metainspector 1.8.8 → 1.8.9
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.
- data/lib/meta_inspector/scraper.rb +6 -3
- data/lib/meta_inspector/version.rb +1 -1
- data/meta_inspector.gemspec +3 -3
- data/samples/spider.rb +1 -0
- metadata +15 -15
@@ -3,7 +3,6 @@
|
|
3
3
|
require 'open-uri'
|
4
4
|
require 'nokogiri'
|
5
5
|
require 'charguess'
|
6
|
-
require 'iconv'
|
7
6
|
require 'hashie/rash'
|
8
7
|
|
9
8
|
# MetaInspector provides an easy way to scrape web pages and get its elements
|
@@ -86,8 +85,9 @@ module MetaInspector
|
|
86
85
|
def parsed_document
|
87
86
|
@parsed_document ||= Nokogiri::HTML(document)
|
88
87
|
|
89
|
-
rescue
|
88
|
+
rescue Exception => e
|
90
89
|
warn 'An exception occurred while trying to scrape the page!'
|
90
|
+
warn e.message
|
91
91
|
end
|
92
92
|
|
93
93
|
# Returns the original, unparsed document
|
@@ -99,8 +99,11 @@ module MetaInspector
|
|
99
99
|
@scraped = false
|
100
100
|
rescue TimeoutError
|
101
101
|
warn 'Timeout!!!'
|
102
|
-
|
102
|
+
@scraped = false
|
103
|
+
rescue Exception => e
|
103
104
|
warn 'An exception occurred while trying to fetch the page!'
|
105
|
+
warn e.message
|
106
|
+
@scraped = false
|
104
107
|
end
|
105
108
|
|
106
109
|
# Scrapers for all meta_tags in the form of "meta_name" are automatically defined. This has been tested for
|
data/meta_inspector.gemspec
CHANGED
@@ -14,12 +14,12 @@ Gem::Specification.new do |gem|
|
|
14
14
|
gem.require_paths = ["lib"]
|
15
15
|
gem.version = MetaInspector::VERSION
|
16
16
|
|
17
|
-
gem.add_dependency 'nokogiri', '1.5.
|
17
|
+
gem.add_dependency 'nokogiri', '1.5.3'
|
18
18
|
gem.add_dependency 'charguess', '1.3.20111021164500'
|
19
19
|
gem.add_dependency 'rash', '0.3.2'
|
20
20
|
|
21
|
-
gem.add_development_dependency 'rspec', '2.
|
21
|
+
gem.add_development_dependency 'rspec', '2.10.0'
|
22
22
|
gem.add_development_dependency 'fakeweb', '1.3.0'
|
23
|
-
gem.add_development_dependency 'awesome_print', '0.
|
23
|
+
gem.add_development_dependency 'awesome_print', '1.0.2'
|
24
24
|
gem.add_development_dependency 'rake', '0.9.2.2'
|
25
25
|
end
|
data/samples/spider.rb
CHANGED
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: metainspector
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 37
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 1
|
8
8
|
- 8
|
9
|
-
-
|
10
|
-
version: 1.8.
|
9
|
+
- 9
|
10
|
+
version: 1.8.9
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Jaime Iniesta
|
@@ -15,7 +15,7 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date:
|
18
|
+
date: 2012-06-03 00:00:00 Z
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
21
21
|
name: nokogiri
|
@@ -25,12 +25,12 @@ dependencies:
|
|
25
25
|
requirements:
|
26
26
|
- - "="
|
27
27
|
- !ruby/object:Gem::Version
|
28
|
-
hash:
|
28
|
+
hash: 5
|
29
29
|
segments:
|
30
30
|
- 1
|
31
31
|
- 5
|
32
|
-
-
|
33
|
-
version: 1.5.
|
32
|
+
- 3
|
33
|
+
version: 1.5.3
|
34
34
|
type: :runtime
|
35
35
|
version_requirements: *id001
|
36
36
|
- !ruby/object:Gem::Dependency
|
@@ -73,12 +73,12 @@ dependencies:
|
|
73
73
|
requirements:
|
74
74
|
- - "="
|
75
75
|
- !ruby/object:Gem::Version
|
76
|
-
hash:
|
76
|
+
hash: 39
|
77
77
|
segments:
|
78
78
|
- 2
|
79
|
-
-
|
79
|
+
- 10
|
80
80
|
- 0
|
81
|
-
version: 2.
|
81
|
+
version: 2.10.0
|
82
82
|
type: :development
|
83
83
|
version_requirements: *id004
|
84
84
|
- !ruby/object:Gem::Dependency
|
@@ -105,12 +105,12 @@ dependencies:
|
|
105
105
|
requirements:
|
106
106
|
- - "="
|
107
107
|
- !ruby/object:Gem::Version
|
108
|
-
hash:
|
108
|
+
hash: 19
|
109
109
|
segments:
|
110
|
+
- 1
|
110
111
|
- 0
|
111
|
-
-
|
112
|
-
|
113
|
-
version: 0.4.0
|
112
|
+
- 2
|
113
|
+
version: 1.0.2
|
114
114
|
type: :development
|
115
115
|
version_requirements: *id006
|
116
116
|
- !ruby/object:Gem::Dependency
|
@@ -193,7 +193,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
193
193
|
requirements: []
|
194
194
|
|
195
195
|
rubyforge_project:
|
196
|
-
rubygems_version: 1.8.
|
196
|
+
rubygems_version: 1.8.15
|
197
197
|
signing_key:
|
198
198
|
specification_version: 3
|
199
199
|
summary: MetaInspector is a ruby gem for web scraping purposes, that returns a hash with metadata from a given URL
|