spidr_epg 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +10 -0
- data/.rspec +1 -0
- data/.yardopts +1 -0
- data/ChangeLog.md +291 -0
- data/ChangeLog.md~ +291 -0
- data/Gemfile +16 -0
- data/Gemfile.lock +49 -0
- data/Gemfile~ +16 -0
- data/LICENSE.txt +20 -0
- data/README.md +193 -0
- data/README.md~ +190 -0
- data/Rakefile +29 -0
- data/gemspec.yml +19 -0
- data/lib/spidr/actions/actions.rb +83 -0
- data/lib/spidr/actions/exceptions/action.rb +9 -0
- data/lib/spidr/actions/exceptions/paused.rb +11 -0
- data/lib/spidr/actions/exceptions/skip_link.rb +12 -0
- data/lib/spidr/actions/exceptions/skip_page.rb +12 -0
- data/lib/spidr/actions/exceptions.rb +4 -0
- data/lib/spidr/actions.rb +2 -0
- data/lib/spidr/agent.rb +866 -0
- data/lib/spidr/auth_credential.rb +28 -0
- data/lib/spidr/auth_store.rb +161 -0
- data/lib/spidr/body.rb +98 -0
- data/lib/spidr/cookie_jar.rb +202 -0
- data/lib/spidr/events.rb +537 -0
- data/lib/spidr/extensions/uri.rb +52 -0
- data/lib/spidr/extensions.rb +1 -0
- data/lib/spidr/filters.rb +539 -0
- data/lib/spidr/headers.rb +370 -0
- data/lib/spidr/links.rb +229 -0
- data/lib/spidr/page.rb +108 -0
- data/lib/spidr/rules.rb +79 -0
- data/lib/spidr/sanitizers.rb +56 -0
- data/lib/spidr/session_cache.rb +145 -0
- data/lib/spidr/spidr.rb +107 -0
- data/lib/spidr/version.rb +4 -0
- data/lib/spidr/version.rb~ +4 -0
- data/lib/spidr.rb +3 -0
- data/pkg/spidr-1.0.0.gem +0 -0
- data/spec/actions_spec.rb +59 -0
- data/spec/agent_spec.rb +81 -0
- data/spec/auth_store_spec.rb +85 -0
- data/spec/cookie_jar_spec.rb +144 -0
- data/spec/extensions/uri_spec.rb +43 -0
- data/spec/filters_spec.rb +61 -0
- data/spec/helpers/history.rb +34 -0
- data/spec/helpers/page.rb +8 -0
- data/spec/helpers/wsoc.rb +83 -0
- data/spec/page_examples.rb +21 -0
- data/spec/page_spec.rb +125 -0
- data/spec/rules_spec.rb +45 -0
- data/spec/sanitizers_spec.rb +61 -0
- data/spec/session_cache.rb +58 -0
- data/spec/spec_helper.rb +4 -0
- data/spec/spidr_spec.rb +39 -0
- data/spidr.gemspec +133 -0
- data/spidr.gemspec~ +131 -0
- metadata +158 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
NTcxZjE1YTc5OTY1MTQyM2NmYTRjM2VlODE5ZWIwZjBiMjc1OGVmMg==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
ZWIyNzI5NGMwMGMwNzJmYTA4Nzg2YzI4OTk3YTIyNjYyZGU4ZDQzYw==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
ODdiYzJjYWM3NjM3NzBjZjExMzI1YzJmN2I2YzA2YTQ5Y2I5N2IwNTRhMzE3
|
10
|
+
YWE0NDI5MGMwZTM1M2U2YTFkNWNiOWNjY2Q1Y2ExYjYzY2M4MDI1MTliODhi
|
11
|
+
NTM3Y2UyNDUxZDkxZjIwNTRmNzI1NzZjZjliNzE0YzcwNTUyMjk=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
MDZkYjMwYTBkZTUyMGMwMGRkZTgxZWM4ZWY3YTgwNWJlNTQ4NmVlNjVkNDli
|
14
|
+
ZWQ3M2FiYjkwYjJkNjI1NGQyOTJhMmM5ZTk2NTZjMzk4ZTgxNmYyNmIxNTA2
|
15
|
+
YTZlNmVmYTg0ZGVmYWFjODMzOTBjMmE3MTAzY2NiYTAxYTQ5ZTU=
|
data/.gitignore
ADDED
data/.rspec
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--colour --format documentation
|
data/.yardopts
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
--markup markdown --title 'Spidr Documentation' --protected --files ChangeLog.md,LICENSE.txt
|
data/ChangeLog.md
ADDED
@@ -0,0 +1,291 @@
|
|
1
|
+
### 1.4.2 /2012-04-12
|
2
|
+
|
3
|
+
* 对此gem进行了修改.
|
4
|
+
|
5
|
+
|
6
|
+
### 0.4.1 / 2011-12-08
|
7
|
+
|
8
|
+
* Catch `OpenSSL::SSL::SSLError` exceptions when initiated HTTPS Sessions.
|
9
|
+
|
10
|
+
### 0.4.0 / 2011-08-07
|
11
|
+
|
12
|
+
* Added {Spidr::Headers#content_charset}.
|
13
|
+
* Pass the Page `url` and `content_charset` to Nokogiri in {Spidr::Body#doc}.
|
14
|
+
This ensures that Nokogiri will preserve the body encoding.
|
15
|
+
* Made {Spidr::Headers#is_content_type?} public.
|
16
|
+
* Allow {Spidr::Headers#is_content_type?} to match the full Content-Type
|
17
|
+
or the sub-type.
|
18
|
+
|
19
|
+
### 0.3.2 / 2011-06-20
|
20
|
+
|
21
|
+
* Added separate intitialize methods for {Spidr::Actions}, {Spidr::Events},
|
22
|
+
{Spidr::Filters} and {Spidr::Sanitizers}.
|
23
|
+
* Aliased {Spidr::Events#urls_like} to {Spidr::Events#every_url_like}.
|
24
|
+
* Reduce usage of `self.included` and `module_eval`.
|
25
|
+
* Reduce usage of nested-blocks.
|
26
|
+
* Reduce usage of `return`.
|
27
|
+
|
28
|
+
### 0.3.1 / 2011-04-22
|
29
|
+
|
30
|
+
* Require `set` in `spidr/headers.rb`.
|
31
|
+
|
32
|
+
### 0.3.0 / 2011-04-14
|
33
|
+
|
34
|
+
* Switched from Jeweler to [Ore](http://github.com/ruby-ore/ore).
|
35
|
+
* Split all header related methods out of {Spidr::Page} and into
|
36
|
+
{Spidr::Headers}.
|
37
|
+
* Split all body related methods out of {Spidr::Page} and into
|
38
|
+
{Spidr::Body}.
|
39
|
+
* Split all link related methods out of {Spidr::Page} and into
|
40
|
+
{Spidr::Links}.
|
41
|
+
* Added {Spidr::Headers#directory?}.
|
42
|
+
* Added {Spidr::Headers#json?}.
|
43
|
+
* Added {Spidr::Links#each_url}.
|
44
|
+
* Added {Spidr::Links#each_link}.
|
45
|
+
* Added {Spidr::Links#each_redirect}.
|
46
|
+
* Added {Spidr::Links#each_meta_redirect}.
|
47
|
+
* Aliased {Spidr::Headers#raw_cookie} to {Spidr::Headers#cookie}.
|
48
|
+
* Aliased {Spidr::Body#to_s} to {Spidr::Body#body}.
|
49
|
+
* Also check for `application/xml` in {Spidr::Headers#xml?}.
|
50
|
+
* Catch all exceptions when merging URIs in {Spidr::Links#to_absolute}.
|
51
|
+
* Always prepend a `/` to all FTP URI paths. Fixes a Ruby 1.8 specific
|
52
|
+
bug, where it expects an absolute path for all FTP URIs.
|
53
|
+
* Refactored {URI.expand_path}.
|
54
|
+
* Start the session in {Spidr::SessionCache#[]} to prevent multiple
|
55
|
+
`CONNECT` commands being sent to HTTP Proxies (thanks falaise).
|
56
|
+
|
57
|
+
### 0.2.7 / 2010-08-17
|
58
|
+
|
59
|
+
* Added {Spidr::CookieJar#cookies_for_host} (thanks zapnap).
|
60
|
+
* Renamed `Spidr::Page#cookie` to `Spidr::Page#raw_cookie`.
|
61
|
+
* Rescue `URI::InvalidComponentError` exceptions in
|
62
|
+
`Spidr::Page#to_absolute` (thanks zapnap).
|
63
|
+
|
64
|
+
### 0.2.6 / 2010-07-05
|
65
|
+
|
66
|
+
* Fixed a bug in `Spidr::Page#meta_redirect`, by calling
|
67
|
+
`Nokogiri::XML::Element#get_attribute` instead of `attr`.
|
68
|
+
|
69
|
+
### 0.2.5 / 2010-07-02
|
70
|
+
|
71
|
+
* Added `Spidr::Page#meta_redirect`.
|
72
|
+
* Added `Spidr::Page#meta_redirect?`.
|
73
|
+
* Manage development dependencies with Bundler.
|
74
|
+
* Support following "old-school" meta-refresh redirects (thanks zapnap).
|
75
|
+
* Allow {Spidr::CookieJar} inherit cookies set by a parent domain.
|
76
|
+
* Fixed a constant lookup issue in {Spidr::Agent}.
|
77
|
+
* Use `yield` instead of `block.call` when necessary.
|
78
|
+
|
79
|
+
### 0.2.4 / 2010-05-05
|
80
|
+
|
81
|
+
* Added {Spidr::Filters#visit_urls}.
|
82
|
+
* Added {Spidr::Filters#visit_urls_like}.
|
83
|
+
* Added {Spidr::Filters#ignore_urls}.
|
84
|
+
* Added {Spidr::Filters#ignore_urls_like}.
|
85
|
+
* Added `Spidr::Page#is_content_type?`.
|
86
|
+
* Default `Spidr::Page#body` to an empty String.
|
87
|
+
* Default `Spidr::Page#content_type` to an empty String.
|
88
|
+
* Default `Spidr::Page#content_types` to an empty Array.
|
89
|
+
* Improved reliability of {Spidr::Page#is_redirect?}.
|
90
|
+
* Improved content type detection in {Spidr::Page} to handle `Content-Type`
|
91
|
+
headers containing charsets (thanks Josh Lindsey).
|
92
|
+
|
93
|
+
### 0.2.3 / 2010-02-27
|
94
|
+
|
95
|
+
* Migrated to Jeweler, for the packaging and releasing RubyGems.
|
96
|
+
* Switched to MarkDown formatted YARD documentation.
|
97
|
+
* Added {Spidr::Events#every_link}.
|
98
|
+
* Added {Spidr::SessionCache#active?}.
|
99
|
+
* Added specs for {Spidr::SessionCache}.
|
100
|
+
|
101
|
+
### 0.2.2 / 2010-01-06
|
102
|
+
|
103
|
+
* Require Web Spider Obstacle Course (WSOC) >= 0.1.1.
|
104
|
+
* Integrated the new WSOC into the specs.
|
105
|
+
* Removed the built-in Web Spider Obstacle Course.
|
106
|
+
* Added `Spidr::Page#content_types`.
|
107
|
+
* Added `Spidr::Page#cookie`.
|
108
|
+
* Added `Spidr::Page#cookies`.
|
109
|
+
* Added `Spidr::Page#cookie_params`.
|
110
|
+
* Added {Spidr::Sanitizers}.
|
111
|
+
* Added {Spidr::SessionCache}.
|
112
|
+
* Added {Spidr::CookieJar} (thanks Nick Plante).
|
113
|
+
* Added {Spidr::AuthStore} (thanks Nick Plante).
|
114
|
+
* Added {Spidr::Agent#post_page} (thanks Nick Plante).
|
115
|
+
* Renamed `Spidr::Agent#get_session` to {Spidr::SessionCache#[]}.
|
116
|
+
* Renamed `Spidr::Agent#kill_session` to {Spidr::SessionCache#kill!}.
|
117
|
+
|
118
|
+
### 0.2.1 / 2009-11-25
|
119
|
+
|
120
|
+
* Added {Spidr::Events#every_ok_page}.
|
121
|
+
* Added {Spidr::Events#every_redirect_page}.
|
122
|
+
* Added {Spidr::Events#every_timedout_page}.
|
123
|
+
* Added {Spidr::Events#every_bad_request_page}.
|
124
|
+
* Added {Spidr::Events#every_unauthorized_page}.
|
125
|
+
* Added {Spidr::Events#every_forbidden_page}.
|
126
|
+
* Added {Spidr::Events#every_missing_page}.
|
127
|
+
* Added {Spidr::Events#every_internal_server_error_page}.
|
128
|
+
* Added {Spidr::Events#every_txt_page}.
|
129
|
+
* Added {Spidr::Events#every_html_page}.
|
130
|
+
* Added {Spidr::Events#every_xml_page}.
|
131
|
+
* Added {Spidr::Events#every_xsl_page}.
|
132
|
+
* Added {Spidr::Events#every_doc}.
|
133
|
+
* Added {Spidr::Events#every_html_doc}.
|
134
|
+
* Added {Spidr::Events#every_xml_doc}.
|
135
|
+
* Added {Spidr::Events#every_xsl_doc}.
|
136
|
+
* Added {Spidr::Events#every_rss_doc}.
|
137
|
+
* Added {Spidr::Events#every_atom_doc}.
|
138
|
+
* Added {Spidr::Events#every_javascript_page}.
|
139
|
+
* Added {Spidr::Events#every_css_page}.
|
140
|
+
* Added {Spidr::Events#every_rss_page}.
|
141
|
+
* Added {Spidr::Events#every_atom_page}.
|
142
|
+
* Added {Spidr::Events#every_ms_word_page}.
|
143
|
+
* Added {Spidr::Events#every_pdf_page}.
|
144
|
+
* Added {Spidr::Events#every_zip_page}.
|
145
|
+
* Fixed a bug where {Spidr::Agent#delay} was not being used to delay
|
146
|
+
requesting pages.
|
147
|
+
* Spider `link` and `script` tags in HTML pages (thanks Nick Plante).
|
148
|
+
|
149
|
+
### 0.2.0 / 2009-10-10
|
150
|
+
|
151
|
+
* Added {URI.expand_path}.
|
152
|
+
* Added `Spidr::Page#search`.
|
153
|
+
* Added `Spidr::Page#at`.
|
154
|
+
* Added `Spidr::Page#title`.
|
155
|
+
* Added {Spidr::Agent#failures=}.
|
156
|
+
* Added a HTTP session cache to {Spidr::Agent}, per suggestion of falter.
|
157
|
+
* Added `Spidr::Agent#get_session`.
|
158
|
+
* Added `Spidr::Agent#kill_session`.
|
159
|
+
* Added {Spidr.proxy=}.
|
160
|
+
* Added {Spidr.disable_proxy!}.
|
161
|
+
* Aliased `Spidr::Page#txt?` to `Spidr::Page#plain_text?`.
|
162
|
+
* Aliased `Spidr::Page#ok?` to `Spidr::Page#is_ok?`.
|
163
|
+
* Aliased `Spidr::Page#redirect?` to `Spidr::Page#is_redirect?`.
|
164
|
+
* Aliased `Spidr::Page#unauthorized?` to `Spidr::Page#is_unauthorized?`.
|
165
|
+
* Aliased `Spidr::Page#forbidden?` to `Spidr::Page#is_forbidden?`.
|
166
|
+
* Aliased `Spidr::Page#missing?` to `Spidr::Page#is_missing?`.
|
167
|
+
* Split URL filtering code out of {Spidr::Agent} and into
|
168
|
+
{Spidr::Filters}.
|
169
|
+
* Split URL / Page event code out of {Spidr::Agent} and into
|
170
|
+
{Spidr::Events}.
|
171
|
+
* Split pause! / continue! / skip_link! / skip_page! methods out of
|
172
|
+
{Spidr::Agent} and into {Spidr::Actions}.
|
173
|
+
* Fixed a bug in `Spidr::Page#code`, where it was not returning an Integer.
|
174
|
+
* Make sure `Spidr::Page#doc` returns `Nokogiri::XML::Document` objects for
|
175
|
+
RSS/RDF/Atom pages as well.
|
176
|
+
* Fixed the handling of the Location header in `Spidr::Page#links`
|
177
|
+
(thanks falter).
|
178
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where trailing `/` characters on
|
179
|
+
URI paths were not being preserved (thanks falter).
|
180
|
+
* Fixed a bug where the URI query was not being sent with the request
|
181
|
+
in {Spidr::Agent#get_page} (thanks Damian Steer).
|
182
|
+
* Fixed a bug where SSL sessions were not being properly setup
|
183
|
+
(thanks falter).
|
184
|
+
* Switched {Spidr::Agent#history} to be a Set, to improve search-time
|
185
|
+
of the history (thanks falter).
|
186
|
+
* Switched {Spidr::Agent#failures} to a Set.
|
187
|
+
* Allow a block to be passed to {Spidr::Agent#run}, which will receive all
|
188
|
+
pages visited.
|
189
|
+
* Allow `Spidr::Agent#start_at` and `Spidr::Agent#continue!` to pass blocks
|
190
|
+
to {Spidr::Agent#run}.
|
191
|
+
* Made {Spidr::Agent#visit_page} public.
|
192
|
+
* Moved to YARD based documentation.
|
193
|
+
|
194
|
+
### 0.1.9 / 2009-06-13
|
195
|
+
|
196
|
+
* Upgraded to Hoe 2.0.0.
|
197
|
+
* Use Hoe.spec instead of Hoe.new.
|
198
|
+
* Use the Hoe signing task for signed gems.
|
199
|
+
* Added the `Spidr::Agent#schemes` and `Spidr::Agent#schemes=` methods.
|
200
|
+
* Added a warning message if 'net/https' cannot be loaded.
|
201
|
+
* Allow the list of acceptable URL schemes to be passed into
|
202
|
+
{Spidr::Agent#initialize}.
|
203
|
+
* Allow history and queue information to be passed into
|
204
|
+
{Spidr::Agent#initialize}.
|
205
|
+
* {Spidr::Agent#start_at} no longer clears the history or the queue.
|
206
|
+
* Fixed a bug in the sanitization of semi-escaped URLs.
|
207
|
+
* Fixed a bug where https URLs would be followed even if 'net/https'
|
208
|
+
could not be loaded.
|
209
|
+
* Removed Spidr::Agent::SCHEMES.
|
210
|
+
|
211
|
+
### 0.1.8 / 2009-05-27
|
212
|
+
|
213
|
+
* Added the `Spidr::Agent#pause!` and `Spidr::Agent#continue!` methods.
|
214
|
+
* Added the `Spidr::Agent#running?` and `Spidr::Agent#paused?` methods.
|
215
|
+
* Added an alias for pending_urls to the queue methods.
|
216
|
+
* Added {Spidr::Agent#queue} to provide read access to the queue.
|
217
|
+
* Added {Spidr::Agent#queue=} and {Spidr::Agent#history=} for setting the
|
218
|
+
queue and history.
|
219
|
+
* Added {Spidr::Agent#to_hash} which returns a Hash of the agents queue and
|
220
|
+
history.
|
221
|
+
* Made {Spidr::Agent#enqueue} and {Spidr::Agent#queued?} public.
|
222
|
+
* Added more specs.
|
223
|
+
|
224
|
+
### 0.1.7 / 2009-04-24
|
225
|
+
|
226
|
+
* Added `Spidr::Agent#all_headers`.
|
227
|
+
* Fixed a bug where {Spidr::Page#headers} was always `nil`.
|
228
|
+
* {Spidr::Agent} will now follow the Location header in HTTP 300,
|
229
|
+
301, 302, 303 and 307 Redirects.
|
230
|
+
* {Spidr::Agent} will now follow iframe and frame tags.
|
231
|
+
|
232
|
+
### 0.1.6 / 2009-04-14
|
233
|
+
|
234
|
+
* Added {Spidr::Agent#failures}, a list of URLs which could not be visited.
|
235
|
+
* Added {Spidr::Agent#failed?}.
|
236
|
+
* Added `Spidr::Agent#every_failed_url`.
|
237
|
+
* Added {Spidr::Agent#clear}, which clears the history and failures URL
|
238
|
+
lists.
|
239
|
+
* Improved fault tolerance in {Spidr::Agent#get_page}.
|
240
|
+
* If a Network or HTTP error is encountered, the URL will be added to
|
241
|
+
the failures list and the next URL will be visited.
|
242
|
+
* Fixed a typo in `Spidr::Agent#ignore_exts_like`.
|
243
|
+
* Updated the Web Spider Obstacle Course with links that always fail to be
|
244
|
+
visited.
|
245
|
+
|
246
|
+
### 0.1.5 / 2009-03-22
|
247
|
+
|
248
|
+
* Catch malformed URIs in `Spidr::Page#to_absolute` and return `nil`.
|
249
|
+
* Filter out `nil` URIs in `Spidr::Page#urls`.
|
250
|
+
|
251
|
+
### 0.1.4 / 2009-01-15
|
252
|
+
|
253
|
+
* Use Nokogiri for HTML and XML parsing.
|
254
|
+
|
255
|
+
### 0.1.3 / 2009-01-10
|
256
|
+
|
257
|
+
* Added the `:host` options to {Spidr::Agent#initialize}.
|
258
|
+
* Added the Web Spider Obstacle Course files to the Manifest.
|
259
|
+
* Aliased {Spidr::Agent#visited_urls} to {Spidr::Agent#history}.
|
260
|
+
|
261
|
+
### 0.1.2 / 2008-11-06
|
262
|
+
|
263
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where URLs with no path were not
|
264
|
+
receiving a default path of `/`.
|
265
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where URL paths were not being
|
266
|
+
expanded, in order to remove `..` and `.` directories.
|
267
|
+
* Fixed a bug where absolute URLs could have a blank path, thus causing
|
268
|
+
{Spidr::Agent#get_page} to crash when it performed the HTTP request.
|
269
|
+
* Added RSpec spec tests.
|
270
|
+
* Created a Web-Spider Obstacle Course
|
271
|
+
(http://spidr.rubyforge.org/course/start.html) which is used in the spec
|
272
|
+
tests.
|
273
|
+
|
274
|
+
### 0.1.1 / 2008-10-04
|
275
|
+
|
276
|
+
* Added a reader method for the response instance variable in Page.
|
277
|
+
* Fixed a bug in {Spidr::Page#method_missing}.
|
278
|
+
|
279
|
+
### 0.1.0 / 2008-05-23
|
280
|
+
|
281
|
+
* Initial release.
|
282
|
+
* Black-list or white-list URLs based upon:
|
283
|
+
* Host name
|
284
|
+
* Port number
|
285
|
+
* Full link
|
286
|
+
* URL extension
|
287
|
+
* Provides call-backs for:
|
288
|
+
* Every visited Page.
|
289
|
+
* Every visited URL.
|
290
|
+
* Every visited URL that matches a specified pattern.
|
291
|
+
|
data/ChangeLog.md~
ADDED
@@ -0,0 +1,291 @@
|
|
1
|
+
### 0.4.2 /2012-04-12
|
2
|
+
|
3
|
+
* 对此gem进行了修改.
|
4
|
+
|
5
|
+
|
6
|
+
### 0.4.1 / 2011-12-08
|
7
|
+
|
8
|
+
* Catch `OpenSSL::SSL::SSLError` exceptions when initiated HTTPS Sessions.
|
9
|
+
|
10
|
+
### 0.4.0 / 2011-08-07
|
11
|
+
|
12
|
+
* Added {Spidr::Headers#content_charset}.
|
13
|
+
* Pass the Page `url` and `content_charset` to Nokogiri in {Spidr::Body#doc}.
|
14
|
+
This ensures that Nokogiri will preserve the body encoding.
|
15
|
+
* Made {Spidr::Headers#is_content_type?} public.
|
16
|
+
* Allow {Spidr::Headers#is_content_type?} to match the full Content-Type
|
17
|
+
or the sub-type.
|
18
|
+
|
19
|
+
### 0.3.2 / 2011-06-20
|
20
|
+
|
21
|
+
* Added separate intitialize methods for {Spidr::Actions}, {Spidr::Events},
|
22
|
+
{Spidr::Filters} and {Spidr::Sanitizers}.
|
23
|
+
* Aliased {Spidr::Events#urls_like} to {Spidr::Events#every_url_like}.
|
24
|
+
* Reduce usage of `self.included` and `module_eval`.
|
25
|
+
* Reduce usage of nested-blocks.
|
26
|
+
* Reduce usage of `return`.
|
27
|
+
|
28
|
+
### 0.3.1 / 2011-04-22
|
29
|
+
|
30
|
+
* Require `set` in `spidr/headers.rb`.
|
31
|
+
|
32
|
+
### 0.3.0 / 2011-04-14
|
33
|
+
|
34
|
+
* Switched from Jeweler to [Ore](http://github.com/ruby-ore/ore).
|
35
|
+
* Split all header related methods out of {Spidr::Page} and into
|
36
|
+
{Spidr::Headers}.
|
37
|
+
* Split all body related methods out of {Spidr::Page} and into
|
38
|
+
{Spidr::Body}.
|
39
|
+
* Split all link related methods out of {Spidr::Page} and into
|
40
|
+
{Spidr::Links}.
|
41
|
+
* Added {Spidr::Headers#directory?}.
|
42
|
+
* Added {Spidr::Headers#json?}.
|
43
|
+
* Added {Spidr::Links#each_url}.
|
44
|
+
* Added {Spidr::Links#each_link}.
|
45
|
+
* Added {Spidr::Links#each_redirect}.
|
46
|
+
* Added {Spidr::Links#each_meta_redirect}.
|
47
|
+
* Aliased {Spidr::Headers#raw_cookie} to {Spidr::Headers#cookie}.
|
48
|
+
* Aliased {Spidr::Body#to_s} to {Spidr::Body#body}.
|
49
|
+
* Also check for `application/xml` in {Spidr::Headers#xml?}.
|
50
|
+
* Catch all exceptions when merging URIs in {Spidr::Links#to_absolute}.
|
51
|
+
* Always prepend a `/` to all FTP URI paths. Fixes a Ruby 1.8 specific
|
52
|
+
bug, where it expects an absolute path for all FTP URIs.
|
53
|
+
* Refactored {URI.expand_path}.
|
54
|
+
* Start the session in {Spidr::SessionCache#[]} to prevent multiple
|
55
|
+
`CONNECT` commands being sent to HTTP Proxies (thanks falaise).
|
56
|
+
|
57
|
+
### 0.2.7 / 2010-08-17
|
58
|
+
|
59
|
+
* Added {Spidr::CookieJar#cookies_for_host} (thanks zapnap).
|
60
|
+
* Renamed `Spidr::Page#cookie` to `Spidr::Page#raw_cookie`.
|
61
|
+
* Rescue `URI::InvalidComponentError` exceptions in
|
62
|
+
`Spidr::Page#to_absolute` (thanks zapnap).
|
63
|
+
|
64
|
+
### 0.2.6 / 2010-07-05
|
65
|
+
|
66
|
+
* Fixed a bug in `Spidr::Page#meta_redirect`, by calling
|
67
|
+
`Nokogiri::XML::Element#get_attribute` instead of `attr`.
|
68
|
+
|
69
|
+
### 0.2.5 / 2010-07-02
|
70
|
+
|
71
|
+
* Added `Spidr::Page#meta_redirect`.
|
72
|
+
* Added `Spidr::Page#meta_redirect?`.
|
73
|
+
* Manage development dependencies with Bundler.
|
74
|
+
* Support following "old-school" meta-refresh redirects (thanks zapnap).
|
75
|
+
* Allow {Spidr::CookieJar} inherit cookies set by a parent domain.
|
76
|
+
* Fixed a constant lookup issue in {Spidr::Agent}.
|
77
|
+
* Use `yield` instead of `block.call` when necessary.
|
78
|
+
|
79
|
+
### 0.2.4 / 2010-05-05
|
80
|
+
|
81
|
+
* Added {Spidr::Filters#visit_urls}.
|
82
|
+
* Added {Spidr::Filters#visit_urls_like}.
|
83
|
+
* Added {Spidr::Filters#ignore_urls}.
|
84
|
+
* Added {Spidr::Filters#ignore_urls_like}.
|
85
|
+
* Added `Spidr::Page#is_content_type?`.
|
86
|
+
* Default `Spidr::Page#body` to an empty String.
|
87
|
+
* Default `Spidr::Page#content_type` to an empty String.
|
88
|
+
* Default `Spidr::Page#content_types` to an empty Array.
|
89
|
+
* Improved reliability of {Spidr::Page#is_redirect?}.
|
90
|
+
* Improved content type detection in {Spidr::Page} to handle `Content-Type`
|
91
|
+
headers containing charsets (thanks Josh Lindsey).
|
92
|
+
|
93
|
+
### 0.2.3 / 2010-02-27
|
94
|
+
|
95
|
+
* Migrated to Jeweler, for the packaging and releasing RubyGems.
|
96
|
+
* Switched to MarkDown formatted YARD documentation.
|
97
|
+
* Added {Spidr::Events#every_link}.
|
98
|
+
* Added {Spidr::SessionCache#active?}.
|
99
|
+
* Added specs for {Spidr::SessionCache}.
|
100
|
+
|
101
|
+
### 0.2.2 / 2010-01-06
|
102
|
+
|
103
|
+
* Require Web Spider Obstacle Course (WSOC) >= 0.1.1.
|
104
|
+
* Integrated the new WSOC into the specs.
|
105
|
+
* Removed the built-in Web Spider Obstacle Course.
|
106
|
+
* Added `Spidr::Page#content_types`.
|
107
|
+
* Added `Spidr::Page#cookie`.
|
108
|
+
* Added `Spidr::Page#cookies`.
|
109
|
+
* Added `Spidr::Page#cookie_params`.
|
110
|
+
* Added {Spidr::Sanitizers}.
|
111
|
+
* Added {Spidr::SessionCache}.
|
112
|
+
* Added {Spidr::CookieJar} (thanks Nick Plante).
|
113
|
+
* Added {Spidr::AuthStore} (thanks Nick Plante).
|
114
|
+
* Added {Spidr::Agent#post_page} (thanks Nick Plante).
|
115
|
+
* Renamed `Spidr::Agent#get_session` to {Spidr::SessionCache#[]}.
|
116
|
+
* Renamed `Spidr::Agent#kill_session` to {Spidr::SessionCache#kill!}.
|
117
|
+
|
118
|
+
### 0.2.1 / 2009-11-25
|
119
|
+
|
120
|
+
* Added {Spidr::Events#every_ok_page}.
|
121
|
+
* Added {Spidr::Events#every_redirect_page}.
|
122
|
+
* Added {Spidr::Events#every_timedout_page}.
|
123
|
+
* Added {Spidr::Events#every_bad_request_page}.
|
124
|
+
* Added {Spidr::Events#every_unauthorized_page}.
|
125
|
+
* Added {Spidr::Events#every_forbidden_page}.
|
126
|
+
* Added {Spidr::Events#every_missing_page}.
|
127
|
+
* Added {Spidr::Events#every_internal_server_error_page}.
|
128
|
+
* Added {Spidr::Events#every_txt_page}.
|
129
|
+
* Added {Spidr::Events#every_html_page}.
|
130
|
+
* Added {Spidr::Events#every_xml_page}.
|
131
|
+
* Added {Spidr::Events#every_xsl_page}.
|
132
|
+
* Added {Spidr::Events#every_doc}.
|
133
|
+
* Added {Spidr::Events#every_html_doc}.
|
134
|
+
* Added {Spidr::Events#every_xml_doc}.
|
135
|
+
* Added {Spidr::Events#every_xsl_doc}.
|
136
|
+
* Added {Spidr::Events#every_rss_doc}.
|
137
|
+
* Added {Spidr::Events#every_atom_doc}.
|
138
|
+
* Added {Spidr::Events#every_javascript_page}.
|
139
|
+
* Added {Spidr::Events#every_css_page}.
|
140
|
+
* Added {Spidr::Events#every_rss_page}.
|
141
|
+
* Added {Spidr::Events#every_atom_page}.
|
142
|
+
* Added {Spidr::Events#every_ms_word_page}.
|
143
|
+
* Added {Spidr::Events#every_pdf_page}.
|
144
|
+
* Added {Spidr::Events#every_zip_page}.
|
145
|
+
* Fixed a bug where {Spidr::Agent#delay} was not being used to delay
|
146
|
+
requesting pages.
|
147
|
+
* Spider `link` and `script` tags in HTML pages (thanks Nick Plante).
|
148
|
+
|
149
|
+
### 0.2.0 / 2009-10-10
|
150
|
+
|
151
|
+
* Added {URI.expand_path}.
|
152
|
+
* Added `Spidr::Page#search`.
|
153
|
+
* Added `Spidr::Page#at`.
|
154
|
+
* Added `Spidr::Page#title`.
|
155
|
+
* Added {Spidr::Agent#failures=}.
|
156
|
+
* Added a HTTP session cache to {Spidr::Agent}, per suggestion of falter.
|
157
|
+
* Added `Spidr::Agent#get_session`.
|
158
|
+
* Added `Spidr::Agent#kill_session`.
|
159
|
+
* Added {Spidr.proxy=}.
|
160
|
+
* Added {Spidr.disable_proxy!}.
|
161
|
+
* Aliased `Spidr::Page#txt?` to `Spidr::Page#plain_text?`.
|
162
|
+
* Aliased `Spidr::Page#ok?` to `Spidr::Page#is_ok?`.
|
163
|
+
* Aliased `Spidr::Page#redirect?` to `Spidr::Page#is_redirect?`.
|
164
|
+
* Aliased `Spidr::Page#unauthorized?` to `Spidr::Page#is_unauthorized?`.
|
165
|
+
* Aliased `Spidr::Page#forbidden?` to `Spidr::Page#is_forbidden?`.
|
166
|
+
* Aliased `Spidr::Page#missing?` to `Spidr::Page#is_missing?`.
|
167
|
+
* Split URL filtering code out of {Spidr::Agent} and into
|
168
|
+
{Spidr::Filters}.
|
169
|
+
* Split URL / Page event code out of {Spidr::Agent} and into
|
170
|
+
{Spidr::Events}.
|
171
|
+
* Split pause! / continue! / skip_link! / skip_page! methods out of
|
172
|
+
{Spidr::Agent} and into {Spidr::Actions}.
|
173
|
+
* Fixed a bug in `Spidr::Page#code`, where it was not returning an Integer.
|
174
|
+
* Make sure `Spidr::Page#doc` returns `Nokogiri::XML::Document` objects for
|
175
|
+
RSS/RDF/Atom pages as well.
|
176
|
+
* Fixed the handling of the Location header in `Spidr::Page#links`
|
177
|
+
(thanks falter).
|
178
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where trailing `/` characters on
|
179
|
+
URI paths were not being preserved (thanks falter).
|
180
|
+
* Fixed a bug where the URI query was not being sent with the request
|
181
|
+
in {Spidr::Agent#get_page} (thanks Damian Steer).
|
182
|
+
* Fixed a bug where SSL sessions were not being properly setup
|
183
|
+
(thanks falter).
|
184
|
+
* Switched {Spidr::Agent#history} to be a Set, to improve search-time
|
185
|
+
of the history (thanks falter).
|
186
|
+
* Switched {Spidr::Agent#failures} to a Set.
|
187
|
+
* Allow a block to be passed to {Spidr::Agent#run}, which will receive all
|
188
|
+
pages visited.
|
189
|
+
* Allow `Spidr::Agent#start_at` and `Spidr::Agent#continue!` to pass blocks
|
190
|
+
to {Spidr::Agent#run}.
|
191
|
+
* Made {Spidr::Agent#visit_page} public.
|
192
|
+
* Moved to YARD based documentation.
|
193
|
+
|
194
|
+
### 0.1.9 / 2009-06-13
|
195
|
+
|
196
|
+
* Upgraded to Hoe 2.0.0.
|
197
|
+
* Use Hoe.spec instead of Hoe.new.
|
198
|
+
* Use the Hoe signing task for signed gems.
|
199
|
+
* Added the `Spidr::Agent#schemes` and `Spidr::Agent#schemes=` methods.
|
200
|
+
* Added a warning message if 'net/https' cannot be loaded.
|
201
|
+
* Allow the list of acceptable URL schemes to be passed into
|
202
|
+
{Spidr::Agent#initialize}.
|
203
|
+
* Allow history and queue information to be passed into
|
204
|
+
{Spidr::Agent#initialize}.
|
205
|
+
* {Spidr::Agent#start_at} no longer clears the history or the queue.
|
206
|
+
* Fixed a bug in the sanitization of semi-escaped URLs.
|
207
|
+
* Fixed a bug where https URLs would be followed even if 'net/https'
|
208
|
+
could not be loaded.
|
209
|
+
* Removed Spidr::Agent::SCHEMES.
|
210
|
+
|
211
|
+
### 0.1.8 / 2009-05-27
|
212
|
+
|
213
|
+
* Added the `Spidr::Agent#pause!` and `Spidr::Agent#continue!` methods.
|
214
|
+
* Added the `Spidr::Agent#running?` and `Spidr::Agent#paused?` methods.
|
215
|
+
* Added an alias for pending_urls to the queue methods.
|
216
|
+
* Added {Spidr::Agent#queue} to provide read access to the queue.
|
217
|
+
* Added {Spidr::Agent#queue=} and {Spidr::Agent#history=} for setting the
|
218
|
+
queue and history.
|
219
|
+
* Added {Spidr::Agent#to_hash} which returns a Hash of the agents queue and
|
220
|
+
history.
|
221
|
+
* Made {Spidr::Agent#enqueue} and {Spidr::Agent#queued?} public.
|
222
|
+
* Added more specs.
|
223
|
+
|
224
|
+
### 0.1.7 / 2009-04-24
|
225
|
+
|
226
|
+
* Added `Spidr::Agent#all_headers`.
|
227
|
+
* Fixed a bug where {Spidr::Page#headers} was always `nil`.
|
228
|
+
* {Spidr::Agent} will now follow the Location header in HTTP 300,
|
229
|
+
301, 302, 303 and 307 Redirects.
|
230
|
+
* {Spidr::Agent} will now follow iframe and frame tags.
|
231
|
+
|
232
|
+
### 0.1.6 / 2009-04-14
|
233
|
+
|
234
|
+
* Added {Spidr::Agent#failures}, a list of URLs which could not be visited.
|
235
|
+
* Added {Spidr::Agent#failed?}.
|
236
|
+
* Added `Spidr::Agent#every_failed_url`.
|
237
|
+
* Added {Spidr::Agent#clear}, which clears the history and failures URL
|
238
|
+
lists.
|
239
|
+
* Improved fault tolerance in {Spidr::Agent#get_page}.
|
240
|
+
* If a Network or HTTP error is encountered, the URL will be added to
|
241
|
+
the failures list and the next URL will be visited.
|
242
|
+
* Fixed a typo in `Spidr::Agent#ignore_exts_like`.
|
243
|
+
* Updated the Web Spider Obstacle Course with links that always fail to be
|
244
|
+
visited.
|
245
|
+
|
246
|
+
### 0.1.5 / 2009-03-22
|
247
|
+
|
248
|
+
* Catch malformed URIs in `Spidr::Page#to_absolute` and return `nil`.
|
249
|
+
* Filter out `nil` URIs in `Spidr::Page#urls`.
|
250
|
+
|
251
|
+
### 0.1.4 / 2009-01-15
|
252
|
+
|
253
|
+
* Use Nokogiri for HTML and XML parsing.
|
254
|
+
|
255
|
+
### 0.1.3 / 2009-01-10
|
256
|
+
|
257
|
+
* Added the `:host` options to {Spidr::Agent#initialize}.
|
258
|
+
* Added the Web Spider Obstacle Course files to the Manifest.
|
259
|
+
* Aliased {Spidr::Agent#visited_urls} to {Spidr::Agent#history}.
|
260
|
+
|
261
|
+
### 0.1.2 / 2008-11-06
|
262
|
+
|
263
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where URLs with no path were not
|
264
|
+
receiving a default path of `/`.
|
265
|
+
* Fixed a bug in `Spidr::Page#to_absolute` where URL paths were not being
|
266
|
+
expanded, in order to remove `..` and `.` directories.
|
267
|
+
* Fixed a bug where absolute URLs could have a blank path, thus causing
|
268
|
+
{Spidr::Agent#get_page} to crash when it performed the HTTP request.
|
269
|
+
* Added RSpec spec tests.
|
270
|
+
* Created a Web-Spider Obstacle Course
|
271
|
+
(http://spidr.rubyforge.org/course/start.html) which is used in the spec
|
272
|
+
tests.
|
273
|
+
|
274
|
+
### 0.1.1 / 2008-10-04
|
275
|
+
|
276
|
+
* Added a reader method for the response instance variable in Page.
|
277
|
+
* Fixed a bug in {Spidr::Page#method_missing}.
|
278
|
+
|
279
|
+
### 0.1.0 / 2008-05-23
|
280
|
+
|
281
|
+
* Initial release.
|
282
|
+
* Black-list or white-list URLs based upon:
|
283
|
+
* Host name
|
284
|
+
* Port number
|
285
|
+
* Full link
|
286
|
+
* URL extension
|
287
|
+
* Provides call-backs for:
|
288
|
+
* Every visited Page.
|
289
|
+
* Every visited URL.
|
290
|
+
* Every visited URL that matches a specified pattern.
|
291
|
+
|
data/Gemfile
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
source 'http://ruby.taobao.org'
|
2
|
+
|
3
|
+
platform :jruby do
|
4
|
+
gem 'jruby-openssl'
|
5
|
+
end
|
6
|
+
|
7
|
+
gemspec
|
8
|
+
|
9
|
+
group :development do
|
10
|
+
gem 'rake', '~> 10.0'
|
11
|
+
gem 'rubygems-tasks', '~> 0.1'
|
12
|
+
gem 'rspec', '~> 2.4'
|
13
|
+
|
14
|
+
gem 'wsoc', '~> 0.1.3'
|
15
|
+
gem 'kramdown', '~> 0.12'
|
16
|
+
end
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
spidr_epg (1.0.0)
|
5
|
+
nokogiri (~> 1.3)
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: http://ruby.taobao.org/
|
9
|
+
specs:
|
10
|
+
diff-lcs (1.2.3)
|
11
|
+
json (1.7.7)
|
12
|
+
kramdown (0.14.2)
|
13
|
+
nokogiri (1.5.9)
|
14
|
+
rack (1.5.2)
|
15
|
+
rack-protection (1.5.0)
|
16
|
+
rack
|
17
|
+
rake (10.0.4)
|
18
|
+
rspec (2.13.0)
|
19
|
+
rspec-core (~> 2.13.0)
|
20
|
+
rspec-expectations (~> 2.13.0)
|
21
|
+
rspec-mocks (~> 2.13.0)
|
22
|
+
rspec-core (2.13.1)
|
23
|
+
rspec-expectations (2.13.0)
|
24
|
+
diff-lcs (>= 1.1.3, < 2.0)
|
25
|
+
rspec-mocks (2.13.1)
|
26
|
+
rubygems-tasks (0.2.4)
|
27
|
+
sinatra (1.4.2)
|
28
|
+
rack (~> 1.5, >= 1.5.2)
|
29
|
+
rack-protection (~> 1.4)
|
30
|
+
tilt (~> 1.3, >= 1.3.4)
|
31
|
+
tilt (1.3.7)
|
32
|
+
wsoc (0.1.4)
|
33
|
+
json (~> 1.4)
|
34
|
+
sinatra (~> 1.0)
|
35
|
+
yard (0.8.5.2)
|
36
|
+
|
37
|
+
PLATFORMS
|
38
|
+
ruby
|
39
|
+
|
40
|
+
DEPENDENCIES
|
41
|
+
bundler (~> 1.0)
|
42
|
+
jruby-openssl
|
43
|
+
kramdown (~> 0.12)
|
44
|
+
rake (~> 10.0)
|
45
|
+
rspec (~> 2.4)
|
46
|
+
rubygems-tasks (~> 0.1)
|
47
|
+
spidr_epg!
|
48
|
+
wsoc (~> 0.1.3)
|
49
|
+
yard (~> 0.7)
|
data/Gemfile~
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
source 'http://ruby.taobao.org'
|
2
|
+
|
3
|
+
platform :jruby do
|
4
|
+
gem 'jruby-openssl'
|
5
|
+
end
|
6
|
+
|
7
|
+
gemspec
|
8
|
+
|
9
|
+
group :development do
|
10
|
+
gem 'rake', '~> 10.0'
|
11
|
+
gem 'rubygems-tasks', '~> 0.1'
|
12
|
+
gem 'rspec', '~> 2.4'
|
13
|
+
|
14
|
+
gem 'wsoc', '~> 0.1.3'
|
15
|
+
gem 'kramdown', '~> 0.12'
|
16
|
+
end
|