taiwanese_news_parser 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +23 -0
- data/Rakefile +4 -0
- data/g0v.json +37 -0
- data/lib/taiwanese_news_parser/parser/apple_daily.rb +69 -0
- data/lib/taiwanese_news_parser/parser/china_times.rb +76 -0
- data/lib/taiwanese_news_parser/parser/cna.rb +59 -0
- data/lib/taiwanese_news_parser/parser/cts.rb +52 -0
- data/lib/taiwanese_news_parser/parser/ettoday.rb +53 -0
- data/lib/taiwanese_news_parser/parser/liberty_times.rb +66 -0
- data/lib/taiwanese_news_parser/parser/liberty_times_big5.rb +51 -0
- data/lib/taiwanese_news_parser/parser/now_news.rb +53 -0
- data/lib/taiwanese_news_parser/parser/tvbs.rb +46 -0
- data/lib/taiwanese_news_parser/parser/udn.rb +43 -0
- data/lib/taiwanese_news_parser/parser.rb +57 -0
- data/lib/taiwanese_news_parser/url_cleaner.rb +19 -0
- data/lib/taiwanese_news_parser/version.rb +3 -0
- data/lib/taiwanese_news_parser.rb +15 -0
- data/spec/spec_helper.rb +9 -0
- data/spec/taiwanese_news_parser/parser/apple_daily_s1.html +484 -0
- data/spec/taiwanese_news_parser/parser/apple_daily_s2.html +333 -0
- data/spec/taiwanese_news_parser/parser/apple_daily_s3.html +334 -0
- data/spec/taiwanese_news_parser/parser/apple_daily_spec.rb +57 -0
- data/spec/taiwanese_news_parser/parser/china_times_s1.html +513 -0
- data/spec/taiwanese_news_parser/parser/china_times_s2.html +538 -0
- data/spec/taiwanese_news_parser/parser/china_times_s3.html +893 -0
- data/spec/taiwanese_news_parser/parser/china_times_s4.html +1045 -0
- data/spec/taiwanese_news_parser/parser/china_times_spec.rb +63 -0
- data/spec/taiwanese_news_parser/parser/cna_s1.html +1616 -0
- data/spec/taiwanese_news_parser/parser/cna_spec.rb +33 -0
- data/spec/taiwanese_news_parser/parser/cts_s1.html +672 -0
- data/spec/taiwanese_news_parser/parser/cts_s2.html +672 -0
- data/spec/taiwanese_news_parser/parser/cts_spec.rb +36 -0
- data/spec/taiwanese_news_parser/parser/ettoday_s1.html +1817 -0
- data/spec/taiwanese_news_parser/parser/ettoday_s2.html +1822 -0
- data/spec/taiwanese_news_parser/parser/ettoday_spec.rb +35 -0
- data/spec/taiwanese_news_parser/parser/liberty_times_big5_s1.html +213 -0
- data/spec/taiwanese_news_parser/parser/liberty_times_big5_spec.rb +31 -0
- data/spec/taiwanese_news_parser/parser/liberty_times_s1.html +145 -0
- data/spec/taiwanese_news_parser/parser/liberty_times_spec.rb +29 -0
- data/spec/taiwanese_news_parser/parser/now_news_s1.html +968 -0
- data/spec/taiwanese_news_parser/parser/now_news_s2.html +986 -0
- data/spec/taiwanese_news_parser/parser/now_news_spec.rb +31 -0
- data/spec/taiwanese_news_parser/parser/tvbs_s1.html +734 -0
- data/spec/taiwanese_news_parser/parser/tvbs_s2.html +739 -0
- data/spec/taiwanese_news_parser/parser/tvbs_spec.rb +36 -0
- data/spec/taiwanese_news_parser/parser/udn_s1.html +1678 -0
- data/spec/taiwanese_news_parser/parser/udn_spec.rb +42 -0
- data/taiwanese_news_parser.gemspec +30 -0
- metadata +237 -0
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
require 'spec_helper'
|
|
2
|
+
|
|
3
|
+
describe TaiwaneseNewsParser::Parser::Cna do
|
|
4
|
+
describe '#parse' do
|
|
5
|
+
it do
|
|
6
|
+
url = 'http://www.cna.com.tw/News/FirstNews/201306290064-1.aspx'
|
|
7
|
+
FakeWeb.register_uri(:get, url, body:sample(__FILE__,'cna_s1.html'))
|
|
8
|
+
article = described_class.new(url).parse
|
|
9
|
+
article[:title].should == '電競亞室運 中華隊奪牌希望濃'
|
|
10
|
+
article[:content].should include('中華代表隊選手楊家正（Sen），今天在韓國仁川進行的2013亞洲室內暨武藝運動會中的電競比賽「星海爭霸II」預賽')
|
|
11
|
+
article[:company_name].should == '中央社'
|
|
12
|
+
#TODO article[:reporter_name].should == '姜遠珍'
|
|
13
|
+
article[:published_at].should == Time.new(2013,6,29,19,3)
|
|
14
|
+
end
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
describe '#parse_url_id' do
|
|
18
|
+
it 'hanle different versions of same news' do
|
|
19
|
+
url = 'http://www.cna.com.tw/News/FirstNews/201308140023.aspx'
|
|
20
|
+
described_class.parse_url_id(url).should == '201308140023'
|
|
21
|
+
|
|
22
|
+
url = 'http://www.cna.com.tw/News/FirstNews/201308160018-1.aspx'
|
|
23
|
+
described_class.parse_url_id(url).should == '201308160018'
|
|
24
|
+
|
|
25
|
+
url = 'http://www.cna.com.tw/News/FirstNews/201308110023-3.aspx'
|
|
26
|
+
described_class.parse_url_id(url).should == '201308110023'
|
|
27
|
+
end
|
|
28
|
+
it 'handle grouped news url' do
|
|
29
|
+
url = 'http://www.cna.com.tw/Topic/Popular/3912-1/201308140022-1.aspx'
|
|
30
|
+
described_class.parse_url_id(url).should == '201308140022'
|
|
31
|
+
end
|
|
32
|
+
end
|
|
33
|
+
end
|