site_analyzer 0.3.11 → 0.3.12
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 +4 -4
- data/Gemfile.lock +1 -1
- data/lib/site_analyzer/page.rb +9 -3
- data/lib/site_analyzer/site.rb +9 -2
- data/lib/site_analyzer/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: fe1d0ebb0469f94188c31f5111d4493337eb0c01
|
4
|
+
data.tar.gz: 0f4e260c964d757cfe17ba1f0a24c6ced3ccc004
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0cf6c7e6ffa7819b39bb2bd9acab7e461056206f4d7de38d45a719287c67e361f0d92471c2209aea308b10d8b795e8fe68aa91a45e375535122c753f29876497
|
7
|
+
data.tar.gz: 705126a665745b90106c274cea37d2c550ca2b8de2b4d941d1d62a4a89800f3618059dfaa35596ee7fd2f040b6b9dfe89ca62cd672b847c2489522b808987f3a
|
data/Gemfile.lock
CHANGED
data/lib/site_analyzer/page.rb
CHANGED
@@ -103,8 +103,11 @@ module SiteAnalyzer
|
|
103
103
|
def home_a
|
104
104
|
if @page
|
105
105
|
home_a = []
|
106
|
-
all_a_tags_href.each do |link|
|
107
|
-
|
106
|
+
all_a_tags_href.uniq.each do |link|
|
107
|
+
if get_domain(link) && @site_url
|
108
|
+
domain = get_domain(link)
|
109
|
+
home_a << link if domain == @site_url
|
110
|
+
end
|
108
111
|
end
|
109
112
|
home_a
|
110
113
|
end
|
@@ -114,7 +117,10 @@ module SiteAnalyzer
|
|
114
117
|
if @page
|
115
118
|
remote_a = []
|
116
119
|
all_a_tags_href.uniq.each do |link|
|
117
|
-
|
120
|
+
if get_domain(link) && @site_url
|
121
|
+
domain = get_domain(link)
|
122
|
+
remote_a << link unless domain == @site_url
|
123
|
+
end
|
118
124
|
end
|
119
125
|
remote_a
|
120
126
|
end
|
data/lib/site_analyzer/site.rb
CHANGED
@@ -31,6 +31,8 @@ module SiteAnalyzer
|
|
31
31
|
add_page @pages_for_scan.pop
|
32
32
|
return if @max_pages <= 0
|
33
33
|
add_pages_for_scan!
|
34
|
+
optimize_scan!
|
35
|
+
return if @pages_for_scan.size == 0
|
34
36
|
end
|
35
37
|
end
|
36
38
|
|
@@ -41,11 +43,10 @@ module SiteAnalyzer
|
|
41
43
|
@bad_pages << page.page_url unless page.page
|
42
44
|
if page.page
|
43
45
|
page.home_a.each do |link|
|
44
|
-
@pages_for_scan << link unless link.nil? ||
|
46
|
+
@pages_for_scan << link unless link.nil? || link.start_with?('mailto:') || link.start_with?('skype:') || link.end_with?('.jpg')
|
45
47
|
end
|
46
48
|
end
|
47
49
|
end
|
48
|
-
@pages_for_scan.clear if @pages_for_scan.size == 0
|
49
50
|
end
|
50
51
|
|
51
52
|
def add_page(url)
|
@@ -103,5 +104,11 @@ module SiteAnalyzer
|
|
103
104
|
end
|
104
105
|
result.compact
|
105
106
|
end
|
107
|
+
|
108
|
+
def optimize_scan!
|
109
|
+
@pages_for_scan.uniq.compact!
|
110
|
+
@scanned_pages.uniq.compact!
|
111
|
+
@pages_for_scan = @pages_for_scan - @scanned_pages
|
112
|
+
end
|
106
113
|
end
|
107
114
|
end
|