textract 0.0.13 → 0.0.14
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/version.rb +1 -1
- data/lib/textract.rb +18 -1
- data/spec/fixtures/vcr_cassettes/twitter_byline.yml +2277 -0
- data/spec/lib/textract_spec.rb +15 -1
- metadata +3 -1
data/spec/lib/textract_spec.rb
CHANGED
|
@@ -16,7 +16,7 @@ describe Textract do
|
|
|
16
16
|
article = Textract.get_text(url)
|
|
17
17
|
expect(article.text.include?("Import")).to eq true
|
|
18
18
|
expect(article.md5).to eq "9cc00fcdeb4bc41e0649d0776cbb2157"
|
|
19
|
-
expect(article.author).to eq "Hamilton Nolan"
|
|
19
|
+
expect(article.author[:name]).to eq "Hamilton Nolan"
|
|
20
20
|
end
|
|
21
21
|
end
|
|
22
22
|
|
|
@@ -69,6 +69,20 @@ describe Textract do
|
|
|
69
69
|
expect(Textract.get_author(html)).to eq "Adam Pash"
|
|
70
70
|
end
|
|
71
71
|
|
|
72
|
+
it "gets twitter handle from metadata" do
|
|
73
|
+
html = '<html><head><meta name="twitter:creator" content="@adampash"></head><body><h1>FOO!</h1></body></html>'
|
|
74
|
+
expect(Textract.get_twitter(html)).to eq "@adampash"
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
it "gets more author detail when possible" do
|
|
78
|
+
VCR.use_cassette('twitter byline') do
|
|
79
|
+
url = "http://www.buzzfeed.com/daviddobbs/weighing-the-promises-of-big-genomics"
|
|
80
|
+
text = Textract.get_text(url)
|
|
81
|
+
expect(text.author[:name]).to eq "David Dobbs"
|
|
82
|
+
expect(text.author[:twitter]).to eq "@david_dobbs"
|
|
83
|
+
end
|
|
84
|
+
end
|
|
85
|
+
|
|
72
86
|
it "converts itself to json" do
|
|
73
87
|
VCR.use_cassette('json') do
|
|
74
88
|
url = "http://gawker.com/1694508525"
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: textract
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.14
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Adam Pash
|
|
@@ -175,6 +175,7 @@ files:
|
|
|
175
175
|
- spec/fixtures/vcr_cassettes/robots.yml
|
|
176
176
|
- spec/fixtures/vcr_cassettes/selector.yml
|
|
177
177
|
- spec/fixtures/vcr_cassettes/stackoverflow.yml
|
|
178
|
+
- spec/fixtures/vcr_cassettes/twitter_byline.yml
|
|
178
179
|
- spec/lib/textract_spec.rb
|
|
179
180
|
- spec/spec_helper.rb
|
|
180
181
|
- textract.gemspec
|
|
@@ -213,5 +214,6 @@ test_files:
|
|
|
213
214
|
- spec/fixtures/vcr_cassettes/robots.yml
|
|
214
215
|
- spec/fixtures/vcr_cassettes/selector.yml
|
|
215
216
|
- spec/fixtures/vcr_cassettes/stackoverflow.yml
|
|
217
|
+
- spec/fixtures/vcr_cassettes/twitter_byline.yml
|
|
216
218
|
- spec/lib/textract_spec.rb
|
|
217
219
|
- spec/spec_helper.rb
|