html2rss 0.3.3 → 0.4.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (61) hide show
  1. checksums.yaml +4 -4
  2. data/.rubocop.yml +18 -11
  3. data/.travis.yml +3 -3
  4. data/.yardopts +6 -0
  5. data/Gemfile.lock +23 -5
  6. data/README.md +2 -1
  7. data/docs/Html2rss.html +353 -0
  8. data/docs/Html2rss/AttributePostProcessors.html +203 -0
  9. data/docs/Html2rss/AttributePostProcessors/ParseTime.html +332 -0
  10. data/docs/Html2rss/AttributePostProcessors/ParseUri.html +314 -0
  11. data/docs/Html2rss/AttributePostProcessors/SanitizeHtml.html +346 -0
  12. data/docs/Html2rss/AttributePostProcessors/Substring.html +321 -0
  13. data/docs/Html2rss/AttributePostProcessors/Template.html +336 -0
  14. data/docs/Html2rss/Config.html +795 -0
  15. data/docs/Html2rss/FeedBuilder.html +295 -0
  16. data/docs/Html2rss/Item.html +654 -0
  17. data/docs/Html2rss/ItemExtractors.html +297 -0
  18. data/docs/Html2rss/ItemExtractors/Attribute.html +317 -0
  19. data/docs/Html2rss/ItemExtractors/CurrentTime.html +297 -0
  20. data/docs/Html2rss/ItemExtractors/Href.html +319 -0
  21. data/docs/Html2rss/ItemExtractors/Html.html +314 -0
  22. data/docs/Html2rss/ItemExtractors/Static.html +301 -0
  23. data/docs/Html2rss/ItemExtractors/Text.html +312 -0
  24. data/docs/Html2rss/Utils.html +115 -0
  25. data/docs/Html2rss/Utils/IndifferentAccessHash.html +142 -0
  26. data/docs/_index.html +300 -0
  27. data/docs/class_list.html +51 -0
  28. data/docs/css/common.css +1 -0
  29. data/docs/css/full_list.css +58 -0
  30. data/docs/css/style.css +496 -0
  31. data/docs/file.README.html +135 -0
  32. data/docs/file_list.html +56 -0
  33. data/docs/frames.html +17 -0
  34. data/docs/index.html +135 -0
  35. data/docs/js/app.js +303 -0
  36. data/docs/js/full_list.js +216 -0
  37. data/docs/js/jquery.js +4 -0
  38. data/docs/method_list.html +435 -0
  39. data/docs/top-level-namespace.html +110 -0
  40. data/html2rss.gemspec +3 -0
  41. data/lib/html2rss.rb +19 -4
  42. data/lib/html2rss/attribute_post_processors.rb +5 -3
  43. data/lib/html2rss/attribute_post_processors/parse_time.rb +29 -3
  44. data/lib/html2rss/attribute_post_processors/parse_uri.rb +20 -1
  45. data/lib/html2rss/attribute_post_processors/sanitize_html.rb +65 -3
  46. data/lib/html2rss/attribute_post_processors/substring.rb +24 -3
  47. data/lib/html2rss/attribute_post_processors/template.rb +37 -10
  48. data/lib/html2rss/config.rb +11 -12
  49. data/lib/html2rss/feed_builder.rb +8 -6
  50. data/lib/html2rss/item.rb +28 -19
  51. data/lib/html2rss/item_extractors.rb +29 -0
  52. data/lib/html2rss/item_extractors/attribute.rb +37 -0
  53. data/lib/html2rss/item_extractors/current_time.rb +21 -0
  54. data/lib/html2rss/item_extractors/href.rb +36 -0
  55. data/lib/html2rss/item_extractors/html.rb +34 -0
  56. data/lib/html2rss/item_extractors/static.rb +28 -0
  57. data/lib/html2rss/item_extractors/text.rb +32 -0
  58. data/lib/html2rss/utils.rb +25 -0
  59. data/lib/html2rss/version.rb +1 -1
  60. metadata +88 -4
  61. data/lib/html2rss/item_extractor.rb +0 -37
@@ -0,0 +1,297 @@
1
+ <!DOCTYPE html>
2
+ <html>
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
6
+ <title>
7
+ Class: Html2rss::ItemExtractors::CurrentTime
8
+
9
+ &mdash; Documentation by YARD 0.9.20
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
+ pathId = "Html2rss::ItemExtractors::CurrentTime";
19
+ relpath = '../../';
20
+ </script>
21
+
22
+
23
+ <script type="text/javascript" charset="utf-8" src="../../js/jquery.js"></script>
24
+
25
+ <script type="text/javascript" charset="utf-8" src="../../js/app.js"></script>
26
+
27
+
28
+ </head>
29
+ <body>
30
+ <div class="nav_wrap">
31
+ <iframe id="nav" src="../../class_list.html?1"></iframe>
32
+ <div id="resizer"></div>
33
+ </div>
34
+
35
+ <div id="main" tabindex="-1">
36
+ <div id="header">
37
+ <div id="menu">
38
+
39
+ <a href="../../_index.html">Index (C)</a> &raquo;
40
+ <span class='title'><span class='object_link'><a href="../../Html2rss.html" title="Html2rss (module)">Html2rss</a></span></span> &raquo; <span class='title'><span class='object_link'><a href="../ItemExtractors.html" title="Html2rss::ItemExtractors (module)">ItemExtractors</a></span></span>
41
+ &raquo;
42
+ <span class="title">CurrentTime</span>
43
+
44
+ </div>
45
+
46
+ <div id="search">
47
+
48
+ <a class="full_list_link" id="class_list_link"
49
+ href="../../class_list.html">
50
+
51
+ <svg width="24" height="24">
52
+ <rect x="0" y="4" width="24" height="4" rx="1" ry="1"></rect>
53
+ <rect x="0" y="12" width="24" height="4" rx="1" ry="1"></rect>
54
+ <rect x="0" y="20" width="24" height="4" rx="1" ry="1"></rect>
55
+ </svg>
56
+ </a>
57
+
58
+ </div>
59
+ <div class="clear"></div>
60
+ </div>
61
+
62
+ <div id="content"><h1>Class: Html2rss::ItemExtractors::CurrentTime
63
+
64
+
65
+
66
+ </h1>
67
+ <div class="box_info">
68
+
69
+ <dl>
70
+ <dt>Inherits:</dt>
71
+ <dd>
72
+ <span class="inheritName">Object</span>
73
+
74
+ <ul class="fullTree">
75
+ <li>Object</li>
76
+
77
+ <li class="next">Html2rss::ItemExtractors::CurrentTime</li>
78
+
79
+ </ul>
80
+ <a href="#" class="inheritanceTree">show all</a>
81
+
82
+ </dd>
83
+ </dl>
84
+
85
+
86
+
87
+
88
+
89
+
90
+
91
+
92
+
93
+
94
+
95
+ <dl>
96
+ <dt>Defined in:</dt>
97
+ <dd>lib/html2rss/item_extractors/current_time.rb</dd>
98
+ </dl>
99
+
100
+ </div>
101
+
102
+ <h2>Overview</h2><div class="docstring">
103
+ <div class="discussion">
104
+
105
+ <p>Returns the current Time.</p>
106
+
107
+ <p>YAML usage example:</p>
108
+
109
+ <pre class="code ruby"><code class="ruby">selectors:
110
+ updated:
111
+ extractor: current_time
112
+ </code></pre>
113
+
114
+
115
+ </div>
116
+ </div>
117
+ <div class="tags">
118
+
119
+
120
+ </div>
121
+
122
+
123
+
124
+
125
+
126
+
127
+
128
+ <h2>
129
+ Instance Method Summary
130
+ <small><a href="#" class="summary_toggle">collapse</a></small>
131
+ </h2>
132
+
133
+ <ul class="summary">
134
+
135
+ <li class="public ">
136
+ <span class="summary_signature">
137
+
138
+ <a href="#get-instance_method" title="#get (instance method)">#<strong>get</strong> &#x21d2; Time </a>
139
+
140
+
141
+
142
+ </span>
143
+
144
+
145
+
146
+
147
+
148
+
149
+
150
+
151
+
152
+ <span class="summary_desc"><div class='inline'></div></span>
153
+
154
+ </li>
155
+
156
+
157
+ <li class="public ">
158
+ <span class="summary_signature">
159
+
160
+ <a href="#initialize-instance_method" title="#initialize (instance method)">#<strong>initialize</strong>(_xml, _options) &#x21d2; CurrentTime </a>
161
+
162
+
163
+
164
+ </span>
165
+
166
+
167
+ <span class="note title constructor">constructor</span>
168
+
169
+
170
+
171
+
172
+
173
+
174
+
175
+
176
+ <span class="summary_desc"><div class='inline'>
177
+ <p>A new instance of CurrentTime.</p>
178
+ </div></span>
179
+
180
+ </li>
181
+
182
+
183
+ </ul>
184
+
185
+
186
+ <div id="constructor_details" class="method_details_list">
187
+ <h2>Constructor Details</h2>
188
+
189
+ <div class="method_details first">
190
+ <h3 class="signature first" id="initialize-instance_method">
191
+
192
+ #<strong>initialize</strong>(_xml, _options) &#x21d2; <tt><span class='object_link'><a href="" title="Html2rss::ItemExtractors::CurrentTime (class)">CurrentTime</a></span></tt>
193
+
194
+
195
+
196
+
197
+
198
+ </h3><div class="docstring">
199
+ <div class="discussion">
200
+
201
+ <p>Returns a new instance of CurrentTime</p>
202
+
203
+
204
+ </div>
205
+ </div>
206
+ <div class="tags">
207
+
208
+
209
+ </div><table class="source_code">
210
+ <tr>
211
+ <td>
212
+ <pre class="lines">
213
+
214
+
215
+ 12</pre>
216
+ </td>
217
+ <td>
218
+ <pre class="code"><span class="info file"># File 'lib/html2rss/item_extractors/current_time.rb', line 12</span>
219
+
220
+ <span class='kw'>def</span> <span class='id identifier rubyid_initialize'>initialize</span><span class='lparen'>(</span><span class='id identifier rubyid__xml'>_xml</span><span class='comma'>,</span> <span class='id identifier rubyid__options'>_options</span><span class='rparen'>)</span><span class='semicolon'>;</span> <span class='kw'>end</span></pre>
221
+ </td>
222
+ </tr>
223
+ </table>
224
+ </div>
225
+
226
+ </div>
227
+
228
+
229
+ <div id="instance_method_details" class="method_details_list">
230
+ <h2>Instance Method Details</h2>
231
+
232
+
233
+ <div class="method_details first">
234
+ <h3 class="signature first" id="get-instance_method">
235
+
236
+ #<strong>get</strong> &#x21d2; <tt>Time</tt>
237
+
238
+
239
+
240
+
241
+
242
+ </h3><div class="docstring">
243
+ <div class="discussion">
244
+
245
+
246
+ </div>
247
+ </div>
248
+ <div class="tags">
249
+
250
+ <p class="tag_title">Returns:</p>
251
+ <ul class="return">
252
+
253
+ <li>
254
+
255
+
256
+ <span class='type'>(<tt>Time</tt>)</span>
257
+
258
+
259
+
260
+ </li>
261
+
262
+ </ul>
263
+
264
+ </div><table class="source_code">
265
+ <tr>
266
+ <td>
267
+ <pre class="lines">
268
+
269
+
270
+ 16
271
+ 17
272
+ 18</pre>
273
+ </td>
274
+ <td>
275
+ <pre class="code"><span class="info file"># File 'lib/html2rss/item_extractors/current_time.rb', line 16</span>
276
+
277
+ <span class='kw'>def</span> <span class='id identifier rubyid_get'>get</span>
278
+ <span class='const'>Time</span><span class='period'>.</span><span class='id identifier rubyid_new'>new</span>
279
+ <span class='kw'>end</span></pre>
280
+ </td>
281
+ </tr>
282
+ </table>
283
+ </div>
284
+
285
+ </div>
286
+
287
+ </div>
288
+
289
+ <div id="footer">
290
+ Generated on Sun Jul 14 19:35:06 2019 by
291
+ <a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
292
+ 0.9.20 (ruby-2.6.3).
293
+ </div>
294
+
295
+ </div>
296
+ </body>
297
+ </html>
@@ -0,0 +1,319 @@
1
+ <!DOCTYPE html>
2
+ <html>
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
6
+ <title>
7
+ Class: Html2rss::ItemExtractors::Href
8
+
9
+ &mdash; Documentation by YARD 0.9.20
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
+ pathId = "Html2rss::ItemExtractors::Href";
19
+ relpath = '../../';
20
+ </script>
21
+
22
+
23
+ <script type="text/javascript" charset="utf-8" src="../../js/jquery.js"></script>
24
+
25
+ <script type="text/javascript" charset="utf-8" src="../../js/app.js"></script>
26
+
27
+
28
+ </head>
29
+ <body>
30
+ <div class="nav_wrap">
31
+ <iframe id="nav" src="../../class_list.html?1"></iframe>
32
+ <div id="resizer"></div>
33
+ </div>
34
+
35
+ <div id="main" tabindex="-1">
36
+ <div id="header">
37
+ <div id="menu">
38
+
39
+ <a href="../../_index.html">Index (H)</a> &raquo;
40
+ <span class='title'><span class='object_link'><a href="../../Html2rss.html" title="Html2rss (module)">Html2rss</a></span></span> &raquo; <span class='title'><span class='object_link'><a href="../ItemExtractors.html" title="Html2rss::ItemExtractors (module)">ItemExtractors</a></span></span>
41
+ &raquo;
42
+ <span class="title">Href</span>
43
+
44
+ </div>
45
+
46
+ <div id="search">
47
+
48
+ <a class="full_list_link" id="class_list_link"
49
+ href="../../class_list.html">
50
+
51
+ <svg width="24" height="24">
52
+ <rect x="0" y="4" width="24" height="4" rx="1" ry="1"></rect>
53
+ <rect x="0" y="12" width="24" height="4" rx="1" ry="1"></rect>
54
+ <rect x="0" y="20" width="24" height="4" rx="1" ry="1"></rect>
55
+ </svg>
56
+ </a>
57
+
58
+ </div>
59
+ <div class="clear"></div>
60
+ </div>
61
+
62
+ <div id="content"><h1>Class: Html2rss::ItemExtractors::Href
63
+
64
+
65
+
66
+ </h1>
67
+ <div class="box_info">
68
+
69
+ <dl>
70
+ <dt>Inherits:</dt>
71
+ <dd>
72
+ <span class="inheritName">Object</span>
73
+
74
+ <ul class="fullTree">
75
+ <li>Object</li>
76
+
77
+ <li class="next">Html2rss::ItemExtractors::Href</li>
78
+
79
+ </ul>
80
+ <a href="#" class="inheritanceTree">show all</a>
81
+
82
+ </dd>
83
+ </dl>
84
+
85
+
86
+
87
+
88
+
89
+
90
+
91
+
92
+
93
+
94
+
95
+ <dl>
96
+ <dt>Defined in:</dt>
97
+ <dd>lib/html2rss/item_extractors/href.rb</dd>
98
+ </dl>
99
+
100
+ </div>
101
+
102
+ <h2>Overview</h2><div class="docstring">
103
+ <div class="discussion">
104
+
105
+ <p>Returns the value of the <code>href</code> attribute. It always returns absolute URLs. If the extracted <code>href</code> value is a relative URL, it prepends the channel&#39;s URL.</p>
106
+
107
+ <p>Imagine this <code>a</code> HTML element with a <code>href</code> attribute:</p>
108
+
109
+ <pre class="code ruby"><code class="ruby">&lt;a href=&quot;/posts/latest-findings&quot;&gt;...&lt;/a&gt;
110
+ </code></pre>
111
+
112
+ <p>YAML usage example:</p>
113
+
114
+ <pre class="code ruby"><code class="ruby">channel:
115
+ url: http://blog-without-a-feed.example.com
116
+ ...
117
+ selectors:
118
+ link:
119
+ selector: a
120
+ extractor: href
121
+ </code></pre>
122
+
123
+ <p>Would return:</p>
124
+
125
+ <pre class="code ruby"><code class="ruby"><span class='tstring'><span class='tstring_beg'>&#39;</span><span class='tstring_content'>http://blog-without-a-feed.example.com/posts/latest-findings</span><span class='tstring_end'>&#39;</span></span>
126
+ </code></pre>
127
+
128
+
129
+ </div>
130
+ </div>
131
+ <div class="tags">
132
+
133
+
134
+ </div>
135
+
136
+
137
+
138
+
139
+
140
+
141
+
142
+ <h2>
143
+ Instance Method Summary
144
+ <small><a href="#" class="summary_toggle">collapse</a></small>
145
+ </h2>
146
+
147
+ <ul class="summary">
148
+
149
+ <li class="public ">
150
+ <span class="summary_signature">
151
+
152
+ <a href="#get-instance_method" title="#get (instance method)">#<strong>get</strong> &#x21d2; URI::HTTPS, URI::HTTP </a>
153
+
154
+
155
+
156
+ </span>
157
+
158
+
159
+
160
+
161
+
162
+
163
+
164
+
165
+
166
+ <span class="summary_desc"><div class='inline'></div></span>
167
+
168
+ </li>
169
+
170
+
171
+ <li class="public ">
172
+ <span class="summary_signature">
173
+
174
+ <a href="#initialize-instance_method" title="#initialize (instance method)">#<strong>initialize</strong>(xml, options) &#x21d2; Href </a>
175
+
176
+
177
+
178
+ </span>
179
+
180
+
181
+ <span class="note title constructor">constructor</span>
182
+
183
+
184
+
185
+
186
+
187
+
188
+
189
+
190
+ <span class="summary_desc"><div class='inline'>
191
+ <p>A new instance of Href.</p>
192
+ </div></span>
193
+
194
+ </li>
195
+
196
+
197
+ </ul>
198
+
199
+
200
+ <div id="constructor_details" class="method_details_list">
201
+ <h2>Constructor Details</h2>
202
+
203
+ <div class="method_details first">
204
+ <h3 class="signature first" id="initialize-instance_method">
205
+
206
+ #<strong>initialize</strong>(xml, options) &#x21d2; <tt><span class='object_link'><a href="" title="Html2rss::ItemExtractors::Href (class)">Href</a></span></tt>
207
+
208
+
209
+
210
+
211
+
212
+ </h3><div class="docstring">
213
+ <div class="discussion">
214
+
215
+ <p>Returns a new instance of Href</p>
216
+
217
+
218
+ </div>
219
+ </div>
220
+ <div class="tags">
221
+
222
+
223
+ </div><table class="source_code">
224
+ <tr>
225
+ <td>
226
+ <pre class="lines">
227
+
228
+
229
+ 24
230
+ 25
231
+ 26
232
+ 27
233
+ 28</pre>
234
+ </td>
235
+ <td>
236
+ <pre class="code"><span class="info file"># File 'lib/html2rss/item_extractors/href.rb', line 24</span>
237
+
238
+ <span class='kw'>def</span> <span class='id identifier rubyid_initialize'>initialize</span><span class='lparen'>(</span><span class='id identifier rubyid_xml'>xml</span><span class='comma'>,</span> <span class='id identifier rubyid_options'>options</span><span class='rparen'>)</span>
239
+ <span class='ivar'>@options</span> <span class='op'>=</span> <span class='id identifier rubyid_options'>options</span>
240
+ <span class='id identifier rubyid_element'>element</span> <span class='op'>=</span> <span class='const'><span class='object_link'><a href="../ItemExtractors.html" title="Html2rss::ItemExtractors (module)">ItemExtractors</a></span></span><span class='period'>.</span><span class='id identifier rubyid_element'><span class='object_link'><a href="../ItemExtractors.html#element-class_method" title="Html2rss::ItemExtractors.element (method)">element</a></span></span><span class='lparen'>(</span><span class='id identifier rubyid_xml'>xml</span><span class='comma'>,</span> <span class='id identifier rubyid_options'>options</span><span class='rparen'>)</span>
241
+ <span class='ivar'>@href</span> <span class='op'>=</span> <span class='id identifier rubyid_element'>element</span><span class='period'>.</span><span class='id identifier rubyid_attr'>attr</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>&#39;</span><span class='tstring_content'>href</span><span class='tstring_end'>&#39;</span></span><span class='rparen'>)</span><span class='period'>.</span><span class='id identifier rubyid_to_s'>to_s</span>
242
+ <span class='kw'>end</span></pre>
243
+ </td>
244
+ </tr>
245
+ </table>
246
+ </div>
247
+
248
+ </div>
249
+
250
+
251
+ <div id="instance_method_details" class="method_details_list">
252
+ <h2>Instance Method Details</h2>
253
+
254
+
255
+ <div class="method_details first">
256
+ <h3 class="signature first" id="get-instance_method">
257
+
258
+ #<strong>get</strong> &#x21d2; <tt>URI::HTTPS</tt>, <tt>URI::HTTP</tt>
259
+
260
+
261
+
262
+
263
+
264
+ </h3><div class="docstring">
265
+ <div class="discussion">
266
+
267
+
268
+ </div>
269
+ </div>
270
+ <div class="tags">
271
+
272
+ <p class="tag_title">Returns:</p>
273
+ <ul class="return">
274
+
275
+ <li>
276
+
277
+
278
+ <span class='type'>(<tt>URI::HTTPS</tt>, <tt>URI::HTTP</tt>)</span>
279
+
280
+
281
+
282
+ </li>
283
+
284
+ </ul>
285
+
286
+ </div><table class="source_code">
287
+ <tr>
288
+ <td>
289
+ <pre class="lines">
290
+
291
+
292
+ 31
293
+ 32
294
+ 33</pre>
295
+ </td>
296
+ <td>
297
+ <pre class="code"><span class="info file"># File 'lib/html2rss/item_extractors/href.rb', line 31</span>
298
+
299
+ <span class='kw'>def</span> <span class='id identifier rubyid_get'>get</span>
300
+ <span class='id identifier rubyid_href'>href</span><span class='period'>.</span><span class='id identifier rubyid_start_with?'>start_with?</span><span class='lparen'>(</span><span class='tstring'><span class='tstring_beg'>&#39;</span><span class='tstring_content'>http</span><span class='tstring_end'>&#39;</span></span><span class='rparen'>)</span> <span class='op'>?</span> <span class='id identifier rubyid_absolute_url'>absolute_url</span> <span class='op'>:</span> <span class='id identifier rubyid_build_absolute_url_from_relative'>build_absolute_url_from_relative</span>
301
+ <span class='kw'>end</span></pre>
302
+ </td>
303
+ </tr>
304
+ </table>
305
+ </div>
306
+
307
+ </div>
308
+
309
+ </div>
310
+
311
+ <div id="footer">
312
+ Generated on Sun Jul 14 19:35:05 2019 by
313
+ <a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
314
+ 0.9.20 (ruby-2.6.3).
315
+ </div>
316
+
317
+ </div>
318
+ </body>
319
+ </html>