\u5927\u962a\u99c5\u524d \u30d0\u30b9\u6642\u523b\u8868 (62\u7cfb\u7d71\u30fb103\u7cfb\u7d71)<\/a><\/p>\n\u3053\u3053\u304b\u308962\u7cfb\u7d71\u306e\u767a\u6642\u523b\u3092\u629c\u304d\u51fa\u3057\u305f\u3044\u3002<\/p>\n
\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u3092\u898b\u3066\u307f\u308b\u3002\u3059\u308b\u3068class\u306btimetable\u304c\u6307\u5b9a\u3055\u308c\u305ftable\u8981\u7d20\u304c\u3042\u308b\u3002a\u8981\u7d20\u306b\u96a3\u63a5\u3057\u3066\u3044\u308b\u3002<\/p>\n
\u305d\u306etable\u8981\u7d20\u306e\u4e0b\u306btr\u8981\u7d20\u304c\u3042\u3063\u30661\u6642\u9593\u3054\u3068\u306b\u51fa\u767a\u3059\u308b\u30d0\u30b9\u304c\u307e\u3068\u3081\u3089\u308c\u3066\u3044\u308b\u3002<\/p>\n
\u305d\u306e\u4e0b\u306b\u306fth\u8981\u7d20\u3068td\u8981\u7d20\u304c3\u3064\u306a\u3089\u3093\u3067\u3044\u3066\u3001th\u306f\u767a\u6642\u3001td\u305d\u308c\u305e\u308c\u306f\u5e73\u65e5\u30fb\u571f\u66dc\u30fb\u4f11\u65e5\u306e\u767a\u8eca\u3059\u308b\u30d0\u30b9\u3092\u793a\u3057\u3066\u3044\u308b\u3002<\/p>\n
\u305d\u306etd\u8981\u7d20\u306e\u4e2d\u306b\u306f\u30d0\u30b9\u3054\u3068\u306bdiv\u8981\u7d20\u304c\u4e26\u3093\u3067\u3044\u3066\u3001\u6ce8\u91c8\u3092\u4ed8\u3051\u308bdiv\u8981\u7d20\u3068\u3001\u5206\u3092\u793a\u3059div\u8981\u7d20\u304c\u3042\u308b\u3002<\/p>\n
\n \u3055\u3066\u3001\u305d\u308c\u3092Perl\u306eWeb::Scraper\u3092\u4f7f\u3063\u3066\u629c\u304d\u51fa\u3057\u3066NextTrain\u306eTBL\u30c7\u30fc\u30bf\u306b\u52a0\u5de5\u3059\u308b\u30d7\u30ed\u30b0\u30e9\u30e0\u304c\u3053\u308c\u3060\u3002 <\/p>\n
use strict;\nuse warnings;\nuse Encode;\nuse Web::Scraper;\nuse URI;\nuse utf8;\nmy $getdetailurl=scraper{\n process \"\/\/table[\\@class='timetable'][1]\/colgroup\/tr[position()>1]\",\"lines[]\"=>scraper{\n process \"\/\/th\",\"hour\"=>'TEXT';\n process \"\/\/td\",'section[]'=>scraper{\n process \"\/\/div[\\@class='item'][div[2]\/text()!='\u3000']\",'bus[]'=>scraper{\n process \"\/div\/div[1]\",'attr'=>'TEXT';\n process \"\/div\/div[2]\",'min'=>'TEXT';\n }\n };\n };\n};\nmy $res=$getdetailurl->scrape(URI->new(\"http:\/\/kensaku.kotsu.city.osaka.jp\/bus\/dia\/jikoku\/jikoku034484.html\"));\nopen my $ofh,'>:encoding(shiftjis)','out.tbl';\nsub attr{\n #if($_[0]=~m\/\u2605\/){ return ('NS'); }\n #else { return (); }\n}\nmy %attr=();\nsub todata{\n my @res;\n for(@{$_[0]}){\n my @attr=attr($_->{'attr'});\n $attr{$_}++ for @attr;\n push @res,[$_->{'min'}+0,[@attr]];\n }\n return @res;\n}\nmy @data=([],[],[]);\nfor my $l(@{$res->{'lines'}}){\n push @{$data[$_]} ,[$l->{'hour'}+0 , [todata($l->{'section'}->[$_]->{'bus'})] ] for 0..2;\n}\nmy $chr=ord('A');\nfor(keys(%attr)){\n print $ofh chr($chr),':',$_.\"\\n\";\n $attr{$_}=chr($chr);\n}\nprint $ofh \"\\n\";\nfor(0..2){\n print $ofh ($_==0 ? \"[MON][TUE][WED][THU][FRI]\\n#(\u5e73\u65e5)\\n\" : $_==1 ? \"[SAT]\\n#(\u571f\u66dc)\\n\" : \"[SUN][HOL]\\n#(\u4f11\u65e5)\\n\");\n for(@{$data[$_]}){\n print $ofh $_->[0].': ';\n for(@{$_->[1]}){\n print $ofh $attr{$_} for @{$_->[1]};\n print $ofh $_->[0],' ';\n }\n print $ofh \"\\n\";\n }\n print $ofh \"\\n\"\n}<\/pre>\n\u3053\u306e\u4e2d\u3067Web::Scraper\u3067\u51e6\u7406\u3092\u3057\u3066\u3044\u308b\u306e\u306f\u6700\u521d\u306e\u65b9\u3067\u3042\u308b\u3002<\/p>\n
scraper{ \u2026 } \u3068\u3044\u3046\u98a8\u306b\u66f8\u3051\u3070\u51e6\u7406\u306e\u305f\u3081\u306e\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u304c\u5f97\u3089\u308c\u308b\u3002<\/p>\n
{ \u2026 } \u306b\u306f\u51e6\u7406\u306e\u5185\u5bb9\u3092\u66f8\u304d\u8fbc\u3080\u304c\u3001process\u3067\u306fXPath\u307e\u305f\u306fCSS\u30bb\u30ec\u30af\u30bf\u3067\u6307\u5b9a\u3057\u305f\u8981\u7d20\u306b\u3064\u3044\u3066\u3068\u3084\u304b\u304f\u3059\u308b\u3053\u3068\u304c\u304b\u3051\u308b\u3002<\/p>\n
\u4eca\u56de\u306f\u3042\u3048\u3066XPath\u5f0f\u3067\u66f8\u3044\u3066\u307f\u305f\u3002<\/p>\n
\/\/table[@class=’timetable’][1]\/colgroup\/tr[position()>1] \u3068\u3044\u3046XPath\u5f0f\u3067\u3001class\u304ctimetable\u306etable\u8981\u7d20\u306e\u6700\u521d\u306e\u3082\u306e\u306e\u76f4\u4e0b\u306ecolgroup\u76f4\u4e0b\u306etr\u8981\u7d20\u306e\u3046\u30612\u756a\u76ee\u304b\u3089\u3068\u3044\u3046\u6761\u4ef6\u3067\u629c\u304d\u51fa\u3057\u3066\u3044\u308b\u3002<\/p>\n<\/p>\n
\u304b\u306a\u308a\u8907\u96d1\u3060\u304c\u3001\u3053\u308c\u306762\u7cfb\u7d71\u306e\u6bce\u6642\u306e\u51fa\u767a\u3059\u308b\u6642\u523b\u306e\u66f8\u304b\u308c\u305f\u884c\u3060\u3051\u629c\u304d\u51fa\u305b\u305f\u3002<\/p>\n
103\u7cfb\u7d71\u306e\u3068\u304d\u306f2\u756a\u76ee\u306e\u8868\u306b\u3042\u308b\u304b\u3089\u3001\u6700\u521d\u306e[1]\u3092[2]\u306b\u66f8\u304d\u63db\u3048\u308c\u3070\u3044\u3044\u3002<\/p>\n
\u629c\u304d\u51fa\u3057\u305f\u30c7\u30fc\u30bf\u306f”lines[]”\u3068\u66f8\u3044\u305f\u304b\u3089\u3001$res->{“lines”}\u306b\u6761\u4ef6\u3092\u6e80\u305f\u3059\u8981\u7d20\u306b\u3064\u3044\u3066=>\u306e\u5f8c\u308d\u306b\u793a\u3057\u305f\u6761\u4ef6\u3067\u51e6\u7406\u3055\u308c\u305f\u3082\u306e\u304c\u51fa\u3066\u304f\u308b\u3002<\/p>\n
=>\u4ee5\u964d\u306b\u306fscraper{\u2026}\u3067\u4f5c\u3089\u308c\u305f\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u3001\u30b5\u30d6\u30eb\u30fc\u30c1\u30f3\u30ea\u30d5\u30a1\u30ec\u30f3\u30b9\u3001\u305d\u3057\u3066”TEXT”\u3067\u30c6\u30ad\u30b9\u30c8\u3001”@href”\u3067\u5c5e\u6027\u3060\u3068\u304b\u304c\u53d6\u308a\u51fa\u305b\u308b\u3002<\/p>\n
\u3044\u308d\u3044\u308d\u7d30\u304b\u3044\u7d30\u5de5\u3092XPath\u3067\u66f8\u3044\u3066\u3042\u308b\u304c\u3001\u304a\u304a\u3056\u3063\u3071\u306b\u629c\u304d\u51fa\u3057\u3066\u7d30\u304b\u304f\u9078\u3073\u51fa\u3059\u306e\u306fPerl\u3067\u3084\u308b\u3068\u3044\u3046\u306e\u3082\u3088\u3044\u304b\u3082\u3057\u308c\u306a\u3044\u3002<\/p>\n
XPath\u306f\u78ba\u304b\u306b\u3044\u308d\u3044\u308d\u8868\u73fe\u3067\u304d\u308b\u3051\u3069\u3001\u7d30\u304b\u3044\u4e8b\u3092\u3059\u308b\u306e\u306f\u3081\u3093\u3069\u304f\u3055\u3044\u3002\u304a\u304a\u3056\u3063\u3071\u306bCSS\u30bb\u30ec\u30af\u30bf\u3067\u629c\u304d\u51fa\u3057\u3066\u3057\u307e\u3048\u3070\u697d\u306a\u306e\u3082\u78ba\u304b\u306a\u8a71\u3060\u3002<\/p>\n
\n\u3053\u3093\u306a\u98a8\u306b\u3057\u3066HTML\u304b\u3089\u5fc5\u8981\u306a\u30c7\u30fc\u30bf\u3092\u629c\u304d\u51fa\u3057\u3066\u51e6\u7406\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u308f\u3051\u3060\u3002<\/p>\n
\u76ee\u3067\u898b\u3066\u5fc5\u8981\u306a\u30c7\u30fc\u30bf\u3092\u898b\u3064\u3051\u308b\u306e\u306b\u6bd4\u3079\u308b\u3068\u3001\u3069\u3053\u306b\u3042\u308b\u304b\u63a2\u3057\u3066\u6307\u5b9a\u3059\u308b\u306e\u306b\u306f\u624b\u9593\u304c\u304b\u304b\u308b\u3002<\/p>\n
\u3057\u304b\u3057\u4e00\u5ea6\u6307\u5b9a\u3059\u308c\u3070\u3042\u3068\u306f\u81ea\u52d5\u3067\u629c\u304d\u51fa\u3057\u3066\u304f\u308c\u308b\u306e\u306f\u4fbf\u5229\u3060\u3057\u9593\u9055\u3048\u304c\u306a\u3044\u3002<\/p>\n
\u5b9f\u306b\u30b9\u30af\u30e9\u30a4\u30d4\u30f3\u30b0\u306e\u610f\u7fa9\u306f\u305d\u3053\u306a\u3093\u3058\u3083\u306a\u3044\u304b\u306a\u3068\u601d\u3063\u3066\u3044\u308b\u3002<\/p>\n
\u672c\u5f53\u306f\u51e6\u7406\u306b\u4fbf\u5229\u306a\u3088\u3046\u306bXML\u3068\u304b\u3067\u914d\u5e03\u3057\u3066\u304f\u308c\u308c\u3070\u3046\u308c\u3057\u3044\u3051\u3069\u3001\u306a\u304b\u306a\u304b\u305d\u3093\u306a\u6c17\u306e\u5229\u3044\u305f\u30b5\u30fc\u30d3\u30b9\u306f\u306a\u3044\u3002<\/p>\n
\u3051\u3069\u3001\u4eba\u304c\u76ee\u3067\u898b\u308b\u305f\u3081\u306b\u306f\u4fbf\u5229\u306a\u3082\u306e\u304c\u305f\u304f\u3055\u3093\u3042\u308b\u3002\u305d\u308c\u3092\u30d7\u30ed\u30b0\u30e9\u30e0\u3067\u4e0a\u624b\u304f\u51e6\u7406\u3067\u304d\u308c\u3070\u5f97\u3089\u308c\u308b\u30c7\u30fc\u30bf\u306e\u5e45\u306f\u5e83\u304c\u308b\u3002<\/p>\n
\u305d\u3046\u3044\u3046\u3053\u3068\u3067\u3059\u3088\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
\u304a\u3068\u3068\u3044\u304b\u3089\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u3060\u3068\u304b\u8a00\u3063\u3066\u308b\u3051\u3069\u3001Web\u30b5\u30a4\u30c8\u306eHTML\u3092\u89e3\u6790\u3057\u3066\u5fc5\u8981\u306a\u30c7\u30fc\u30bf\u3092\u53d6\u3063\u3066\u304f\u308b\u3053\u3068\u306e\u3053\u3068\u3067\u3042\u308b\u3002 \u884c\u5100\u304c\u60aa\u3044\u65b9\u6cd5\u3060\u304c\u3001HTML\u3092\u89e3\u6790\u3059\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u5f97\u3089\u308c\u308b\u30c7\u30fc\u30bf\u306f\u591a\u3044\u3002 \u50d5\u304c\u5b9f\u969b\u306b\u8fd1\u9244\u306eNext […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-2384","post","type-post","status-publish","format-standard","hentry","category-computer"],"_links":{"self":[{"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=\/wp\/v2\/posts\/2384","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2384"}],"version-history":[{"count":0,"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=\/wp\/v2\/posts\/2384\/revisions"}],"wp:attachment":[{"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hdmr.org\/d\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}