# frozen_string_literal: true
require 'rails_helper'
describe RetrieveTitle do
context "extract_title" do
it "will extract the value from the title tag" do
title = RetrieveTitle.extract_title(
"My Cool Title"
)
expect(title).to eq("My Cool Title")
end
it "will strip whitespace" do
title = RetrieveTitle.extract_title(
" Another Title\n\n "
)
expect(title).to eq("Another Title")
end
it "will pick og:title if title is missing" do
title = RetrieveTitle.extract_title(<<~HTML
HTML
)
expect(title).to eq("Good Title")
end
it "will prefer the title from an opengraph tag" do
title = RetrieveTitle.extract_title(<<~HTML
Good Title
HTML
)
expect(title).to eq("Good Title")
end
it "will parse a YouTube url from javascript" do
title = RetrieveTitle.extract_title(<<~HTML
YouTube
HTML
)
expect(title).to eq("Video Title")
end
end
context "crawl" do
it "can properly extract a title from a url" do
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(status: 200, body: "very amazing")
# we still resolve the IP address for every host
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("very amazing")
end
it "detects and uses encoding from Content-Type header" do
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(
status: 200,
body: "fancy apostrophes ’’’".dup.force_encoding('ASCII-8BIT'),
headers: { 'Content-Type' => 'text/html; charset="utf-8"' }
)
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("fancy apostrophes ’’’")
stub_request(:get, "https://brelksdjflaskfj.com/amazing")
.to_return(
status: 200,
body: "japanese こんにちは website".encode('EUC-JP').force_encoding('ASCII-8BIT'),
headers: { 'Content-Type' => 'text/html;charset=euc-jp' }
)
IPSocket.stubs(:getaddress).returns('100.2.3.4')
expect(RetrieveTitle.crawl("https://brelksdjflaskfj.com/amazing")).to eq("japanese こんにちは website")
end
end
end