linkedincrawler 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.
- checksums.yaml +7 -0
- data/lib/linkedin_crawler.rb +47 -0
- metadata +87 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 266cfd3d2297b67906c17aa1781ddf37b9519683
|
|
4
|
+
data.tar.gz: 9c46996cd2eef74e646e4378099afcfe5d357cc7
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 350fa16c241578c88e840b9ccaab17267bdc9b7af9bb38882e6b73a5a9c72b06511b752dc8e47015bc2698840b38870559c5bd40f58a4d3cdb914884244cc6cd
|
|
7
|
+
data.tar.gz: de3aef7908c810900828f4a9a399cf939950ddf32495835dba4cd613804b80044e4f9757f5cec707b2f009aa680ca2fbf5eb0c545e046e08f323c3603822c6d2
|
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
require 'linkedinparser'
|
|
2
|
+
require 'generalscraper'
|
|
3
|
+
require 'selenium-webdriver'
|
|
4
|
+
require 'pry'
|
|
5
|
+
|
|
6
|
+
class LinkedinCrawler
|
|
7
|
+
include ProxyManager
|
|
8
|
+
def initialize(search_terms)
|
|
9
|
+
@search_terms = search_terms
|
|
10
|
+
@output = Array.new
|
|
11
|
+
end
|
|
12
|
+
|
|
13
|
+
# Run search terms and get results
|
|
14
|
+
def search
|
|
15
|
+
# Run Google search
|
|
16
|
+
g = GeneralScraper.new("site:linkedin.com/pub", @search_terms, "/home/shidash/proxies", false)
|
|
17
|
+
|
|
18
|
+
# Scrape each resulting LinkedIn page
|
|
19
|
+
gen_driver
|
|
20
|
+
JSON.parse(g.getURLs).each do |profile|
|
|
21
|
+
scrape(profile)
|
|
22
|
+
end
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
# Generate driver for searches
|
|
26
|
+
def gen_driver
|
|
27
|
+
profile = Selenium::WebDriver::Firefox::Profile.new
|
|
28
|
+
profile['intl.accept_languages'] = 'en'
|
|
29
|
+
profile["javascript.enabled"] = false
|
|
30
|
+
@driver = Selenium::WebDriver.for :firefox, profile: profile
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
# Scrape each page
|
|
34
|
+
def scrape(profile_url)
|
|
35
|
+
# Get profile page
|
|
36
|
+
profile_html = getPage(profile_url, @driver, nil, 5, false).page_source
|
|
37
|
+
|
|
38
|
+
# Parse profile and add to output
|
|
39
|
+
l = LinkedinParser.new(profile_html, profile_url, {timestamp: Time.now})
|
|
40
|
+
@output += JSON.parse(l.results_by_job)
|
|
41
|
+
end
|
|
42
|
+
|
|
43
|
+
# Print output in JSON
|
|
44
|
+
def gen_json
|
|
45
|
+
JSON.pretty_generate(@output)
|
|
46
|
+
end
|
|
47
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: linkedincrawler
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.0.1
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- M. C. McGrath
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2015-11-01 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: linkedinparser
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - ">="
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '0'
|
|
20
|
+
type: :runtime
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - ">="
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '0'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: generalscraper
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - ">="
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '0'
|
|
34
|
+
type: :runtime
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - ">="
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: selenium-webdriver
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ">="
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '0'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ">="
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '0'
|
|
55
|
+
description: Crawls public LinkedIn profiles via Google
|
|
56
|
+
email: shidash@shidash.com
|
|
57
|
+
executables: []
|
|
58
|
+
extensions: []
|
|
59
|
+
extra_rdoc_files: []
|
|
60
|
+
files:
|
|
61
|
+
- lib/linkedin_crawler.rb
|
|
62
|
+
homepage: https://github.com/TransparencyToolkit/linkedincrawler
|
|
63
|
+
licenses:
|
|
64
|
+
- GPL
|
|
65
|
+
metadata: {}
|
|
66
|
+
post_install_message:
|
|
67
|
+
rdoc_options: []
|
|
68
|
+
require_paths:
|
|
69
|
+
- lib
|
|
70
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
71
|
+
requirements:
|
|
72
|
+
- - ">="
|
|
73
|
+
- !ruby/object:Gem::Version
|
|
74
|
+
version: '0'
|
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
76
|
+
requirements:
|
|
77
|
+
- - ">="
|
|
78
|
+
- !ruby/object:Gem::Version
|
|
79
|
+
version: '0'
|
|
80
|
+
requirements: []
|
|
81
|
+
rubyforge_project:
|
|
82
|
+
rubygems_version: 2.4.8
|
|
83
|
+
signing_key:
|
|
84
|
+
specification_version: 4
|
|
85
|
+
summary: Crawls public LinkedIn profiles
|
|
86
|
+
test_files: []
|
|
87
|
+
has_rdoc:
|