linkedincrawler 0.0.13 → 0.0.14
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 +24 -10
- 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: 9cab546fac1482b262f2435257af20d645b7a2ca
|
4
|
+
data.tar.gz: 8a18d774dbaf1791b13a104b85bd96edd3400dc9
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: fb059768cdaf5204cfef18ca7fc8ec8670c0ed4bed5346fc984ab57a44eb6d7fa988e8e2b584920b1f500a20257196fcf45bedaafdf86197887e3ad232fe398c
|
7
|
+
data.tar.gz: e6b09adb74fec01250746172e372e82b5277badda83c8156d8c60049945d36bdafcc528e5bf69f2063c219cfc3508c771138d363a0226742ac45aa25a0eb00e7
|
data/lib/linkedincrawler.rb
CHANGED
@@ -44,25 +44,39 @@ class LinkedinCrawler
|
|
44
44
|
@retry_count < @retry_limit
|
45
45
|
end
|
46
46
|
|
47
|
+
# Add the parsed profile to output, reset the retry count, and continue
|
48
|
+
def save_and_continue(parsed_profile)
|
49
|
+
@output += parsed_profile if parsed_profile != nil && !parsed_profile.empty?
|
50
|
+
@retry_count = 0
|
51
|
+
end
|
52
|
+
|
53
|
+
# Check if profile parsed successfully
|
54
|
+
def profile_parsing_failed?(parsed_profile)
|
55
|
+
return (parsed_profile == nil) || parsed_profile.empty? || parsed_profile.first["parsing_failed"]
|
56
|
+
end
|
57
|
+
|
47
58
|
# Scrape each page
|
48
59
|
def scrape(profile_url)
|
49
60
|
# Get profile page
|
50
61
|
profile_html = @requests.get_page(profile_url)
|
51
62
|
|
52
|
-
# Parse profile
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
#
|
59
|
-
if
|
63
|
+
# Parse profile
|
64
|
+
l = LinkedinParser.new(profile_html, profile_url, {timestamp: Time.now, search_terms: @search_terms})
|
65
|
+
parsed_profile = JSON.parse(l.results_by_job)
|
66
|
+
|
67
|
+
# Check if it failed or succeeded
|
68
|
+
if profile_parsing_failed?(parsed_profile)
|
69
|
+
# Handle something wrong- restart in case it is blocked and rescrape
|
70
|
+
if @retry_count < @retry_limit
|
60
71
|
@requests.restart_browser
|
61
72
|
@retry_count += 1
|
62
73
|
scrape(profile_url)
|
63
|
-
else
|
64
|
-
|
74
|
+
else # Just save it and move on
|
75
|
+
save_and_continue(parsed_profile)
|
65
76
|
end
|
77
|
+
|
78
|
+
else # It succeeded!
|
79
|
+
save_and_continue(parsed_profile)
|
66
80
|
end
|
67
81
|
end
|
68
82
|
|
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: 0.0.14
|
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: 2015-12-
|
11
|
+
date: 2015-12-06 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Crawls public LinkedIn profiles via Google
|
14
14
|
email: shidash@shidash.com
|