RubyGems - pstuteville-scrubyt - Versions diffs - 0.4.31 → 0.5.0 - Mend

pstuteville-scrubyt 0.4.31 → 0.5.0

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 (462) hide show

data/examples/misc/rubyforge_login/test.rb DELETED Viewed

@@ -1,30 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../lib')
-require 'scrubyt'
-#Example of: - logging to an account - rubyforge.org this time
-#            - submitting the form with a button
-#
-#Goal:       Go to 'http://rubyforge.org/' and login. Once you are inside,
-#            scrape something not really interesting just to show you are in!
-#Solution:   Go to rubyforge.org and click on the 'Log In' link. This gets you to the
-#            login page, where you fill in the appropriate textfields.
-#            Submitting the textfield once everything is setup up for the show is a bit
-#            different this time - since a simple form.submit does not work. You have
-#            to submit the form by pressing a button. The solution is to specify the index
-#            of the button which should be pressed.
-rubyforge_data = Scrubyt::Extractor.define do
-  fetch          'http://rubyforge.org/'
-  click_link     'Log In'
-  fill_textfield 'form_loginname', '*login_here*'
-  fill_textfield 'form_pw', '*pass_here*'
-  submit 0
-  stuff 'My Personal Page'
-end
-rubyforge_data.to_xml.write($stdout, 1)
-Scrubyt::ResultDumper.print_statistics(rubyforge_data)

data/examples/misc/tables/ambigous_records/input.html DELETED Viewed

@@ -1,17 +0,0 @@
-<html>
-  <body>
-    <table>
-      <tr>
-        <td>Ruby</td>
-        <tb>Python</tb>
-      </tr>
-      <tr>
-        <td><b>Java</b></td>
-        <td>C#</td>
-      </tr>
-      <tr>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/ambigous_records/test.rb DELETED Viewed

@@ -1,37 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../../lib')
-require 'scrubyt'
-#Example of:
-#  - Sepecyfiing multiple examples
-#
-#Goal:       From this simple table, scrape the languages and their rivals, into
-#            a structure like
-#
-#            <language_war>
-#              <lang>Ruby</lang>
-#              <rival>Python</rival>
-#            </language_war>
-#
-#            Try it as you would normally - i.e. just supply lang the example 'Ruby'
-#            and rival the example 'Python' and it won't work. This is because
-#            in the document, the other two semantically similar records (Java and
-#            C#) are contained at different places in the structure. This is a dummy
-#            example, but in the real life you have this with a lot of webshops
-#            and other pages as well.
-#
-#Solution:   Specify multiple examples as in the example below - until you get
-#            everything you need (i.e. theoretically you can specify even
-#            12345 examples, however that would be unmaintainable :-))
-ambigous_data = Scrubyt::Extractor.define do
-  fetch File.join(File.dirname(__FILE__), "input.html")
-  #Construct the wrapper
-  language_war do
-    lang  'Ruby', 'Java'
-    rival 'Python', 'C#'
-  end
-end
-ambigous_data.to_xml.write($stdout, 1)
-Scrubyt::ResultDumper.print_statistics(ambigous_data)

data/examples/misc/tables/another_plain_table/input.html DELETED Viewed

@@ -1,15 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>1, 2, 3</td>
-        <td>Vancouver, Quebec</td>
-      </tr>
-      <tr>
-        <td>London and Vienna and Prague</td>
-        <td>1, Spam, 3, Ham</td>
-        <td>Just a simple text cell</td>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/another_plain_table/test.rb DELETED Viewed

@@ -1,25 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../../lib')
-require 'scrubyt'
-#Example of:
-#  - using a regexp pattern
-#
-#Goal:      Extract the numbers one by one from the pattern 'cell'
-#Solution:  Add a regexp pattern to the pattern 'cell'.
-table_data = Scrubyt::Extractor.define do
-  #Perform the action(s)
-  fetch File.join(File.dirname(__FILE__), "input.html")
-  #Construct the wrapper
-  table do
-    row :generalize => true do
-      cell '1, 2, 3', :generalize => true do
-        numbers /\d+/
-      end
-    end
-  end
-end
-table_data.to_xml.write($stdout, 1)
-Scrubyt::ResultDumper.print_statistics(table_data)

data/examples/misc/tables/complex_table/input.html DELETED Viewed

@@ -1,45 +0,0 @@
-<html>
-  <body>
-    <table>
-      <tr>
-        <td>The Matrix</td>
-        <td>Neo</td>
-      </tr>
-      <tr>
-        <td>Star Wars</td>
-        <td>Luke Skywalker</td>
-      </tr>
-      <tr>
-        <td>Garfield</td>
-      </tr>
-      <tr>
-        <td>Saw</td>
-        <td>Jigsaw</td>
-      </tr>
-      <tr>
-        <td>Pirates of the Caribbean</td>
-        <td><b>Jack Sparrow<b></td>
-      </tr>
-      <tr>
-        <td>Pirates of the Amazonas</td>
-      </tr>
-      <tr></tr>
-      <tr><td>Starsky & Hutch</td></tr>
-      <tr><h1>The coolest stuff</h1>
-        <td>Test cell</td>
-        <td>
-        <table>
-          <tr>
-            <td>Kill Bill</td>
-            <td>The Bride</td>
-          </tr>
-          <tr>
-            <td>Kill Bill, vol 2.</td>
-            <td>Beatrix Kiddo</td>
-          </tr>
-        </table>
-        </td>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/complex_table/test.rb DELETED Viewed

@@ -1,30 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../../lib')
-require 'scrubyt'
-#Example of:
-#  - Sepecyfying multiple examples
-#  - Narrowig the results by requiring the presence of some patterns
-#
-#Goal:      We want to extract all movies, containing their title and their
-#           main_character. Moreover, we need only those movies which
-#           have both the title and the main_character specified
-#
-#Solution:  See the ambigous_records example on why to use multiple examples.
-#           Use the ensure_presence_of_pattern constraint to extract only
-#           those movies which have child patterns named 'title' and
-#           'main_character'
-table_data_comp = Scrubyt::Extractor.define do
-  #Perform the action(s)
-  fetch File.join(File.dirname(__FILE__), "input.html")
-  #Construct the wrapper
-    movie do
-      title 'The Matrix', 'Kill Bill'
-      main_character 'Neo', 'The Bride'
-    end.ensure_presence_of_pattern('title').
-        ensure_presence_of_pattern('main_character')
-end
-table_data_comp.to_xml.write($stdout, 1)
-Scrubyt::ResultDumper.print_statistics(table_data_comp)

data/examples/misc/tables/grab_rows/input.html DELETED Viewed

@@ -1,20 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>1</td>
-        <td>2</td>
-        <td>3</td>
-        <td>4</td>
-        <td>5</td>
-        <td>6</td>
-        <td>7</td>
-        <td>8</td>
-        <td>9</td>
-        <td>10</td>
-        <td>11</td>
-        <td>12</td>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/grab_rows/test.rb DELETED Viewed

@@ -1,30 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../../lib')
-require 'scrubyt'
-#Example of:
-#  - Extracting some (specific) rows from a table
-#  - Using the :generalize option
-#  - Using the select_indices function
-#
-#Goal:      Extract the first, 4th, 5th and last row from the input table
-#
-#Solution:  Since by default only the root child(ren) of the extractor
-#           is/are generalized, and we need every <tr> (so we can select the ones we need)
-#           we have to set :generalize => true.
-#           Once we have all the indices, we select the relevant ones with the 'select_indices'
-#           function.
-table_data = Scrubyt::Extractor.define do
-  #Perform the action(s)
-  fetch File.join(File.dirname(__FILE__), "input.html")
-  #Construct the wrapper
-  table do
-    row :generalize => true do
-      value('1', :generalize => true).select_indices([3..4, :first,:last])
-    end
-  end
-end
-table_data.to_xml.write($stdout, 1)
-Scrubyt::ResultDumper.print_statistics(table_data)

data/examples/misc/tables/plain_table/input.html DELETED Viewed

@@ -1,39 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>1</td>
-        <td>2</td>
-      </tr>
-      <tr>
-        <td>3</td>
-        <td>4</td>
-        <td>5</td>
-      </tr>
-    </table>
-    <br/>
-    <table border=1 padding=10>
-      <tr>
-        <td>6</td>
-      </tr>
-      <tr>
-        <td>7</td>
-      </tr>
-      <tr>
-        <td>8</td>
-      </tr>
-    </table>
-    <br>
-    <table border=1 padding=10>
-      <tr>
-        <td>9</td>
-	<td>10</td>
-      </tr>
-      <tr>
-      </tr>
-      <tr>
-        <td>11</td>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/plain_table/test.rb DELETED Viewed

@@ -1,35 +0,0 @@
-$:.unshift File.join(File.dirname(__FILE__), '../../../../lib')
-require 'scrubyt'
-#Example of:
-#  - Extracting every td from a table
-#  - Using the :generalize option
-#
-#Goal:      Extract every td from all tables on the page
-#
-#Solution:  Since by default only the root child(ren) of the extractor
-#           is/are generalized, and we need every <td> in every <tr>, we
-#           need to generalize the patterns that extracted them, too.
-#           To achieve this, use the the :generalize option as shown below!
-#
-table_data = Scrubyt::Extractor.define do
-  #Perform the action(s)
-  fetch File.join(File.dirname(__FILE__), "input.html")
-  #Construct the wrapper
-  table do
-    row :generalize => true do
-      value '1', :generalize => true
-    end.ensure_presence_of_pattern('value')
-  end
-end
-table_data.to_xml.write($stdout, 1)
-#puts table_data.table[1].row[0].value[0].to_text
-Scrubyt::ResultDumper.print_statistics(table_data)
-#table_data.export(__FILE__)

data/examples/misc/tables/plain_table_morepages/2.html DELETED Viewed

@@ -1,38 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>12</td>
-        <td>13</td>
-        <td>14</td>
-        <td>15</td>
-      </tr>
-      <tr>
-        <td>16</td>
-      </tr>
-    </table>
-    <br/>
-    <table border=1 padding=10>
-      <tr>
-        <td>17</td>
-        <td>18</td>
-      </tr>
-      <tr>
-        <td>19</td>
-      </tr>
-    </table>
-    <br>
-    <table border=1 padding=10>
-      <tr>
-        <td>20</td>
-	<td>21</td>
-      </tr>
-      <tr>
-      </tr>
-      <tr>
-        <td>22</td>
-      </tr>
-    </table>
-    <a href='3.html'>Next</a>
-  </body>
-</html>

data/examples/misc/tables/plain_table_morepages/3.html DELETED Viewed

@@ -1,33 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>23</td>
-        <td>24</td>
-        <td>25</td>
-      </tr>
-    </table>
-    <br/>
-    <table border=1 padding=10>
-      <tr>
-        <td>26</td>
-      </tr>
-      <tr>
-        <td>27</td>
-        <td>28</td>
-      </tr>
-    </table>
-    <br>
-    <table border=1 padding=10>
-      <tr>
-        <td>29</td>
-	<td>30</td>
-      </tr>
-      <tr>
-      </tr>
-      <tr>
-        <td>31</td>
-      </tr>
-    </table>
-  </body>
-</html>

data/examples/misc/tables/plain_table_morepages/input.html DELETED Viewed

@@ -1,40 +0,0 @@
-<html>
-  <body>
-    <table border=1 padding=10>
-      <tr>
-        <td>1</td>
-        <td>2</td>
-      </tr>
-      <tr>
-        <td>3</td>
-        <td>4</td>
-        <td>5</td>
-      </tr>
-    </table>
-    <br/>
-    <table border=1 padding=10>
-      <tr>
-        <td>6</td>
-      </tr>
-      <tr>
-        <td>7</td>
-      </tr>
-      <tr>
-        <td>8</td>
-      </tr>
-    </table>
-    <br>
-    <table border=1 padding=10>
-      <tr>
-        <td>9</td>
-	<td>10</td>
-      </tr>
-      <tr>
-      </tr>
-      <tr>
-        <td>11</td>
-      </tr>
-    </table>
-    <a href='2.html'>Next</a>
-  </body>
-</html>