linkedincrawler 0.0.14 → 0.0.15
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/linkedincrawler.rb +9 -3
- 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: d133e662b783dcf61594013b375ddec17cb22102
|
|
4
|
+
data.tar.gz: 4c477ee0f284c4bc13171d25c747cf9f2b42c090
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 47a121927417ce0d195d5be681d533f35c88613710f104d540e032bc9539ebd25840163eda54c75a63caeb27924f1fc65fd767042e5e18664d4c0fd13809e01e
|
|
7
|
+
data.tar.gz: 87f53246bb4d98c67683525ea32095729a453502e0426f87268edd949809fea93ea27da0f288598a1698202b433e7a75f660c64820a2bb66b2605a56ad8d563c
|
data/lib/linkedincrawler.rb
CHANGED
|
@@ -6,7 +6,7 @@ require 'selenium-webdriver'
|
|
|
6
6
|
require 'pry'
|
|
7
7
|
|
|
8
8
|
class LinkedinCrawler
|
|
9
|
-
def initialize(search_terms, retry_limit, requests, requests_google, solver_details)
|
|
9
|
+
def initialize(search_terms, retry_limit, requests, requests_google, requests_google2, solver_details)
|
|
10
10
|
@search_terms = search_terms
|
|
11
11
|
@output = Array.new
|
|
12
12
|
|
|
@@ -15,6 +15,7 @@ class LinkedinCrawler
|
|
|
15
15
|
|
|
16
16
|
@requests = requests
|
|
17
17
|
@requests_google = requests_google
|
|
18
|
+
@requests_google2 = requests_google2
|
|
18
19
|
@solver_details = solver_details
|
|
19
20
|
end
|
|
20
21
|
|
|
@@ -23,9 +24,13 @@ class LinkedinCrawler
|
|
|
23
24
|
# Run Google search
|
|
24
25
|
g = GeneralScraper.new("site:linkedin.com/pub -site:linkedin.com/pub/dir/", @search_terms, @requests_google, @solver_details)
|
|
25
26
|
urls = g.getURLs
|
|
26
|
-
|
|
27
|
+
|
|
28
|
+
# Look for new LI urls
|
|
29
|
+
g2 = GeneralScraper.new("site:linkedin.com/in", @search_terms, @requests_google2, @solver_details)
|
|
30
|
+
urls = JSON.parse(urls) + JSON.parse(g2.getURLs)
|
|
31
|
+
|
|
27
32
|
# Scrape each resulting LinkedIn page
|
|
28
|
-
|
|
33
|
+
urls.each do |profile|
|
|
29
34
|
if check_right_page(profile)
|
|
30
35
|
scrape(profile)
|
|
31
36
|
end
|
|
@@ -85,3 +90,4 @@ class LinkedinCrawler
|
|
|
85
90
|
JSON.pretty_generate(@output)
|
|
86
91
|
end
|
|
87
92
|
end
|
|
93
|
+
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: linkedincrawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.15
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- M. C. McGrath
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2016-03-16 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Crawls public LinkedIn profiles via Google
|
|
14
14
|
email: shidash@shidash.com
|