shadowfacts
/
frenzy
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Compare commits

base: shadowfacts:f79d84e294da7d3b501321588bd055d9b25ea8ea
Branches Tags
shadowfacts:main
shadowfacts:master
..
compare: shadowfacts:37a802b7a88bacc9e3437ff4b3e9e85cdd22040f
Branches Tags
shadowfacts:main
shadowfacts:master

3 Commits
f79d84e294 ... 37a802b7a8

Author SHA1 Message Date
Shadowfacts 37a802b7a8 Don't put content from builtin extractor through readable_html twice 2021-11-06 12:01:23 -04:00
Shadowfacts d2d4651f1d Add Ars Technica extractor for multi-page articles 2021-11-06 12:00:35 -04:00
Shadowfacts e84ebc473a Add support for external readability implementation 2021-11-06 12:00:35 -04:00
1 changed files with 2 additions and 2 deletions
Show Stats Expand all files Collapse all files

4
lib/frenzy/pipeline/scrape_stage.ex
View File

@ -89,7 +89,7 @@ defmodule Frenzy.Pipeline.ScrapeStage do
defp handle_response(url, %Tesla.Env{body: body}, opts) do
case opts["extractor"] do
"builtin" ->
{:ok, BuiltinExtractor.article(url, body), true}
{:ok, BuiltinExtractor.article(url, body)}
module_name ->
html_tree = Floki.parse(body)
@ -123,7 +123,7 @@ defmodule Frenzy.Pipeline.ScrapeStage do
)
end
{:ok, BuiltinExtractor.article(url, body), true}
{:ok, BuiltinExtractor.article(url, body)}
end
end
|> case do