site_analyzer 0.3.6 → 0.3.7

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.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 01f6ddeb9574d0402169ad3af49b61843d6facd1
4
- data.tar.gz: 92754bb42e9d2e127c6733b57bd576149ac562f7
3
+ metadata.gz: 4f05a59c87eede4f51732073b0be7431fb6f65ec
4
+ data.tar.gz: 108843386db0fff5d6f35887f441c6bcadd2292f
5
5
  SHA512:
6
- metadata.gz: 0a7d38af78374c61bea5ad3a1070e3ba030ae43827588056d517bd84d835a6148b7a0b57e1b3e3e4c77af554e528de99f076b96c5627b2e027939d55bd4e848e
7
- data.tar.gz: d3176091cf933db367f8d01d08c1242e5afe4ed6661ab203ecc985767f2b5a49a36bc06395b34ee87e478b15d2479df38bffe45cfab0c9b0c572be8c96737cfb
6
+ metadata.gz: d085dc4331fd2bb4e133979e9e50863da259e1d9fe44493ab299478e55995488f9e25c05885e6efac51d74c7c4e573b58d6b467102a9990f950a9729c7d29a72
7
+ data.tar.gz: f62e9e991372ae6d9637fc23544ebed5c33ec480a50104ca90c822a56a69f2b146d17b2610e50ed86cca3b0bfbcad346bfbe8439958307009df035f61a0f22b4
data/Gemfile.lock CHANGED
@@ -1,7 +1,7 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- site_analyzer (0.3.5)
4
+ site_analyzer (0.3.6)
5
5
  addressable (~> 2.3)
6
6
  nokogiri (~> 1.6)
7
7
  robotstxt (~> 0.5)
@@ -18,6 +18,8 @@ module SiteAnalyzer
18
18
 
19
19
  def get_page(url)
20
20
  timeout(10) { Nokogiri::HTML(open(url)) }
21
+ rescue Timeout::Error
22
+ ['Timeout exception']
21
23
  end
22
24
 
23
25
  def get_domain(url)
@@ -44,9 +44,10 @@ module SiteAnalyzer
44
44
  puts header
45
45
  @report.each_pair do |key, value|
46
46
  rows = []
47
+ value = ['Too many for console report'] if key == :a_tags_list
47
48
  value.each do |r|
48
49
  r = [r] if r.class == String
49
- rows << r unless key == :a_tags_list
50
+ rows << r
50
51
  end
51
52
  table = Terminal::Table.new title: key, rows: rows
52
53
  puts table
@@ -116,8 +117,12 @@ module SiteAnalyzer
116
117
  def bad_url
117
118
  result = []
118
119
  a_tag_array.each do |url|
119
- url[1] = '-' unless url[1]
120
- result << url unless URI(url[1][0]).path =~ /^[\/a-z0-9-]+$/
120
+ begin
121
+ uri = URI(url[1])
122
+ result << url if (uri.scheme == 'http' || uri.scheme == 'https' ) unless uri.path =~ /^[\/a-z0-9-.]+$/
123
+ rescue URI::InvalidURIError
124
+ result << url
125
+ end
121
126
  end
122
127
  result
123
128
  end
@@ -135,7 +140,7 @@ module SiteAnalyzer
135
140
  end
136
141
 
137
142
  def h2_doubles
138
- find_doubles(@site.all_h2)
143
+ find_doubles @site.all_h2
139
144
  end
140
145
 
141
146
  def not_uniq_words_in_h2
@@ -82,8 +82,12 @@ module SiteAnalyzer
82
82
  def all_a
83
83
  result = []
84
84
  @pages.each do |page|
85
- tags = page.all_a_tags.compact
86
- result << [page.page_url, tags[0], tags[1], tags[2]]
85
+ page.all_a_tags.compact.each do |tag|
86
+ tag[0] = '-' unless tag[0]
87
+ tag[1] = '-' unless tag[1]
88
+ tag[2] = '-' unless tag[2]
89
+ result << [page.page_url, tag[0], tag[1], tag[2]]
90
+ end
87
91
  end
88
92
  result.compact
89
93
  end
@@ -1,3 +1,3 @@
1
1
  module SiteAnalyzer
2
- VERSION = "0.3.6"
2
+ VERSION = "0.3.7"
3
3
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: site_analyzer
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.3.6
4
+ version: 0.3.7
5
5
  platform: ruby
6
6
  authors:
7
7
  - Denis Savchuk