inc_5000_list_scraper 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/inc_5000_list_scraper.rb +41 -0
- metadata +2 -2
- data/lib/inc5000_scraper.rb +0 -39
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: a1fdabaa64a2333f6504d053c4b023ecb4d20de2b0e510cd85a47c2ce9fb4644
|
|
4
|
+
data.tar.gz: 2a18dbf526443ddf96512e37566777384560eddfac878a589e84cd2a01d829a1
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a395975a49afc72336caa9efb9bcc424d839b4eec3b1618d2adbe64c32c506863d275da337a97bee244bb6f8bbd7bf15fb30ab00b4548ef5fb84e84345fbdf62
|
|
7
|
+
data.tar.gz: 410e1de2d4b2f5ca41d45df423034b66f43894e0665178a415784bc7321371d4424810eb45769e998d42a97e8da0c130353f951883eac5b034b8c8f15df06667
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
module Inc5000List
|
|
2
|
+
class Scraper
|
|
3
|
+
INC_LIST_REST_URI = 'https://www.inc.com/rest/i5list/2020'.freeze
|
|
4
|
+
|
|
5
|
+
def self.create_csv!
|
|
6
|
+
new.scrape!
|
|
7
|
+
end
|
|
8
|
+
|
|
9
|
+
def scrape!
|
|
10
|
+
CSV.open('inc_5000_list.csv', 'wb') do |out|
|
|
11
|
+
out << company_row(companies.first).keys
|
|
12
|
+
|
|
13
|
+
companies.each do |company|
|
|
14
|
+
out << company_row(company).values
|
|
15
|
+
end
|
|
16
|
+
end
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
def list_as_text
|
|
20
|
+
OpenURI.open_uri(INC_LIST_REST_URI).read
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
def list_as_json
|
|
24
|
+
@list_as_json ||= JSON.parse(list_as_text)
|
|
25
|
+
end
|
|
26
|
+
|
|
27
|
+
def companies
|
|
28
|
+
@companies ||= list_as_json['companies'].map { |c| OpenStruct.new(c) }
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def company_row(company)
|
|
32
|
+
{
|
|
33
|
+
rank: company.rank,
|
|
34
|
+
company_name: company.company,
|
|
35
|
+
city: company.city,
|
|
36
|
+
state: company.state_s,
|
|
37
|
+
website: company.website
|
|
38
|
+
}
|
|
39
|
+
end
|
|
40
|
+
end
|
|
41
|
+
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: inc_5000_list_scraper
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Bryan Thompson
|
|
@@ -16,7 +16,7 @@ executables: []
|
|
|
16
16
|
extensions: []
|
|
17
17
|
extra_rdoc_files: []
|
|
18
18
|
files:
|
|
19
|
-
- lib/
|
|
19
|
+
- lib/inc_5000_list_scraper.rb
|
|
20
20
|
homepage: https://github.com/SnowboardTechie/inc_5000_list_scraper_gem
|
|
21
21
|
licenses: []
|
|
22
22
|
metadata:
|
data/lib/inc5000_scraper.rb
DELETED
|
@@ -1,39 +0,0 @@
|
|
|
1
|
-
module Inc5000Scraper
|
|
2
|
-
INC_LIST_REST_URI = 'https://www.inc.com/rest/i5list/2020'.freeze
|
|
3
|
-
|
|
4
|
-
def self.scrape!
|
|
5
|
-
new.scrape!
|
|
6
|
-
end
|
|
7
|
-
|
|
8
|
-
def scrape!
|
|
9
|
-
CSV.open('inc_5000_list.csv', 'wb') do |out|
|
|
10
|
-
out << company_row(companies.first).keys
|
|
11
|
-
|
|
12
|
-
companies.each do |company|
|
|
13
|
-
out << company_row(company).values
|
|
14
|
-
end
|
|
15
|
-
end
|
|
16
|
-
end
|
|
17
|
-
|
|
18
|
-
def list_as_text
|
|
19
|
-
OpenURI.open_uri(INC_LIST_REST_URI).read
|
|
20
|
-
end
|
|
21
|
-
|
|
22
|
-
def list_as_json
|
|
23
|
-
@list_as_json ||= JSON.parse(list_as_text)
|
|
24
|
-
end
|
|
25
|
-
|
|
26
|
-
def companies
|
|
27
|
-
@companies ||= list_as_json['companies'].map { |c| OpenStruct.new(c) }
|
|
28
|
-
end
|
|
29
|
-
|
|
30
|
-
def company_row(company)
|
|
31
|
-
{
|
|
32
|
-
rank: company.rank,
|
|
33
|
-
company_name: company.company,
|
|
34
|
-
city: company.city,
|
|
35
|
-
state: company.state_s,
|
|
36
|
-
website: company.website
|
|
37
|
-
}
|
|
38
|
-
end
|
|
39
|
-
end
|