linkedincrawler 0.0.8 → 0.0.9
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 +7 -7
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b74b092961100795e56f07f3936d3619bb412485
|
|
4
|
+
data.tar.gz: f47e7d0d0dfc6dcf8868f86ee79183fd4e646ab2
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ac3641eabfb51af81e88256b8a6e7a854ed19ce8aadab2f75961773f560278de7b304abad3f0bf1a5e27a8c31864dd08688faa642ed0b4883463bb95547aaf6a
|
|
7
|
+
data.tar.gz: 13c09495a5fe0fdf7d7458e306a566f915ac4db18104fbae53e9150525bd51177522dd7364bfcbdeb9f6a97b52b61af582f1c33a507eaa5da4367eec6f9c17c0
|
data/lib/linkedincrawler.rb
CHANGED
|
@@ -19,23 +19,23 @@ class LinkedinCrawler
|
|
|
19
19
|
def search
|
|
20
20
|
# Run Google search
|
|
21
21
|
g = GeneralScraper.new("site:linkedin.com/pub -site:linkedin.com/pub/dir/", @search_terms, nil)
|
|
22
|
-
|
|
22
|
+
# begin
|
|
23
23
|
urls = g.getURLs
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
end
|
|
24
|
+
# rescue # Search again if it didn't work the first time
|
|
25
|
+
# search
|
|
26
|
+
#end
|
|
27
27
|
|
|
28
28
|
# Search again if it didn't run
|
|
29
|
-
|
|
29
|
+
# if urls.length == 0 || urls.empty?
|
|
30
30
|
search
|
|
31
|
-
|
|
31
|
+
# else
|
|
32
32
|
# Scrape each resulting LinkedIn page
|
|
33
33
|
JSON.parse(urls).each do |profile|
|
|
34
34
|
if profile.include?(".linkedin.") && !profile.include?("/search")
|
|
35
35
|
scrape(profile)
|
|
36
36
|
end
|
|
37
37
|
end
|
|
38
|
-
|
|
38
|
+
# end
|
|
39
39
|
|
|
40
40
|
# Close all the browsers
|
|
41
41
|
@requests.close_all_browsers
|