eolclub_scraper 0.0.2 → 0.0.3
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
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1aa81ece4ef8fbd1d10cc1794c302b88c56e3ac1
|
4
|
+
data.tar.gz: c529ba35fdb15771a21f7614007b729cb75aca3b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8d8591d3ea3391ba59c783251cc3f5e32af95a512d5ac4d0e9dabc5691b998645662374b994430f52133b53ab8c66f30b5273e7811d943cd90b9aba762596a80
|
7
|
+
data.tar.gz: e2ca1d3ae68c831e8b1016e9edaa0c3abfb4914dd221f048f502b1c91ab6fe12bbdf995cd6da75ab33527fa66aac4cee67cb4034b0569c0187e936a3bb36c215
|
@@ -10,12 +10,14 @@ module EolclubScraper
|
|
10
10
|
# the same format, so that may be okay.
|
11
11
|
def parse(content)
|
12
12
|
doc = Nokogiri::HTML.parse(content)
|
13
|
+
description = doc.css('p').first(3).to_s
|
13
14
|
schedule_text = doc.css('p')[1].text.split("\n")[2].split(',').last.strip.split
|
14
15
|
start_time, end_time = schedule_text.last.split(/\W/)
|
15
16
|
|
16
17
|
Event.new(
|
17
18
|
Chronic.parse( [ schedule_text[0], schedule_text[1], start_time ].join(' ') ),
|
18
|
-
Chronic.parse( [ schedule_text[0], schedule_text[1], end_time ].join(' ') )
|
19
|
+
Chronic.parse( [ schedule_text[0], schedule_text[1], end_time ].join(' ') ),
|
20
|
+
description
|
19
21
|
)
|
20
22
|
end
|
21
23
|
|
@@ -3,13 +3,18 @@ require 'eolclub_scraper/event_parser'
|
|
3
3
|
describe EolclubScraper::EventParser do
|
4
4
|
|
5
5
|
describe '#parse' do
|
6
|
+
let(:parsed) { subject.parse(content) }
|
7
|
+
|
6
8
|
it 'parses an Event from the supplied content' do
|
7
|
-
expect(
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
9
|
+
expect( parsed.start_time ).to eq( Time.local(2013, 12, 9, 18, 0, 0) )
|
10
|
+
expect( parsed.end_time ).to eq( Time.local(2013, 12, 9, 23, 0, 0) )
|
11
|
+
end
|
12
|
+
|
13
|
+
it 'provides the HTML description from the scraped page' do
|
14
|
+
desc = parsed.description
|
15
|
+
expect(desc).to include("Monthly Providence, RI hacknight.")
|
16
|
+
expect(desc).to include("Our next meetup is")
|
17
|
+
expect(desc).to include("@EOLclub")
|
13
18
|
end
|
14
19
|
end
|
15
20
|
|