IntenseWebs/discourse
3
0
Fork 0
mirror of https://github.com/discourse/discourse.git synced 2024-11-22 08:57:10 -06:00
Code Issues Packages Projects Releases Wiki Activity

FIX: Hack our title retriever so that it parses YouTube URLs

Browse Source
This commit is contained in:
Robin Ward 2017-09-28 09:29:50 -04:00
parent cd6dff58dd
commit 07e84a3afa
2 changed files with 21 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/retrieve_title.rb
View File

@ -15,6 +15,12 @@ module RetrieveTitle
title = doc.at('title')&.inner_text
# A horrible hack - YouTube uses `document.title` to populate the title
# for some reason. For any other site than YouTube this wouldn't be worth it.
if title == "YouTube" && html =~ /document\.title *= *"(.*)";/
title = Regexp.last_match[1].sub(/ - YouTube$/, '')
end
if !title && node = doc.at('meta[property="og:title"]')
title = node['content']
end
@ -32,9 +38,11 @@ module RetrieveTitle
private
def self.max_chunk_size(uri)
# Amazon leaves the title until very late. Normally it's a bad idea to make an exception for
# one host but amazon is a big one.
# Amazon and YouTube leave the title until very late. Exceptions are bad
# but these are large sites.
return 80 if uri.host =~ /amazon\.(com|ca|co\.uk|es|fr|de|it|com\.au|com\.br|cn|in|co\.jp|com\.mx)$/
return 300 if uri.host =~ /youtube\.com$/ || uri.host =~ /youtu.be/
# default is 10k
10

11
spec/components/retrieve_title_spec.rb
View File

@ -44,6 +44,17 @@ describe RetrieveTitle do
expect(title).to eq("Good Title")
end
it "will parse a YouTube url from javascript" do
title = RetrieveTitle.extract_title(<<~HTML
<html>
<title>YouTube</title>
<script>document.title = "Video Title";</script>
</html>
HTML
)
expect(title).to eq("Video Title")
end
end
end