scrappy 0.3.0 → 0.3.1

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 (38) hide show
  1. data/History.txt +6 -0
  2. data/Manifest +21 -14
  3. data/README.rdoc +5 -9
  4. data/Rakefile +1 -2
  5. data/bin/scrappy +141 -51
  6. data/lib/scrappy.rb +6 -9
  7. data/lib/scrappy/agent/agent.rb +3 -3
  8. data/lib/scrappy/extractor/extractor.rb +108 -0
  9. data/lib/scrappy/{agent → extractor}/formats.rb +0 -0
  10. data/lib/scrappy/extractor/fragment.rb +111 -0
  11. data/lib/scrappy/extractor/selector.rb +41 -0
  12. data/lib/scrappy/{selectors → extractor/selectors}/base_uri.rb +1 -3
  13. data/lib/scrappy/extractor/selectors/css.rb +5 -0
  14. data/lib/scrappy/{selectors → extractor/selectors}/new_uri.rb +1 -3
  15. data/lib/scrappy/{selectors → extractor/selectors}/root.rb +1 -4
  16. data/lib/scrappy/{selectors → extractor/selectors}/section.rb +1 -4
  17. data/lib/scrappy/{selectors → extractor/selectors}/slice.rb +1 -3
  18. data/lib/scrappy/{selectors → extractor/selectors}/uri.rb +2 -4
  19. data/lib/scrappy/{selectors → extractor/selectors}/uri_pattern.rb +2 -4
  20. data/lib/scrappy/extractor/selectors/visual.rb +39 -0
  21. data/lib/scrappy/{selectors → extractor/selectors}/xpath.rb +1 -4
  22. data/lib/scrappy/server/admin.rb +89 -2
  23. data/lib/scrappy/server/helpers.rb +11 -2
  24. data/lib/scrappy/server/server.rb +1 -0
  25. data/lib/scrappy/trainer/trainer.rb +101 -0
  26. data/public/javascripts/annotator.js +75 -0
  27. data/public/javascripts/remote.js +132 -0
  28. data/public/stylesheets/application.css +39 -12
  29. data/scrappy.gemspec +13 -11
  30. data/views/extractors.haml +24 -0
  31. data/views/layout.haml +14 -4
  32. data/views/patterns.haml +19 -0
  33. data/views/samples.haml +28 -0
  34. metadata +58 -56
  35. data/lib/scrappy/agent/extractor.rb +0 -196
  36. data/lib/scrappy/selectors/css.rb +0 -10
  37. data/public/javascripts/scrappy.js +0 -65
  38. data/views/kb.haml +0 -15
@@ -1,10 +0,0 @@
1
- module Sc
2
- class CssSelector
3
- include RDF::NodeProxy
4
-
5
- def filter doc
6
- # By using Nokogiri, CSS and XPath use the same search method
7
- Sc::XPathSelector.new(node).filter doc
8
- end
9
- end
10
- end
@@ -1,65 +0,0 @@
1
- add_visual_data = function() {
2
- var items = document.documentElement.getElementsByTagName('*');
3
- var i=0;
4
- for(var i=0; i<items.length; i++) {
5
- var item = items[i];
6
- item.setAttribute('vx', item.offsetLeft);
7
- item.setAttribute('vy', item.offsetTop);
8
- item.setAttribute('vw', item.offsetWidth);
9
- item.setAttribute('vh', item.offsetHeight);
10
- item.setAttribute('vsize', document.defaultView.getComputedStyle(item, null).getPropertyValue('font-size'));
11
- var weight = document.defaultView.getComputedStyle(item, null).getPropertyValue('font-weight');
12
- if (weight == 'normal') weight = 400;
13
- if (weight == 'bold') weight = 700;
14
- item.setAttribute('vweight', weight);
15
- item.setAttribute('vcolor', document.defaultView.getComputedStyle(item, null).getPropertyValue('color'));
16
- item.setAttribute('vbcolor', document.defaultView.getComputedStyle(item, null).getPropertyValue('background-color'));
17
- }
18
- }
19
-
20
- $(document).ready(function(){
21
- $("body").append("<div id='myTrees'></div>")
22
- $("#page > *").bind('mouseover', function(e){
23
- e.stopPropagation();
24
- $(this).addClass("changeBg");
25
- })
26
- .mouseout(function(){
27
- $(this).removeClass("changeBg");
28
- });
29
- });
30
-
31
- $(document).ready(function(){
32
- $("*").bind('click', function(e){
33
- e.stopPropagation();
34
- var element = $(e.target).closest(this.tagName).get(0).tagName;
35
- var parents = $(this).parents();
36
- var string = element.toString();
37
- for(j=0;j<parents.length;j++) {
38
- string = string + " " + parents[j].tagName;
39
- }
40
-
41
- var tree = [];
42
- var treeString = "";
43
- for(h=parents.length-1; h>=0; h-- ) {
44
- tree.push(parents[h].tagName);
45
-
46
- if( treeString == "" ) {
47
- treeString = treeString + parents[h].tagName;
48
- } else {
49
- treeString = treeString + " > " + parents[h].tagName;
50
- }
51
- }
52
-
53
- tree.push(element);
54
- treeString = treeString + " > " + element;
55
-
56
- var myTrees = document.getElementById("myTrees");
57
- var ul = document.createElement("ul");
58
- var li = document.createElement("li");
59
- myTrees.appendChild(ul);
60
- li.innerHTML = treeString;
61
- myTrees.appendChild(li);
62
- });
63
- });
64
-
65
- window.scrappy_loaded = true
data/views/kb.haml DELETED
@@ -1,15 +0,0 @@
1
- #body
2
- %h1 Knowledge base
3
- %p
4
- %ul.detail
5
- -@uris.each do |uri|
6
- %li
7
- %span.name
8
- -if !uri.include?('*')
9
- %a{:href=>uri}=uri
10
- -else
11
- =uri
12
- -if !uri.include?('*')
13
- -[['RDF', :rdf], ['JSON', :ejson], ['YARF', :yarf], ['nTriples', :ntriples], ['PNG', :png]].reverse.each do |format, format_code|
14
- %span.format
15
- %a{:href=>"#{settings.base_uri}/#{format_code}/#{uri}"}=format