upton 0.2.7 → 0.2.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (12) hide show
  1. checksums.yaml +4 -4
  2. data/lib/upton.rb +86 -116
  3. data/lib/upton/downloader.rb +126 -0
  4. data/lib/upton/utils.rb +43 -0
  5. data/spec/data/propublica.html +269 -269
  6. data/spec/data/propublica_search.html +388 -0
  7. data/spec/data/propublica_search_page_2.html +375 -0
  8. data/spec/spec_helper.rb +20 -0
  9. data/spec/upton_downloader_spec.rb +75 -0
  10. data/spec/upton_spec.rb +110 -47
  11. metadata +26 -3
  12. data/lib/utils.rb +0 -74
data/spec/data/propublica_search.html ADDED
@@ -0,0 +1,388 @@
1
+
2
+
3
+
4
+ <!DOCTYPE html>
5
+
6
+ <html lang="en" xmlns:fb="http://www.facebook.com/2008/fbml">
7
+ <head prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns/fb# article: http://ogp.me/ns/article#">
8
+ <meta http-equiv="X-UA-Compatible" content="IE=Edge;chrome=1">
9
+
10
+
11
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12
+
13
+ <!-- ProPublica Typekit account -->
14
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/typekit.js?1349797800"></script>
15
+
16
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/all.js"></script>
17
+
18
+
19
+ <script type="text/javascript">var _sf_startpt=(new Date()).getTime()</script>
20
+ <meta name="google-site-verification" content="xPf4zxBdgQHZIRLVMiZyNYR1igMQUhsHogunEnOtD1k" />
21
+
22
+ <link rel="stylesheet" href="//www.propublica.org/css/960/reset.css?2012101501" type="text/css" media="all" charset="utf-8" />
23
+ <link rel="stylesheet" href="//www.propublica.org/css/960/propublica-text.css?2012101501" type="text/css" media="all" charset="utf-8" />
24
+ <link rel="stylesheet" href="//www.propublica.org/css/master.css?2012101501" type="text/css" media="screen" charset="utf-8" />
25
+
26
+ <link rel="stylesheet" href="//www.propublica.org/css/print.css?2012101501" type="text/css" media="print" charset="utf-8" />
27
+
28
+ <link rel="stylesheet" href="//www.propublica.org/css/headfoot2011.css?2012101501" type="text/css" media="all" charset="utf-8">
29
+
30
+ <!-- adaptive -->
31
+ <meta name="viewport" content="width=device-width">
32
+ <link rel="stylesheet" type="text/css" media="screen and (max-width: 480px)" href="//www.propublica.org/css/woland.css?2012101501" charset="utf-8">
33
+ <link rel="stylesheet" type="text/css" href="//www.propublica.org/css/zoom-fix.css" charset="UTF-8">
34
+ <!-- <link rel="stylesheet" type="text/css" media="screen and (max-width: 800px) and (min-width: 481px)" href="//www.propublica.org/css/behemoth.css?2012101501" charset="utf-8" /> -->
35
+ <!-- /adaptive -->
36
+
37
+ <!--[if IE]>
38
+ <link rel="stylesheet" href="//www.propublica.org/css/ie.css?2012101501" type="text/css" media="screen" charset="utf-8" />
39
+ <![endif]-->
40
+ <!--[if IE 7]>
41
+ <link rel="stylesheet" href="//www.propublica.org/css/ie7.css?2012101501" type="text/css" media="screen" charset="utf-8" />
42
+ <link rel="stylesheet" href="//www.propublica.org/css/ie7-2011.css?2012101501" type="text/css" media="screen" charset="utf-8" />
43
+ <![endif]-->
44
+ <!--[if lt IE 7]>
45
+ <link rel="stylesheet" href="//www.propublica.org/css/ie6.css?2012101501" type="text/css" media="screen" charset="utf-8" />
46
+ <script src="//www.propublica.org/js/DD_belatedPNG_0.0.8a-min.js" type="text/javascript" charset="utf-8"></script>
47
+ <script src="//www.propublica.org/js/pngfix.js type="text/javascript" charset="utf-8"></script>
48
+ <![endif]-->
49
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads_boot.js"></script>
50
+
51
+ <title>ProPublica | Search results for tools</title>
52
+ </head>
53
+ <body class="search-results">
54
+
55
+ <title>ProPublica</title>
56
+ </head>
57
+ <body class="search-results old-page-new-wrapper">
58
+
59
+ <header class="shell">
60
+ <a href="/" id="dorothy" class="wNarrow"></a>
61
+ <aside id="header-donate-mobile" class="wMed"><h1><a href="https://www.propublica.org/mobile/donate">Donate</a></h1></aside>
62
+ <div id="h-wafer1">
63
+ <div class="wrapper">
64
+ <nav id="dont-miss">
65
+ <div class="wrapper unwrapper">
66
+ </div>
67
+ </nav>
68
+ </div><!-- /wrapper -->
69
+ </div><!-- /h-wafer-1 -->
70
+ <div id="h-wafer2">
71
+ <div class="wrapper">
72
+ <div class="donate">
73
+ <h1><a href="https://propublica.org/site/donate/">Donate</a></h1>
74
+ </div>
75
+ <div id="seo-hgroup">
76
+ <p><a href="/" class="pngfix">ProPublica</a></p>
77
+ <h2>Journalism in the Public Interest</h2>
78
+ </div>
79
+ <form class="has-xid email-sub" id='freeform' method="post" action="http://www.propublica.org/" >
80
+ <div class='hiddenFields'>
81
+ <input type="hidden" name="ACT" value="40" />
82
+ <input type="hidden" name="URI" value="/rails/header2-search_2011" />
83
+ <input type="hidden" name="status" value="open" />
84
+ <input type="hidden" name="return" value="/forms/thank_you" />
85
+ <input type="hidden" name="redirect_on_duplicate" value="" />
86
+ <input type="hidden" name="dynamic_xid" value="y" />
87
+ <input type="hidden" name="disable_xid" value="y" />
88
+ <input type="hidden" name="tracker_email_one" value="" />
89
+ <input type="hidden" name="tracker_template_one" value="" />
90
+ <input type="hidden" name="RET" value="http://www.propublica.org/rails/header2-search_2011/" />
91
+ <input type="hidden" name="form_name" value="daily_email_form" />
92
+ <input type="hidden" name="ajax_request" value="n" />
93
+ <input type="hidden" name="params_id" value="79668560" />
94
+ <input type="hidden" name="site_id" value="1" />
95
+ </div>
96
+
97
+
98
+ <input type='hidden' value='1' name='subscribe_daily_email' /><!-- .banner_2011 hi -->
99
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-mail-28.png">
100
+ <label for="email">Receive our top stories daily</label>
101
+ <input type="email" name="email" placeholder="Email address">
102
+ <input type="submit" value="Subscribe">
103
+ <div class="popper">
104
+ <input type="text" name="postalcode" placeholder="Zip-code">
105
+ <label for="zipcode">optional</label>
106
+ </div>
107
+ </form>
108
+ </div><!-- /wrapper -->
109
+ </div><!-- /h-wafer-2 -->
110
+
111
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads_boot.js?2012101501" charset="utf-8"></script>
112
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads.js?2012101501" charset="utf-8"></script>
113
+
114
+ <div id="h-wafer3">
115
+ <div class="wrapper">
116
+ <nav>
117
+ <a href="http://www.propublica.org/" >Home</a>
118
+ <a href="http://www.propublica.org/investigations/" ><span class="wFull">Our Investigations</span><span class="wNarrow">Projects</span></a>
119
+ <a href="http://www.propublica.org/tools/" class="wMed wFull ">Tools &amp; Data</a>
120
+ <a href="http://www.propublica.org/muckreads" class="wMed wFull ">MuckReads</a>
121
+ <a href="http://www.propublica.org/getinvolved" >Get Involved</a>
122
+ <a href="http://www.propublica.org/about/" class=""><span class="wFull">About Us</span><span class="wNarrow">About</span></a>
123
+ </nav>
124
+ <aside class="fb">
125
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-fb-top-nav.png">
126
+ <div class="jspopper">
127
+
128
+ <iframe src="//www.facebook.com/plugins/likebox.php?href=http%3A%2F%2Fwww.facebook.com%2Fpropublica&width=292&colorscheme=light&show_faces=true&border_color=%23 525E6A&stream=true&header=true&height=590" scrolling="no" frameborder="0" style="border:none; overflow:hidden; width:292px; height:590px; background: #ffffff" allowTransparency="false"></iframe>
129
+
130
+
131
+ </div>
132
+ </aside>
133
+ <aside class="tw">
134
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-tw-top-nav.png">
135
+ <div class="popper">
136
+
137
+ <h1>ProPublica on Twitter</h1>
138
+
139
+ <a class="twitter-timeline" width="285" height="350" data-dnt=true href="https://twitter.com/ProPublica" data-widget-id="250304934812205056">Tweets by @ProPublica</a>
140
+ <script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0];if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src="//platform.twitter.com/widgets.js";fjs.parentNode.insertBefore(js,fjs);}}(document,"script","twitter-wjs");</script>
141
+
142
+
143
+ </div>
144
+ </aside>
145
+ <div id="search-toggler">
146
+ <div class="wNarrow search-toggle" id="search-glass"></div>
147
+ <form action="//www.propublica.org/search/search.php" method="get">
148
+ <input type="search" placeholder="Search ProPublica" name="q">
149
+ <input type="image" src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icn-search.png">
150
+ <div class="wNarrow btn-ios search-toggle">Cancel</div>
151
+ </form>
152
+ </div>
153
+ </div><!-- /wrapper -->
154
+ </div><!-- /h-wafer-3 -->
155
+ </header>
156
+
157
+ <!-- Top_Pushdown -->
158
+ <div id='google-Top_Pushdown' style="z-index: 3;" >
159
+ <script type='text/javascript'>
160
+ googletag.display('google-Top_Pushdown');
161
+ </script>
162
+ </div>
163
+
164
+ <div id="content-header">
165
+ <div class="wrapper">
166
+ <div class="content-header-text">
167
+ <h1 class="title-link">
168
+ Search Results
169
+ <span class="wNarrow">for <span class="search-term">tools</span></span>
170
+ </h1>
171
+ </div>
172
+ </div><!--/.wrapper-->
173
+ </div><!--/.content-header-->
174
+ <div id="content">
175
+ <div class="wrapper">
176
+ <div class="content-main">
177
+ <form action="" class="simple-search">
178
+ <input type="text" class="text-input" name="q" value="tools">
179
+ <input type="submit" class="btn-input" value="Search" />
180
+ </form>
181
+
182
+
183
+ <div class="compact-list-header utility-text">
184
+ <p class="results-count">
185
+ 1-15 of <strong>22700</strong> results
186
+ </p>
187
+
188
+ </div>
189
+
190
+ <div class="compact-list">
191
+ <div class="compact-list-item">
192
+ <h2><a href="webinar.html" class="title-link"><b>Tools</b> &amp; Data </a><!-- --></h2>
193
+ <p><b>Tools</b> &amp; Data. ProPublica&#39;s News Applications, Graphics, Databases, and <b>Tools</b>. <b>....</b> Use this <b>tool</b> to find and compare doctors and other top prescribers in 2010.</p>
194
+ </div> <div class="compact-list-item">
195
+ <h2><a href="prosecutor.html" class="title-link"><b>Tools</b> and Resources for Reporting the Stimulus </a><!-- --></h2>
196
+ <p>Jul 13, 2009 … Here&#39;s some tips of how to keep track of how federal stimulus dollars are being spent in your community.</p>
197
+ </div> </div><!--/.results-list-->
198
+
199
+
200
+
201
+ <div class="stories">
202
+ <ul>
203
+
204
+ </ul>
205
+ </div>
206
+ <p><a href="http://www.propublica.org/tag/data+tools">More ...</a></p>
207
+ </div> -->
208
+ </div>
209
+ </div><!--/.results-list-->
210
+
211
+ <div class="pagination">
212
+ <div class="pagination-menu">
213
+
214
+ <!-- <li><a href="#">&laquo; prev</a></li> -->
215
+
216
+
217
+ <strong>1</strong>
218
+
219
+ <a href="./search.php?q=tools&o=r&p=2">2</a>
220
+ <a href="./search.php?q=tools&o=r&p=3">3</a>
221
+ <a href="./search.php?q=tools&o=r&p=4">4</a>
222
+ <a href="./search.php?q=tools&o=r&p=5">5</a>
223
+ <a href="./search.php?q=tools&o=r&p=6">6</a>
224
+ <a href="./search.php?q=tools&o=r&p=7">7</a>
225
+
226
+ <!-- <li><a href="#">next &raquo;</a></li> -->
227
+ </div>
228
+ </div>
229
+
230
+ <!-- Page 1 of 1514 -->
231
+
232
+
233
+
234
+
235
+
236
+
237
+
238
+
239
+
240
+ </div><!--/.content-main-->
241
+
242
+ <div class="content-right">
243
+ <div class="updates-module module">
244
+ <div class="module-top module-content">
245
+ <h3>Get Updates</h3>
246
+ </div>
247
+ <div class="module-btm module-content">
248
+ <form class="has-xid" id='freeform' method="post" action="http://www.propublica.org/" >
249
+ <div class='hiddenFields'>
250
+ <input type="hidden" name="ACT" value="40" />
251
+ <input type="hidden" name="URI" value="/rails/search_sidebar" />
252
+ <input type="hidden" name="status" value="open" />
253
+ <input type="hidden" name="return" value="/forms/thank_you" />
254
+ <input type="hidden" name="redirect_on_duplicate" value="" />
255
+ <input type="hidden" name="dynamic_xid" value="y" />
256
+ <input type="hidden" name="tracker_email_one" value="" />
257
+ <input type="hidden" name="tracker_template_one" value="" />
258
+ <input type="hidden" name="RET" value="http://www.propublica.org/rails/search_sidebar/" />
259
+ <input type="hidden" name="form_name" value="daily_email_form" />
260
+ <input type="hidden" name="ajax_request" value="y" />
261
+ <input type="hidden" name="params_id" value="79668565" />
262
+ <input type="hidden" name="site_id" value="1" />
263
+ </div>
264
+
265
+
266
+ <input type='hidden' value='1' name='subscribe_daily_email' />
267
+ <p>Stay on top of what we&#8217;re working on by subscribing to our email digest.</p>
268
+ <div class="form-row text-row">
269
+ <label for="subscribe-email">email</label> <input type="text" name="email" class="text-input" id="subscribe-email" />
270
+ </div>
271
+ <div class="form-row text-row">
272
+ <label for="subscribe-zip">zip code</label> <input type="text" name="postalcode" class="text-input" id="subscribe-zip" /> <span>optional</span>
273
+ </div>
274
+ <div class="form-row buttons-row">
275
+ <input type="submit" value="Subscribe" class="btn-input" />
276
+ </div>
277
+ </form>
278
+ </div>
279
+ </div>
280
+
281
+ <div class="donate-module module">
282
+ <div class="module-top module-content">
283
+ <h3>Safeguard the public interest.</h3>
284
+ <div class="module-icon pngfix"><!-- --></div>
285
+ </div>
286
+ <div class="module-btm module-content">
287
+ <p>Support ProPublica’s award-winning investigative journalism.</p>
288
+ <p><a href="http://www.propublica.org/site/donate/" class="btn-input">Donate</a></p>
289
+ </div>
290
+ </div><!--/.donate-module-->
291
+ <div class="simple-follow-module follow-module-single module">
292
+ <div class="module-top module-content">
293
+ <h3>Follow ProPublica</h3>
294
+ <div class="module-icon pngfix"><!-- --></div>
295
+ </div>
296
+ <div class="module-btm module-content">
297
+ <ul>
298
+ <li><a href="http://www.propublica.org/forms/newsletter_daily_email" class="email-sq-link">Email</a></li>
299
+ <li><a href="http://www.facebook.com/propublica" class="fb-link">Facebook</a></li>
300
+ <li><a href="http://www.twitter.com/propublica" class="tw-link">Twitter</a></li>
301
+ </ul>
302
+ <ul>
303
+ <li><a href="http://iphone.propublica.org/" class="apple-link">iPhone App</a></li>
304
+ <li><a href="/podcast/" class="podcast-link">Podcast</a></li>
305
+ <li><a href="http://feeds.propublica.org/propublica/main" class="feed-link">RSS</a></li>
306
+ </ul>
307
+ <div class="clear"></div>
308
+ </div>
309
+ </div><!--/follow-module-->
310
+ </div><!--/.content-right-->
311
+ </div><!--/.wrapper-->
312
+
313
+ </div><!--/#content-->
314
+
315
+
316
+ <footer class="shell wFull">
317
+ <div class="wrapper">
318
+ <a href="https://www.propublica.org/site/donate" id="foot-tab-donate">Donate</a>
319
+ <section class="copyright">
320
+ <p id="footer-logo-image">ProPublica</p>
321
+ <p>
322
+ &copy; Copyright 2013<br>
323
+ Pro Publica Inc.
324
+ </p>
325
+ </section>
326
+ <ul>
327
+ <li><a href="http://www.propublica.org/about/">About Us</a></li>
328
+ <li><a href="http://propublica.org/about/staff">Staff</a></li>
329
+ <li><a href="http://propublica.org/about/contact">Contact</a></li>
330
+ <li><a href="http://propublica.org/about/jobs">Jobs</a></li>
331
+ <li><a href="http://propublica.org/about/corrections">Complaints and Corrections</a></li>
332
+ <li><a href="http://propublica.org/about/legal">Privacy Policy and Other Terms</a></li>
333
+ <li><a href="http://www.propublica.org/about/frequently-asked-questions/">FAQ</a></li>
334
+ </ul>
335
+ <ul>
336
+ <li>Subscribe: <a href="http://www.propublica.org/forms/newsletter_daily_email">Email</a> | <a href="http://feeds.propublica.org/propublica/main">RSS</a></li>
337
+ <li>Follow us: <a href="http://www.twitter.com/propublica">Twitter</a> | <a href="http://www.facebook.com/propublica">Facebook</a></li>
338
+ <li><a href="https://twitter.com/ProPublica/propublica-staff">See staff Twitter accounts</a></li>
339
+ <li><a href="http://www.propublica.org/getinvolved/about">Get Involved @ ProPublica</a></li>
340
+ <li>Download our apps for:<br> &nbsp;&nbsp;&nbsp;<a href="http://iphone.propublica.org/">iPhone</a> | <a href="https://market.android.com/details?id=com.propublica">Android</a></li>
341
+ <li><a href="http://www.propublica.org/podcast/">Listen to our Podcast</a></li>
342
+ </ul>
343
+ <section class="republish">
344
+ <a href="http://www.propublica.org/about/steal-our-stories" id="foot-tab-republish">Steal Our Stories</a>
345
+ <p>Unless otherwise noted, you can republish our stories for free if you <a href="http://www.propublica.org/about/steal-our-stories">follow these rules</a>.</p>
346
+ <!-- cc_ad -->
347
+ <div id='google-cc_ad' >
348
+ <script type='text/javascript'>
349
+ googletag.display('google-cc_ad');
350
+ </script>
351
+ </div>
352
+
353
+ </section>
354
+ </div><!-- /wrapper -->
355
+ </footer>
356
+ <footer class="shell wNarrow">
357
+ <div class="wrapper">
358
+ <aside class="untoggler">
359
+ <h1>Safeguard the public interest</h1>
360
+ <div>
361
+ <p>Support ProPublica's award-winning investigative journalism.</p>
362
+ <p class="btn-row"><a href="https://www.propublica.org/mobile/donate" class="btn-ios">Donate</a></p>
363
+ </div>
364
+ </aside>
365
+ <nav>
366
+ <a href="http://www.propublica.org/about/steal-our-stories">Steal Our Stories <span class="note">follow these rules</span></a>
367
+ <a href="http://propublica.org/about/legal">Privacy Policy</a>
368
+ <a href="http://www.propublica.org/forms/newsletter_daily_email">Sign up for our email list</a>
369
+ <p>&copy; Copyright 2013 Pro Publica Inc.</p>
370
+ </nav>
371
+ </div><!-- /wrapper -->
372
+ </footer>
373
+
374
+
375
+
376
+
377
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/beacons.js"></script>
378
+
379
+
380
+ <script src="http://www.propublica.org/static/fonts/ss-social.js"></script>
381
+ <script src="http://www.propublica.org/static/fonts/ss-standard.js"></script>
382
+
383
+ </body>
384
+ </html>
385
+
386
+
387
+ </body>
388
+ </html>
data/spec/data/propublica_search_page_2.html ADDED
@@ -0,0 +1,375 @@
1
+
2
+
3
+
4
+ <!DOCTYPE html>
5
+
6
+ <html lang="en" xmlns:fb="http://www.facebook.com/2008/fbml">
7
+ <head prefix="og: http://ogp.me/ns# fb: http://ogp.me/ns/fb# article: http://ogp.me/ns/article#">
8
+ <meta http-equiv="X-UA-Compatible" content="IE=Edge;chrome=1">
9
+
10
+
11
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12
+
13
+ <!-- ProPublica Typekit account -->
14
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/typekit.js?1349797800"></script>
15
+
16
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/all.js"></script>
17
+
18
+
19
+ <script type="text/javascript">var _sf_startpt=(new Date()).getTime()</script>
20
+ <meta name="google-site-verification" content="xPf4zxBdgQHZIRLVMiZyNYR1igMQUhsHogunEnOtD1k" />
21
+
22
+ <link rel="stylesheet" href="//www.propublica.org/css/960/reset.css?2012101501" type="text/css" media="all" charset="utf-8" />
23
+ <link rel="stylesheet" href="//www.propublica.org/css/960/propublica-text.css?2012101501" type="text/css" media="all" charset="utf-8" />
24
+ <link rel="stylesheet" href="//www.propublica.org/css/master.css?2012101501" type="text/css" media="screen" charset="utf-8" />
25
+
26
+ <link rel="stylesheet" href="//www.propublica.org/css/print.css?2012101501" type="text/css" media="print" charset="utf-8" />
27
+
28
+ <link rel="stylesheet" href="//www.propublica.org/css/headfoot2011.css?2012101501" type="text/css" media="all" charset="utf-8">
29
+
30
+ <!-- adaptive -->
31
+ <meta name="viewport" content="width=device-width">
32
+ <link rel="stylesheet" type="text/css" media="screen and (max-width: 480px)" href="//www.propublica.org/css/woland.css?2012101501" charset="utf-8">
33
+ <link rel="stylesheet" type="text/css" href="//www.propublica.org/css/zoom-fix.css" charset="UTF-8">
34
+ <!-- <link rel="stylesheet" type="text/css" media="screen and (max-width: 800px) and (min-width: 481px)" href="//www.propublica.org/css/behemoth.css?2012101501" charset="utf-8" /> -->
35
+ <!-- /adaptive -->
36
+
37
+ <!--[if IE]>
38
+ <link rel="stylesheet" href="//www.propublica.org/css/ie.css?2012101501" type="text/css" media="screen" charset="utf-8" />
39
+ <![endif]-->
40
+ <!--[if IE 7]>
41
+ <link rel="stylesheet" href="//www.propublica.org/css/ie7.css?2012101501" type="text/css" media="screen" charset="utf-8" />
42
+ <link rel="stylesheet" href="//www.propublica.org/css/ie7-2011.css?2012101501" type="text/css" media="screen" charset="utf-8" />
43
+ <![endif]-->
44
+ <!--[if lt IE 7]>
45
+ <link rel="stylesheet" href="//www.propublica.org/css/ie6.css?2012101501" type="text/css" media="screen" charset="utf-8" />
46
+ <script src="//www.propublica.org/js/DD_belatedPNG_0.0.8a-min.js" type="text/javascript" charset="utf-8"></script>
47
+ <script src="//www.propublica.org/js/pngfix.js type="text/javascript" charset="utf-8"></script>
48
+ <![endif]-->
49
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads_boot.js"></script>
50
+
51
+ <title>ProPublica | Search results for tools</title>
52
+ </head>
53
+ <body class="search-results">
54
+
55
+ <title>ProPublica</title>
56
+ </head>
57
+ <body class="search-results old-page-new-wrapper">
58
+
59
+ <header class="shell">
60
+ <a href="/" id="dorothy" class="wNarrow"></a>
61
+ <aside id="header-donate-mobile" class="wMed"><h1><a href="https://www.propublica.org/mobile/donate">Donate</a></h1></aside>
62
+ <div id="h-wafer1">
63
+ <div class="wrapper">
64
+ <nav id="dont-miss">
65
+ <div class="wrapper unwrapper">
66
+ </div>
67
+ </nav>
68
+ </div><!-- /wrapper -->
69
+ </div><!-- /h-wafer-1 -->
70
+ <div id="h-wafer2">
71
+ <div class="wrapper">
72
+ <div class="donate">
73
+ <h1><a href="https://propublica.org/site/donate/">Donate</a></h1>
74
+ </div>
75
+ <div id="seo-hgroup">
76
+ <p><a href="/" class="pngfix">ProPublica</a></p>
77
+ <h2>Journalism in the Public Interest</h2>
78
+ </div>
79
+ <form class="has-xid email-sub" id='freeform' method="post" action="http://www.propublica.org/" >
80
+ <div class='hiddenFields'>
81
+ <input type="hidden" name="ACT" value="40" />
82
+ <input type="hidden" name="URI" value="/rails/header2-search_2011" />
83
+ <input type="hidden" name="status" value="open" />
84
+ <input type="hidden" name="return" value="/forms/thank_you" />
85
+ <input type="hidden" name="redirect_on_duplicate" value="" />
86
+ <input type="hidden" name="dynamic_xid" value="y" />
87
+ <input type="hidden" name="disable_xid" value="y" />
88
+ <input type="hidden" name="tracker_email_one" value="" />
89
+ <input type="hidden" name="tracker_template_one" value="" />
90
+ <input type="hidden" name="RET" value="http://www.propublica.org/rails/header2-search_2011/" />
91
+ <input type="hidden" name="form_name" value="daily_email_form" />
92
+ <input type="hidden" name="ajax_request" value="n" />
93
+ <input type="hidden" name="params_id" value="79668560" />
94
+ <input type="hidden" name="site_id" value="1" />
95
+ </div>
96
+
97
+
98
+ <input type='hidden' value='1' name='subscribe_daily_email' /><!-- .banner_2011 hi -->
99
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-mail-28.png">
100
+ <label for="email">Receive our top stories daily</label>
101
+ <input type="email" name="email" placeholder="Email address">
102
+ <input type="submit" value="Subscribe">
103
+ <div class="popper">
104
+ <input type="text" name="postalcode" placeholder="Zip-code">
105
+ <label for="zipcode">optional</label>
106
+ </div>
107
+ </form>
108
+ </div><!-- /wrapper -->
109
+ </div><!-- /h-wafer-2 -->
110
+
111
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads_boot.js?2012101501" charset="utf-8"></script>
112
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/google_ads.js?2012101501" charset="utf-8"></script>
113
+
114
+ <div id="h-wafer3">
115
+ <div class="wrapper">
116
+ <nav>
117
+ <a href="http://www.propublica.org/" >Home</a>
118
+ <a href="http://www.propublica.org/investigations/" ><span class="wFull">Our Investigations</span><span class="wNarrow">Projects</span></a>
119
+ <a href="http://www.propublica.org/tools/" class="wMed wFull ">Tools &amp; Data</a>
120
+ <a href="http://www.propublica.org/muckreads" class="wMed wFull ">MuckReads</a>
121
+ <a href="http://www.propublica.org/getinvolved" >Get Involved</a>
122
+ <a href="http://www.propublica.org/about/" class=""><span class="wFull">About Us</span><span class="wNarrow">About</span></a>
123
+ </nav>
124
+ <aside class="fb">
125
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-fb-top-nav.png">
126
+ <div class="jspopper">
127
+
128
+ <iframe src="//www.facebook.com/plugins/likebox.php?href=http%3A%2F%2Fwww.facebook.com%2Fpropublica&width=292&colorscheme=light&show_faces=true&border_color=%23 525E6A&stream=true&header=true&height=590" scrolling="no" frameborder="0" style="border:none; overflow:hidden; width:292px; height:590px; background: #ffffff" allowTransparency="false"></iframe>
129
+
130
+
131
+ </div>
132
+ </aside>
133
+ <aside class="tw">
134
+ <img src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icon-tw-top-nav.png">
135
+ <div class="popper">
136
+
137
+ <h1>ProPublica on Twitter</h1>
138
+
139
+ <a class="twitter-timeline" width="285" height="350" data-dnt=true href="https://twitter.com/ProPublica" data-widget-id="250304934812205056">Tweets by @ProPublica</a>
140
+ <script>!function(d,s,id){var js,fjs=d.getElementsByTagName(s)[0];if(!d.getElementById(id)){js=d.createElement(s);js.id=id;js.src="//platform.twitter.com/widgets.js";fjs.parentNode.insertBefore(js,fjs);}}(document,"script","twitter-wjs");</script>
141
+
142
+
143
+ </div>
144
+ </aside>
145
+ <div id="search-toggler">
146
+ <div class="wNarrow search-toggle" id="search-glass"></div>
147
+ <form action="//www.propublica.org/search/search.php" method="get">
148
+ <input type="search" placeholder="Search ProPublica" name="q">
149
+ <input type="image" src="//s3.amazonaws.com/cdn.propublica.net/deploy/images/common/icn-search.png">
150
+ <div class="wNarrow btn-ios search-toggle">Cancel</div>
151
+ </form>
152
+ </div>
153
+ </div><!-- /wrapper -->
154
+ </div><!-- /h-wafer-3 -->
155
+ </header>
156
+
157
+ <!-- Top_Pushdown -->
158
+ <div id='google-Top_Pushdown' style="z-index: 3;" >
159
+ <script type='text/javascript'>
160
+ googletag.display('google-Top_Pushdown');
161
+ </script>
162
+ </div>
163
+
164
+ <div id="content-header">
165
+ <div class="wrapper">
166
+ <div class="content-header-text">
167
+ <h1 class="title-link">
168
+ Search Results
169
+ <span class="wNarrow">for <span class="search-term">tools</span></span>
170
+ </h1>
171
+ </div>
172
+ </div><!--/.wrapper-->
173
+ </div><!--/.content-header-->
174
+ <div id="content">
175
+ <div class="wrapper">
176
+ <div class="content-main">
177
+ <form action="" class="simple-search">
178
+ <input type="text" class="text-input" name="q" value="tools">
179
+ <input type="submit" class="btn-input" value="Search" />
180
+ </form>
181
+
182
+
183
+ <div class="compact-list-header utility-text">
184
+ <p class="results-count">
185
+ 16-30 of <strong>22700</strong> results
186
+ </p>
187
+
188
+ </div>
189
+
190
+ <div class="compact-list">
191
+ <div class="compact-list-item">
192
+ <h2><a href="sixfacts.html" class="title-link">Chapter 1. Using Google Refine to Clean Messy Data </a><!-- --></h2>
193
+ <p>Dec 30, 2010 … Google Refine (the program formerly known as Freebase Gridworks) is described by its creators as a “power <b>tool</b> for working with messy data”&nbsp;…</p>
194
+ </div> </div><!--/.results-list-->
195
+
196
+ <div class="pagination">
197
+ <div class="pagination-menu">
198
+
199
+ <!-- <li><a href="#">&laquo; prev</a></li> -->
200
+
201
+
202
+ <a href="./search.php?q=tools&o=r&p=1">1</a>
203
+
204
+ <strong>2</strong>
205
+
206
+ <a href="./search.php?q=tools&o=r&p=3">3</a>
207
+ <a href="./search.php?q=tools&o=r&p=4">4</a>
208
+ <a href="./search.php?q=tools&o=r&p=5">5</a>
209
+ <a href="./search.php?q=tools&o=r&p=6">6</a>
210
+ <a href="./search.php?q=tools&o=r&p=7">7</a>
211
+ <a href="./search.php?q=tools&o=r&p=8">8</a>
212
+
213
+ <!-- <li><a href="#">next &raquo;</a></li> -->
214
+ </div>
215
+ </div>
216
+
217
+ <!-- Page 2 of 1514 -->
218
+
219
+
220
+
221
+
222
+
223
+
224
+
225
+
226
+
227
+ </div><!--/.content-main-->
228
+
229
+ <div class="content-right">
230
+ <div class="updates-module module">
231
+ <div class="module-top module-content">
232
+ <h3>Get Updates</h3>
233
+ </div>
234
+ <div class="module-btm module-content">
235
+ <form class="has-xid" id='freeform' method="post" action="http://www.propublica.org/" >
236
+ <div class='hiddenFields'>
237
+ <input type="hidden" name="ACT" value="40" />
238
+ <input type="hidden" name="URI" value="/rails/search_sidebar" />
239
+ <input type="hidden" name="status" value="open" />
240
+ <input type="hidden" name="return" value="/forms/thank_you" />
241
+ <input type="hidden" name="redirect_on_duplicate" value="" />
242
+ <input type="hidden" name="dynamic_xid" value="y" />
243
+ <input type="hidden" name="tracker_email_one" value="" />
244
+ <input type="hidden" name="tracker_template_one" value="" />
245
+ <input type="hidden" name="RET" value="http://www.propublica.org/rails/search_sidebar/" />
246
+ <input type="hidden" name="form_name" value="daily_email_form" />
247
+ <input type="hidden" name="ajax_request" value="y" />
248
+ <input type="hidden" name="params_id" value="79668565" />
249
+ <input type="hidden" name="site_id" value="1" />
250
+ </div>
251
+
252
+
253
+ <input type='hidden' value='1' name='subscribe_daily_email' />
254
+ <p>Stay on top of what we&#8217;re working on by subscribing to our email digest.</p>
255
+ <div class="form-row text-row">
256
+ <label for="subscribe-email">email</label> <input type="text" name="email" class="text-input" id="subscribe-email" />
257
+ </div>
258
+ <div class="form-row text-row">
259
+ <label for="subscribe-zip">zip code</label> <input type="text" name="postalcode" class="text-input" id="subscribe-zip" /> <span>optional</span>
260
+ </div>
261
+ <div class="form-row buttons-row">
262
+ <input type="submit" value="Subscribe" class="btn-input" />
263
+ </div>
264
+ </form>
265
+ </div>
266
+ </div>
267
+
268
+ <div class="donate-module module">
269
+ <div class="module-top module-content">
270
+ <h3>Safeguard the public interest.</h3>
271
+ <div class="module-icon pngfix"><!-- --></div>
272
+ </div>
273
+ <div class="module-btm module-content">
274
+ <p>Support ProPublica’s award-winning investigative journalism.</p>
275
+ <p><a href="http://www.propublica.org/site/donate/" class="btn-input">Donate</a></p>
276
+ </div>
277
+ </div><!--/.donate-module-->
278
+ <div class="simple-follow-module follow-module-single module">
279
+ <div class="module-top module-content">
280
+ <h3>Follow ProPublica</h3>
281
+ <div class="module-icon pngfix"><!-- --></div>
282
+ </div>
283
+ <div class="module-btm module-content">
284
+ <ul>
285
+ <li><a href="http://www.propublica.org/forms/newsletter_daily_email" class="email-sq-link">Email</a></li>
286
+ <li><a href="http://www.facebook.com/propublica" class="fb-link">Facebook</a></li>
287
+ <li><a href="http://www.twitter.com/propublica" class="tw-link">Twitter</a></li>
288
+ </ul>
289
+ <ul>
290
+ <li><a href="http://iphone.propublica.org/" class="apple-link">iPhone App</a></li>
291
+ <li><a href="/podcast/" class="podcast-link">Podcast</a></li>
292
+ <li><a href="http://feeds.propublica.org/propublica/main" class="feed-link">RSS</a></li>
293
+ </ul>
294
+ <div class="clear"></div>
295
+ </div>
296
+ </div><!--/follow-module-->
297
+ </div><!--/.content-right-->
298
+ </div><!--/.wrapper-->
299
+
300
+ </div><!--/#content-->
301
+
302
+
303
+ <footer class="shell wFull">
304
+ <div class="wrapper">
305
+ <a href="https://www.propublica.org/site/donate" id="foot-tab-donate">Donate</a>
306
+ <section class="copyright">
307
+ <p id="footer-logo-image">ProPublica</p>
308
+ <p>
309
+ &copy; Copyright 2013<br>
310
+ Pro Publica Inc.
311
+ </p>
312
+ </section>
313
+ <ul>
314
+ <li><a href="http://www.propublica.org/about/">About Us</a></li>
315
+ <li><a href="http://propublica.org/about/staff">Staff</a></li>
316
+ <li><a href="http://propublica.org/about/contact">Contact</a></li>
317
+ <li><a href="http://propublica.org/about/jobs">Jobs</a></li>
318
+ <li><a href="http://propublica.org/about/corrections">Complaints and Corrections</a></li>
319
+ <li><a href="http://propublica.org/about/legal">Privacy Policy and Other Terms</a></li>
320
+ <li><a href="http://www.propublica.org/about/frequently-asked-questions/">FAQ</a></li>
321
+ </ul>
322
+ <ul>
323
+ <li>Subscribe: <a href="http://www.propublica.org/forms/newsletter_daily_email">Email</a> | <a href="http://feeds.propublica.org/propublica/main">RSS</a></li>
324
+ <li>Follow us: <a href="http://www.twitter.com/propublica">Twitter</a> | <a href="http://www.facebook.com/propublica">Facebook</a></li>
325
+ <li><a href="https://twitter.com/ProPublica/propublica-staff">See staff Twitter accounts</a></li>
326
+ <li><a href="http://www.propublica.org/getinvolved/about">Get Involved @ ProPublica</a></li>
327
+ <li>Download our apps for:<br> &nbsp;&nbsp;&nbsp;<a href="http://iphone.propublica.org/">iPhone</a> | <a href="https://market.android.com/details?id=com.propublica">Android</a></li>
328
+ <li><a href="http://www.propublica.org/podcast/">Listen to our Podcast</a></li>
329
+ </ul>
330
+ <section class="republish">
331
+ <a href="http://www.propublica.org/about/steal-our-stories" id="foot-tab-republish">Steal Our Stories</a>
332
+ <p>Unless otherwise noted, you can republish our stories for free if you <a href="http://www.propublica.org/about/steal-our-stories">follow these rules</a>.</p>
333
+ <!-- cc_ad -->
334
+ <div id='google-cc_ad' >
335
+ <script type='text/javascript'>
336
+ googletag.display('google-cc_ad');
337
+ </script>
338
+ </div>
339
+
340
+ </section>
341
+ </div><!-- /wrapper -->
342
+ </footer>
343
+ <footer class="shell wNarrow">
344
+ <div class="wrapper">
345
+ <aside class="untoggler">
346
+ <h1>Safeguard the public interest</h1>
347
+ <div>
348
+ <p>Support ProPublica's award-winning investigative journalism.</p>
349
+ <p class="btn-row"><a href="https://www.propublica.org/mobile/donate" class="btn-ios">Donate</a></p>
350
+ </div>
351
+ </aside>
352
+ <nav>
353
+ <a href="http://www.propublica.org/about/steal-our-stories">Steal Our Stories <span class="note">follow these rules</span></a>
354
+ <a href="http://propublica.org/about/legal">Privacy Policy</a>
355
+ <a href="http://www.propublica.org/forms/newsletter_daily_email">Sign up for our email list</a>
356
+ <p>&copy; Copyright 2013 Pro Publica Inc.</p>
357
+ </nav>
358
+ </div><!-- /wrapper -->
359
+ </footer>
360
+
361
+
362
+
363
+
364
+ <script type="text/javascript" src="//www.propublica.org/js/public/assets/beacons.js"></script>
365
+
366
+
367
+ <script src="http://www.propublica.org/static/fonts/ss-social.js"></script>
368
+ <script src="http://www.propublica.org/static/fonts/ss-standard.js"></script>
369
+
370
+ </body>
371
+ </html>
372
+
373
+
374
+ </body>
375
+ </html>