Add parser for categories (shelfRenderer)

This commit adds a new parser for YT's shelfRenderers which are
typically used to denote different categories.The code for featured
channels parsing has also been moved to use the new parser but some
additional refactoring are needed there.

The ContinuationExtractor has also been improved and is now capable of
extraction continuation data that is packaged under
"appendContinuationItemsAction"

In additional this commit adds some useful helper functions to extract
the current selected tab the continuation token. This is to mainly
reduce code size and repetition.
--
This cherry-picked commit also removes the code for parsing featured
channels present on the original.

(cherry picked from commit 8000d538dbbf1eb9c78e000b1449926ba3b24da9)
This commit is contained in:
syeopite
2021-05-07 05:13:53 -07:00
parent 1323b94b7a
commit a50f64f6e9
5 changed files with 389 additions and 244 deletions

View File

@@ -248,12 +248,37 @@ def html_to_content(description_html : String)
end
def extract_videos(initial_data : Hash(String, JSON::Any), author_fallback : String? = nil, author_id_fallback : String? = nil)
extract_items(initial_data, author_fallback, author_id_fallback).select(&.is_a?(SearchVideo)).map(&.as(SearchVideo))
extracted = extract_items(initial_data, author_fallback, author_id_fallback)
if extracted.is_a?(Category)
target = extracted.contents
else
target = extracted
end
return target.select(&.is_a?(SearchVideo)).map(&.as(SearchVideo))
end
def extract_selected_tab(tabs)
# Extract the selected tab from the array of tabs Youtube returns
return selected_target = tabs.as_a.select(&.["tabRenderer"]?.try &.["selected"].as_bool)[0]
return selected_target = tabs.as_a.select(&.["tabRenderer"]?.try &.["selected"].as_bool)[0]["tabRenderer"]
end
def fetch_continuation_token(items : Array(JSON::Any))
# Fetches the continuation token from an array of items
return items.last["continuationItemRenderer"]?
.try &.["continuationEndpoint"]["continuationCommand"]["token"].as_s
end
def fetch_continuation_token(initial_data : Hash(String, JSON::Any))
# Fetches the continuation token from initial data
if initial_data["onResponseReceivedActions"]?
continuation_items = initial_data["onResponseReceivedActions"][0]["appendContinuationItemsAction"]["continuationItems"]
else
tab = extract_selected_tab(initial_data["contents"]["twoColumnBrowseResultsRenderer"]["tabs"])
continuation_items = tab["content"]["sectionListRenderer"]["contents"][0]["itemSectionRenderer"]["contents"][0]["gridRenderer"]["items"]
end
return fetch_continuation_token(continuation_items.as_a)
end
def check_enum(db, enum_name, struct_type = nil)