textract 0.0.9 → 0.0.10
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/textract.rb +1 -1
- data/lib/textract/version.rb +1 -1
- data/spec/fixtures/vcr_cassettes/buzzfeed_hash.yml +2158 -0
- data/spec/lib/textract_spec.rb +14 -1
- metadata +4 -2
data/spec/lib/textract_spec.rb
CHANGED
|
@@ -15,7 +15,7 @@ describe Textract do
|
|
|
15
15
|
url = "http://gawker.com/1694508525"
|
|
16
16
|
article = Textract.get_text(url)
|
|
17
17
|
expect(article.text.include?("Import")).to eq true
|
|
18
|
-
expect(article.md5).to eq "
|
|
18
|
+
expect(article.md5).to eq "9cc00fcdeb4bc41e0649d0776cbb2157"
|
|
19
19
|
expect(article.author).to eq "Hamilton Nolan"
|
|
20
20
|
end
|
|
21
21
|
end
|
|
@@ -29,6 +29,19 @@ describe Textract do
|
|
|
29
29
|
end
|
|
30
30
|
end
|
|
31
31
|
|
|
32
|
+
it "returns the canonical url if available" do
|
|
33
|
+
VCR.use_cassette("hamno") do
|
|
34
|
+
url = "http://gawker.com/1694508525"
|
|
35
|
+
article = Textract.get_text(url)
|
|
36
|
+
expect(article.url).to eq "http://gawker.com/there-are-no-candidates-for-the-middle-class-1694508525"
|
|
37
|
+
end
|
|
38
|
+
VCR.use_cassette("buzzfeed hash") do
|
|
39
|
+
url = "http://www.buzzfeed.com/katenocera/rand-paul-is-on-his-own-this-time#.sseGm85KG"
|
|
40
|
+
article = Textract.get_text(url)
|
|
41
|
+
expect(article.url).to eq "http://www.buzzfeed.com/katenocera/rand-paul-is-on-his-own-this-time"
|
|
42
|
+
end
|
|
43
|
+
end
|
|
44
|
+
|
|
32
45
|
it "returns article text based on opengraph description" do
|
|
33
46
|
VCR.use_cassette('og') do
|
|
34
47
|
url = "http://www.tedcruz.org/record/our-standard-the-constitution/"
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: textract
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.10
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Adam Pash
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-
|
|
11
|
+
date: 2015-05-21 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: opengraph_parser
|
|
@@ -166,6 +166,7 @@ files:
|
|
|
166
166
|
- lib/textract.rb
|
|
167
167
|
- lib/textract/version.rb
|
|
168
168
|
- spec/fixtures/vcr_cassettes/bad_frisky.yml
|
|
169
|
+
- spec/fixtures/vcr_cassettes/buzzfeed_hash.yml
|
|
169
170
|
- spec/fixtures/vcr_cassettes/cruz.yml
|
|
170
171
|
- spec/fixtures/vcr_cassettes/hamno.yml
|
|
171
172
|
- spec/fixtures/vcr_cassettes/imgs.yml
|
|
@@ -201,6 +202,7 @@ specification_version: 4
|
|
|
201
202
|
summary: Extracts article text from a URL
|
|
202
203
|
test_files:
|
|
203
204
|
- spec/fixtures/vcr_cassettes/bad_frisky.yml
|
|
205
|
+
- spec/fixtures/vcr_cassettes/buzzfeed_hash.yml
|
|
204
206
|
- spec/fixtures/vcr_cassettes/cruz.yml
|
|
205
207
|
- spec/fixtures/vcr_cassettes/hamno.yml
|
|
206
208
|
- spec/fixtures/vcr_cassettes/imgs.yml
|