textract 0.0.2 → 0.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6c0f4e826cede5d69f4c35d74129c33ffe6fd59a
-  data.tar.gz: 8884dac18c1ddf501ccabbfbde7d5f50c24e37d3
+  metadata.gz: 746f24065d2e6b1062f2b4e8c0386957098119a1
+  data.tar.gz: b14700f3c1ff7a1cdc5d20d34444cf096516c288
 SHA512:
-  metadata.gz: 43d1097a7252e581849883b43c4581757b029e9a8f2e8cca754c396a1ff519cd92e538d984fd163c7733b5a8fdeb1211465cc24a29bffd34918c06d9bce68ce7
-  data.tar.gz: 8658b5de346c5e47214bcc294627c9d9c2d0bf40446af26192836e8925429dd029c9a91cd75c54d2d3be62db32417d05a85a11c05b0786e80d8c868006b57bbb
+  metadata.gz: 92a531364daa3afffc42bad5de554e8c04334191d3584dceffad502273a124d4d447e1b3884a19d3143247386df06e7fde1143a6744f0573be838e52a681d13f
+  data.tar.gz: 9df332865ada80fa1fae38562d8c7934916787cc0410cf80909ecdbea8fe8cf72620f397c07aa3b6d82ade4352bce9abc18ed9dd9f51eb53e2d7aacbb7da2bf1

data/lib/textract.rb

@@ -21,7 +21,6 @@ module Textract
     if selectors.nil?
       article = doc.search('article')
     else
-      require 'pry'; binding.pry
       article = doc.search(selectors)
     end
     if article.count == 1
@@ -47,14 +46,16 @@ module Textract
                                         tags: %w[div span p a img ul ol li blockquote table tr td h1 h2 h3 h4 h5 b em i strong],
                                         attributes: %w[src href],
                                         remove_empty_nodes: true,
-                                       ).content
-    markdown = ReverseMarkdown.convert article, unknown_tags: :bypass
-    # TODO change to drop once article is supported by reversemarkdown
-    markdown
+                                       )
   end
 
   def self.get_page_title(html)
-    Nokogiri::HTML(html).search('title').text
+    Nokogiri::HTML(html).search('head').search('title').text
+  end
+
+  def self.get_author(html)
+    name_meta = Nokogiri::HTML(html).search('meta[name="author"]')
+    name_meta.attribute('content').value unless name_meta.empty?
   end
 
   class Client
@@ -63,6 +64,7 @@ module Textract
     attr_reader :tags
     attr_reader :title
     attr_reader :text
+    attr_reader :author
 
     def initialize(url, selectors)
       @url = url
@@ -70,14 +72,11 @@ module Textract
       agent.user_agent_alias = 'Mac Safari'
       @html = agent.get(url).content
       @tags = Textract.get_og_tags(@html)
-      if @tags.nil? or @tags.description.nil?
-        # use readability method
-        @text = Textract.get_text_from_description(@html, nil, selectors)
-        @title = Textract.get_page_title(@html)
-      else
-        @text = Textract.get_text_from_description(@html, @tags.description, selectors)
-        @title = @tags.title
-      end
+
+      @article = Textract.get_text_from_description(@html, @tags.description, selectors)
+      @text = ReverseMarkdown.convert @article.content, unknown_tags: :bypass
+      @author = @article.author || Textract.get_author(@html)
+      @title = @tags.title || Textract.get_page_title(@html)
     end
   end
 end

data/lib/textract/version.rb

@@ -1,3 +1,3 @@
 module Textract
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/spec/lib/textract_spec.rb

@@ -2,27 +2,28 @@ require_relative '../../lib/textract'
 describe Textract do
   it "initializes with the get_text method" do
     url = "http://www.tedcruz.org/about/"
-    textract = Textract.get_text(url)
-    expect(textract).to be_a_kind_of Textract::Client
+    article = Textract.get_text(url)
+    expect(article).to be_a_kind_of Textract::Client
   end
 
   it "returns article text based on article tag" do
     url = "http://gawker.com/1694508525"
-    textract = Textract.get_text(url)
-    expect(textract.text[0..5]).to eq "Import"
+    article = Textract.get_text(url)
+    expect(article.text[0..5]).to eq "Import"
+    expect(article.author).to eq "Hamilton Nolan"
   end
 
   it "returns article text based on opengraph description" do
     url = "http://www.tedcruz.org/record/our-standard-the-constitution/"
-    textract = Textract.get_text(url)
-    expect(textract.text[0..5]).to eq "Ted Cr"
+    article = Textract.get_text(url)
+    expect(article.text[0..5]).to eq "Ted Cr"
   end
 
   it "can find a twitter profile given a selector" do
     url = "https://twitter.com/lifehacker"
-    textract = Textract.get_text(url, 'p.ProfileHeaderCard-bio.u-dir')
-    expect(textract.text.strip).to eq "Don't live to geek; geek to live."
-    expect(textract.title).to eq "Lifehacker (@lifehacker) | Twitter"
+    article = Textract.get_text(url, 'p.ProfileHeaderCard-bio.u-dir')
+    expect(article.text.strip).to eq "Don't live to geek; geek to live."
+    expect(article.title).to eq "Lifehacker (@lifehacker) | Twitter"
   end
 
   it "gets the page title from the title tag" do
@@ -30,4 +31,9 @@ describe Textract do
     expect(Textract.get_page_title(html)).to eq "Stuff"
   end
 
+  it "gets the author from the meta name tag" do
+    html = '<html><head><meta name="author" content="Adam Pash"></head><body><h1>FOO!</h1></body></html>'
+    expect(Textract.get_author(html)).to eq "Adam Pash"
+  end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: textract
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Adam Pash