RubyGems - xp - Versions diffs - 1.0.0 → 2.0.0 - Mend

xp 1.0.0 → 2.0.0

Files changed (24) hide show

checksums.yaml +4 -4
data/.gitignore +1 -0
data/Gemfile +8 -0
data/Gemfile.lock +16 -0
data/LICENSE.txt +22 -0
data/README.markdown +38 -0
data/Rakefile +1 -0
data/bin/xp +13 -12
data/lib/user_agents.rb +10 -0
data/lib/xp.rb +55 -0
data/pkg/xp-0.0.1.gem +0 -0
data/pkg/xp-0.0.2.gem +0 -0
data/pkg/xp-1.0.0.gem +0 -0
data/research/attribute_extractor.rb +7 -0
data/research/bb_parser.rb +8 -0
data/research/interface.rb +7 -0
data/research/load.rb +1 -0
data/research/selector.rb +10 -0
data/research/y.htm +4452 -0
data/test/test_content.html +122 -0
data/test/test_helper.rb +6 -0
data/test/xp_test.rb +55 -0
data/xp.gemspec +17 -0
metadata +33 -9

@@ -0,0 +1,122 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+<html class="evernote_clearly__before_visible evernote_clearly__is_visible"><head>
+<meta http-equiv="content-type" content="text/html; charset=windows-1252"><script src="test_content_files/fa27bb6ce937aea400cc8e5f11aa42d5.js" async="" type="text/javascript"></script><script type="text/javascript">
+ <!--
+ (new Image).src="http://store.yahoo.net/cgi-bin/refsd?e=http://paulgraham.com/know.html&h=paulgraham.com&v=1.0&dr=" + escape(document.referrer);
+ -->
+ </script>
+<title>How You Know</title><!-- <META NAME="ROBOTS" CONTENT="NOODP"> -->
+<link rel="shortcut icon" href="http://ycombinator.com/arc/arc.png">
+<style type="text/css"></style></head><body class="evernote_clearly__before_visible evernote_clearly__is_visible" bgcolor="ffffff" background="test_content_files/paulgraham_2271_0.gif" text="000000" vlink="464646" link="000099"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr valign="top"><td><map name="10fe3548f29bf95"><area shape="rect" coords="0,0,67,21" href="http://paulgraham.com/index.html"><area shape="rect" coords="0,21,67,42" href="http://paulgraham.com/articles.html"><area shape="rect" coords="0,42,67,63" href="http://www.amazon.com/gp/product/0596006624"><area shape="rect" coords="0,63,67,84" href="http://paulgraham.com/books.html"><area shape="rect" coords="0,84,67,105" href="http://ycombinator.com/"><area shape="rect" coords="0,105,67,126" href="http://startupschool.org/"><area shape="rect" coords="0,126,67,147" href="http://paulgraham.com/arc.html"><area shape="rect" coords="0,147,67,168" href="http://paulgraham.com/lisp.html"><area shape="rect" coords="0,168,67,189" href="http://paulgraham.com/antispam.html"><area shape="rect" coords="0,189,67,210" href="http://paulgraham.com/kedrosky.html"><area shape="rect" coords="0,210,67,231" href="http://paulgraham.com/faq.html"><area shape="rect" coords="0,231,67,252" href="http://paulgraham.com/raq.html"><area shape="rect" coords="0,252,67,273" href="http://paulgraham.com/quo.html"><area shape="rect" coords="0,273,67,294" href="http://paulgraham.com/rss.html"><area shape="rect" coords="0,294,67,315" href="http://paulgraham.com/bio.html"><area shape="rect" coords="0,315,67,336" href="https://twitter.com/paulg"><area shape="rect" coords="0,336,67,357" href="http://paulgraham.com/nsearch.html"><area shape="rect" coords="0,357,67,378" href="http://paulgraham.com/ind.html"></map><img src="test_content_files/essays-1.gif" usemap="#10fe3548f29bf95" ismap="ismap" border="0" height="378" hspace="0" vspace="0" width="69"></td><td><img src="test_content_files/trans_1x1.gif" border="0" height="1" width="26"></td><td><a href="http://paulgraham.com/index.html"><img src="test_content_files/paulgraham_2271_3232.gif" border="0" height="45" hspace="0" vspace="0" width="410"></a><br><br><table border="0" cellpadding="0" cellspacing="0" width="435"><tbody><tr valign="top"><td width="435"><img src="test_content_files/how-you-know-1.gif" alt="How You Know" border="0" height="18" hspace="0" vspace="0" width="120"><br><br><font face="verdana" size="2">December 2014<br><br>I've read Villehardouin's chronicle of the Fourth Crusade at least
+two times, maybe three.  And yet if I had to write down everything
+I remember from it, I doubt it would amount to much more than a
+page.  Multiply this times several hundred, and I get an uneasy
+feeling when I look at my bookshelves. What use is it to read all
+these books if I remember so little from them?<br><br>A few months ago, as I was reading Constance Reid's excellent
+biography of Hilbert, I figured out if not the answer to this
+question, at least something that made me feel better about it.
+She writes:
+<blockquote>
+  Hilbert had no patience with mathematical lectures which filled
+  the students with facts but did not teach them how to frame a
+  problem and solve it. He often used to tell them that "a perfect
+  formulation of a problem is already half its solution."
+</blockquote>
+That has always seemed to me an important point, and I was even
+more convinced of it after hearing it confirmed by Hilbert.<br><br>But how had I come to believe in this idea in the first place?  A
+combination of my own experience and other things I'd read.  None
+of which I could at that moment remember!  And eventually I'd forget
+that Hilbert had confirmed it too.  But my increased belief in the
+importance of this idea would remain something I'd learned from
+this book, even after I'd forgotten I'd learned it.<br><br>Reading and experience train your model of the world.  And even if
+you forget the experience or what you read, its effect on your model
+of the world persists.  Your mind is like a compiled program you've
+lost the source of.  It works, but you don't know why.<br><br>The place to look for what I learned from Villehardouin's chronicle
+is not what I remember from it, but my mental models of the crusades,
+Venice, medieval culture, siege warfare, and so on.  Which doesn't
+mean I couldn't have read more attentively, but at least the harvest
+of reading is not so miserably small as it might seem.<br><br>This is one of those things that seem obvious in retrospect.  But
+it was a surprise to me and presumably would be to anyone else who
+felt uneasy about (apparently) forgetting so much they'd read.<br><br>Realizing it does more than make you feel a little better about
+forgetting, though.  There are specific implications.<br><br>For example, reading and experience are usually "compiled" at the
+time they happen, using the state of your brain at that time.  The
+same book would get compiled differently at different points in
+your life.  Which means it is very much worth reading important
+books multiple times.  I always used to feel some misgivings about
+rereading books.  I unconsciously lumped reading together with work
+like carpentry, where having to do something again is a sign you
+did it wrong the first time.  Whereas now the phrase "already read"
+seems almost ill-formed.<br><br>Intriguingly, this implication isn't limited to books.  Technology
+will increasingly make it possible to relive our experiences.  When
+people do that today it's usually to enjoy them again (e.g. when
+looking at pictures of a trip) or to find the origin of some bug in
+their compiled code (e.g. when Stephen Fry succeeded in remembering
+the childhood trauma that prevented him from singing).  But as
+technologies for recording and playing back your life improve, it
+may become common for people to relive experiences without any goal
+in mind, simply to learn from them again as one might when rereading
+a book.<br><br>Eventually we may be able not just to play back experiences but
+also to index and even edit them. So although not knowing how you
+know things may seem part of being human, it may not be.<br><br><br><br><br><br><br><br>
+<b>Thanks</b> to Sam Altman, Jessica Livingston, and Robert Morris for reading
+drafts of this.<br><br></font></td></tr></tbody></table><table border="0" cellpadding="0" cellspacing="0" width="435"><tbody><tr><td><font face="verdana" size="2"><br><br><hr></font></td></tr></tbody></table></td></tr></tbody></table>
+<script type="text/javascript">
+csell_env = 'bf1';
+</script>
+<script type="text/javascript">
+// Begin Yahoo Store Generated Code
+ </script> <script type="text/javascript" src="test_content_files/ylc_1.js"></script> <script type="text/javascript" src="test_content_files/beacon-1.js">
+</script>
+<script type="text/javascript">
+// Begin Yahoo Store Generated Code
+ csell_page_data = {}; csell_page_rec_data = []; ts='TOK_STORE_ID';
+</script>
+<script type="text/javascript">
+// Begin Yahoo Store Generated Code
+function csell_GLOBAL_INIT_TAG() { var csell_token_map = {}; csell_token_map['TOK_ITEM_ID_LIST'] = 'know'; csell_token_map['TOK_BEACON_TYPE'] = 'prod'; csell_token_map['TOK_RAND_KEY'] = 't'; csell_token_map['TOK_SPACEID'] = '2022276099'; csell_token_map['TOK_IS_ORDERABLE'] = '2'; csell_token_map['TOK_STORE_ID'] = 'paulgraham'; csell_token_map['TOK_URL'] = 'http://geo.yahoo.com'; csell_token_map['TOK_ORDER_HOST'] = 'order.store.yahoo.net';  c = csell_page_data; var t = csell_token_map; c['s'] = t['TOK_SPACEID']; c['url'] = t['TOK_URL']; c['si'] = t[ts]; c['ii'] = t['TOK_ITEM_ID_LIST']; c['bt'] = t['TOK_BEACON_TYPE']; c['rnd'] = t['TOK_RAND_KEY']; c['io'] = t['TOK_IS_ORDERABLE']; YStore.addItemUrl = 'http%s://'+t['TOK_ORDER_HOST']+'/'+t[ts]+'/ymix/MetaController.html?eventName.addEvent&cartDS.shoppingcart_ROW0_m_orderItemVector_ROW0_m_itemId=%s&cartDS.shoppingcart_ROW0_m_orderItemVector_ROW0_m_quantity=1&ysco_key_cs_item=1&sectionId=ysco.cart&ysco_key_store_id='+t[ts]; }
+</script>
+<script type="text/javascript">
+// Begin Yahoo Store Generated Code
+function csell_REC_VIEW_TAG() {  var env = (typeof csell_env == 'string')?csell_env:'prod'; var p = csell_page_data; var a = '/sid='+p['si']+'/io='+p['io']+'/ii='+p['ii']+'/bt='+p['bt']+'-view'+'/en='+env; var r=Math.random(); YStore.CrossSellBeacon.renderBeaconWithRecData(p['url']+'/p/s='+p['s']+'/'+p['rnd']+'='+r+a); }
+</script>
+<script type="text/javascript">
+// Begin Yahoo Store Generated Code
+var csell_token_map = {}; csell_token_map['TOK_PAGE'] = 'p'; csell_token_map['TOK_WS_URL'] = 'http://paulgraham.csell.store.yahoo.net/cs/recommend?itemids=know&location=p'; csell_token_map['TOK_SHOW_CS_RECS'] = 'false'; csell_token_map['TOK_CURR_SYM'] = '$';  var t = csell_token_map; csell_GLOBAL_INIT_TAG(); YStore.page = t['TOK_PAGE']; YStore.currencySymbol = t['TOK_CURR_SYM']; YStore.crossSellUrl = t['TOK_WS_URL']; YStore.showCSRecs = t['TOK_SHOW_CS_RECS']; </script> <script type="text/javascript" src="test_content_files/recs-1.js"></script> <script type="text/javascript">
+</script>
+<script type="text/javascript">
+ <!--
+ if (document.referrer && (document.referrer!='') && window.Image)
+ {
+ (new Image).src="http://redirect1.vip.store.yahoo.com/cgi-bin/referadd?spcl=1&et=54903f22&catalog=paulgraham&r=" + escape(document.referrer) + "&v=1"; }
+ // -->
+ </script><script type="text/javascript">
+ <!--
+ if (document.referrer && (document.referrer!='') && window.Image)
+ {
+ (new Image).src="http://redirect1.vip.store.yahoo.net/cgi-bin/referadd?spcl=1&et=54903f22&catalog=paulgraham&r=" + escape(document.referrer) + "&v=3"; }
+ // -->
+ </script><script type="text/javascript">(function (d, w) { var f = function () { var x = d.getElementsByTagName('SCRIPT')[0]; var s = d.createElement('SCRIPT'); s.type = 'text/javascript'; s.async = true; s.src = '//np.lexity.com/embed/YA/fa27bb6ce937aea400cc8e5f11aa42d5?id=06de067e4a3b'; x.parentNode.insertBefore(s, x); }; w.attachEvent ? w.attachEvent('onload',f) : w.addEventListener('load',f,false); }(document, window)); </script><div id="evernote_clearly__container"><style type="text/css" id="evernote_clearly__css_for_container">#evernote_clearly__container { position: absolute !important; width: 5px !important; height: 5px !important; top: -1000px !important; left: -1000px !important; margin: 0 !important; padding: 0 !important; border: none !important; }
+#evernote_clearly__definitions { display: none !important; }
+</style><div id="evernote_clearly__definitions"><div id="evernote_clearly__serialized__option__text_font">"PT Serif"</div><div id="evernote_clearly__serialized__option__text_font_header">"PT Serif"</div><div id="evernote_clearly__serialized__option__text_font_monospace">Inconsolata</div><div id="evernote_clearly__serialized__option__text_size">20px</div><div id="evernote_clearly__serialized__option__text_line_height">1.5em</div><div id="evernote_clearly__serialized__option__box_width">36em</div><div id="evernote_clearly__serialized__option__color_background">#f3f2ee</div><div id="evernote_clearly__serialized__option__color_text">#1f0909</div><div id="evernote_clearly__serialized__option__color_links">#065588</div><div id="evernote_clearly__serialized__option__text_align">normal</div><div id="evernote_clearly__serialized__option__base">theme-1</div><div id="evernote_clearly__serialized__option__footnote_links">on_print</div><div id="evernote_clearly__serialized__option__large_graphics">do_nothing</div><div id="evernote_clearly__serialized__option__custom_css">none</div><div id="evernote_clearly__serialized__var__theme">theme-1</div><div id="evernote_clearly__serialized__var__keys_activation">Control + Command + Right Arrow</div><div id="evernote_clearly__serialized__var__keys_clip">Control + Command + Up Arrow</div><div id="evernote_clearly__serialized__var__keys_highlight">Control + Command + H</div><div id="evernote_clearly__serialized__var__keys_speech">Control + Command + S</div><div id="evernote_clearly__serialized__var__clip_tag">none</div><div id="evernote_clearly__serialized__var__clip_notebook">none</div><div id="evernote_clearly__serialized__var__clip_notebook_guid">none</div><div id="evernote_clearly__serialized__var__related_notes">enabled</div><div id="evernote_clearly__serialized__var__smart_filing">enabled</div><div id="evernote_clearly__serialized__var__smart_filing_for_business">disabled</div><div id="evernote_clearly__serialized__var__speech_speed">normal</div><div id="evernote_clearly__serialized__var__speech_gender">default</div><div id="evernote_clearly__serialized__var__open_notes_in">web</div><div id="evernote_clearly__serialized__var__custom_theme_options">none</div><div id="evernote_clearly__serialized__translation__menu__close__tooltip">Hide the overlay.</div><div id="evernote_clearly__serialized__translation__menu__clip_to_evernote__tooltip">Clip to Evernote.</div><div id="evernote_clearly__serialized__translation__menu__highlight_to_evernote__tooltip">Highlight.</div><div id="evernote_clearly__serialized__translation__menu__print__tooltip">Print.</div><div id="evernote_clearly__serialized__translation__menu__settings__tooltip">Show Themes.</div><div id="evernote_clearly__serialized__translation__menu__fitts__tooltip">Hide the overlay.</div><div id="evernote_clearly__serialized__translation__menu__speak__tooltip">Text To Speech</div><div id="evernote_clearly__serialized__translation__menu__speak__play__tooltip">Play</div><div id="evernote_clearly__serialized__translation__menu__speak__pause__tooltip">Pause</div><div id="evernote_clearly__serialized__translation__menu__speak__forward__tooltip">Go Forwards</div><div id="evernote_clearly__serialized__translation__menu__speak__rewind__tooltip">Go Backwards</div><div id="evernote_clearly__serialized__translation__rtl__main__label">Text direction?</div><div id="evernote_clearly__serialized__translation__rtl__ltr__label">Left-to-right</div><div id="evernote_clearly__serialized__translation__rtl__rtl__label">Right-to-left</div><div id="evernote_clearly__serialized__translation__blank_error__heading">Tips for using Evernote Clearly</div><div id="evernote_clearly__serialized__translation__blank_error__body">Clearly
+ is currently designed to work on article pages. An article page is any
+page that contains one large block of text -- like, for example, a
+newspaper article or blog post.</div><div id="evernote_clearly__serialized__translation__related_notes__title">Related Notes</div><div id="evernote_clearly__serialized__translation__related_notes__disable_short">Disable?</div><div id="evernote_clearly__serialized__translation__related_notes__disable_long">Do you want to disable Related Notes?</div><div id="evernote_clearly__serialized__translation__filing_info__title_normal">Filed in:</div><div id="evernote_clearly__serialized__translation__filing_info__title_smart">Smart Filed in:</div><div id="evernote_clearly__serialized__translation__filing_info__default_notebook">Your default Notebook</div><div id="evernote_clearly__serialized__translation__filing_info__view">View</div><div id="evernote_clearly__serialized__translation__filing_info__edit">Edit</div><div id="evernote_clearly__serialized__translation__filing_info__sentence">Clipped into the [=notebook] notebook, and tagged with [=tags].</div><div id="evernote_clearly__serialized__translation__filing_info__sentence_no_tags">Clipped into the [=notebook] notebook.</div><div id="evernote_clearly__serialized__translation__filing_info__sentence_and">and</div><div id="evernote_clearly__serialized__translation__filing_info__sentence_other_tags">other tags</div><div id="evernote_clearly__serialized__translation__evernote_clipping">Clipping...</div><div id="evernote_clearly__serialized__translation__evernote_clipping_failed">Clipping failed.</div><div id="evernote_clearly__serialized__translation__evernote_login__request">To sign in to Evernote, please click the Clearly icon in Chrome's toolbar.</div><div id="evernote_clearly__serialized__translation__evernote_login__heading">Sign in to Evernote</div><div id="evernote_clearly__serialized__translation__evernote_login__spinner">Signing in to Evernote</div><div id="evernote_clearly__serialized__translation__evernote_login__create_account">Create an account</div><div id="evernote_clearly__serialized__translation__evernote_login__button_do__label">Sign in</div><div id="evernote_clearly__serialized__translation__evernote_login__button_cancel__label">Cancel</div><div id="evernote_clearly__serialized__translation__evernote_login__username__label">Evernote Username or Email Address</div><div id="evernote_clearly__serialized__translation__evernote_login__password__label">Password</div><div id="evernote_clearly__serialized__translation__evernote_login__rememberMe__label">Remember me</div><div id="evernote_clearly__serialized__translation__evernote_login__username__error__required">Username is required.</div><div id="evernote_clearly__serialized__translation__evernote_login__username__error__length">Username must be between 1 and 64 characters long.</div><div id="evernote_clearly__serialized__translation__evernote_login__username__error__format">Username contains bad characters.</div><div id="evernote_clearly__serialized__translation__evernote_login__username__error__invalid">Not a valid, active user.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__required">Password is required.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__length">Password must be between 6 and 64 characters long.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__format">Password contains bad characters.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__invalid">Username and password do not match existing user.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__timeout">Login session timed-out. Please try again.</div><div id="evernote_clearly__serialized__translation__evernote_login__password__error__reset">Your password has expired. Please reset it now.</div><div id="evernote_clearly__serialized__translation__evernote_login__general__error">Authentication failed.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__message__sms">We sent a text message with a verification code to</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__message__google">Enter the verification code displayed in your Google Authenticator app.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__code__label">Six-digit code</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__code__error__required">Verification code is required.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__code__error__length">Verification code should be at least 6 characters long.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__code__error__format">Verification code should be only numbers.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__code__error__invalid">Verification code is incorrect.</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__button_do__label">Continue</div><div id="evernote_clearly__serialized__translation__evernote_two_factor__button_help__label">I need help getting a verification code</div><div id="evernote_clearly__serialized__translation__settings__theme__1__not_translated">Newsprint</div><div id="evernote_clearly__serialized__translation__settings__theme__2__not_translated">Notable</div><div id="evernote_clearly__serialized__translation__settings__theme__3__not_translated">Night Owl</div><div id="evernote_clearly__serialized__translation__settings__theme__1">Newsprint</div><div id="evernote_clearly__serialized__translation__settings__theme__2">Notable</div><div id="evernote_clearly__serialized__translation__settings__theme__3">Night Owl</div><div id="evernote_clearly__serialized__translation__settings__theme__custom">Custom</div><div id="evernote_clearly__serialized__translation__settings__fontSize__small">small</div><div id="evernote_clearly__serialized__translation__settings__fontSize__medium">medium</div><div id="evernote_clearly__serialized__translation__settings__fontSize__large">large</div><div id="evernote_clearly__serialized__translation__features__title__new">You have a new version of Evernote Clearly</div><div id="evernote_clearly__serialized__translation__features__title__all">Welcome to the new Evernote Clearly</div><div id="evernote_clearly__serialized__translation__features__speech__title">Text To Speech</div><div id="evernote_clearly__serialized__translation__features__speech__text">Sit
+ back and let Clearly read blog posts, articles, and web pages to you
+thanks to the new Text To Speech feature, available exclusively for
+Evernote Premium subscribers.</div><div id="evernote_clearly__serialized__translation__features__speech__text__powered">Evernote Clearly is powered by [=service].</div><div id="evernote_clearly__serialized__translation__features__speech__text__requires">Requires [=product].</div><div id="evernote_clearly__serialized__translation__features__speech__text__available">Text To Speech in 21 languages:</div><div id="evernote_clearly__serialized__translation__features__speech__text__available_languages">English,
+ Japanese, Spanish, French, German, Chinese, Korean, Arabic, Czech,
+Danish, Dutch, Finnish, Greek, Hungarian, Italian, Norwegian, Polish,
+Portuguese, Russian, Swedish and Turkish.</div><div id="evernote_clearly__serialized__translation__features__speech__text__try">Try Text To Speech</div><div id="evernote_clearly__serialized__translation__features__speech__text__upgrade">Upgrade to Evernote Premium</div><div id="evernote_clearly__serialized__translation__features__speech__text__language">Language not supported</div><div id="evernote_clearly__serialized__translation__features__speech__text__play">Play using this language</div><div id="evernote_clearly__serialized__translation__features__speech__text__cancel">Cancel</div><div id="evernote_clearly__serialized__translation__features__speech__no_language_title">Language not supported</div><div id="evernote_clearly__serialized__translation__features__speech__no_language_explanation">Evernote
+ Clearly was not able to determine the language of this article. If you
+recognize the language, select it below and we'll play it.</div><div id="evernote_clearly__serialized__translation__features__clipping__title">Clip to Evernote</div><div id="evernote_clearly__serialized__translation__features__clipping__text">Save what you're reading to your Evernote account with one click. Access clips from any device, anytime in Evernote.</div><div id="evernote_clearly__serialized__translation__features__highlighting__title">Highlighting</div><div id="evernote_clearly__serialized__translation__features__highlighting__text">Highlight
+ text you want to remember &amp; quickly find it in your Evernote
+account. Highlighting changes you make in Clearly will be updated in
+your Evernote account automatically.</div><div id="evernote_clearly__serialized__translation__features__related_notes__title">Related Notes</div><div id="evernote_clearly__serialized__translation__features__related_notes__text">Magically
+ rediscover notes from your Evernote account that are related to the
+page you are viewing. Related Notes are displayed at the bottom of the
+article or on the right side if space permits.</div><div id="evernote_clearly__serialized__translation__features__smart_filing__title">Smart Filing</div><div id="evernote_clearly__serialized__translation__features__smart_filing__text">Automatically assign tags to your Web clips and saves them to the appropriate notebook, so you don't have to.</div><div id="evernote_clearly__serialized__translation__features__eula_notice">By using Clearly, you agree to our [=eula].</div><div id="evernote_clearly__serialized__translation__features__close2">Close</div><div id="evernote_clearly__serialized__translation__misc__page">page</div></div><script class="evernote_clearly__launcher" src="test_content_files/launch.js"></script><script id="evernote_clearly__init" src="test_content_files/init.js"></script><iframe scrolling="auto" allowtransparency="true" id="evernote_clearly__controller" frameborder="0"></iframe><style type="text/css" id="evernote_clearly__css_for_reformat">html.evernote_clearly__before_visible, html > body.evernote_clearly__before_visible, body.evernote_clearly__before_visible { position: static !important; margin: 0 !important; padding: 0 !important; border: 0 !important; }
+html.evernote_clearly__is_visible, html > body.evernote_clearly__is_visible, body.evernote_clearly__is_visible { overflow: hidden !important; overflow-x: hidden !important; overflow-y: hidden !important; }
+html.evernote_clearly__before_visible object, html.evernote_clearly__before_visible embed, html.evernote_clearly__before_visible iframe, html > body.evernote_clearly__before_visible object, html > body.evernote_clearly__before_visible embed, html > body.evernote_clearly__before_visible iframe, body.evernote_clearly__before_visible object, body.evernote_clearly__before_visible embed, body.evernote_clearly__before_visible iframe { visibility: hidden !important; }
+#evernote_clearly__reformat { margin: 0 !important; padding: 0 !important; border: none !important; position: absolute !important; width: 100% !important; height: 100% !important; min-height: 100% !important; top: -100%; left: -100%; z-index: 2147483647 !important; }
+html.evernote_clearly__before_visible #evernote_clearly__reformat, html > body.evernote_clearly__before_visible #evernote_clearly__reformat, body.evernote_clearly__before_visible #evernote_clearly__reformat, #evernote_clearly__reformat { display: block !important; overflow: auto !important; visibility: visible !important; }
+</style></div><iframe style="top: 0px; left: 0px;" scrolling="auto" allowtransparency="true" id="evernote_clearly__reformat" frameborder="0"></iframe><style type="text/css" id="clearly_next_pages_container__css">#clearly_next_pages_container { margin: 0; padding: 0; border: none; position: absolute; width: 10px; height: 10px; top: -100px; left: -100px; } #clearly_next_pages_container iframe { margin: 0; padding: 0; border: none; position: absolute; width: 10px; height: 10px; top: -100px; left: -100px; } </style><div id="clearly_next_pages_container"></div></body></html>

data/test/test_helper.rb ADDED

@@ -0,0 +1,6 @@
+require 'minitest/autorun'
+require 'minitest/reporters'
+require_relative './xp_test.rb'
+reporter_options = { color: true, slow_count: 5 }
+Minitest::Reporters.use! [Minitest::Reporters::DefaultReporter.new(reporter_options)]

data/test/xp_test.rb ADDED

@@ -0,0 +1,55 @@
+require './lib/xp'
+HTML = File.open('./test/test_content.html').read
+XPATH_QUERY = '//title'
+XPATH_RESULT = "<title>How You Know</title>\n"
+CSS_QUERY = 'title'
+CSS_RESULT = "<title>How You Know</title>\n"
+LYNX = 'http://www.delorie.com/web/lynxview.html'
+LYNX_TAGLINE = 'Lynx Viewer'
+SIMPLE_PAGE_URL = "http://w3m.sourceforge.net/"
+TEST_URL = 'http://qucentis.com/unavailable_404_link'
+TEST_FILE_URL = 'http://abc.com/file/hello.mov?key=123&id=569'
+TEST_FILE_BASENAME = 'hello'
+TEST_FILE_EXTENSION = '.mov'
+class TestXP < Minitest::Test
+  String.send(:include, XP)
+  def setup
+    @html = File.open('./test/test_content.html').read
+  end
+  def test_all_methods_introduced
+    %w|to_nokogiri page_source download|.each do |method|
+      assert_respond_to "http://google.com", method
+    end
+  end
+  def test_to_nokogiri
+    assert_instance_of Nokogiri::HTML::Document, HTML.to_nokogiri
+    assert_equal LYNX_TAGLINE, LYNX.to_nokogiri.xpath('//title/text()').to_s
+  end
+  def test_conversion_to_nodeset
+    assert_equal HTML.to_nokogiri.css(CSS_QUERY).to_html, CSS_RESULT
+    assert_equal HTML.to_nokogiri.css(XPATH_QUERY).to_html, XPATH_RESULT
+    assert_equal HTML.to_nokogiri.css(XPATH_QUERY).xpath("//title/text()").to_html, "How You Know"
+  end
+  def test_page_source
+    assert_equal SIMPLE_PAGE_URL.page_source.to_nokogiri.xpath("//address/a/text()").to_html, "aito@fw.ipsj.or.jp"
+  end
+  def test_css
+    assert_respond_to "", :css
+    assert_equal HTML.to_nokogiri.css(CSS_QUERY).to_html, HTML.css(CSS_QUERY).to_html
+  end
+  def test_xpath
+    assert_respond_to "", :xpath
+    assert_equal HTML.to_nokogiri.xpath(XPATH_QUERY).to_html, HTML.xpath(XPATH_QUERY).to_html
+  end
+end

data/xp.gemspec ADDED

@@ -0,0 +1,17 @@
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+Gem::Specification.new do |s|
+  s.name = "xp"
+  s.version = "2.0.0"
+  s.authors = ["Jikku Jose"]
+  s.email = ['jikkujose@gmail.com']
+  s.summary = "Gem that enables String class to help quick & dirty scraping tasks."
+  s.description = "Provides a monkey patched String class that can download & filter web pages using CSS/XPATH selectors; also has a very intuitive method to download files directly from their urls."
+  s.homepage = "http://github.com/JikkuJose/xp"
+  s.license = "MIT"
+  s.files = `git ls-files -z`.split("\x0")
+  s.executables = ["xp"]
+  s.add_dependency "nokogiri", '~> 1.6'
+end

metadata CHANGED

@@ -1,37 +1,61 @@
 --- !ruby/object:Gem::Specification
 name: xp
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 2.0.0
 platform: ruby
 authors:
 - Jikku Jose
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-09-06 00:00:00.000000000 Z
+date: 2014-12-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '1.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ~>
       - !ruby/object:Gem::Version
-        version: '0'
-description: A 10 line xpath parser using Nokogiri to be used in commandline.
-email:
+        version: '1.6'
+description: Provides a monkey patched String class that can download & filter web
+  pages using CSS/XPATH selectors; also has a very intuitive method to download files
+  directly from their urls.
+email:
+- jikkujose@gmail.com
 executables:
 - xp
 extensions: []
 extra_rdoc_files: []
 files:
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.markdown
+- Rakefile
 - bin/xp
+- lib/user_agents.rb
+- lib/xp.rb
+- pkg/xp-0.0.1.gem
+- pkg/xp-0.0.2.gem
+- pkg/xp-1.0.0.gem
+- research/attribute_extractor.rb
+- research/bb_parser.rb
+- research/interface.rb
+- research/load.rb
+- research/selector.rb
+- research/y.htm
+- test/test_content.html
+- test/test_helper.rb
+- test/xp_test.rb
+- xp.gemspec
 homepage: http://github.com/JikkuJose/xp
 licenses:
 - MIT
@@ -55,5 +79,5 @@ rubyforge_project:
 rubygems_version: 2.2.2
 signing_key:
 specification_version: 4
-summary: A very simple commandline xpath parser.
+summary: Gem that enables String class to help quick & dirty scraping tasks.
 test_files: []