0
本示例抓取數據使用nutch 2.3.1，其中我需要獲取標題和網址內部鏈接和網站附加的外部鏈接任何建議最受歡迎。如何使用豬腳本從網絡抓取的數據中提取特定數據（nutch）
我用這個命令從HBase的數據導入到豬
`data9 = load 'hbase://htest15_webpage' using org.apache.pig.backend.hadoop.hbase.HBaseStorage('f:cnt', '-loadKey true');
`
column=f:cnt, timestamp=1487743991250, value=<!DOCTYPE htm
l>\x0D\x0A<!--[if IE 7]>\x0D\x0A<html class="ie ie7" lang=
"en-US" prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns
/fb#">\x0D\x0A<![endif]-->\x0D\x0A<!--[if IE 8]>\x0D\x0A<h
tml class="ie ie8" lang="en-US" prefix="og: http://ogp.me/
ns# fb: http://ogp.me/ns/fb#">\x0D\x0A<![endif]-->\x0D\x0A
<!--[if !(IE 7) | !(IE 8) ]><!-->\x0D\x0A<html lang="en-U
S" prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns/fb#"
>\x0D\x0A<!--<![endif]-->\x0D\x0A<head>\x0D\x0A <meta cha
rset="UTF-8" /> \x0D\x0A <meta name="viewport" content="w
idth=device-width" /> \x0D\x0A \x0D\x0A<title>www.hardhe
ro.com</title>\x0A\x0A<!-- SEO Ultimate (http://www.seodes
ignsolutions.com/wordpress-seo/) -->\x0A\x09<meta name="de
scription" content="hardhero.com blog that provides intere
sting articles on general topics and ideas." />\x0A\x09<me
ta name="keywords" content="Internet Blog,SEO Blog,Interne
t Marketing Guide" />\x0A\x09<meta property="og:type" cont
ent="blog" />\x0A\x09<meta property="og:title" content="ww
w.hardhero.com" />\x0A\x09<meta property="og:url" content=
"http://hardhero.com/" />\x0A\x09<meta property="og:site_n
ame" content="www.hardhero.com" />\x0A\x09<meta name="twit
ter:card" content="summary" />\x0A<!-- /SEO Ultimate -->\x
0A\x0A<link rel="alternate" type="application/rss+xml" tit
le="www.hardhero.com » Feed" href="http://hardhero.c
om/feed/" />\x0A<link rel="alternate" type="application/rs
s+xml" title="www.hardhero.com » Comments Feed" href
="http://hardhero.com/comments/feed/" />\x0A\x09\x09<scrip
t type="text/javascript">\x0A\x09\x09\x09window._wpemojiSe
ttings = {"baseUrl":"http:\x5C/\x5C/s.w.org\x5C/images\x5C
/core\x5C/emoji\x5C/72x72\x5C/","ext":".png","source":{"co
ncatemoji":"http:\x5C/\x5C/hardhero.com\x5C/wp-includes\x5
C/js\x5C/wp-emoji-release.min.js?ver=4.2.11"}};\x0A\x09\x0
9\x09!function(a,b,c){function d(a){var c=b.createElement(
"canvas"),d=c.getContext&&c.getContext("2d");return d&&d.f
illText?(d.textBaseline="top",d.font="600 32px Arial","fla
g"===a?(d.fillText(String.fromCharCode(55356,56812,55356,5
6807),0,0),c.toDataURL().length>3e3):(d.fillText(String.fr
omCharCode(55357,56835),0,0),0!==d.getImageData(16,16,1,1)
.data[0])):!1}function e(a){var c=b.createElement("script"
);c.src=a,c.type="text/javascript",b.getElementsByTagName(
"head")[0].appendChild(c)}var f,g;c.supports={simple:d("si
mple"),flag:d("flag")},c.DOMReady=!1,c.readyCallback=funct
ion(){c.DOMReady=!0},c.supports.simple&&c.supports.flag||(
g=function(){c.readyCallback()},b.addEventListener?(b.addE
ventListener("DOMContentLoaded",g,!1),a.addEventListener("
load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onr
eadystatechange",function(){"complete"===b.readyState&&c.r
eadyCallback()})),f=c.source||{},f.concatemoji?e(f.concate
moji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(
window,document,window._wpemojiSettings);\x0A\x09\x09</scr
ipt>\x0A\x09\x09<style type="text/css">\x0Aimg.wp-smiley,\
x0Aimg.emoji {\x0A\x09display: inline !important;\x0A\x09b
order: none !important;\x0A\x09box-shadow: none !important
;\x0A\x09height: 1em !important;\x0A\x09width: 1em !import
ant;\x0A\x09margin: 0 .07em !important;\x0A\x09vertical-al
ign: -0.1em !important;\x0A\x09background: none !important
;\x0A\x09padding: 0 !important;\x0A}\x0A</style>\x0A<link
rel='stylesheet' id='es-widget-css-css' href='http://hard
hero.com/wp-content/plugins/email-subscribers/widget/es-wi
dget.css?ver=4.2.11' type='text/css' media='all' />\x0A<li
nk rel='stylesheet' id='shootingstar-style-css' href='htt
p://hardhero.com/wp-content/themes/shootingstar/style.css?
ver=4.2.11' type='text/css' media='all' />\x0A<link rel='s
tylesheet' id='shootingstar-elegantfont-css' href='http:/
/hardhero.com/wp-content/themes/shootingstar/css/elegantfo
>
三江源@alex讓我來試試它的工作，我會帶你回去。 –