scrubyt 0.4.1 → 0.4.05
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +3 -12
- data/Rakefile +6 -6
- data/lib/scrubyt/core/navigation/agents/firewatir.rb +5 -36
- data/lib/scrubyt/core/navigation/agents/mechanize.rb +5 -10
- data/lib/scrubyt/core/navigation/navigation_actions.rb +5 -17
- data/lib/scrubyt/core/scraping/filters/attribute_filter.rb +3 -0
- data/lib/scrubyt/core/scraping/filters/constant_filter.rb +3 -0
- data/lib/scrubyt/core/scraping/filters/detail_page_filter.rb +4 -0
- data/lib/scrubyt/core/scraping/filters/download_filter.rb +4 -0
- data/lib/scrubyt/core/scraping/filters/html_subtree_filter.rb +3 -0
- data/lib/scrubyt/core/scraping/filters/regexp_filter.rb +4 -0
- data/lib/scrubyt/core/scraping/filters/script_filter.rb +3 -0
- data/lib/scrubyt/core/scraping/filters/text_filter.rb +3 -0
- data/lib/scrubyt/core/scraping/filters/tree_filter.rb +8 -0
- data/lib/scrubyt/core/scraping/pattern.rb +26 -1
- data/lib/scrubyt/core/scraping/result_indexer.rb +4 -0
- metadata +3 -3
data/CHANGELOG
CHANGED
@@ -1,20 +1,15 @@
|
|
1
1
|
= scRUBYt! Changelog
|
2
2
|
|
3
3
|
== 0.4.05
|
4
|
-
==
|
4
|
+
== 14th November
|
5
5
|
|
6
6
|
=<tt>changes:</tt>
|
7
|
-
- [NEW] possibility to use FireWatir as the agent for scraping (credit:
|
7
|
+
- [NEW] possibility to use FireWatir as the agent for scraping (credit: Glen Gillen)
|
8
8
|
- [FIX] navigation doesn't crash if a 404/500 is returned (credit: Glen Gillen)
|
9
|
-
- [NEW] navigation
|
9
|
+
- [NEW] navigation actions: click_by_xpath, click_link_and_wait
|
10
10
|
- [MOD] dropped dependencies: RubyInline, ParseTree, Ruby2Ruby (hooray for win32 users)
|
11
|
-
- [NEW] scraping through frames (e.g. google analytics)
|
12
11
|
- [MOD] exporting temporarily doesn't work - for now, generated XPaths are printed to the screen
|
13
|
-
- [MOD] possibility to wait after clicking link/filling textfield (to be able to scrape inserted AJAX stuff)
|
14
|
-
- [NEW] possibility to fetch from a string, by specifying nil as the url and the html string with the :html option
|
15
|
-
- [FIX] firewatir slowness (credit: jak4)
|
16
12
|
- [FIX] lot of bugfixes and stability fixes
|
17
|
-
-
|
18
13
|
|
19
14
|
== 0.4.0 (unofficial)
|
20
15
|
=== 31st October, 2007
|
@@ -27,10 +22,6 @@
|
|
27
22
|
== 0.3.4
|
28
23
|
=== 26th September, 2007
|
29
24
|
|
30
|
-
=<tt>changes:</tt>
|
31
|
-
It seems I have been too busy to update the changelog ;)
|
32
|
-
|
33
|
-
|
34
25
|
== 0.3.1
|
35
26
|
=== 29th May, 2007
|
36
27
|
|
data/Rakefile
CHANGED
@@ -17,7 +17,7 @@ task "cleanup_readme" => ["rdoc"]
|
|
17
17
|
|
18
18
|
gem_spec = Gem::Specification.new do |s|
|
19
19
|
s.name = 'scrubyt'
|
20
|
-
s.version = '0.4.
|
20
|
+
s.version = '0.4.05'
|
21
21
|
s.summary = 'A powerful Web-scraping framework built on Mechanize and Hpricot (and FireWatir)'
|
22
22
|
s.description = %{scRUBYt! is an easy to learn and use, yet powerful and effective web scraping framework. It's most interesting part is a Web-scraping DSL built on HPricot and WWW::Mechanize, which allows to navigate to the page of interest, then extract and query data records with a few lines of code. It is hard to describe scRUBYt! in a few sentences - you have to see it for yourself!}
|
23
23
|
# Files containing Test::Unit test cases.
|
@@ -94,8 +94,8 @@ Rake::GemPackageTask.new(gem_spec) do |pkg|
|
|
94
94
|
pkg.need_tar = false
|
95
95
|
end
|
96
96
|
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
97
|
+
Rake::PackageTask.new('scrubyt-examples', gem_spec.version) do |pkg|
|
98
|
+
pkg.need_zip = true
|
99
|
+
pkg.need_tar = true
|
100
|
+
pkg.package_files.include("examples/**/*")
|
101
|
+
end
|
@@ -21,7 +21,6 @@ module Scrubyt
|
|
21
21
|
@@host_name = nil
|
22
22
|
@@history = []
|
23
23
|
@@current_form = nil
|
24
|
-
@@current_frame = nil
|
25
24
|
|
26
25
|
##
|
27
26
|
#Action to fetch a document (either a file or a http address)
|
@@ -59,33 +58,12 @@ module Scrubyt
|
|
59
58
|
@@hpricot_doc = Hpricot(PreFilterDocument.br_to_newline(@@mechanize_doc))
|
60
59
|
store_host_name(@@agent.url) # in case we're on a new host
|
61
60
|
end
|
62
|
-
|
63
|
-
def self.frame(attribute, value)
|
64
|
-
if @@current_frame
|
65
|
-
@@current_frame.frame(attribute, value)
|
66
|
-
else
|
67
|
-
@@current_frame = @@agent.frame(attribute, value)
|
68
|
-
end
|
69
|
-
end
|
70
61
|
|
71
62
|
##
|
72
63
|
#Submit the last form;
|
73
|
-
def self.submit(current_form,
|
74
|
-
|
75
|
-
|
76
|
-
#this sucks FAIL omg
|
77
|
-
@@current_frame.locate
|
78
|
-
form = Document.new(@@current_frame).all.find{|t| t.tagName=="FORM"}
|
79
|
-
form.submit
|
80
|
-
else
|
81
|
-
@@agent.element_by_xpath(@@current_form).submit
|
82
|
-
end
|
83
|
-
|
84
|
-
if sleep_time
|
85
|
-
sleep sleep_time
|
86
|
-
@@agent.wait
|
87
|
-
end
|
88
|
-
|
64
|
+
def self.submit(current_form, button=nil, type=nil)
|
65
|
+
@@agent.element_by_xpath(@@current_form).submit
|
66
|
+
@@agent.wait
|
89
67
|
@@current_doc_url = @@agent.url
|
90
68
|
@@mechanize_doc = "<html>#{@@agent.html}</html>"
|
91
69
|
@@hpricot_doc = Hpricot(PreFilterDocument.br_to_newline(@@mechanize_doc))
|
@@ -196,18 +174,9 @@ module Scrubyt
|
|
196
174
|
end
|
197
175
|
end
|
198
176
|
|
199
|
-
def self.fill_textfield(textfield_name, query_string
|
177
|
+
def self.fill_textfield(textfield_name, query_string)
|
200
178
|
@@current_form = "//input[@name='#{textfield_name}']/ancestor::form"
|
201
|
-
|
202
|
-
if useValue
|
203
|
-
target.text_field(:name,textfield_name).value = query_string
|
204
|
-
else
|
205
|
-
target.text_field(:name,textfield_name).set(query_string)
|
206
|
-
end
|
207
|
-
sleep(wait_secs) if wait_secs > 0
|
208
|
-
@@mechanize_doc = "<html>#{@@agent.html}</html>"
|
209
|
-
@@hpricot_doc = Hpricot(PreFilterDocument.br_to_newline(@@mechanize_doc))
|
210
|
-
|
179
|
+
@@agent.text_field(:name,textfield_name).set(query_string)
|
211
180
|
end
|
212
181
|
|
213
182
|
##
|
@@ -32,21 +32,16 @@ module Scrubyt
|
|
32
32
|
|
33
33
|
if args.size > 0
|
34
34
|
mechanize_doc = args[0][:mechanize_doc]
|
35
|
-
html = args[0][:html]
|
36
35
|
resolve = args[0][:resolve]
|
37
36
|
basic_auth = args[0][:basic_auth]
|
38
37
|
parse_and_set_basic_auth(basic_auth) if basic_auth
|
39
|
-
if html
|
40
|
-
@@current_doc_protocol = 'string'
|
41
|
-
mechanize_doc = page = WWW::Mechanize::Page.new(nil, {'content-type' => 'text/html'}, html)
|
42
|
-
end
|
43
38
|
else
|
44
39
|
mechanize_doc = nil
|
45
40
|
resolve = :full
|
46
41
|
end
|
47
42
|
|
48
43
|
@@current_doc_url = doc_url
|
49
|
-
@@current_doc_protocol
|
44
|
+
@@current_doc_protocol = determine_protocol
|
50
45
|
|
51
46
|
if mechanize_doc.nil? && @@current_doc_protocol != 'file'
|
52
47
|
handle_relative_path(doc_url)
|
@@ -64,13 +59,13 @@ module Scrubyt
|
|
64
59
|
@@hpricot_doc = Hpricot(PreFilterDocument.br_to_newline(open(@@current_doc_url).read))
|
65
60
|
else
|
66
61
|
@@hpricot_doc = Hpricot(PreFilterDocument.br_to_newline(@@mechanize_doc.body))
|
67
|
-
store_host_name(self.get_current_doc_url)
|
62
|
+
store_host_name(self.get_current_doc_url) # in case we're on a new host
|
68
63
|
end
|
69
64
|
end
|
70
65
|
|
71
66
|
##
|
72
67
|
#Submit the last form;
|
73
|
-
def self.submit(index=nil,
|
68
|
+
def self.submit(index=nil, type=nil)
|
74
69
|
Scrubyt.log :ACTION, 'Submitting form...'
|
75
70
|
if index == nil
|
76
71
|
result_page = @@agent.submit(@@current_form)
|
@@ -91,7 +86,7 @@ module Scrubyt
|
|
91
86
|
|
92
87
|
##
|
93
88
|
#Click the link specified by the text
|
94
|
-
def self.click_link(link_spec,index = 0
|
89
|
+
def self.click_link(link_spec,index = 0)
|
95
90
|
Scrubyt.log :ACTION, "Clicking link specified by: %p" % link_spec
|
96
91
|
if link_spec.is_a? Hash
|
97
92
|
clicked_elem = CompoundExampleLookup.find_node_from_compund_example(@@hpricot_doc, link_spec, false, index)
|
@@ -177,7 +172,7 @@ module Scrubyt
|
|
177
172
|
end
|
178
173
|
end
|
179
174
|
|
180
|
-
def self.fill_textfield(textfield_name, query_string
|
175
|
+
def self.fill_textfield(textfield_name, query_string)
|
181
176
|
lookup_form_for_tag('input','textfield',textfield_name,query_string)
|
182
177
|
eval("@@current_form['#{textfield_name}'] = '#{query_string}'")
|
183
178
|
end
|
@@ -23,12 +23,8 @@ module Scrubyt
|
|
23
23
|
#textfield is 'q'
|
24
24
|
#
|
25
25
|
#_query_string_ - the string that should be entered into the textfield
|
26
|
-
def fill_textfield(textfield_name, query_string
|
27
|
-
FetchAction.fill_textfield(textfield_name, query_string
|
28
|
-
end
|
29
|
-
|
30
|
-
def fill_textfield_and_wait(textfield_name, query_string, sleep_secs=0, use_value=nil)
|
31
|
-
FetchAction.fill_textfield(textfield_name, query_string, sleep_secs, use_value)
|
26
|
+
def fill_textfield(textfield_name, query_string)
|
27
|
+
FetchAction.fill_textfield(textfield_name, query_string)
|
32
28
|
end
|
33
29
|
|
34
30
|
##
|
@@ -59,17 +55,13 @@ module Scrubyt
|
|
59
55
|
##
|
60
56
|
#Submit the current form
|
61
57
|
def submit(index=nil, type=nil)
|
62
|
-
FetchAction.submit(
|
63
|
-
end
|
64
|
-
|
65
|
-
def submit_and_wait(sleep_time, index=nil, type=nil)
|
66
|
-
FetchAction.submit(index, sleep_time, type)
|
58
|
+
FetchAction.submit(index, type)
|
67
59
|
end
|
68
60
|
|
69
61
|
##
|
70
62
|
#Click the link specified by the text
|
71
|
-
def click_link(link_spec,index=0)
|
72
|
-
FetchAction.click_link(link_spec,index,
|
63
|
+
def click_link(link_spec,index=0, sleep_secs=0)
|
64
|
+
FetchAction.click_link(link_spec,index, sleep_secs)
|
73
65
|
end
|
74
66
|
|
75
67
|
def click_link_and_wait(link_spec, sleep_secs=0)
|
@@ -84,10 +76,6 @@ module Scrubyt
|
|
84
76
|
FetchAction.click_image_map(index)
|
85
77
|
end
|
86
78
|
|
87
|
-
def frame(attribute,value)
|
88
|
-
FetchAction.frame(attribute,value)
|
89
|
-
end
|
90
|
-
|
91
79
|
def wait(time=1)
|
92
80
|
FetchAction.wait(time)
|
93
81
|
end
|
@@ -134,5 +134,13 @@ module Scrubyt
|
|
134
134
|
@xpath = XPathUtils.generate_relative_XPath_from_XPaths(parent_xpath, @xpath) if (@xpath =~ /^\/html/) #TODO: should not rely on <html> being the root node
|
135
135
|
end
|
136
136
|
|
137
|
+
def to_sexp
|
138
|
+
if @example =~ /.+\[@.+\]$/
|
139
|
+
[:str, "#{@xpath}/@#{@example.scan(/\[@(.+?)\]/)[0][0]}"]
|
140
|
+
else
|
141
|
+
[:str, @xpath]
|
142
|
+
end
|
143
|
+
end
|
144
|
+
|
137
145
|
end #End of class TreeFilter
|
138
146
|
end #End of module Scrubyt
|
@@ -78,7 +78,6 @@ module Scrubyt
|
|
78
78
|
|
79
79
|
#grab any examples that are defined
|
80
80
|
examples = look_for_examples(args)
|
81
|
-
|
82
81
|
#parse the options hash if provided
|
83
82
|
parse_options_hash(args[-1]) if args[-1].is_a? Hash
|
84
83
|
|
@@ -309,6 +308,32 @@ module Scrubyt
|
|
309
308
|
end
|
310
309
|
end
|
311
310
|
|
311
|
+
def to_sexp
|
312
|
+
#collect arguments
|
313
|
+
args = []
|
314
|
+
args.push(*@filters.to_sexp_array) if type != :detail_page #TODO: this if shouldn't be there
|
315
|
+
args.push(@options.to_sexp) if !@options.empty?
|
316
|
+
|
317
|
+
#build main call
|
318
|
+
sexp = [:fcall, @name, [:array, *args]]
|
319
|
+
|
320
|
+
if type == :detail_page
|
321
|
+
#add detail page extractor
|
322
|
+
sexp = [:iter, sexp, nil, @filters[0].get_detail_sexp]
|
323
|
+
else
|
324
|
+
#add child block if the pattern has children
|
325
|
+
sexp = [:iter, sexp, nil, [:block, *@children.to_sexp_array ]] if !@children.empty?
|
326
|
+
end
|
327
|
+
|
328
|
+
#add modifier calls - TODO: remove when everything is exported to the options hash
|
329
|
+
@modifier_calls.each do |modifier_sexp|
|
330
|
+
sexp = [:call, sexp, *modifier_sexp]
|
331
|
+
end
|
332
|
+
|
333
|
+
#return complete sexp
|
334
|
+
sexp
|
335
|
+
end
|
336
|
+
|
312
337
|
private
|
313
338
|
def parse_options_hash(hash)
|
314
339
|
#merge provided hash
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scrubyt
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.4.
|
4
|
+
version: 0.4.05
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Peter Szinek
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2008-
|
12
|
+
date: 2008-11-15 00:00:00 +01:00
|
13
13
|
default_executable:
|
14
14
|
dependencies:
|
15
15
|
- !ruby/object:Gem::Dependency
|
@@ -100,7 +100,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
100
100
|
requirements: []
|
101
101
|
|
102
102
|
rubyforge_project:
|
103
|
-
rubygems_version: 1.
|
103
|
+
rubygems_version: 1.2.0
|
104
104
|
signing_key:
|
105
105
|
specification_version: 2
|
106
106
|
summary: A powerful Web-scraping framework built on Mechanize and Hpricot (and FireWatir)
|