spidr 0.2.1 → 0.2.2
Sign up to get free protection for your applications and to get access to all the features.
- data.tar.gz.sig +0 -0
- data/History.rdoc +191 -0
- data/Manifest.txt +10 -34
- data/{README.txt → README.rdoc} +3 -1
- data/Rakefile +6 -4
- data/lib/spidr/agent.rb +137 -97
- data/lib/spidr/auth_credential.rb +25 -0
- data/lib/spidr/auth_store.rb +157 -0
- data/lib/spidr/cookie_jar.rb +166 -0
- data/lib/spidr/filters.rb +2 -0
- data/lib/spidr/page.rb +75 -11
- data/lib/spidr/sanitizers.rb +59 -0
- data/lib/spidr/session_cache.rb +119 -0
- data/lib/spidr/version.rb +1 -1
- data/spec/agent_spec.rb +2 -2
- data/spec/helpers/history.rb +34 -0
- data/spec/helpers/wsoc.rb +83 -0
- data/spec/page_examples.rb +5 -1
- data/spec/page_spec.rb +30 -0
- data/spec/sanitizers_spec.rb +67 -0
- data/tasks/yard.rb +1 -1
- metadata +24 -40
- metadata.gz.sig +0 -0
- data/History.txt +0 -167
- data/spec/helpers/course.rb +0 -95
- data/static/course/absolute/index.html +0 -10
- data/static/course/absolute/next.html +0 -9
- data/static/course/absolute/start.html +0 -19
- data/static/course/empty/index.html +0 -10
- data/static/course/empty/start.html +0 -23
- data/static/course/fail.html +0 -14
- data/static/course/frames/frame.html +0 -15
- data/static/course/frames/frame_next.html +0 -9
- data/static/course/frames/iframe.html +0 -15
- data/static/course/frames/iframe_next.html +0 -9
- data/static/course/frames/index.html +0 -10
- data/static/course/frames/start.html +0 -15
- data/static/course/index.html +0 -10
- data/static/course/javascript/index.html +0 -10
- data/static/course/javascript/start.html +0 -19
- data/static/course/loop/index.html +0 -10
- data/static/course/loop/next.html +0 -13
- data/static/course/loop/start.html +0 -19
- data/static/course/relative/current_directory.html +0 -9
- data/static/course/relative/index.html +0 -10
- data/static/course/relative/normal.html +0 -9
- data/static/course/relative/same_directory.html +0 -9
- data/static/course/relative/start.html +0 -27
- data/static/course/remote/index.html +0 -10
- data/static/course/remote/next.html +0 -9
- data/static/course/remote/start.html +0 -27
- data/static/course/scripts/course.js +0 -29
- data/static/course/scripts/jquery-1.2.6.min.js +0 -32
- data/static/course/specs.json +0 -1
- data/static/course/start.html +0 -27
- data/tasks/course.rb +0 -63
data.tar.gz.sig
CHANGED
Binary file
|
data/History.rdoc
ADDED
@@ -0,0 +1,191 @@
|
|
1
|
+
=== 0.2.2 / 2010-01-06
|
2
|
+
|
3
|
+
* Require Web Spider Obstacle Course (WSOC) >= 0.1.1.
|
4
|
+
* Integrated the new WSOC into the specs.
|
5
|
+
* Removed the built-in Web Spider Obstacle Course.
|
6
|
+
* Added {Spidr::Page#content_types}.
|
7
|
+
* Added {Spidr::Page#cookie}.
|
8
|
+
* Added {Spidr::Page#cookies}.
|
9
|
+
* Added {Spidr::Page#cookie_params}.
|
10
|
+
* Added {Spidr::Sanitizers}.
|
11
|
+
* Added {Spidr::SessionCache}.
|
12
|
+
* Added {Spidr::CookieJar} (thanks Nick Plante).
|
13
|
+
* Added {Spidr::AuthStore} (thanks Nick Plante).
|
14
|
+
* Added {Spidr::Agent#post_page} (thanks Nick Plante).
|
15
|
+
* Renamed Spidr::Agent#get_session to {Spidr::SessionCache#[]}.
|
16
|
+
* Renamed Spidr::Agent#kill_session to {Spidr::SessionCache#kill!}.
|
17
|
+
|
18
|
+
=== 0.2.1 / 2009-11-25
|
19
|
+
|
20
|
+
* Added {Spidr::Events#every_ok_page}.
|
21
|
+
* Added {Spidr::Events#every_redirect_page}.
|
22
|
+
* Added {Spidr::Events#every_timedout_page}.
|
23
|
+
* Added {Spidr::Events#every_bad_request_page}.
|
24
|
+
* Added {Spidr::Events#every_unauthorized_page}.
|
25
|
+
* Added {Spidr::Events#every_forbidden_page}.
|
26
|
+
* Added {Spidr::Events#every_missing_page}.
|
27
|
+
* Added {Spidr::Events#every_internal_server_error_page}.
|
28
|
+
* Added {Spidr::Events#every_txt_page}.
|
29
|
+
* Added {Spidr::Events#every_html_page}.
|
30
|
+
* Added {Spidr::Events#every_xml_page}.
|
31
|
+
* Added {Spidr::Events#every_xsl_page}.
|
32
|
+
* Added {Spidr::Events#every_doc}.
|
33
|
+
* Added {Spidr::Events#every_html_doc}.
|
34
|
+
* Added {Spidr::Events#every_xml_doc}.
|
35
|
+
* Added {Spidr::Events#every_xsl_doc}.
|
36
|
+
* Added {Spidr::Events#every_rss_doc}.
|
37
|
+
* Added {Spidr::Events#every_atom_doc}.
|
38
|
+
* Added {Spidr::Events#every_javascript_page}.
|
39
|
+
* Added {Spidr::Events#every_css_page}.
|
40
|
+
* Added {Spidr::Events#every_rss_page}.
|
41
|
+
* Added {Spidr::Events#every_atom_page}.
|
42
|
+
* Added {Spidr::Events#every_ms_word_page}.
|
43
|
+
* Added {Spidr::Events#every_pdf_page}.
|
44
|
+
* Added {Spidr::Events#every_zip_page}.
|
45
|
+
* Fixed a bug where {Spidr::Agent#delay} was not being used to delay
|
46
|
+
requesting pages.
|
47
|
+
* Spider +link+ and +script+ tags in HTML pages (thanks Nick Plante).
|
48
|
+
|
49
|
+
=== 0.2.0 / 2009-10-10
|
50
|
+
|
51
|
+
* Added {URI.expand_path}.
|
52
|
+
* Added {Spidr::Page#search}.
|
53
|
+
* Added {Spidr::Page#at}.
|
54
|
+
* Added {Spidr::Page#title}.
|
55
|
+
* Added {Spidr::Agent#failures=}.
|
56
|
+
* Added a HTTP session cache to {Spidr::Agent}, per suggestion of falter.
|
57
|
+
* Added Spidr::Agent#get_session.
|
58
|
+
* Added Spidr::Agent#kill_session.
|
59
|
+
* Added {Spidr.proxy=}.
|
60
|
+
* Added {Spidr.disable_proxy!}.
|
61
|
+
* Aliased Spidr::Page#txt? to {Spidr::Page#plain_text?}.
|
62
|
+
* Aliased Spidr::Page#ok? to {Spidr::Page#is_ok?}.
|
63
|
+
* Aliased Spidr::Page#redirect? to {Spidr::Page#is_redirect?}.
|
64
|
+
* Aliased Spidr::Page#unauthorized? to {Spidr::Page#is_unauthorized?}.
|
65
|
+
* Aliased Spidr::Page#forbidden? to {Spidr::Page#is_forbidden?}.
|
66
|
+
* Aliased Spidr::Page#missing? to {Spidr::Page#is_missing?}.
|
67
|
+
* Split URL filtering code out of {Spidr::Agent} and into
|
68
|
+
{Spidr::Filters}.
|
69
|
+
* Split URL / Page event code out of {Spidr::Agent} and into
|
70
|
+
{Spidr::Events}.
|
71
|
+
* Split pause! / continue! / skip_link! / skip_page! methods out of
|
72
|
+
{Spidr::Agent} and into {Spidr::Actions}.
|
73
|
+
* Fixed a bug in {Spidr::Page#code}, where it was not returning an Integer.
|
74
|
+
* Make sure {Spidr::Page#doc} returns Nokogiri::XML::Document objects for
|
75
|
+
RSS/RDF/Atom pages as well.
|
76
|
+
* Fixed the handling of the Location header in {Spidr::Page#links}
|
77
|
+
(thanks falter).
|
78
|
+
* Fixed a bug in {Spidr::Page#to_absolute} where trailing '/' characters on
|
79
|
+
URI paths were not being preserved (thanks falter).
|
80
|
+
* Fixed a bug where the URI query was not being sent with the request
|
81
|
+
in {Spidr::Agent#get_page} (thanks Damian Steer).
|
82
|
+
* Fixed a bug where SSL sessions were not being properly setup
|
83
|
+
(thanks falter).
|
84
|
+
* Switched {Spidr::Agent#history} to be a Set, to improve search-time
|
85
|
+
of the history (thanks falter).
|
86
|
+
* Switched {Spidr::Agent#failures} to a Set.
|
87
|
+
* Allow a block to be passed to {Spidr::Agent#run}, which will receive all
|
88
|
+
pages visited.
|
89
|
+
* Allow Spidr::Agent#start_at and Spidr::Agent#continue! to pass blocks
|
90
|
+
to {Spidr::Agent#run}.
|
91
|
+
* Made {Spidr::Agent#visit_page} public.
|
92
|
+
* Moved to YARD based documentation.
|
93
|
+
|
94
|
+
=== 0.1.9 / 2009-06-13
|
95
|
+
|
96
|
+
* Upgraded to Hoe 2.0.0.
|
97
|
+
* Use Hoe.spec instead of Hoe.new.
|
98
|
+
* Use the Hoe signing task for signed gems.
|
99
|
+
* Added the Spidr::Agent#schemes and Spidr::Agent#schemes= methods.
|
100
|
+
* Added a warning message if 'net/https' cannot be loaded.
|
101
|
+
* Allow the list of acceptable URL schemes to be passed into
|
102
|
+
{Spidr::Agent#initialize}.
|
103
|
+
* Allow history and queue information to be passed into
|
104
|
+
{Spidr::Agent#initialize}.
|
105
|
+
* {Spidr::Agent#start_at} no longer clears the history or the queue.
|
106
|
+
* Fixed a bug in the sanitization of semi-escaped URLs.
|
107
|
+
* Fixed a bug where https URLs would be followed even if 'net/https'
|
108
|
+
could not be loaded.
|
109
|
+
* Removed Spidr::Agent::SCHEMES.
|
110
|
+
|
111
|
+
=== 0.1.8 / 2009-05-27
|
112
|
+
|
113
|
+
* Added the Spidr::Agent#pause! and Spidr::Agent#continue! methods.
|
114
|
+
* Added the Spidr::Agent#running? and Spidr::Agent#paused? methods.
|
115
|
+
* Added an alias for pending_urls to the queue methods.
|
116
|
+
* Added {Spidr::Agent#queue} to provide read access to the queue.
|
117
|
+
* Added {Spidr::Agent#queue=} and {Spidr::Agent#history=} for setting the
|
118
|
+
queue and history.
|
119
|
+
* Added {Spidr::Agent#to_hash} which returns a Hash of the agents queue and
|
120
|
+
history.
|
121
|
+
* Made {Spidr::Agent#enqueue} and {Spidr::Agent#queued?} public.
|
122
|
+
* Added more specs.
|
123
|
+
|
124
|
+
=== 0.1.7 / 2009-04-24
|
125
|
+
|
126
|
+
* Added Spidr::Agent#all_headers.
|
127
|
+
* Fixed a bug where Page#headers was always +nil+.
|
128
|
+
* {Spidr::Spidr::Agent} will now follow the Location header in HTTP 300,
|
129
|
+
301, 302, 303 and 307 Redirects.
|
130
|
+
* {Spidr::Agent} will now follow iframe and frame tags.
|
131
|
+
|
132
|
+
=== 0.1.6 / 2009-04-14
|
133
|
+
|
134
|
+
* Added {Spidr::Agent#failures}, a list of URLs which could not be visited.
|
135
|
+
* Added {Spidr::Agent#failed?}.
|
136
|
+
* Added Spidr::Agent#every_failed_url.
|
137
|
+
* Added {Spidr::Agent#clear}, which clears the history and failures URL
|
138
|
+
lists.
|
139
|
+
* Improved fault tolerance in {Spidr::Agent#get_page}.
|
140
|
+
* If a Network or HTTP error is encountered, the URL will be added to
|
141
|
+
the failures list and the next URL will be visited.
|
142
|
+
* Fixed a typo in Spidr::Agent#ignore_exts_like.
|
143
|
+
* Updated the Web Spider Obstacle Course with links that always fail to be
|
144
|
+
visited.
|
145
|
+
|
146
|
+
=== 0.1.5 / 2009-03-22
|
147
|
+
|
148
|
+
* Catch malformed URIs in {Spidr::Page#to_absolute} and return +nil+.
|
149
|
+
* Filter out +nil+ URIs in {Spidr::Page#urls}.
|
150
|
+
|
151
|
+
=== 0.1.4 / 2009-01-15
|
152
|
+
|
153
|
+
* Use Nokogiri for HTML and XML parsing.
|
154
|
+
|
155
|
+
=== 0.1.3 / 2009-01-10
|
156
|
+
|
157
|
+
* Added the :host options to {Spidr::Agent#initialize}.
|
158
|
+
* Added the Web Spider Obstacle Course files to the Manifest.
|
159
|
+
* Aliased {Spidr::Agent#visited_urls} to {Spidr::Agent#history}.
|
160
|
+
|
161
|
+
=== 0.1.2 / 2008-11-06
|
162
|
+
|
163
|
+
* Fixed a bug in {Spidr::Page#to_absolute} where URLs with no path were not
|
164
|
+
receiving a default path of <tt>/</tt>.
|
165
|
+
* Fixed a bug in {Spidr::Page#to_absolute} where URL paths were not being
|
166
|
+
expanded, in order to remove <tt>..</tt> and <tt>.</tt> directories.
|
167
|
+
* Fixed a bug where absolute URLs could have a blank path, thus causing
|
168
|
+
{Spidr::Agent#get_page} to crash when it performed the HTTP request.
|
169
|
+
* Added RSpec spec tests.
|
170
|
+
* Created a Web-Spider Obstacle Course
|
171
|
+
(http://spidr.rubyforge.org/course/start.html) which is used in the spec
|
172
|
+
tests.
|
173
|
+
|
174
|
+
=== 0.1.1 / 2008-10-04
|
175
|
+
|
176
|
+
* Added a reader method for the response instance variable in Page.
|
177
|
+
* Fixed a bug in {Spidr::Page#method_missing}.
|
178
|
+
|
179
|
+
=== 0.1.0 / 2008-05-23
|
180
|
+
|
181
|
+
* Initial release.
|
182
|
+
* Black-list or white-list URLs based upon:
|
183
|
+
* Host name
|
184
|
+
* Port number
|
185
|
+
* Full link
|
186
|
+
* URL extension
|
187
|
+
* Provides call-backs for:
|
188
|
+
* Every visited Page.
|
189
|
+
* Every visited URL.
|
190
|
+
* Every visited URL that matches a specified pattern.
|
191
|
+
|
data/Manifest.txt
CHANGED
@@ -1,11 +1,12 @@
|
|
1
|
-
History.
|
1
|
+
History.rdoc
|
2
2
|
Manifest.txt
|
3
|
-
README.
|
3
|
+
README.rdoc
|
4
4
|
Rakefile
|
5
5
|
lib/spidr.rb
|
6
6
|
lib/spidr/extensions.rb
|
7
7
|
lib/spidr/extensions/uri.rb
|
8
8
|
lib/spidr/page.rb
|
9
|
+
lib/spidr/sanitizers.rb
|
9
10
|
lib/spidr/rules.rb
|
10
11
|
lib/spidr/filters.rb
|
11
12
|
lib/spidr/events.rb
|
@@ -16,50 +17,25 @@ lib/spidr/actions/exceptions/paused.rb
|
|
16
17
|
lib/spidr/actions/exceptions/skip_link.rb
|
17
18
|
lib/spidr/actions/exceptions/skip_page.rb
|
18
19
|
lib/spidr/actions/actions.rb
|
20
|
+
lib/spidr/session_cache.rb
|
21
|
+
lib/spidr/cookie_jar.rb
|
22
|
+
lib/spidr/auth_credential.rb
|
23
|
+
lib/spidr/auth_store.rb
|
19
24
|
lib/spidr/agent.rb
|
20
25
|
lib/spidr/spidr.rb
|
21
26
|
lib/spidr/version.rb
|
22
27
|
tasks/spec.rb
|
23
28
|
tasks/yard.rb
|
24
|
-
tasks/course.rb
|
25
29
|
spec/spec_helper.rb
|
26
|
-
spec/helpers/
|
30
|
+
spec/helpers/history.rb
|
31
|
+
spec/helpers/wsoc.rb
|
27
32
|
spec/helpers/page.rb
|
28
33
|
spec/extensions/uri_spec.rb
|
29
34
|
spec/page_examples.rb
|
30
35
|
spec/page_spec.rb
|
31
36
|
spec/rules_spec.rb
|
37
|
+
spec/sanitizers_spec.rb
|
32
38
|
spec/filters_spec.rb
|
33
39
|
spec/actions_spec.rb
|
34
40
|
spec/agent_spec.rb
|
35
41
|
spec/spidr_spec.rb
|
36
|
-
static/course/index.html
|
37
|
-
static/course/start.html
|
38
|
-
static/course/fail.html
|
39
|
-
static/course/scripts/jquery-1.2.6.min.js
|
40
|
-
static/course/scripts/course.js
|
41
|
-
static/course/empty/index.html
|
42
|
-
static/course/empty/start.html
|
43
|
-
static/course/javascript/index.html
|
44
|
-
static/course/javascript/start.html
|
45
|
-
static/course/loop/index.html
|
46
|
-
static/course/loop/start.html
|
47
|
-
static/course/loop/next.html
|
48
|
-
static/course/relative/index.html
|
49
|
-
static/course/relative/start.html
|
50
|
-
static/course/relative/normal.html
|
51
|
-
static/course/relative/current_directory.html
|
52
|
-
static/course/relative/same_directory.html
|
53
|
-
static/course/absolute/index.html
|
54
|
-
static/course/absolute/start.html
|
55
|
-
static/course/absolute/next.html
|
56
|
-
static/course/remote/index.html
|
57
|
-
static/course/remote/start.html
|
58
|
-
static/course/remote/next.html
|
59
|
-
static/course/frames/index.html
|
60
|
-
static/course/frames/start.html
|
61
|
-
static/course/frames/iframe.html
|
62
|
-
static/course/frames/iframe_next.html
|
63
|
-
static/course/frames/frame.html
|
64
|
-
static/course/frames/frame_next.html
|
65
|
-
static/course/specs.json
|
data/{README.txt → README.rdoc}
RENAMED
@@ -18,7 +18,9 @@ and easy to use.
|
|
18
18
|
* a tags.
|
19
19
|
* iframe tags.
|
20
20
|
* frame tags.
|
21
|
+
* Cookie protected links.
|
21
22
|
* HTTP 300, 301, 302, 303 and 307 Redirects.
|
23
|
+
* HTTP Basic Auth protected links.
|
22
24
|
* Black-list or white-list URLs based upon:
|
23
25
|
* URL scheme.
|
24
26
|
* Host name
|
@@ -156,7 +158,7 @@ and easy to use.
|
|
156
158
|
|
157
159
|
The MIT License
|
158
160
|
|
159
|
-
Copyright (c) 2008-
|
161
|
+
Copyright (c) 2008-2010 Hal Brodigan
|
160
162
|
|
161
163
|
Permission is hereby granted, free of charge, to any person obtaining
|
162
164
|
a copy of this software and associated documentation files (the
|
data/Rakefile
CHANGED
@@ -5,20 +5,22 @@ require 'hoe'
|
|
5
5
|
require 'hoe/signing'
|
6
6
|
require './tasks/spec.rb'
|
7
7
|
require './tasks/yard.rb'
|
8
|
-
require './tasks/course.rb'
|
9
|
-
require './lib/spidr/version.rb'
|
10
8
|
|
11
9
|
Hoe.spec('spidr') do
|
12
|
-
self.rubyforge_name = 'spidr'
|
13
10
|
self.developer('Postmodern', 'postmodern.mod3@gmail.com')
|
11
|
+
|
12
|
+
self.readme_file = 'README.rdoc'
|
13
|
+
self.history_file = 'History.rdoc'
|
14
14
|
self.remote_rdoc_dir = 'docs'
|
15
|
+
|
15
16
|
self.extra_deps = [
|
16
17
|
['nokogiri', '>=1.2.0']
|
17
18
|
]
|
18
19
|
|
19
20
|
self.extra_dev_deps = [
|
20
21
|
['rspec', '>=1.2.8'],
|
21
|
-
['yard', '>=0.4.0']
|
22
|
+
['yard', '>=0.4.0'],
|
23
|
+
['wsoc', '>=0.1.1']
|
22
24
|
]
|
23
25
|
|
24
26
|
self.spec_extras = {:has_rdoc => 'yard'}
|
data/lib/spidr/agent.rb
CHANGED
@@ -1,7 +1,11 @@
|
|
1
|
+
require 'spidr/sanitizers'
|
1
2
|
require 'spidr/filters'
|
2
3
|
require 'spidr/events'
|
3
4
|
require 'spidr/actions'
|
4
5
|
require 'spidr/page'
|
6
|
+
require 'spidr/session_cache'
|
7
|
+
require 'spidr/cookie_jar'
|
8
|
+
require 'spidr/auth_store'
|
5
9
|
require 'spidr/spidr'
|
6
10
|
|
7
11
|
require 'net/http'
|
@@ -10,16 +14,17 @@ require 'set'
|
|
10
14
|
module Spidr
|
11
15
|
class Agent
|
12
16
|
|
17
|
+
include Sanitizers
|
13
18
|
include Filters
|
14
19
|
include Events
|
15
20
|
include Actions
|
16
21
|
|
17
|
-
# Proxy to use
|
18
|
-
attr_accessor :proxy
|
19
|
-
|
20
22
|
# User-Agent to use
|
21
23
|
attr_accessor :user_agent
|
22
24
|
|
25
|
+
# HTTP Authentication credentials
|
26
|
+
attr_accessor :authorized
|
27
|
+
|
23
28
|
# Referer to use
|
24
29
|
attr_accessor :referer
|
25
30
|
|
@@ -35,6 +40,9 @@ module Spidr
|
|
35
40
|
# Queue of URLs to visit
|
36
41
|
attr_reader :queue
|
37
42
|
|
43
|
+
# Cached cookies
|
44
|
+
attr_reader :cookies
|
45
|
+
|
38
46
|
#
|
39
47
|
# Creates a new Agent object.
|
40
48
|
#
|
@@ -79,18 +87,19 @@ module Spidr
|
|
79
87
|
# The newly created agent.
|
80
88
|
#
|
81
89
|
def initialize(options={},&block)
|
82
|
-
@proxy = (options[:proxy] || Spidr.proxy)
|
83
90
|
@user_agent = (options[:user_agent] || Spidr.user_agent)
|
84
91
|
@referer = options[:referer]
|
85
92
|
|
93
|
+
@sessions = SessionCache.new(options[:proxy] || Spidr.proxy)
|
94
|
+
@cookies = CookieJar.new
|
95
|
+
@authorized = AuthStore.new
|
96
|
+
|
86
97
|
@running = false
|
87
98
|
@delay = (options[:delay] || 0)
|
88
99
|
@history = Set[]
|
89
100
|
@failures = Set[]
|
90
101
|
@queue = []
|
91
102
|
|
92
|
-
@sessions = {}
|
93
|
-
|
94
103
|
super(options)
|
95
104
|
|
96
105
|
block.call(self) if block
|
@@ -222,14 +231,6 @@ module Spidr
|
|
222
231
|
|
223
232
|
@running = false
|
224
233
|
|
225
|
-
@sessions.each_value do |sess|
|
226
|
-
begin
|
227
|
-
sess.finish
|
228
|
-
rescue IOError
|
229
|
-
nil
|
230
|
-
end
|
231
|
-
end
|
232
|
-
|
233
234
|
@sessions.clear
|
234
235
|
return self
|
235
236
|
end
|
@@ -244,6 +245,37 @@ module Spidr
|
|
244
245
|
@running == true
|
245
246
|
end
|
246
247
|
|
248
|
+
#
|
249
|
+
# The proxy information the agent uses.
|
250
|
+
#
|
251
|
+
# @return [Hash]
|
252
|
+
# The proxy information.
|
253
|
+
#
|
254
|
+
# @see SessionCache#proxy
|
255
|
+
#
|
256
|
+
# @since 0.2.2
|
257
|
+
#
|
258
|
+
def proxy
|
259
|
+
@sessions.proxy
|
260
|
+
end
|
261
|
+
|
262
|
+
#
|
263
|
+
# Sets the proxy information that the agent uses.
|
264
|
+
#
|
265
|
+
# @param [Hash] new_proxy
|
266
|
+
# The new proxy information.
|
267
|
+
#
|
268
|
+
# @return [Hash]
|
269
|
+
# The new proxy information.
|
270
|
+
#
|
271
|
+
# @see SessionCache#proxy=
|
272
|
+
#
|
273
|
+
# @since 0.2.2
|
274
|
+
#
|
275
|
+
def proxy=(new_proxy)
|
276
|
+
@sessions.proxy = new_proxy
|
277
|
+
end
|
278
|
+
|
247
279
|
#
|
248
280
|
# Sets the history of URLs that were previously visited.
|
249
281
|
#
|
@@ -400,10 +432,11 @@ module Spidr
|
|
400
432
|
# Specifies whether the URL was enqueued, or ignored.
|
401
433
|
#
|
402
434
|
def enqueue(url)
|
403
|
-
|
404
|
-
url = URI(link) unless url.kind_of?(URI)
|
435
|
+
url = sanitize_url(url)
|
405
436
|
|
406
437
|
if (!(queued?(url)) && visit?(url))
|
438
|
+
link = url.to_s
|
439
|
+
|
407
440
|
begin
|
408
441
|
@every_url_blocks.each { |block| block.call(url) }
|
409
442
|
|
@@ -443,37 +476,51 @@ module Spidr
|
|
443
476
|
# The page for the response, or +nil+ if the request failed.
|
444
477
|
#
|
445
478
|
def get_page(url,&block)
|
446
|
-
url = URI(url.to_s)
|
479
|
+
url = URI(url.to_s)
|
447
480
|
|
448
|
-
|
449
|
-
|
481
|
+
prepare_request(url) do |session,path,headers|
|
482
|
+
new_page = Page.new(url,session.get(path,headers))
|
450
483
|
|
451
|
-
|
452
|
-
|
453
|
-
else
|
454
|
-
path = '/'
|
455
|
-
end
|
484
|
+
# save any new cookies
|
485
|
+
@cookies.from_page(new_page)
|
456
486
|
|
457
|
-
|
458
|
-
|
487
|
+
block.call(new_page) if block
|
488
|
+
return new_page
|
489
|
+
end
|
490
|
+
end
|
459
491
|
|
460
|
-
|
461
|
-
|
492
|
+
#
|
493
|
+
# Posts supplied form data and creates a new Page object from a given URL.
|
494
|
+
#
|
495
|
+
# @param [URI::HTTP] url
|
496
|
+
# The URL to request.
|
497
|
+
#
|
498
|
+
# @param [String] post_data
|
499
|
+
# Form option data.
|
500
|
+
#
|
501
|
+
# @yield [page]
|
502
|
+
# If a block is given, it will be passed the page that represents the
|
503
|
+
# response.
|
504
|
+
#
|
505
|
+
# @yieldparam [Page] page
|
506
|
+
# The page for the response.
|
507
|
+
#
|
508
|
+
# @return [Page, nil]
|
509
|
+
# The page for the response, or +nil+ if the request failed.
|
510
|
+
#
|
511
|
+
# @since 0.2.2
|
512
|
+
#
|
513
|
+
def post_page(url,post_data='',&block)
|
514
|
+
url = URI(url.to_s)
|
462
515
|
|
463
|
-
|
464
|
-
|
465
|
-
headers['User-Agent'] = @user_agent if @user_agent
|
466
|
-
headers['Referer'] = @referer if @referer
|
516
|
+
prepare_request(url) do |session,path,headers|
|
517
|
+
new_page = Page.new(url,session.post(path,post_data,headers))
|
467
518
|
|
468
|
-
|
519
|
+
# save any new cookies
|
520
|
+
@cookies.from_page(new_page)
|
469
521
|
|
470
|
-
|
471
|
-
|
472
|
-
end
|
473
|
-
rescue SystemCallError, Timeout::Error, Net::HTTPBadResponse, IOError
|
474
|
-
failed(url)
|
475
|
-
kill_session(url.scheme,host,port)
|
476
|
-
return nil
|
522
|
+
block.call(new_page) if block
|
523
|
+
return new_page
|
477
524
|
end
|
478
525
|
end
|
479
526
|
|
@@ -529,73 +576,66 @@ module Spidr
|
|
529
576
|
protected
|
530
577
|
|
531
578
|
#
|
532
|
-
#
|
533
|
-
# and
|
534
|
-
#
|
535
|
-
# @param [String] scheme
|
536
|
-
# The scheme of the URL, which will be requested later.
|
537
|
-
#
|
538
|
-
# @param [String] host
|
539
|
-
# The host that the session is needed with.
|
579
|
+
# Normalizes the request path and grabs a session to handle page
|
580
|
+
# get and post requests.
|
540
581
|
#
|
541
|
-
# @param [
|
542
|
-
# The
|
582
|
+
# @param [URI::HTTP] url
|
583
|
+
# The URL to request.
|
543
584
|
#
|
544
|
-
# @yield [
|
545
|
-
#
|
585
|
+
# @yield [request]
|
586
|
+
# A block whose purpose is to make a page request.
|
546
587
|
#
|
547
588
|
# @yieldparam [Net::HTTP] session
|
548
|
-
#
|
549
|
-
#
|
550
|
-
def get_session(scheme,host,port,&block)
|
551
|
-
key = [scheme,host,port]
|
552
|
-
|
553
|
-
unless @sessions[key]
|
554
|
-
session = Net::HTTP::Proxy(
|
555
|
-
@proxy[:host],
|
556
|
-
@proxy[:port],
|
557
|
-
@proxy[:user],
|
558
|
-
@proxy[:password]
|
559
|
-
).new(host,port)
|
560
|
-
|
561
|
-
if scheme == 'https'
|
562
|
-
session.use_ssl = true
|
563
|
-
session.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
564
|
-
end
|
565
|
-
|
566
|
-
@sessions[key] = session
|
567
|
-
end
|
568
|
-
|
569
|
-
session = @sessions[key]
|
570
|
-
block.call(session) if block
|
571
|
-
return session
|
572
|
-
end
|
573
|
-
|
574
|
-
#
|
575
|
-
# Destroys an HTTP session for the given scheme, host and port.
|
589
|
+
# An HTTP session object.
|
576
590
|
#
|
577
|
-
# @
|
578
|
-
#
|
591
|
+
# @yieldparam [String] path
|
592
|
+
# Normalized URL string.
|
579
593
|
#
|
580
|
-
# @
|
581
|
-
#
|
594
|
+
# @yieldparam [Hash] headers
|
595
|
+
# A Hash of request header options.
|
582
596
|
#
|
583
|
-
# @
|
584
|
-
# The port that the session was connected to.
|
597
|
+
# @since 0.2.2
|
585
598
|
#
|
586
|
-
def
|
587
|
-
|
588
|
-
|
599
|
+
def prepare_request(url,&block)
|
600
|
+
host = url.host
|
601
|
+
port = url.port
|
589
602
|
|
590
|
-
|
591
|
-
|
592
|
-
|
593
|
-
|
603
|
+
unless url.path.empty?
|
604
|
+
path = url.path
|
605
|
+
else
|
606
|
+
path = '/'
|
594
607
|
end
|
595
608
|
|
596
|
-
|
597
|
-
|
598
|
-
|
609
|
+
# append the URL query to the path
|
610
|
+
path += "?#{url.query}" if url.query
|
611
|
+
|
612
|
+
begin
|
613
|
+
sleep(@delay) if @delay > 0
|
614
|
+
|
615
|
+
headers = {}
|
616
|
+
headers['User-Agent'] = @user_agent if @user_agent
|
617
|
+
headers['Referer'] = @referer if @referer
|
618
|
+
|
619
|
+
if (authorization = @authorized.for_url(url))
|
620
|
+
headers['Authorization'] = "Basic #{authorization}"
|
621
|
+
end
|
622
|
+
|
623
|
+
if (header_cookies = @cookies.for_host(url.host))
|
624
|
+
headers['Cookie'] = header_cookies
|
625
|
+
end
|
626
|
+
|
627
|
+
block.call(@sessions[url],path,headers)
|
628
|
+
rescue SystemCallError,
|
629
|
+
Timeout::Error,
|
630
|
+
SocketError,
|
631
|
+
Net::HTTPBadResponse,
|
632
|
+
IOError
|
633
|
+
|
634
|
+
@sessions.kill!(url)
|
635
|
+
|
636
|
+
failed(url)
|
637
|
+
return nil
|
638
|
+
end
|
599
639
|
end
|
600
640
|
|
601
641
|
#
|
@@ -633,8 +673,8 @@ module Spidr
|
|
633
673
|
# The URL to add to the failures list.
|
634
674
|
#
|
635
675
|
def failed(url)
|
636
|
-
@every_failed_url_blocks.each { |block| block.call(url) }
|
637
676
|
@failures << url
|
677
|
+
@every_failed_url_blocks.each { |block| block.call(url) }
|
638
678
|
return true
|
639
679
|
end
|
640
680
|
|