details on additional parameters. =item http_request $method => $url, key => value..., $cb->($data, $headers) @@ -68,15 +73,28 @@ (or C if it wasn't available due to errors), and a hash-ref with response headers as second argument. -All the headers in that has are lowercased. In addition to the response +All the headers in that hash are lowercased. In addition to the response headers, the three "pseudo-headers" C, C and C contain the three parts of the HTTP Status-Line of the same -name. +name. If the server sends a header multiple lines, then their contents +will be joined together with C<\x00>. If an internal error occurs, such as not being able to resolve a hostname, then C<$data> will be C, C<< $headers->{Status} >> will be C<599> and the C pseudo-header will contain an error message. +A typical callback might look like this: + + sub { + my ($body, $hdr) = @_; + + if ($hdr->{Status} =~ /^2/) { + ... everything should be ok + } else { + print "error, $hdr->{Status} $hdr->{Reason}\n"; + } + } + Additional parameters are key-value pairs, and are fully optional. They include: @@ -109,10 +127,44 @@ The request body, usually empty. Will be-sent as-is (future versions of this module might offer more options). -=back +=item cookie_jar => $hash_ref + +Passing this parameter enables (simplified) cookie-processing, loosely +based on the original netscape specification. + +The C<$hash_ref> must be an (initially empty) hash reference which will +get updated automatically. It is possible to save the cookie_jar to +persistent storage with something like JSON or Storable, but this is not +recommended, as expire times are currently being ignored. + +Note that this cookie implementation is not of very high quality, nor +meant to be complete. If you want complete cookie management you have to +do that on your own. C is meant as a quick fix to get some +cookie-using sites working. Cookies are a privacy disaster, do not use +them unless required to. =back +Example: make a simple HTTP GET request for http://www.nethype.de/ + + http_request GET => "http://www.nethype.de/", sub { + my ($body, $hdr) = @_; + print "$body\n"; + }; + +Example: make a HTTP HEAD request on https://www.google.com/, use a +timeout of 30 seconds. + + http_request + GET => "https://www.google.com", + timeout => 30, + sub { + my ($body, $hdr) = @_; + use Data::Dumper; + print Dumper $hdr; + } + ; + =cut sub http_request($$$;@) { @@ -123,54 +175,81 @@ $method = uc $method; - if (my $hdr = delete $arg{headers}) { + if (my $hdr = $arg{headers}) { while (my ($k, $v) = each %$hdr) { $hdr{lc $k} = $v; } } - my $proxy = $arg{proxy} || $PROXY; - my $timeout = $arg{timeout} || $TIMEOUT; my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; - $hdr{"user-agent"} ||= $USERAGENT; - - my ($host, $port, $path, $scheme); + return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) + if $recurse < 0; - if ($proxy) { - ($host, $port, $scheme) = @$proxy; - $path = $url; - } else { - ($scheme, my $authority, $path, my $query, my $fragment) = - $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; + my $proxy = $arg{proxy} || $PROXY; + my $timeout = $arg{timeout} || $TIMEOUT; - $port = $scheme eq "http" ? 80 - : $scheme eq "https" ? 443 - : croak "$url: only http and https URLs supported"; + $hdr{"user-agent"} ||= $USERAGENT; - $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x - or croak "$authority: unparsable URL"; + my ($scheme, $authority, $upath, $query, $fragment) = + $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; - $host = $1; - $port = $2 if defined $2; + $scheme = lc $scheme; - $host =~ s/^\[(.*)\]$/$1/; - $path .= "?$query" if length $query; + my $uport = $scheme eq "http" ? 80 + : $scheme eq "https" ? 443 + : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); + + $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x + or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); + + my $uhost = $1; + $uport = $2 if defined $2; + + $uhost =~ s/^\[(.*)\]$/$1/; + $upath .= "?$query" if length $query; + + $upath =~ s%^/?%/%; + + # cookie processing + if (my $jar = $arg{cookie_jar}) { + %$jar = () if $jar->{version} < 1; + + my @cookie; + + while (my ($chost, $v) = each %$jar) { + next unless $chost eq substr $uhost, -length $chost; + next unless $chost =~ /^\./; + + while (my ($cpath, $v) = each %$v) { + next unless $cpath eq substr $upath, 0, length $cpath; + + while (my ($k, $v) = each %$v) { + next if $scheme ne "https" && exists $v->{secure}; + push @cookie, "$k=$v->{value}"; + } + } + } + + $hdr{cookie} = join "; ", @cookie + if @cookie; + } - $path = "/" unless $path; + my ($rhost, $rport, $rpath); # request host, port, path - $hdr{host} = $host = lc $host; + if ($proxy) { + ($rhost, $rport, $scheme) = @$proxy; + $rpath = $url; + } else { + ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); + $hdr{host} = $uhost; } - $scheme = lc $scheme; + $hdr{"content-length"} = length $arg{body}; my %state; - $state{body} = delete $arg{body}; - - $hdr{"content-length"} = length $state{body}; - - $state{connect_guard} = AnyEvent::Socket::tcp_connect $host, $port, sub { + $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { $state{fh} = shift or return $cb->(undef, { Status => 599, Reason => "$!" }); @@ -204,10 +283,10 @@ # send request $state{handle}->push_write ( - "$method $path HTTP/1.0\015\012" + "$method $rpath HTTP/1.0\015\012" . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) . "\015\012" - . (delete $state{body}) + . (delete $arg{body}) ); %hdr = (); # reduce memory usage, save a kitten @@ -218,9 +297,9 @@ or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); my %hdr = ( # response headers - HTTPVersion => ",$1", - Status => ",$2", - Reason => ",$3", + HTTPVersion => "\x00$1", + Status => "\x00$2", + Reason => "\x00$3", ); # headers, could be optimized a bit @@ -228,7 +307,7 @@ for ("$_[1]\012") { # we support spaces in field names, as lotus domino # creates them. - $hdr{lc $1} .= ",$2" + $hdr{lc $1} .= "\x00$2" while /\G ([^:\000-\037]+): [\011\040]* @@ -237,13 +316,50 @@ /gxc; /\G$/ - or return $cb->(undef, { Status => 599, Reason => "garbled response headers" }); + or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); } substr $_, 0, 1, "" for values %hdr; - if ($method ne "HEAD") { + my $finish = sub { + %state = (); + + # set-cookie processing + if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { + for (split /\x00/, $hdr{"set-cookie"}) { + my ($cookie, @arg) = split /;\s*/; + my ($name, $value) = split /=/, $cookie, 2; + my %kv = (value => $value, map { split /=/, $_, 2 } @arg); + + my $cdom = (delete $kv{domain}) || $uhost; + my $cpath = (delete $kv{path}) || "/"; + + $cdom =~ s/^.?/./; # make sure it starts with a "." + + my $ndots = $cdom =~ y/.//; + next if $ndots < ($cdom =~ /[^.]{3}$/ ? 2 : 3); + + # store it + $arg{cookie_jar}{version} = 1; + $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; + } + } + + if ($_[1]{Status} =~ /^x30[12]$/ && $recurse) { + # microsoft and other assholes don't give a shit for following standards, + # try to support a common form of broken Location header. + $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; + + http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); + } else { + $cb->($_[0], $_[1]); + } + }; + + if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { + $finish->(undef, \%hdr); + } else { if (exists $hdr{"content-length"}) { $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { # could cache persistent connection now @@ -251,15 +367,13 @@ # but we don't, due to misdesigns, this is annoyingly complex }; - %state = (); - $cb->($_[1], \%hdr); + $finish->($_[1], \%hdr); }); } else { # too bad, need to read until we get an error or EOF, # no way to detect winged data. $_[0]->on_error (sub { - %state = (); - $cb->($_[0]{rbuf}, \%hdr); + $finish->($_[0]{rbuf}, \%hdr); }); $_[0]->on_eof (undef); $_[0]->on_read (sub { }); @@ -279,11 +393,18 @@ &http_request } +sub http_head($$;@) { + unshift @_, "HEAD"; + &http_request +} + sub http_post($$$;@) { unshift @_, "POST", "body"; &http_request } +=back + =head2 GLOBAL FUNCTIONS AND VARIABLES =over 4