FIX: increase chunk size to fetch title tag correctly (#14144)

This commit is contained in:
Arpit Jalan 2021-09-03 13:15:58 +05:30 committed by GitHub
parent b47a4d0207
commit 763f48abc7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 25 additions and 2 deletions

View File

@ -11,6 +11,9 @@ module RetrieveTitle
def self.extract_title(html, encoding = nil)
title = nil
if html =~ /<title>/ && html !~ /<\/title>/
return nil
end
if doc = Nokogiri::HTML5(html, nil, encoding)
title = doc.at('title')&.inner_text
@ -44,8 +47,8 @@ module RetrieveTitle
return 500 if uri.host =~ /amazon\.(com|ca|co\.uk|es|fr|de|it|com\.au|com\.br|cn|in|co\.jp|com\.mx)$/
return 300 if uri.host =~ /youtube\.com$/ || uri.host =~ /youtu.be/
# default is 10k
10
# default is 20k
20
end
# Fetch the beginning of a HTML document at a url

View File

@ -101,4 +101,24 @@ describe RetrieveTitle do
expect(RetrieveTitle.crawl("http://foobar.com/amazing")).to eq("very amazing")
end
end
context 'fetch_title' do
it "does not parse broken title tag" do
# webmock does not do chunks
stub_request(:get, "https://en.wikipedia.org/wiki/Internet").
to_return(status: 200, body: "<html><head><title>Internet - Wikipedia</ti" , headers: {})
title = RetrieveTitle.fetch_title("https://en.wikipedia.org/wiki/Internet")
expect(title).to eq(nil)
end
it "can parse correct title tag" do
# webmock does not do chunks
stub_request(:get, "https://en.wikipedia.org/wiki/Internet").
to_return(status: 200, body: "<html><head><title>Internet - Wikipedia</title>" , headers: {})
title = RetrieveTitle.fetch_title("https://en.wikipedia.org/wiki/Internet")
expect(title).to eq("Internet - Wikipedia")
end
end
end