indeedcrawler 0.0.1 → 0.0.2
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/indeedcrawler.rb +2 -2
- 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: 733c0a9b4b19d7441025971ab8cd432a4a016b65
|
|
4
|
+
data.tar.gz: 165539a0a501c1f730b408a5ffaa7d9c9bce2f27
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: f0de486ae6199adec6ef6b432bd879b22f8fd9cad92c746fad755cba272c778f52cd125d1ed3198c14540712726432417d8784869cc714d144e4af8a71e37865
|
|
7
|
+
data.tar.gz: 22666895be68a355c658c7321c763c7de50ef29a29ad63d56f7221e8b970f5cb6a0ec87cc48ec66cd8ea4519b30c7fde5bbb3c048347e88aab5a403e5fd63f20
|
data/lib/indeedcrawler.rb
CHANGED
|
@@ -36,7 +36,7 @@ class IndeedCrawler
|
|
|
36
36
|
|
|
37
37
|
# Get each profile link
|
|
38
38
|
profiles.each do |profile|
|
|
39
|
-
@all_resume_links.push("http://indeed.com
|
|
39
|
+
@all_resume_links.push("http://indeed.com"+profile.xpath(".//a[@class='app_link']")[0]['href'])
|
|
40
40
|
end
|
|
41
41
|
|
|
42
42
|
# Navigate to next page if there's a class to do that
|
|
@@ -65,7 +65,7 @@ class IndeedCrawler
|
|
|
65
65
|
def parse_resumes
|
|
66
66
|
@all_resume_links.each do |link|
|
|
67
67
|
resume = load_restart_page(link, 0)
|
|
68
|
-
|
|
68
|
+
|
|
69
69
|
begin
|
|
70
70
|
# Parse resume and add to results
|
|
71
71
|
i = IndeedParser.new(resume, link, {time_scraped: Time.now})
|