linkedindata 0.0.1
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/linkedindata.rb +69 -0
- metadata +47 -0
data/lib/linkedindata.rb
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
require 'mechanize'
|
|
2
|
+
require 'linkedin-scraper'
|
|
3
|
+
require 'json'
|
|
4
|
+
|
|
5
|
+
class LinkedinData
|
|
6
|
+
def initialize(input)
|
|
7
|
+
@input = input
|
|
8
|
+
@output = Array.new
|
|
9
|
+
end
|
|
10
|
+
|
|
11
|
+
# Searches for links on Google
|
|
12
|
+
def search
|
|
13
|
+
agent = Mechanize.new
|
|
14
|
+
gform = agent.get("http://google.com").form("f")
|
|
15
|
+
gform.q = "site:linkedin.com/pub " + @input
|
|
16
|
+
page = agent.submit(gform, gform.buttons.first)
|
|
17
|
+
examine(page)
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
# Examines a search page
|
|
21
|
+
def examine(page)
|
|
22
|
+
startindex = 0
|
|
23
|
+
|
|
24
|
+
page.links.each do |link|
|
|
25
|
+
if (link.href.include? "linkedin.com") && (!link.href.include? "webcache") && (!link.href.include? "site:linkedin.com/pub+")
|
|
26
|
+
saveurl = link.href.split("?q=")
|
|
27
|
+
|
|
28
|
+
if saveurl[1]
|
|
29
|
+
url = saveurl[1].split("&")
|
|
30
|
+
scrape(url[0])
|
|
31
|
+
end
|
|
32
|
+
end
|
|
33
|
+
|
|
34
|
+
if (link.href.include? "&sa=N") && (link.href.include? "&start=")
|
|
35
|
+
url1 = link.href.split("&start=")
|
|
36
|
+
url2 = url1[1].split("&sa=N")
|
|
37
|
+
|
|
38
|
+
if url2[0].to_i < startindex
|
|
39
|
+
agent = Mechanize.new
|
|
40
|
+
examine(agent.get("http://google.com" + link.href))
|
|
41
|
+
else startindex = url2[0].to_i
|
|
42
|
+
end
|
|
43
|
+
end
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
|
|
47
|
+
# Scrapes profile and makes JSON
|
|
48
|
+
def scrape(url)
|
|
49
|
+
profile = Linkedin::Profile.get_profile(url)
|
|
50
|
+
|
|
51
|
+
if profile
|
|
52
|
+
profile.current_companies.each do |c|
|
|
53
|
+
c.merge!(:name => profile.first_name + " " + profile.last_name)
|
|
54
|
+
@output.push(c)
|
|
55
|
+
end
|
|
56
|
+
|
|
57
|
+
profile.past_companies.each do |c|
|
|
58
|
+
c.merge!(:name => profile.first_name + " " + profile.last_name)
|
|
59
|
+
@output.push(c)
|
|
60
|
+
end
|
|
61
|
+
end
|
|
62
|
+
end
|
|
63
|
+
|
|
64
|
+
# Gets all data and returns in JSON
|
|
65
|
+
def getData
|
|
66
|
+
search
|
|
67
|
+
return @output.to_json
|
|
68
|
+
end
|
|
69
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: linkedindata
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
prerelease:
|
|
6
|
+
platform: ruby
|
|
7
|
+
authors:
|
|
8
|
+
- M. C. McGrath
|
|
9
|
+
autorequire:
|
|
10
|
+
bindir: bin
|
|
11
|
+
cert_chain: []
|
|
12
|
+
date: 2014-01-07 00:00:00.000000000 Z
|
|
13
|
+
dependencies: []
|
|
14
|
+
description: Scrapes all LinkedIn profiles including terms you specify.
|
|
15
|
+
email: shidash@shidash.com
|
|
16
|
+
executables: []
|
|
17
|
+
extensions: []
|
|
18
|
+
extra_rdoc_files: []
|
|
19
|
+
files:
|
|
20
|
+
- lib/linkedindata.rb
|
|
21
|
+
homepage: https://github.com/Shidash/LinkedInData
|
|
22
|
+
licenses:
|
|
23
|
+
- GPL
|
|
24
|
+
post_install_message:
|
|
25
|
+
rdoc_options: []
|
|
26
|
+
require_paths:
|
|
27
|
+
- lib
|
|
28
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
29
|
+
none: false
|
|
30
|
+
requirements:
|
|
31
|
+
- - ! '>='
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '0'
|
|
34
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
35
|
+
none: false
|
|
36
|
+
requirements:
|
|
37
|
+
- - ! '>='
|
|
38
|
+
- !ruby/object:Gem::Version
|
|
39
|
+
version: '0'
|
|
40
|
+
requirements: []
|
|
41
|
+
rubyforge_project:
|
|
42
|
+
rubygems_version: 1.8.23
|
|
43
|
+
signing_key:
|
|
44
|
+
specification_version: 3
|
|
45
|
+
summary: Get all LinkedIn profiles including terms you specify
|
|
46
|
+
test_files: []
|
|
47
|
+
has_rdoc:
|