gimme_poc 0.0.2 → 0.0.3
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/lib/gimme_poc/version.rb +1 -1
- data/lib/gimme_poc.rb +14 -15
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6984d721d974f11b5dab3136323f68d924867ad6
|
4
|
+
data.tar.gz: 78503da039ce280bb1bb69898065b5d60a2d5463
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 52770e7b95a98abc5638e7b017674f5c58b61b22bbed847bb009cc5092aea3f533922f0da9bd0a571c5e40050f26779c5734bb21c308f065742c66994f0faf16
|
7
|
+
data.tar.gz: b8405f565d973365c4bd05d6cab1f52295bd4b83c0fac858654e87d738cb3cf758096b6f5e2402716a2c768e11182479b71a6cad7c18869751a0fdadd9e6a7cf
|
data/lib/gimme_poc/version.rb
CHANGED
data/lib/gimme_poc.rb
CHANGED
@@ -9,7 +9,7 @@ module Gimme
|
|
9
9
|
|
10
10
|
# Simple regex that looks for ###.#### or ###-####
|
11
11
|
PHONE_REGEX = /\d{3}[-]\d{4}|\d{3}[.]\d{4}/
|
12
|
-
|
12
|
+
|
13
13
|
# Captures http:// and https://
|
14
14
|
HTTP_REGEX = /\A\bhttps:\/\/|\bhttp:\/\//
|
15
15
|
|
@@ -64,14 +64,15 @@ module Gimme
|
|
64
64
|
puts '-' * 50
|
65
65
|
puts "starting: #{url}"
|
66
66
|
next if get(url).nil?
|
67
|
-
puts
|
67
|
+
puts 'now looking for contact pages'
|
68
68
|
start_contact_links
|
69
69
|
mechpage = go_to_contact_page
|
70
|
+
next if mechpage.nil?
|
70
71
|
save_available_contacts(mechpage.uri.to_s)
|
71
72
|
end
|
72
73
|
Search.all_sites
|
73
74
|
end
|
74
|
-
|
75
|
+
|
75
76
|
# Mechanize needs absolute urls to work.
|
76
77
|
# If http:// or https:// isn't present, append http://.
|
77
78
|
def format_url(str)
|
@@ -115,7 +116,7 @@ module Gimme
|
|
115
116
|
def contact_page
|
116
117
|
contact_link = link_with_href(/contact|Contact/)
|
117
118
|
contact_test_page = merged_link('../contact')
|
118
|
-
|
119
|
+
|
119
120
|
case
|
120
121
|
when !contact_link.nil?
|
121
122
|
puts "#{'success:'.green} Found contact link!\n"
|
@@ -138,32 +139,30 @@ module Gimme
|
|
138
139
|
english_link = page.link_with(href: /english|English/)
|
139
140
|
test_en_page = merged_link('../en')
|
140
141
|
test_english_page = merged_link('../english')
|
141
|
-
|
142
|
+
|
142
143
|
case
|
143
144
|
when !english_link.nil?
|
144
145
|
puts "#{'success:'.green} found english link!"
|
145
146
|
get(merged(english_link)) # already merged link
|
146
147
|
else
|
147
148
|
blind_test(test_en_page) || blind_test(test_english_page)
|
148
|
-
puts
|
149
|
+
puts 'ready to start again'
|
149
150
|
contact_page
|
150
151
|
end
|
151
152
|
end
|
152
153
|
|
153
|
-
# TODO: Sometimes DNS will do a redirect and not give a 404.
|
154
|
+
# TODO: Sometimes DNS will do a redirect and not give a 404.
|
154
155
|
# Need to prevent redirects.
|
155
156
|
#
|
156
157
|
# Blindly tests to see if a url goes through. If there is a 404 error,
|
157
158
|
# this will return nil.
|
158
159
|
def blind_test(url)
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
163
|
-
puts "#{'404 Error:'.red} #{url}"
|
164
|
-
end
|
160
|
+
puts "\nblind testing: #{url}"
|
161
|
+
get(url)
|
162
|
+
rescue Mechanize::ResponseCodeError
|
163
|
+
puts "#{'404 Error:'.red} #{url}"
|
165
164
|
end
|
166
|
-
|
165
|
+
|
167
166
|
##
|
168
167
|
# Used in case of relative paths. Merging guarantees correct url.
|
169
168
|
# This needs a url string as argument to work.
|
@@ -180,7 +179,7 @@ module Gimme
|
|
180
179
|
def link_with_href(str)
|
181
180
|
merged_link(page.link_with(href: /\b#{str}/).uri.to_s)
|
182
181
|
rescue
|
183
|
-
|
182
|
+
nil
|
184
183
|
end
|
185
184
|
|
186
185
|
##
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: gimme_poc
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- John Mason
|
@@ -112,7 +112,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
112
112
|
version: '0'
|
113
113
|
requirements: []
|
114
114
|
rubyforge_project:
|
115
|
-
rubygems_version: 2.4.
|
115
|
+
rubygems_version: 2.4.5
|
116
116
|
signing_key:
|
117
117
|
specification_version: 4
|
118
118
|
summary: Get a point of contact. Given a url or array of urls, extracts social media
|