.\" Automatically generated by Pod::Man 4.14 (Pod::Simple 3.42) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is >0, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{\ . if \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{\ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" ======================================================================== .\" .IX Title "Scrappy::Scraper::Control 3pm" .TH Scrappy::Scraper::Control 3pm "2022-06-17" "perl v5.34.0" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" Scrappy::Scraper::Control \- Scrappy HTTP Request Constraints System .SH "VERSION" .IX Header "VERSION" version 0.94112090 .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 2 \& #!/usr/bin/perl \& use Scrappy::Scraper::Control; \& \& my $control = Scrappy::Scraper::Control\->new; \& \& $control\->allow(\*(Aqhttp://search.cpan.org\*(Aq); \& $control\->allow(\*(Aqhttp://search.cpan.org\*(Aq, if => { \& content_type => [\*(Aqtext/html\*(Aq, \*(Aqapplication/x\-tar\*(Aq] \& } \& ); \& \& $control\->restrict(\*(Aqhttp://www.cpan.org\*(Aq); \& \& if ($control\->is_allowed(\*(Aqhttp://search.cpan.org/\*(Aq)) { \& ... \& } \& \& # constraints will only be checked if the is_allowed method is \& # passed a HTTP::Response object. .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" Scrappy::Scraper::Control provides \s-1HTTP\s0 request access control for the Scrappy framework. .SS "\s-1ATTRIBUTES\s0" .IX Subsection "ATTRIBUTES" The following is a list of object attributes available with every Scrappy::Scraper::Control instance. .PP \fIallowed\fR .IX Subsection "allowed" .PP The allowed attribute holds a hasherf of allowed domain/contraints. .PP .Vb 2 \& my $control = Scrappy::Scraper::Control\->new; \& $control\->allowed; \& \& e.g. \& \& { \& \*(Aqwww.foobar.com\*(Aq => { \& methods => [qw/GET POST PUSH PUT DELETE/], \& content_type => [\*(Aqtext/html\*(Aq] \& } \& } .Ve .PP \fIrestricted\fR .IX Subsection "restricted" .PP The restricted attribute holds a hasherf of restricted domain/contraints. .PP .Vb 2 \& my $control = Scrappy::Scraper::Control\->new; \& $control\->restricted; \& \& e.g. \& \& { \& \*(Aqwww.foobar.com\*(Aq => { \& methods => [qw/GET POST PUSH PUT DELETE/] \& } \& } .Ve .SH "METHODS" .IX Header "METHODS" .SS "allow" .IX Subsection "allow" .Vb 6 \& my $control = Scrappy::Scraper::Control\->new; \& $control\->allow(\*(Aqhttp://www.perl.org\*(Aq); \& $control\->allow(\*(Aqhttp://search.cpan.org\*(Aq, if => { \& content_type => [\*(Aqtext/html\*(Aq, \*(Aqapplication/x\-tar\*(Aq] \& } \& ); .Ve .SS "restrict" .IX Subsection "restrict" .Vb 6 \& my $control = Scrappy::Scraper::Control\->new; \& $control\->restrict(\*(Aqhttp://www.perl.org\*(Aq); \& $control\->restrict(\*(Aqhttp://search.cpan.org\*(Aq, if => { \& content_type => [\*(Aqtext/html\*(Aq, \*(Aqapplication/x\-tar\*(Aq] \& } \& ); .Ve .SS "is_allowed" .IX Subsection "is_allowed" .Vb 3 \& my $control = Scrappy::Scraper::Control\->new; \& $control\->allow(\*(Aqhttp://search.cpan.org\*(Aq); \& $control\->restrict(\*(Aqhttp://www.perl.org\*(Aq); \& \& if (! $control\->is_allowed(\*(Aqhttp://perl.org\*(Aq)) { \& die \*(AqCant get to Perl.org\*(Aq; \& } .Ve .SH "AUTHOR" .IX Header "AUTHOR" Al Newkirk .SH "COPYRIGHT AND LICENSE" .IX Header "COPYRIGHT AND LICENSE" This software is copyright (c) 2010 by awncorp. .PP This is free software; you can redistribute it and/or modify it under the same terms as the Perl 5 programming language system itself.