textract 0.0.4 → 0.0.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/textract/version.rb +1 -1
- data/lib/textract.rb +14 -0
- data/spec/lib/textract_spec.rb +6 -0
- 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: 7dfaec842302697fff5fb526bc358045d63aeabb
|
4
|
+
data.tar.gz: 6bfa752901cf6bf183ea50370100701224a49ba8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f667c4d08fbc1658d1ac98ccd5e79eae4871a51e18e425717573903d2c14f3fceb4f9d37068a410dc01c88e58cf4b6264f26ead1708d8ca867bf430daf439a5d
|
7
|
+
data.tar.gz: cfef813ebb6fb91e37a71c952e06a56cee13520497a198f480d7f090eebc1b598f9f6dbf67bce8de1f0fa9fbee2d7595e8e5842077d14e6b06dca34b84e0c64d
|
data/lib/textract/version.rb
CHANGED
data/lib/textract.rb
CHANGED
@@ -85,5 +85,19 @@ module Textract
|
|
85
85
|
@author = @article.author || Textract.get_author(@html)
|
86
86
|
@title = @tags.title || Textract.get_page_title(@html)
|
87
87
|
end
|
88
|
+
|
89
|
+
def to_json
|
90
|
+
to_h.to_json
|
91
|
+
end
|
92
|
+
|
93
|
+
def to_h
|
94
|
+
{
|
95
|
+
url: @url,
|
96
|
+
text: @text,
|
97
|
+
md5: @md5,
|
98
|
+
author: @author,
|
99
|
+
title: @title,
|
100
|
+
}
|
101
|
+
end
|
88
102
|
end
|
89
103
|
end
|
data/spec/lib/textract_spec.rb
CHANGED
@@ -37,4 +37,10 @@ describe Textract do
|
|
37
37
|
expect(Textract.get_author(html)).to eq "Adam Pash"
|
38
38
|
end
|
39
39
|
|
40
|
+
it "converts itself to json" do
|
41
|
+
url = "http://gawker.com/1694508525"
|
42
|
+
article = Textract.get_text(url)
|
43
|
+
expect(article.to_json).to be_a_kind_of String
|
44
|
+
end
|
45
|
+
|
40
46
|
end
|