extcite 0.3.0 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +0 -1
- data/CHANGELOG.md +9 -0
- data/Gemfile.lock +13 -11
- data/README.md +1 -1
- data/doc/Array.html +205 -0
- data/doc/Configuration.html +296 -0
- data/doc/Extcite.html +1122 -0
- data/doc/Hash.html +380 -0
- data/doc/String.html +289 -0
- data/doc/Textminer.html +601 -0
- data/doc/Textminer/Fetch.html +447 -0
- data/doc/Textminer/Mined.html +509 -0
- data/doc/Textminer/Miner.html +385 -0
- data/doc/Textminer/Request.html +669 -0
- data/doc/Textminer/Response.html +923 -0
- data/doc/_index.html +135 -0
- data/doc/class_list.html +51 -0
- data/doc/css/common.css +1 -0
- data/doc/css/full_list.css +58 -0
- data/doc/css/style.css +496 -0
- data/doc/file.README.html +139 -0
- data/doc/file_list.html +56 -0
- data/doc/frames.html +17 -0
- data/doc/index.html +139 -0
- data/doc/js/app.js +314 -0
- data/doc/js/full_list.js +216 -0
- data/doc/js/jquery.js +4 -0
- data/doc/method_list.html +155 -0
- data/doc/top-level-namespace.html +397 -0
- data/extcite.gemspec +14 -4
- data/lib/extcite.rb +39 -24
- data/lib/extcite/version.rb +1 -1
- metadata +65 -9
data/doc/Textminer.html
ADDED
@@ -0,0 +1,601 @@
|
|
1
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
|
2
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
|
3
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
4
|
+
<head>
|
5
|
+
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
|
6
|
+
<title>
|
7
|
+
Module: Textminer
|
8
|
+
|
9
|
+
— Documentation by YARD 0.8.7.6
|
10
|
+
|
11
|
+
</title>
|
12
|
+
|
13
|
+
<link rel="stylesheet" href="css/style.css" type="text/css" charset="utf-8" />
|
14
|
+
|
15
|
+
<link rel="stylesheet" href="css/common.css" type="text/css" charset="utf-8" />
|
16
|
+
|
17
|
+
<script type="text/javascript" charset="utf-8">
|
18
|
+
hasFrames = window.top.frames.main ? true : false;
|
19
|
+
relpath = '';
|
20
|
+
framesUrl = "frames.html#!Textminer.html";
|
21
|
+
</script>
|
22
|
+
|
23
|
+
|
24
|
+
<script type="text/javascript" charset="utf-8" src="js/jquery.js"></script>
|
25
|
+
|
26
|
+
<script type="text/javascript" charset="utf-8" src="js/app.js"></script>
|
27
|
+
|
28
|
+
|
29
|
+
</head>
|
30
|
+
<body>
|
31
|
+
<div id="header">
|
32
|
+
<div id="menu">
|
33
|
+
|
34
|
+
<a href="_index.html">Index (T)</a> »
|
35
|
+
|
36
|
+
|
37
|
+
<span class="title">Textminer</span>
|
38
|
+
|
39
|
+
|
40
|
+
<div class="noframes"><span class="title">(</span><a href="." target="_top">no frames</a><span class="title">)</span></div>
|
41
|
+
</div>
|
42
|
+
|
43
|
+
<div id="search">
|
44
|
+
|
45
|
+
<a class="full_list_link" id="class_list_link"
|
46
|
+
href="class_list.html">
|
47
|
+
Class List
|
48
|
+
</a>
|
49
|
+
|
50
|
+
<a class="full_list_link" id="method_list_link"
|
51
|
+
href="method_list.html">
|
52
|
+
Method List
|
53
|
+
</a>
|
54
|
+
|
55
|
+
<a class="full_list_link" id="file_list_link"
|
56
|
+
href="file_list.html">
|
57
|
+
File List
|
58
|
+
</a>
|
59
|
+
|
60
|
+
</div>
|
61
|
+
<div class="clear"></div>
|
62
|
+
</div>
|
63
|
+
|
64
|
+
<iframe id="search_frame"></iframe>
|
65
|
+
|
66
|
+
<div id="content"><h1>Module: Textminer
|
67
|
+
|
68
|
+
|
69
|
+
|
70
|
+
</h1>
|
71
|
+
|
72
|
+
<dl class="box">
|
73
|
+
|
74
|
+
|
75
|
+
|
76
|
+
<dt class="r1">Extended by:</dt>
|
77
|
+
<dd class="r1"><span class='object_link'><a href="Configuration.html" title="Configuration (module)">Configuration</a></span></dd>
|
78
|
+
|
79
|
+
|
80
|
+
|
81
|
+
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
<dt class="r2 last">Defined in:</dt>
|
86
|
+
<dd class="r2 last">lib/textminer/mined.rb<span class="defines">,<br />
|
87
|
+
lib/textminer.rb,<br /> lib/textminer/miner.rb,<br /> lib/textminer/request.rb,<br /> lib/textminer/version.rb,<br /> lib/textminer/response.rb</span>
|
88
|
+
</dd>
|
89
|
+
|
90
|
+
</dl>
|
91
|
+
<div class="clear"></div>
|
92
|
+
|
93
|
+
<h2>Overview</h2><div class="docstring">
|
94
|
+
<div class="discussion">
|
95
|
+
|
96
|
+
<p>Textminer::Miner</p>
|
97
|
+
|
98
|
+
<p>Class to give back text mining object</p>
|
99
|
+
|
100
|
+
|
101
|
+
</div>
|
102
|
+
</div>
|
103
|
+
<div class="tags">
|
104
|
+
|
105
|
+
|
106
|
+
</div><h2>Defined Under Namespace</h2>
|
107
|
+
<p class="children">
|
108
|
+
|
109
|
+
|
110
|
+
|
111
|
+
|
112
|
+
<strong class="classes">Classes:</strong> <span class='object_link'><a href="Textminer/Mined.html" title="Textminer::Mined (class)">Mined</a></span>, <span class='object_link'><a href="Textminer/Miner.html" title="Textminer::Miner (class)">Miner</a></span>, <span class='object_link'><a href="Textminer/Request.html" title="Textminer::Request (class)">Request</a></span>, <span class='object_link'><a href="Textminer/Response.html" title="Textminer::Response (class)">Response</a></span>
|
113
|
+
|
114
|
+
|
115
|
+
</p>
|
116
|
+
|
117
|
+
<h2>Constant Summary</h2>
|
118
|
+
|
119
|
+
<dl class="constants">
|
120
|
+
|
121
|
+
<dt id="VERSION-constant" class="">VERSION =
|
122
|
+
|
123
|
+
</dt>
|
124
|
+
<dd><pre class="code"><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>0.1.5</span><span class='tstring_end'>"</span></span></pre></dd>
|
125
|
+
|
126
|
+
</dl>
|
127
|
+
|
128
|
+
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
|
133
|
+
|
134
|
+
|
135
|
+
|
136
|
+
<h2>
|
137
|
+
Class Method Summary
|
138
|
+
<small>(<a href="#" class="summary_toggle">collapse</a>)</small>
|
139
|
+
</h2>
|
140
|
+
|
141
|
+
<ul class="summary">
|
142
|
+
|
143
|
+
<li class="public ">
|
144
|
+
<span class="summary_signature">
|
145
|
+
|
146
|
+
<a href="#extract-class_method" title="extract (class method)">+ (Object) <strong>extract</strong>(path) </a>
|
147
|
+
|
148
|
+
|
149
|
+
|
150
|
+
</span>
|
151
|
+
|
152
|
+
|
153
|
+
|
154
|
+
|
155
|
+
|
156
|
+
|
157
|
+
|
158
|
+
|
159
|
+
|
160
|
+
<span class="summary_desc"><div class='inline'>
|
161
|
+
<p>Thin layer around pdf-reader gem's PDF::Reader.</p>
|
162
|
+
</div></span>
|
163
|
+
|
164
|
+
</li>
|
165
|
+
|
166
|
+
|
167
|
+
<li class="public ">
|
168
|
+
<span class="summary_signature">
|
169
|
+
|
170
|
+
<a href="#fetch-class_method" title="fetch (class method)">+ (Mined) <strong>fetch</strong>(url) </a>
|
171
|
+
|
172
|
+
|
173
|
+
|
174
|
+
</span>
|
175
|
+
|
176
|
+
|
177
|
+
|
178
|
+
|
179
|
+
|
180
|
+
|
181
|
+
|
182
|
+
|
183
|
+
|
184
|
+
<span class="summary_desc"><div class='inline'>
|
185
|
+
<p>Get full text.</p>
|
186
|
+
</div></span>
|
187
|
+
|
188
|
+
</li>
|
189
|
+
|
190
|
+
|
191
|
+
<li class="public ">
|
192
|
+
<span class="summary_signature">
|
193
|
+
|
194
|
+
<a href="#search-class_method" title="search (class method)">+ (Array) <strong>search</strong>(doi: nil, member: nil, filter: nil, limit: nil, options: nil) </a>
|
195
|
+
|
196
|
+
|
197
|
+
|
198
|
+
</span>
|
199
|
+
|
200
|
+
|
201
|
+
|
202
|
+
|
203
|
+
|
204
|
+
|
205
|
+
|
206
|
+
|
207
|
+
|
208
|
+
<span class="summary_desc"><div class='inline'>
|
209
|
+
<p>Search for papers and get full text links.</p>
|
210
|
+
</div></span>
|
211
|
+
|
212
|
+
</li>
|
213
|
+
|
214
|
+
|
215
|
+
</ul>
|
216
|
+
|
217
|
+
|
218
|
+
|
219
|
+
|
220
|
+
|
221
|
+
|
222
|
+
|
223
|
+
|
224
|
+
|
225
|
+
|
226
|
+
|
227
|
+
<h3 class="inherited">Methods included from <span class='object_link'><a href="Configuration.html" title="Configuration (module)">Configuration</a></span></h3>
|
228
|
+
<p class="inherited"><span class='object_link'><a href="Configuration.html#configuration-instance_method" title="Configuration#configuration (method)">configuration</a></span>, <span class='object_link'><a href="Configuration.html#define_setting-instance_method" title="Configuration#define_setting (method)">define_setting</a></span></p>
|
229
|
+
|
230
|
+
|
231
|
+
<div id="class_method_details" class="method_details_list">
|
232
|
+
<h2>Class Method Details</h2>
|
233
|
+
|
234
|
+
|
235
|
+
<div class="method_details first">
|
236
|
+
<h3 class="signature first" id="extract-class_method">
|
237
|
+
|
238
|
+
+ (<tt>Object</tt>) <strong>extract</strong>(path)
|
239
|
+
|
240
|
+
|
241
|
+
|
242
|
+
|
243
|
+
|
244
|
+
</h3><div class="docstring">
|
245
|
+
<div class="discussion">
|
246
|
+
|
247
|
+
<p>Thin layer around pdf-reader gem's PDF::Reader</p>
|
248
|
+
|
249
|
+
<p>This method is used internally within fetch to parse PDFs.</p>
|
250
|
+
|
251
|
+
|
252
|
+
</div>
|
253
|
+
</div>
|
254
|
+
<div class="tags">
|
255
|
+
|
256
|
+
<div class="examples">
|
257
|
+
<p class="tag_title">Examples:</p>
|
258
|
+
|
259
|
+
|
260
|
+
<pre class="example code"><code><span class='id identifier rubyid_require'>require</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>textminer</span><span class='tstring_end'>'</span></span>
|
261
|
+
<span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>member:</span> <span class='int'>2258</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
262
|
+
<span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_pdf'>links_pdf</span><span class='lparen'>(</span><span class='kw'>true</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
263
|
+
<span class='comment'># Get full text for an article
|
264
|
+
</span><span class='id identifier rubyid_out'>out</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
265
|
+
<span class='comment'># extract pdf to text
|
266
|
+
</span><span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_extract'>extract</span><span class='lparen'>(</span><span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_path'>path</span><span class='rparen'>)</span></code></pre>
|
267
|
+
|
268
|
+
</div>
|
269
|
+
<p class="tag_title">Parameters:</p>
|
270
|
+
<ul class="param">
|
271
|
+
|
272
|
+
<li>
|
273
|
+
|
274
|
+
<span class='name'>path</span>
|
275
|
+
|
276
|
+
|
277
|
+
<span class='type'>(<tt>String</tt>)</span>
|
278
|
+
|
279
|
+
|
280
|
+
|
281
|
+
—
|
282
|
+
<div class='inline'>
|
283
|
+
<p>Path to a pdf file downloaded via <span class='object_link'><a href="#fetch-class_method" title="Textminer.fetch (method)">fetch</a></span>, or another way.</p>
|
284
|
+
</div>
|
285
|
+
|
286
|
+
</li>
|
287
|
+
|
288
|
+
</ul>
|
289
|
+
|
290
|
+
|
291
|
+
</div><table class="source_code">
|
292
|
+
<tr>
|
293
|
+
<td>
|
294
|
+
<pre class="lines">
|
295
|
+
|
296
|
+
|
297
|
+
140
|
298
|
+
141
|
299
|
+
142
|
300
|
+
143</pre>
|
301
|
+
</td>
|
302
|
+
<td>
|
303
|
+
<pre class="code"><span class="info file"># File 'lib/textminer.rb', line 140</span>
|
304
|
+
|
305
|
+
<span class='kw'>def</span> <span class='kw'>self</span><span class='period'>.</span><span class='id identifier rubyid_extract'>extract</span><span class='lparen'>(</span><span class='id identifier rubyid_path'>path</span><span class='rparen'>)</span>
|
306
|
+
<span class='id identifier rubyid_rr'>rr</span> <span class='op'>=</span> <span class='const'>PDF</span><span class='op'>::</span><span class='const'>Reader</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='id identifier rubyid_path'>path</span><span class='rparen'>)</span>
|
307
|
+
<span class='id identifier rubyid_rr'>rr</span><span class='period'>.</span><span class='id identifier rubyid_pages'>pages</span><span class='period'>.</span><span class='id identifier rubyid_map'>map</span> <span class='lbrace'>{</span> <span class='op'>|</span><span class='id identifier rubyid_page'>page</span><span class='op'>|</span> <span class='id identifier rubyid_page'>page</span><span class='period'>.</span><span class='id identifier rubyid_text'>text</span> <span class='rbrace'>}</span><span class='period'>.</span><span class='id identifier rubyid_join'>join</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>\n</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
308
|
+
<span class='kw'>end</span></pre>
|
309
|
+
</td>
|
310
|
+
</tr>
|
311
|
+
</table>
|
312
|
+
</div>
|
313
|
+
|
314
|
+
<div class="method_details ">
|
315
|
+
<h3 class="signature " id="fetch-class_method">
|
316
|
+
|
317
|
+
+ (<tt><span class='object_link'><a href="Textminer/Mined.html" title="Textminer::Mined (class)">Mined</a></span></tt>) <strong>fetch</strong>(url)
|
318
|
+
|
319
|
+
|
320
|
+
|
321
|
+
|
322
|
+
|
323
|
+
</h3><div class="docstring">
|
324
|
+
<div class="discussion">
|
325
|
+
|
326
|
+
<p>Get full text</p>
|
327
|
+
|
328
|
+
<p>Work easily for open access papers, but for closed. For non-OA papers, use
|
329
|
+
Crossref's Text and Data Mining service, which requires authentication
|
330
|
+
and pre-authorized IP address. Go to <a
|
331
|
+
href="https://apps.crossref.org/clickthrough/researchers">apps.crossref.org/clickthrough/researchers</a>
|
332
|
+
to sign up for the TDM service, to get your key. The only publishers taking
|
333
|
+
part at this time are Elsevier and Wiley.</p>
|
334
|
+
|
335
|
+
<p>the url requested, the file path, and parsing the plain text, XML, or
|
336
|
+
extracting text from the pdf.</p>
|
337
|
+
|
338
|
+
|
339
|
+
</div>
|
340
|
+
</div>
|
341
|
+
<div class="tags">
|
342
|
+
|
343
|
+
<div class="examples">
|
344
|
+
<p class="tag_title">Examples:</p>
|
345
|
+
|
346
|
+
|
347
|
+
<pre class="example code"><code><span class='id identifier rubyid_require'>require</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>textminer</span><span class='tstring_end'>'</span></span>
|
348
|
+
<span class='comment'># Set authorization
|
349
|
+
</span><span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_configuration'>configuration</span> <span class='kw'>do</span> <span class='op'>|</span><span class='id identifier rubyid_config'>config</span><span class='op'>|</span>
|
350
|
+
<span class='id identifier rubyid_config'>config</span><span class='period'>.</span><span class='id identifier rubyid_tdm_key'>tdm_key</span> <span class='op'>=</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'><your key></span><span class='tstring_end'>"</span></span>
|
351
|
+
<span class='kw'>end</span>
|
352
|
+
<span class='comment'># Get some elsevier works
|
353
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>member:</span> <span class='int'>78</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
354
|
+
<span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_xml'>links_xml</span><span class='lparen'>(</span><span class='kw'>true</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
355
|
+
<span class='comment'># Get full text for an article
|
356
|
+
</span><span class='id identifier rubyid_out'>out</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
357
|
+
<span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_url'>url</span>
|
358
|
+
<span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_path'>path</span>
|
359
|
+
<span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_type'>type</span>
|
360
|
+
<span class='id identifier rubyid_xml'>xml</span> <span class='op'>=</span> <span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span><span class='lparen'>(</span><span class='rparen'>)</span>
|
361
|
+
<span class='id identifier rubyid_puts'>puts</span> <span class='id identifier rubyid_xml'>xml</span>
|
362
|
+
<span class='id identifier rubyid_xml'>xml</span><span class='period'>.</span><span class='id identifier rubyid_xpath'>xpath</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>//xocs:cover-date-text</span><span class='tstring_end'>'</span></span><span class='comma'>,</span> <span class='id identifier rubyid_xml'>xml</span><span class='period'>.</span><span class='id identifier rubyid_root'>root</span><span class='period'>.</span><span class='id identifier rubyid_namespaces'>namespaces</span><span class='rparen'>)</span><span class='period'>.</span><span class='id identifier rubyid_text'>text</span>
|
363
|
+
<span class='comment'># Get lots of articles
|
364
|
+
</span><span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>1</span><span class='op'>..</span><span class='int'>3</span><span class='rbracket'>]</span>
|
365
|
+
<span class='id identifier rubyid_out'>out</span> <span class='op'>=</span> <span class='id identifier rubyid_links'>links</span><span class='period'>.</span><span class='id identifier rubyid_collect'>collect</span><span class='lbrace'>{</span> <span class='op'>|</span><span class='id identifier rubyid_x'>x</span><span class='op'>|</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_x'>x</span><span class='rparen'>)</span> <span class='rbrace'>}</span>
|
366
|
+
<span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_collect'>collect</span><span class='lbrace'>{</span> <span class='op'>|</span><span class='id identifier rubyid_z'>z</span><span class='op'>|</span> <span class='id identifier rubyid_z'>z</span><span class='period'>.</span><span class='id identifier rubyid_path'>path</span> <span class='rbrace'>}</span>
|
367
|
+
<span class='id identifier rubyid_out'>out</span><span class='period'>.</span><span class='id identifier rubyid_collect'>collect</span><span class='lbrace'>{</span> <span class='op'>|</span><span class='id identifier rubyid_z'>z</span><span class='op'>|</span> <span class='id identifier rubyid_z'>z</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span> <span class='rbrace'>}</span>
|
368
|
+
<span class='id identifier rubyid_zz'>zz</span> <span class='op'>=</span> <span class='id identifier rubyid_out'>out</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span>
|
369
|
+
<span class='id identifier rubyid_zz'>zz</span><span class='period'>.</span><span class='id identifier rubyid_xpath'>xpath</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>//xocs:cover-date-text</span><span class='tstring_end'>'</span></span><span class='comma'>,</span> <span class='id identifier rubyid_zz'>zz</span><span class='period'>.</span><span class='id identifier rubyid_root'>root</span><span class='period'>.</span><span class='id identifier rubyid_namespaces'>namespaces</span><span class='rparen'>)</span><span class='period'>.</span><span class='id identifier rubyid_text'>text</span>
|
370
|
+
|
371
|
+
<span class='comment'>## plain text
|
372
|
+
</span><span class='comment'># get full text links, here doing xml
|
373
|
+
</span><span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_plain'>links_plain</span><span class='lparen'>(</span><span class='kw'>true</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
374
|
+
<span class='comment'># Get full text for an article
|
375
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
376
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_url'>url</span>
|
377
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span>
|
378
|
+
|
379
|
+
<span class='comment'># With open access content - using Pensoft
|
380
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>member:</span> <span class='int'>2258</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
381
|
+
<span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_xml'>links_xml</span><span class='lparen'>(</span><span class='kw'>true</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
382
|
+
<span class='comment'># Get full text for an article
|
383
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
384
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_url'>url</span>
|
385
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span>
|
386
|
+
|
387
|
+
<span class='comment'># OA content - pdfs, using pensoft again
|
388
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>member:</span> <span class='int'>2258</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
389
|
+
<span class='id identifier rubyid_links'>links</span> <span class='op'>=</span> <span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_pdf'>links_pdf</span><span class='lparen'>(</span><span class='kw'>true</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
390
|
+
<span class='comment'># Get full text for an article
|
391
|
+
</span><span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='label'>url:</span> <span class='id identifier rubyid_links'>links</span><span class='lbracket'>[</span><span class='int'>0</span><span class='rbracket'>]</span><span class='rparen'>)</span><span class='semicolon'>;</span>
|
392
|
+
<span class='comment'># url used
|
393
|
+
</span><span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_url'>url</span>
|
394
|
+
<span class='comment'># document type
|
395
|
+
</span><span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_type'>type</span>
|
396
|
+
<span class='comment'># document path on your machine
|
397
|
+
</span><span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_path'>path</span>
|
398
|
+
<span class='comment'># get text
|
399
|
+
</span><span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_parse'>parse</span></code></pre>
|
400
|
+
|
401
|
+
</div>
|
402
|
+
<p class="tag_title">Parameters:</p>
|
403
|
+
<ul class="param">
|
404
|
+
|
405
|
+
<li>
|
406
|
+
|
407
|
+
<span class='name'>url</span>
|
408
|
+
|
409
|
+
|
410
|
+
<span class='type'>(<tt>String</tt>)</span>
|
411
|
+
|
412
|
+
|
413
|
+
|
414
|
+
—
|
415
|
+
<div class='inline'>
|
416
|
+
<p>A url for full text</p>
|
417
|
+
</div>
|
418
|
+
|
419
|
+
</li>
|
420
|
+
|
421
|
+
</ul>
|
422
|
+
|
423
|
+
<p class="tag_title">Returns:</p>
|
424
|
+
<ul class="return">
|
425
|
+
|
426
|
+
<li>
|
427
|
+
|
428
|
+
|
429
|
+
<span class='type'>(<tt><span class='object_link'><a href="Textminer/Mined.html" title="Textminer::Mined (class)">Mined</a></span></tt>)</span>
|
430
|
+
|
431
|
+
|
432
|
+
|
433
|
+
—
|
434
|
+
<div class='inline'>
|
435
|
+
<p>An object of class Mined, with methods for extracting</p>
|
436
|
+
</div>
|
437
|
+
|
438
|
+
</li>
|
439
|
+
|
440
|
+
</ul>
|
441
|
+
|
442
|
+
</div><table class="source_code">
|
443
|
+
<tr>
|
444
|
+
<td>
|
445
|
+
<pre class="lines">
|
446
|
+
|
447
|
+
|
448
|
+
120
|
449
|
+
121
|
450
|
+
122</pre>
|
451
|
+
</td>
|
452
|
+
<td>
|
453
|
+
<pre class="code"><span class="info file"># File 'lib/textminer.rb', line 120</span>
|
454
|
+
|
455
|
+
<span class='kw'>def</span> <span class='kw'>self</span><span class='period'>.</span><span class='id identifier rubyid_fetch'>fetch</span><span class='lparen'>(</span><span class='id identifier rubyid_url'>url</span><span class='rparen'>)</span>
|
456
|
+
<span class='const'>Miner</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='id identifier rubyid_url'>url</span><span class='rparen'>)</span><span class='period'>.</span><span class='id identifier rubyid_perform'>perform</span>
|
457
|
+
<span class='kw'>end</span></pre>
|
458
|
+
</td>
|
459
|
+
</tr>
|
460
|
+
</table>
|
461
|
+
</div>
|
462
|
+
|
463
|
+
<div class="method_details ">
|
464
|
+
<h3 class="signature " id="search-class_method">
|
465
|
+
|
466
|
+
+ (<tt><span class='object_link'><a href="Array.html" title="Array (class)">Array</a></span></tt>) <strong>search</strong>(doi: nil, member: nil, filter: nil, limit: nil, options: nil)
|
467
|
+
|
468
|
+
|
469
|
+
|
470
|
+
|
471
|
+
|
472
|
+
</h3><div class="docstring">
|
473
|
+
<div class="discussion">
|
474
|
+
|
475
|
+
<p>Search for papers and get full text links</p>
|
476
|
+
|
477
|
+
|
478
|
+
</div>
|
479
|
+
</div>
|
480
|
+
<div class="tags">
|
481
|
+
|
482
|
+
<div class="examples">
|
483
|
+
<p class="tag_title">Examples:</p>
|
484
|
+
|
485
|
+
|
486
|
+
<pre class="example code"><code><span class='id identifier rubyid_require'>require</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>textminer</span><span class='tstring_end'>'</span></span>
|
487
|
+
<span class='comment'># link to full text available
|
488
|
+
</span><span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>10.3897/phytokeys.42.7604</span><span class='tstring_end'>'</span></span><span class='rparen'>)</span>
|
489
|
+
<span class='comment'># no link to full text available
|
490
|
+
</span><span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>10.1371/journal.pone.0000308</span><span class='tstring_end'>"</span></span><span class='rparen'>)</span>
|
491
|
+
<span class='comment'># many DOIs at once
|
492
|
+
</span><span class='id identifier rubyid_require'>require</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>serrano</span><span class='tstring_end'>'</span></span>
|
493
|
+
<span class='id identifier rubyid_dois'>dois</span> <span class='op'>=</span> <span class='const'>Serrano</span><span class='period'>.</span><span class='id identifier rubyid_random_dois'>random_dois</span><span class='lparen'>(</span><span class='label'>sample:</span> <span class='int'>6</span><span class='rparen'>)</span>
|
494
|
+
<span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='id identifier rubyid_dois'>dois</span><span class='rparen'>)</span>
|
495
|
+
<span class='id identifier rubyid_res'>res</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='lbracket'>[</span><span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>10.3897/phytokeys.42.7604</span><span class='tstring_end'>"</span></span><span class='comma'>,</span> <span class='tstring'><span class='tstring_beg'>"</span><span class='tstring_content'>10.3897/zookeys.516.9439</span><span class='tstring_end'>"</span></span><span class='rbracket'>]</span><span class='rparen'>)</span>
|
496
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links'>links</span>
|
497
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_pdf'>links_pdf</span>
|
498
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_xml'>links_xml</span>
|
499
|
+
<span class='id identifier rubyid_res'>res</span><span class='period'>.</span><span class='id identifier rubyid_links_plain'>links_plain</span>
|
500
|
+
<span class='comment'># only full text available
|
501
|
+
</span><span class='id identifier rubyid_x'>x</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='tstring'><span class='tstring_beg'>'</span><span class='tstring_content'>10.3816/clm.2001.n.006</span><span class='tstring_end'>'</span></span><span class='rparen'>)</span>
|
502
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_xml'>links_xml</span>
|
503
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_plain'>links_plain</span>
|
504
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_pdf'>links_pdf</span>
|
505
|
+
<span class='comment'># no dois
|
506
|
+
</span><span class='id identifier rubyid_x'>x</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span>
|
507
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_xml'>links_xml</span>
|
508
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_plain'>links_plain</span>
|
509
|
+
<span class='id identifier rubyid_x'>x</span> <span class='op'>=</span> <span class='const'>Textminer</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>member:</span> <span class='int'>311</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='lbrace'>{</span><span class='label'>has_full_text:</span> <span class='kw'>true</span><span class='rbrace'>}</span><span class='rparen'>)</span>
|
510
|
+
<span class='id identifier rubyid_x'>x</span><span class='period'>.</span><span class='id identifier rubyid_links_pdf'>links_pdf</span></code></pre>
|
511
|
+
|
512
|
+
</div>
|
513
|
+
<p class="tag_title">Parameters:</p>
|
514
|
+
<ul class="param">
|
515
|
+
|
516
|
+
<li>
|
517
|
+
|
518
|
+
<span class='name'>doi</span>
|
519
|
+
|
520
|
+
|
521
|
+
<span class='type'>(<tt><span class='object_link'><a href="Array.html" title="Array (class)">Array</a></span></tt>)</span>
|
522
|
+
|
523
|
+
|
524
|
+
|
525
|
+
—
|
526
|
+
<div class='inline'>
|
527
|
+
<p>A DOI, digital object identifier</p>
|
528
|
+
</div>
|
529
|
+
|
530
|
+
</li>
|
531
|
+
|
532
|
+
<li>
|
533
|
+
|
534
|
+
<span class='name'>options</span>
|
535
|
+
|
536
|
+
|
537
|
+
<span class='type'>(<tt><span class='object_link'><a href="Array.html" title="Array (class)">Array</a></span></tt>)</span>
|
538
|
+
|
539
|
+
|
540
|
+
|
541
|
+
—
|
542
|
+
<div class='inline'>
|
543
|
+
<p>Curl request options</p>
|
544
|
+
</div>
|
545
|
+
|
546
|
+
</li>
|
547
|
+
|
548
|
+
</ul>
|
549
|
+
|
550
|
+
<p class="tag_title">Returns:</p>
|
551
|
+
<ul class="return">
|
552
|
+
|
553
|
+
<li>
|
554
|
+
|
555
|
+
|
556
|
+
<span class='type'>(<tt><span class='object_link'><a href="Array.html" title="Array (class)">Array</a></span></tt>)</span>
|
557
|
+
|
558
|
+
|
559
|
+
|
560
|
+
—
|
561
|
+
<div class='inline'>
|
562
|
+
<p>the output</p>
|
563
|
+
</div>
|
564
|
+
|
565
|
+
</li>
|
566
|
+
|
567
|
+
</ul>
|
568
|
+
|
569
|
+
</div><table class="source_code">
|
570
|
+
<tr>
|
571
|
+
<td>
|
572
|
+
<pre class="lines">
|
573
|
+
|
574
|
+
|
575
|
+
48
|
576
|
+
49
|
577
|
+
50</pre>
|
578
|
+
</td>
|
579
|
+
<td>
|
580
|
+
<pre class="code"><span class="info file"># File 'lib/textminer.rb', line 48</span>
|
581
|
+
|
582
|
+
<span class='kw'>def</span> <span class='kw'>self</span><span class='period'>.</span><span class='id identifier rubyid_search'>search</span><span class='lparen'>(</span><span class='label'>doi:</span> <span class='kw'>nil</span><span class='comma'>,</span> <span class='label'>member:</span> <span class='kw'>nil</span><span class='comma'>,</span> <span class='label'>filter:</span> <span class='kw'>nil</span><span class='comma'>,</span> <span class='label'>limit:</span> <span class='kw'>nil</span><span class='comma'>,</span> <span class='label'>options:</span> <span class='kw'>nil</span><span class='rparen'>)</span>
|
583
|
+
<span class='const'>Request</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span><span class='lparen'>(</span><span class='id identifier rubyid_doi'>doi</span><span class='comma'>,</span> <span class='id identifier rubyid_member'>member</span><span class='comma'>,</span> <span class='id identifier rubyid_filter'>filter</span><span class='comma'>,</span> <span class='id identifier rubyid_limit'>limit</span><span class='comma'>,</span> <span class='id identifier rubyid_options'>options</span><span class='rparen'>)</span><span class='period'>.</span><span class='id identifier rubyid_perform'>perform</span>
|
584
|
+
<span class='kw'>end</span></pre>
|
585
|
+
</td>
|
586
|
+
</tr>
|
587
|
+
</table>
|
588
|
+
</div>
|
589
|
+
|
590
|
+
</div>
|
591
|
+
|
592
|
+
</div>
|
593
|
+
|
594
|
+
<div id="footer">
|
595
|
+
Generated on Fri Dec 4 20:45:51 2015 by
|
596
|
+
<a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
|
597
|
+
0.8.7.6 (ruby-2.2.3).
|
598
|
+
</div>
|
599
|
+
|
600
|
+
</body>
|
601
|
+
</html>
|