Merge pull request #2968 from mathiusD/description-link

This commit is contained in:
Samantaz Fox 2022-05-21 18:58:47 +02:00
commit 6ff3a633f7
No known key found for this signature in database
GPG Key ID: F42821059186176E
2 changed files with 58 additions and 4 deletions

View File

@ -6,6 +6,7 @@ record AboutChannel,
author_url : String,
author_thumbnail : String,
banner : String?,
description : String,
description_html : String,
total_views : Int64,
sub_count : Int32,
@ -52,8 +53,7 @@ def get_about_info(ucid, locale) : AboutChannel
banners = initdata["header"]["interactiveTabbedHeaderRenderer"]?.try &.["banner"]?.try &.["thumbnails"]?
banner = banners.try &.[-1]?.try &.["url"].as_s?
description = initdata["header"]["interactiveTabbedHeaderRenderer"]["description"]["simpleText"].as_s
description_html = HTML.escape(description)
description_node = initdata["header"]["interactiveTabbedHeaderRenderer"]["description"]
is_family_friendly = initdata["microformat"]["microformatDataRenderer"]["familySafe"].as_bool
allowed_regions = initdata["microformat"]["microformatDataRenderer"]["availableCountries"].as_a.map(&.as_s)
@ -75,13 +75,24 @@ def get_about_info(ucid, locale) : AboutChannel
author_verified_badge = initdata["header"].dig?("c4TabbedHeaderRenderer", "badges", 0, "metadataBadgeRenderer", "tooltip")
author_verified = (author_verified_badge && author_verified_badge == "Verified")
description = initdata["metadata"]["channelMetadataRenderer"]?.try &.["description"]?.try &.as_s? || ""
description_html = HTML.escape(description)
description_node = initdata["metadata"]["channelMetadataRenderer"]?.try &.["description"]?
is_family_friendly = initdata["microformat"]["microformatDataRenderer"]["familySafe"].as_bool
allowed_regions = initdata["microformat"]["microformatDataRenderer"]["availableCountries"].as_a.map(&.as_s)
end
description = !description_node.nil? ? description_node.as_s : ""
description_html = HTML.escape(description)
if !description_node.nil?
if description_node.as_h?.nil?
description_node = text_to_parsed_content(description_node.as_s)
end
description_html = parse_content(description_node)
if description_html == "" && description != ""
description_html = HTML.escape(description)
end
end
total_views = 0_i64
joined = Time.unix(0)
@ -125,6 +136,7 @@ def get_about_info(ucid, locale) : AboutChannel
author_url: author_url,
author_thumbnail: author_thumbnail,
banner: banner,
description: description,
description_html: description_html,
total_views: total_views,
sub_count: sub_count,

View File

@ -560,6 +560,48 @@ def fill_links(html, scheme, host)
return html.to_xml(options: XML::SaveOptions::NO_DECL)
end
def text_to_parsed_content(text : String) : JSON::Any
nodes = [] of JSON::Any
# For each line convert line to array of nodes
text.split('\n').each do |line|
# In first case line is just a simple node before
# check patterns inside line
# { 'text': line }
currentNodes = [] of JSON::Any
initialNode = {"text" => line}
currentNodes << (JSON.parse(initialNode.to_json))
# For each match with url pattern, get last node and preserve
# last node before create new node with url information
# { 'text': match, 'navigationEndpoint': { 'urlEndpoint' : 'url': match } }
line.scan(/https?:\/\/[^ ]*/).each do |urlMatch|
# Retrieve last node and update node without match
lastNode = currentNodes[currentNodes.size - 1].as_h
splittedLastNode = lastNode["text"].as_s.split(urlMatch[0])
lastNode["text"] = JSON.parse(splittedLastNode[0].to_json)
currentNodes[currentNodes.size - 1] = JSON.parse(lastNode.to_json)
# Create new node with match and navigation infos
currentNode = {"text" => urlMatch[0], "navigationEndpoint" => {"urlEndpoint" => {"url" => urlMatch[0]}}}
currentNodes << (JSON.parse(currentNode.to_json))
# If text remain after match create new simple node with text after match
afterNode = {"text" => splittedLastNode.size > 0 ? splittedLastNode[1] : ""}
currentNodes << (JSON.parse(afterNode.to_json))
end
# After processing of matches inside line
# Add \n at end of last node for preserve carriage return
lastNode = currentNodes[currentNodes.size - 1].as_h
lastNode["text"] = JSON.parse("#{currentNodes[currentNodes.size - 1]["text"]}\n".to_json)
currentNodes[currentNodes.size - 1] = JSON.parse(lastNode.to_json)
# Finally add final nodes to nodes returned
currentNodes.each do |node|
nodes << (node)
end
end
return JSON.parse({"runs" => nodes}.to_json)
end
def parse_content(content : JSON::Any, video_id : String? = "") : String
content["simpleText"]?.try &.as_s.rchop('\ufeff').try { |b| HTML.escape(b) }.to_s ||
content["runs"]?.try &.as_a.try { |r| content_to_comment_html(r, video_id).try &.to_s.gsub("\n", "<br>") } || ""