indeed_scraper2022 0.1.0 → 0.1.1
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
- checksums.yaml.gz.sig +0 -0
- data/lib/indeed_scraper2022.rb +69 -7
- data.tar.gz.sig +5 -3
- metadata +2 -2
- metadata.gz.sig +0 -0
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 50a484cf1a272522091413129241620336f12ca94d795b7ab132dd6911802d1c
|
|
4
|
+
data.tar.gz: 06dffee1253aa5076da9b6897bc48009687e8df86aa1a3629ee1d8a4432fdd13
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7327fc5bf9668c4f292eabf673574bfd7ca9fbf180133896c559ac1b7415d4ee880365302d24550aba4b83ee2a709a77bdb059145310e4a5de21840fe11a5058
|
|
7
|
+
data.tar.gz: a84b587275793166a7ac40d63607c8ea2f8dd340a3197ce782f901ca8c27de27b8eeef7f36fc9399aba286ddc399da109b2d14cd9db99b3c6a4a545e6ad9f21c
|
checksums.yaml.gz.sig
CHANGED
|
Binary file
|
data/lib/indeed_scraper2022.rb
CHANGED
|
@@ -25,17 +25,74 @@ class IndeedScraper2022
|
|
|
25
25
|
@results
|
|
26
26
|
end
|
|
27
27
|
|
|
28
|
-
def page()
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
# used for debugging
|
|
32
|
-
#
|
|
33
|
-
def a2()
|
|
34
|
-
@a2
|
|
28
|
+
def page(n)
|
|
29
|
+
url = @results[n-1][:link]
|
|
30
|
+
fetchjob(url)
|
|
35
31
|
end
|
|
36
32
|
|
|
37
33
|
private
|
|
38
34
|
|
|
35
|
+
def fetchjob(url)
|
|
36
|
+
|
|
37
|
+
doc = Nokorexi.new(url).to_doc
|
|
38
|
+
e0 = doc.element("html/body/div/div/div/div/div/div/div/div")
|
|
39
|
+
|
|
40
|
+
#div = e0.element("//div[@class='jobsearch-JobComponent']")
|
|
41
|
+
div1 = e0.element("//div[@class='jobsearch-DesktopStickyContainer']")
|
|
42
|
+
div2 = div1.element("div")
|
|
43
|
+
|
|
44
|
+
# jobsearch (e.g. Full Stack Website Developer (Wordpress))
|
|
45
|
+
jobtitle = div2.element("div[@class='jobsearch-JobInfoHead" \
|
|
46
|
+
"er-title-container']/h1[@class='jobsearch-JobInfoHead" \
|
|
47
|
+
"er-title']").text
|
|
48
|
+
|
|
49
|
+
div3 = div2.element("div[@class='jobsearch-CompanyInfoCon" \
|
|
50
|
+
"tainer']/div[@class='jobsearch-CompanyInfoWithoutHead" \
|
|
51
|
+
"erImage']/div/div[@class='jobsearch-DesktopStickyCont" \
|
|
52
|
+
"ainer-subtitle']")
|
|
53
|
+
|
|
54
|
+
# icl (e.g. Lyles Sutherland)
|
|
55
|
+
cname = div3.xpath("div[@class='jobsearch-DesktopSt" \
|
|
56
|
+
"ickyContainer-companyrating']/div/div[@class='icl-u-x" \
|
|
57
|
+
"s-mr--xs']")[1]
|
|
58
|
+
clink = div3.element('//a')
|
|
59
|
+
company = cname ? cname.text : clink.text
|
|
60
|
+
companylink = clink.attributes[:href] if clink
|
|
61
|
+
|
|
62
|
+
div5 = div3.xpath("div/div")
|
|
63
|
+
location, worklocation = div5.map(&:text).compact
|
|
64
|
+
|
|
65
|
+
# icl (e.g. Full-time, Permanent)
|
|
66
|
+
jobtype = div1.element("div/div/div[@class='jobsearch-J" \
|
|
67
|
+
"obMetadataHeader-item']/span[@class='icl-u-xs-mt--xs']")
|
|
68
|
+
jobtype = jobtype.texts.join if jobtype
|
|
69
|
+
|
|
70
|
+
# jobsearch (e.g. Urgently needed)
|
|
71
|
+
jobnote1 = e0.element("//div[@class='jobsearch-DesktopTag" \
|
|
72
|
+
"']/div[@class='urgently-hiring']/div[@class='jobsearc" \
|
|
73
|
+
"h-DesktopTag-text']")
|
|
74
|
+
jobnote1 = jobnote1.text if jobnote1
|
|
75
|
+
|
|
76
|
+
# jobsearch (e.g. 10 days ago)
|
|
77
|
+
datepost = e0.element("//div[@class='jobsearch-JobTab-con" \
|
|
78
|
+
"tent']/div[@class='jobsearch-JobMetadataFooter']/div").text
|
|
79
|
+
|
|
80
|
+
jobdesc = e0.element("//div[@class='icl-u-xs-mt--md']/div[@cl" \
|
|
81
|
+
"ass='jobsearch-jobDescriptionText']")
|
|
82
|
+
|
|
83
|
+
{
|
|
84
|
+
title: jobtitle,
|
|
85
|
+
company: company,
|
|
86
|
+
companylink: companylink,
|
|
87
|
+
location: location,
|
|
88
|
+
worklocation: worklocation,
|
|
89
|
+
note: jobnote1,
|
|
90
|
+
date: (Date.today - datepost.to_i).to_s,
|
|
91
|
+
desc: jobdesc
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
end
|
|
95
|
+
|
|
39
96
|
def search(q='', location='')
|
|
40
97
|
|
|
41
98
|
a = Mechanize.new
|
|
@@ -47,6 +104,7 @@ class IndeedScraper2022
|
|
|
47
104
|
pg = form.submit
|
|
48
105
|
|
|
49
106
|
doc2 = Nokogiri::XML(pg.body)
|
|
107
|
+
|
|
50
108
|
a2 = doc2.xpath "//a[div/div/div/div/table/tbody/tr/td/div]"
|
|
51
109
|
puts 'a2: ' + a2.length.inspect if @debug
|
|
52
110
|
|
|
@@ -90,6 +148,8 @@ class IndeedScraper2022
|
|
|
90
148
|
date = (Date.today - dateposted.first.to_i).to_s
|
|
91
149
|
|
|
92
150
|
{
|
|
151
|
+
link: @url_base.sub(/\/[^\/]+$/,'') \
|
|
152
|
+
+ doc.root.attributes[:href].gsub(/&/,'&'),
|
|
93
153
|
title: jobtitle,
|
|
94
154
|
salary: salary,
|
|
95
155
|
company: company_name,
|
|
@@ -101,3 +161,5 @@ class IndeedScraper2022
|
|
|
101
161
|
end
|
|
102
162
|
end
|
|
103
163
|
end
|
|
164
|
+
|
|
165
|
+
|
data.tar.gz.sig
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
|
|
1
|
+
�u �qfT���t��\!a�?�-�� x���0���}��Ɉ��[Ъ
|
|
2
|
+
��c�.D���r
|
|
3
|
+
c�Θ�r�1���$Pp������0aQ�d��ږ� x.��]~M�|Х�Ex�S1���ͼ�e��2:\)Kj7s��J
|
|
4
|
+
d&�ݙ�堟;[�I�A�v��P'�q~Ub�_�k=>42�i�4�
|
|
5
|
+
�q���W�?
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: indeed_scraper2022
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- James Robertson
|
|
@@ -35,7 +35,7 @@ cert_chain:
|
|
|
35
35
|
YLGLkwmbiUHX5dRU3RwOwOrZiyvND5BIj7S6dZ6jYHe0I727apgQNc3swTz5mW6I
|
|
36
36
|
SW/2zInu2bkj/meWm5eBoWHT
|
|
37
37
|
-----END CERTIFICATE-----
|
|
38
|
-
date: 2022-01-
|
|
38
|
+
date: 2022-01-25 00:00:00.000000000 Z
|
|
39
39
|
dependencies:
|
|
40
40
|
- !ruby/object:Gem::Dependency
|
|
41
41
|
name: nokorexi
|
metadata.gz.sig
CHANGED
|
Binary file
|