linkedincrawler 0.0.15 → 0.0.16
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 +31 -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: e497521e3f492f55300fe474d802e36645cb9ff3
|
|
4
|
+
data.tar.gz: 1c7599985292c36c758577b0325dfa49fa671ec7
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a7b2616237182ca01b2144ae3b527c27c7adb76f41d454b6cb01f7ae7e10151cbe519815aadeb838ecbb1d0f9ae247829b584bbf74d8c69364cda0d7b262481f
|
|
7
|
+
data.tar.gz: 4911139eb248197b6bf503fe5d3373beee04e3033eae8283106fa4141e3911a938f353190e1ffbe92abc633f184b3c401239c3208469a4f2c13bd36e1166efda
|
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, requests_google2, solver_details)
|
|
9
|
+
def initialize(search_terms, retry_limit, requests, requests_google, requests_google2, solver_details, cm_hash)
|
|
10
10
|
@search_terms = search_terms
|
|
11
11
|
@output = Array.new
|
|
12
12
|
|
|
@@ -17,10 +17,16 @@ class LinkedinCrawler
|
|
|
17
17
|
@requests_google = requests_google
|
|
18
18
|
@requests_google2 = requests_google2
|
|
19
19
|
@solver_details = solver_details
|
|
20
|
+
|
|
21
|
+
# Handle crawler manager info
|
|
22
|
+
@cm_url = cm_hash[:crawler_manager_url] if cm_hash
|
|
23
|
+
@selector_id = cm_hash[:selector_id] if cm_hash
|
|
20
24
|
end
|
|
21
25
|
|
|
22
26
|
# Run search terms and get results
|
|
23
27
|
def search
|
|
28
|
+
|
|
29
|
+
begin
|
|
24
30
|
# Run Google search
|
|
25
31
|
g = GeneralScraper.new("site:linkedin.com/pub -site:linkedin.com/pub/dir/", @search_terms, @requests_google, @solver_details)
|
|
26
32
|
urls = g.getURLs
|
|
@@ -28,6 +34,9 @@ class LinkedinCrawler
|
|
|
28
34
|
# Look for new LI urls
|
|
29
35
|
g2 = GeneralScraper.new("site:linkedin.com/in", @search_terms, @requests_google2, @solver_details)
|
|
30
36
|
urls = JSON.parse(urls) + JSON.parse(g2.getURLs)
|
|
37
|
+
rescue Exception
|
|
38
|
+
binding.pry
|
|
39
|
+
end
|
|
31
40
|
|
|
32
41
|
# Scrape each resulting LinkedIn page
|
|
33
42
|
urls.each do |profile|
|
|
@@ -77,14 +86,33 @@ class LinkedinCrawler
|
|
|
77
86
|
@retry_count += 1
|
|
78
87
|
scrape(profile_url)
|
|
79
88
|
else # Just save it and move on
|
|
80
|
-
|
|
89
|
+
report_results(parsed_profile, profile_url)
|
|
81
90
|
end
|
|
82
91
|
|
|
83
92
|
else # It succeeded!
|
|
84
|
-
|
|
93
|
+
report_results(parsed_profile, profile_url)
|
|
85
94
|
end
|
|
86
95
|
end
|
|
87
96
|
|
|
97
|
+
# Figure out how to report results
|
|
98
|
+
def report_results(results, link)
|
|
99
|
+
if @cm_url
|
|
100
|
+
report_incremental(results, link)
|
|
101
|
+
else
|
|
102
|
+
save_and_continue(results)
|
|
103
|
+
end
|
|
104
|
+
end
|
|
105
|
+
|
|
106
|
+
# Report results back to Harvester incrementally
|
|
107
|
+
def report_incremental(results, link)
|
|
108
|
+
curl_url = @cm_url+"/relay_results"
|
|
109
|
+
@retry_count = 0
|
|
110
|
+
c = Curl::Easy.http_post(curl_url,
|
|
111
|
+
Curl::PostField.content('selector_id', @selector_id),
|
|
112
|
+
Curl::PostField.content('status_message', "Collected " + link),
|
|
113
|
+
Curl::PostField.content('results', JSON.pretty_generate(results)))
|
|
114
|
+
end
|
|
115
|
+
|
|
88
116
|
# Print output in JSON
|
|
89
117
|
def gen_json
|
|
90
118
|
JSON.pretty_generate(@output)
|
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: 0.0.16
|
|
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: 2016-
|
|
11
|
+
date: 2016-10-07 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: Crawls public LinkedIn profiles via Google
|
|
14
14
|
email: shidash@shidash.com
|