FIX: properly support HTML document when converting to markdown

This commit is contained in:
Régis Hanol 2017-04-28 22:02:20 +02:00
parent f05f1a24d3
commit 51ee49aad2
2 changed files with 5 additions and 1 deletions

View File

@ -7,7 +7,7 @@ class HtmlToMarkdown
end
def initialize(html)
@doc = Nokogiri::HTML.fragment(html)
@doc = Nokogiri::HTML(html)
remove_whitespaces!
end

View File

@ -142,6 +142,10 @@ describe HtmlToMarkdown do
expect(html_to_markdown("<ul><li><p>A list item with a blockquote:</p><blockquote><p>This is a <strong>blockquote</strong><br>inside a list item.</p></blockquote></li></ul>")).to eq("- A list item with a blockquote:\n\n > This is a **blockquote**\n > inside a list item.")
end
it "supports html document" do
expect(html_to_markdown("<html><body>Hello<div>World</div></body></html>")).to eq("Hello\nWorld")
end
it "handles <p>" do
expect(html_to_markdown("<p>1st paragraph</p><p>2nd paragraph</p>")).to eq("1st paragraph\n\n2nd paragraph")
end