
#cpan https://cpan.metacpan.org/authors/id/S/SR/SRI/Mojolicious-7.31.tar.gz\n#cpanm -n Mojolicious@7.31\nuse feature ':5.10';\nuse strict;\nuse warnings;\nuse utf8;\nuse Mojo;\nuse Encode qw(decode encode);\n##########################################################################\n$ENV{MOJO_REACTOR} = 'Mojo::Reactor::EV';\n\n#\u4f7f\u7528 EV \u5177\u6709\u66f4\u597d\u7684\u6027\u80fd\nmy $ua = Mojo::UserAgent->new;\n$ua->inactivity_timeout(60);\n$ua->connect_timeout(60);\n$ua->request_timeout(60);\n\n#\u9002\u5f53\u5ef6\u957f\u8d85\u65f6\u7684\u65f6\u95f4\uff0c\u963b\u6b62\u8fc7\u65e9\u7684 http \u8bf7\u6c42\u5931\u8d25\uff0c\u4f1a\u6709\u66f4\u597d\u7684\u6027\u80fd\n$ua->max_connections(1000);\n\n#\u6700\u5927\u8fde\u63a5\u6570 1000\n$ua->max_redirects(0);\n\n#\u963b\u6b62 http3xx \u91cd\u5b9a\u5411\n$ua->transactor->name('Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101 Firefox/102.0');\n\n#\u4f7f\u7528\u6b63\u5e38\u6d4f\u89c8\u5668\u7684 user agent\n$ua->cookie_jar->ignore( sub { 1 } );\n#\u7981\u7528 Mojo::UserAgent \u81ea\u52a8\u5904\u7406 cookie\n$ua->proxy->http('http://127.0.0.1:8080')->https('http://127.0.0.1:8080');\n#\u4f7f\u7528\u4ee3\u7406\u670d\u52a1\u5668\n\n##########################################################################\nmy @list = ();\n\n#\u539f\u59cb\u961f\u5217\nmy @urllist = ();\n\n#\u4e0b\u8f7d\u961f\u5217\nmy $n = 0;\n\n#\u4e0b\u8f7d\u6570\u91cf\nmy $m = 0;\n\n#\u51fa\u9519\u6570\u91cf\nmy $produce_num = 0;\n\n#\u751f\u4ea7\u8005\u6570\u91cf\nmy $consumer_num = 0;\n\n#\u6d88\u8d39\u8005\u6570\u91cf\nmy $cookie_num = 0;\n\n#cookie \u6570\u91cf\nmy @cookielist = ();\n\n#\u4f7f\u7528\u7684 cookie \u961f\u5217\nmy %cookieinvalid = ();\n\n#\u5931\u6548\u7684 cookie \u6563\u5217\n##########################################################################\nopen FILEIN, '<', \"./url.txt\" or die \"$!\";\nwhile (<FILEIN>) {\n my $cOntent= $_;\n chomp($content);\n $cOntent=~ s/\\r//;\n push( @list, $content );\n}\nclose FILEIN;\n\n#\u5bfc\u5165\u4e0b\u8f7d\u5217\u8868\n##########################################################################\nsub append_txt_to_file {\n my $file_name = $_[0];\n my $txt = $_[1];\n local *FH;\n open FH, '>>', $file_name;\n print FH $txt;\n close FH;\n}\n\nsub write_txt_to_file {\n my $file_name = $_[0];\n my $txt = $_[1];\n local *FH;\n open FH, '>', $file_name;\n print FH $txt;\n close FH;\n}\nmy %safe_character = (\n '<' => '\uff1c',\n '>' => '\uff1e',\n ':' => '\uff1a',\n '\"' => '\uff02',\n '/' => '\uff0f',\n '\\\\' => '\uff3c',\n '|' => '\uff5c',\n '?' => '\uff1f',\n '*' => '\uff0a',\n);\n\nsub repace_safe {\n my $per_char = $_[0];\n my $one_txt = $_[1];\n my $output_char;\n if ( exists $safe_character{$per_char} ) {\n $output_char = $safe_character{$per_char};\n }\n else {\n $output_char = $per_char;\n }\n return $output_char;\n}\n\nsub find {\n my $html_bin = $_[0];\n my $id = $_[1];\n if ( $html_bin =~ m/<\\/html>/ ) {\n return '####';\n }\n else {\n return '@@@';\n }\n}\n##########################################################################\nsub get_multiplex {\n my $id = $_[0];\n my $delay = Mojo::IOLoop->delay( sub { get_multiplex($id) } );\n\n #get_multiplex \u9012\u5f52\u8fed\u4ee3\u7684\u5f00\u59cb\u6807\u8bb0\n #$id \u662f\u6bcf\u4e00\u4e2a\u7ebf\u7a0b\uff08\u7aef\u53e3\u7684\u5e8f\u53f7\uff09\n my $end = $delay->begin;\n Mojo::IOLoop->timer( 0.1 => $delay->begin );\n\n #\u6bcf\u4e2a http \u8bf7\u6c42\u524d\u6682\u505c 0.1s\n if ( scalar @urllist == 0 ) {\n if ( $produce_num == $consumer_num ) {\n Mojo::IOLoop->stop;\n\n #\u5f02\u6b65\u5faa\u73af\u7ed3\u675f\n #\u5f53\u961f\u5217\u6570\u91cf\u4e3a 0 \uff0c\u4e14\u6240\u6709\u7684\u7ebf\u7a0b\u6570\u636e\u90fd\u5904\u7406\u5b8c\u6bd5\u7684\u65f6\u5019\uff0c\u7ec8\u6b62\u4e8b\u4ef6\u5faa\u73af\n #return \u5b58\u5728\u4e00\u4e2a\u9012\u5f52\u8fd4\u56de\u94fe\uff0c\u8fd9\u91cc\u53ef\u4ee5\u66f4\u5feb\u5730\u7ed3\u675f\n }\n return;\n\n #\u8fd9\u91cc\u8fd4\u56de\u540e\u5f02\u6b65\u4efb\u52a1\u6570\u91cf\u4e3a 0 \u65f6\uff0c\u7cfb\u7edf\u4f1a\u81ea\u52a8\u7ed3\u675f\u5f02\u6b65\u5faa\u73af\uff0c\u4e0d\u8fc7\u901f\u5ea6\u8f83\u6162\n #return \u8fd4\u56de\u95ed\u5305\u51fd\u6570\u7684\u5f00\u59cb\uff0c\u5e76\u7ed3\u675f\u95ed\u5305\u51fd\u6570\uff0c\u4e0b\u9762\u4e0d\u5f00\u542f\u9012\u5f52\u81ea\u8eab\n }\n else {\n my $object = shift @urllist;\n $produce_num++;\n my $url = $object;\n my $filename = $object;\n $filename =~ s/^http:\\/\\/www\\.bing\\.com\\/w\\///m;\n $filename =~ s/(.)/repace_safe($1)/eg;\n $filename = \"./www.bing.com/\" . $filename . \".html\";\n if ( -e $filename ) {\n syswrite STDERR, encode( 'utf8', $n . \"\\t\" . $object . \"\\t \u8df3\u8fc7\\n\" ); #STDOUT \u7f16\u7801\u5df2\u6539\uff0c\u8f93\u9001\u5230 STDOUT \u4f1a\u51fa\u73b0\u9519\u8bef\n $consumer_num++;\n $end->();\n }\n else {\n my $build_tx = $ua->build_tx( GET => $url );\n $build_tx->req->headers->remove('Accept-Encoding');\n\n #\u963b\u6b62\u7f51\u9875\u538b\u7f29\uff0c\u4fdd\u8bc1\u66f4\u597d\u7684\u6027\u80fd\n $build_tx->req->headers->add( 'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8' );\n $build_tx->req->headers->add( 'Accept-Language' => 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2' );\n $ua->transactor->name( 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:' . int( rand(900) ) . ') Gecko/' . int( rand(40000001) ) . ' Firefox/' . int( rand(900) ) . '.0' );\n\n #\u4f7f\u7528 2 \u4e07\u4e2a cookie\n $ua->start(\n $build_tx => sub {\n my ( $ua, $tx ) = @_;\n if ( !$tx->is_finished ) {\n push( @urllist, $object );\n syswrite STDERR, \"http \u4f20\u8f93\u672a\u5b8c\u6210\" . \"\\n\";\n syswrite STDERR, encode( 'utf8', $url . \"\\t\" . $tx->error->{message} . \"\\n\" );\n }\n else {\n my $code = '';\n $code = $tx->res->code if defined $tx->res->code;\n if ( $code =~ /\\A2/ ) {\n my $size = $tx->res->content->asset->size;\n my $content_length = $tx->res->headers->to_hash->{'Content-Length'};\n if ( ( $size == $content_length ) || !( defined $content_length ) ) {\n my $outnum = find( $tx->res->body, $id );\n if ( $outnum ne '@@@' ) {\n append_txt_to_file( \"url.txt\", $object . \"\\t\" . $outnum . \"\\n\" );\n write_txt_to_file( $filename, $tx->res->body );\n $n++;\n syswrite STDERR, encode( 'utf8', $n . \"\\t\" . $object . \"\\n\" );\n }\n else {\n $n++;\n syswrite STDERR, encode( 'utf8', $m . \"\\t\" . $object . \"\\t \u7f51\u9875\u4e0b\u8f7d\u5b8c\u6574\u4f46\u672a\u63d0\u53d6\u5230\u6570\u636e\\n\" );\n }\n }\n else {\n $m++;\n push( @urllist, $object );\n syswrite STDERR, encode( 'utf8', $m . \"\\t\" . $object . \"\\t \u7f51\u9875\u672a\u4e0b\u8f7d\u5b8c\u6574\\n\" );\n }\n }\n elsif ( $code =~ /\\A4/ ) {\n syswrite STDERR, encode( 'utf8', $m . \"\\t\" . $object . \"\\thttp 4xx\\n\" );\n push( @urllist, $object );\n Mojo::IOLoop->timer( 0.5 => $delay->begin );\n\n #http 404\n }\n else {\n $m++;\n push( @urllist, $object );\n syswrite STDERR, encode( 'utf8', $m . \"\\t\" . $object . \"\\t \u672a\u53d1\u73b0 http code, http 3xx, http 5xx\\n\" );\n\n #\u6807\u8bb0\u5931\u6548\u7684\u4ece cookie http 3xx\n Mojo::IOLoop->timer( 0.5 => $delay->begin );\n\n #\u670d\u52a1\u5668\u8fd4\u56de 5xx \uff0c\u6682\u505c 0.5s\n #\u672a\u53d1\u73b0 http code, http 302, http 503\n }\n }\n $consumer_num++;\n $end->();\n\n #get_multiplex \u9012\u5f52\u8fed\u4ee3\u7684\u7ed3\u675f\u6807\u8bb0\n #\u4ece\u8fd9\u91cc\u8df3\u8f6c\u5230\u4e0b\u4e00\u4e2a get_multiplex\n }\n );\n }\n }\n}\n##########################################################################\n$produce_num = 0;\n$consumer_num = 0;\n@urllist = @list;\n\n#\u5f02\u6b65\u4e0b\u8f7d\u524d\u7684\u53d8\u91cf\u51c6\u5907\nforeach my $id ( 1 .. 50 ) { get_multiplex($id) }\n\n#\u4f7f\u7528 50 \u4e2a\u7ebf\u7a0b\uff08\u7aef\u53e3\uff09\u4e0b\u8f7d\n#\u5982\u679c\u7ebf\u7a0b\u6570\u662f 100 \uff0c\u9650\u5236\u6700\u5927 cookie \u6570\u65e0\u6cd5\u751f\u6548\uff0c\u5e76\u4e14 EV \u4f1a\u51fa\u73b0\u9519\u8bef\nMojo::IOLoop->start;\n\n#\u5f02\u6b65\u5faa\u73af\u542f\u52a8\n##########################################################################\n\n\n", "date_published": "2022-09-15T10:28:30+00:00", "title": "\u4e00\u6bb5 perl \u4ee3\u7801\u5c55\u793a\u5982\u4f55 all in one \u4f18\u96c5\u5730\u7f16\u5199\u4e00\u4e2a\u5f02\u6b65\u722c\u866b", "id": "t/880334" }, { "author": { "url": "member/alexecn", "name": "alexecn", "avatar": "https://cdn.v2ex.com/avatar/72cd/5bef/46081_large.png?m=1598327848" }, "url": "t/827149", "title": "Perl \u6000\u65e7\u7fa4", "id": "t/827149", "date_published": "2022-01-09T09:48:10+00:00", "content_html": "
\u8fd8\u6709\u559c\u6b22 Perl \u7684\u670b\u53cb\uff0c\u53ef\u4ee5\u52a0\u7fa4\u3002
\n\u5c0f\u4f17\u7fa4
\n\u957f\u671f\u8fdb\u7fa4\uff0c\u52a0\u5fae\u4fe1\uff1awwmm9ww
\n" }, { "author": { "url": "member/xiaoming1992", "name": "xiaoming1992", "avatar": "https://cdn.v2ex.com/avatar/c7e9/042b/284747_large.png?m=1753418917" }, "url": "t/813465", "date_modified": "2021-11-06T04:15:02+00:00", "content_html": "\u5b89\u88c5 vscode latex \u63d2\u4ef6\u65f6\u9700\u8981 perl, \u6240\u4ee5\u4ece perl \u5b98\u7f51\u627e\u5230\u4e86 windows \u793e\u533a\u7248, https://www.activestate.com/products/perl/, \u4e0b\u8f7d\u9700\u8981\u6ce8\u518c\uff0c\u70b9\u51fb github \u6ce8\u518c\u65f6, \u63d0\u793a\u9700\u8981\u8bbf\u95ee\u6211\u7684\u79c1\u6709\u5e93\u7684\u53ea\u8bfb\u6743\u9650, \u6211\u4e0d\u77e5\u9053\u662f\u4e0d\u662f\u6211\u7406\u89e3\u6709\u8bef\uff1f\u8fd8\u662f\u8bf4\u4ed6\u786e\u5b9e\u9700\u8981\u6211\u6388\u6743\u8bbf\u95ee\u6211\u7684\u79c1\u6709\u5e93\uff1f\u5982\u679c\u662f\uff0c\u6211\u4e0d\u592a\u660e\u767d\u4e3a\u4ec0\u4e48\u8981\u8bbf\u95ee\u6211\u7684\u79c1\u6709\u5e93...
\n
Perl 6 \u7684\u5b9e\u73b0 rakudo \u5df2\u7ecf\u5f00\u53d1\u7684\u5f88\u597d\u4e86\uff0c\u6709\u4eba\u6709\u5174\u8da3\u4e00\u8d77\u6765\u5b66\u4e60 Perl 6 \u4e48\uff1f
\u987a\u4fbf\u9644\u4e0a\u6211\u505a\u7684\u6a21\u5757\u5730\u5740\uff0c\u6b22\u8fce\u5404\u4f4d star
\nhttps://github.com/araraloren/perl6-terminal-table
\n\u4e0b\u9762\u7684\u4e1c\u897f\u6458\u81ea wiki
\nPerl 6 \u662f\u7f16\u7a0b\u8bed\u8a00 Perl \u8bed\u8a00\u7684\u540e\u7eed\u3002\u7531\u4e8e Perl 6 \u8bed\u8a00\u8bed\u6cd5\u4e0e Perl 5 \u4e0d\u540c\uff0c\u56e0\u6b64\uff0c\u53ef\u4ee5\u628a\u5b83\u770b\u4f5c\u4e00\u79cd\n\u65b0\u7684\u7f16\u7a0b\u8bed\u8a00\uff0c\u5c3d\u7ba1\u5176\u8ba1\u5212\u63d0\u4f9b Perl 5 \u7684\u517c\u5bb9\u6a21\u5f0f\u3002\n\nPerl 6 \u62e5\u6709\u4e30\u5bcc\u7684\u73b0\u4ee3\u8bed\u8a00\u7279\u5f81\uff0c\u62c9\u91cc\u00b7\u6c83\u5c14\u8ba1\u5212\u7528\u91cd\u65b0\u5b9a\u4e49\u6b63\u89c4\u8868\u8fbe\u5f0f\u548c\u589e\u52a0\u51fd\u6570\u5f0f\u7f16\u7a0b\u8bed\u8a00\u7684\u7279\n\u5f81\uff0c\u4f7f\u4e4b\u6210\u4e3a\u53ef\u6f14\u5316\u7684\u8bed\u8a00\u3002\u4e3a\u4fdd\u8bc1 Perl 6 \u548c Perl \u793e\u533a\u7684\u6301\u7eed\u7a33\u5b9a\u53d1\u5c55\uff0cPerl 6 \u7f16\u8bd1\u5668\u9700\u8981\u4f7f\u7528\nPerl 6 \u6765\u91cd\u5199\u3002\u4e3a\u4fdd\u8bc1 Perl \u8bed\u8a00\u539f\u6709\u5e93\u7684\u91cd\u7528\uff0c\u7f16\u8bd1\u5668\u8fd8\u8ba1\u5212\u63d0\u4f9b\u540c Perl 5 \u8bed\u8a00\u7684\u517c\u5bb9\u6a21\u5f0f\u3002\n\n\u7531\u4e8e Perl 6 \u8bed\u8a00\u7684\u8bed\u6cd5\u7279\u5f81\u548c\u8981\u6c42\uff0cPerl 6 \u7f16\u8bd1\u5668\u5b9e\u73b0\u975e\u5e38\u590d\u6742\uff0c\u540c\u65f6\uff0c\u81ea\u7531\u8f6f\u4ef6\u793e\u533a\u7684\u8d44\u6e90\u76f8\u5bf9\n\u8d2b\u4e4f\u3002\u56e0\u6b64\uff0cPerl 6 \u7f16\u8bd1\u5668\u7684\u5f00\u53d1\u663e\u5f97\u76f8\u5f53\u7f13\u6162\u3002\n\nBTW: Perl \u771f\u7684\u597d\u51b7\u6e05\uff0c\u8fd9\u4e2a\u8282\u70b9\u4e00\u5e74\u4e5f\u5c31\u4e00\u4e2a\u5e16\u5b50
\nBTW2: \u8fd8\u662f\u559c\u6b22 asciidoc
\n" }, { "author": { "url": "member/chenhui7373", "name": "chenhui7373", "avatar": "https://cdn.v2ex.com/avatar/d59d/9cee/76124_large.png?m=1489714856" }, "url": "t/260530", "date_modified": "2016-03-02T07:45:32+00:00", "content_html": "http://perl.linuxtoy.org/contents.html\r