diff --git a/newshomepages/extract/hyperlinks.py b/newshomepages/extract/hyperlinks.py index c9e226768d5..b056f4c0f8c 100644 --- a/newshomepages/extract/hyperlinks.py +++ b/newshomepages/extract/hyperlinks.py @@ -31,8 +31,8 @@ def hyperlinks( output_path: typing.Optional[typing.Any] = None, ): """Download and parse the provided site's hyperlinks files.""" - # Get all lighthouse files - hyperlink_df = utils.get_hyperlink_df().sort_values(["handle", "date"]) + # Get all hyperlink files + hyperlink_df = utils.get_hyperlink_df(verbose=True).sort_values(["handle", "date"]) # Get the data we want if site: diff --git a/newshomepages/utils.py b/newshomepages/utils.py index 068e1f661ed..ad2d9c3042f 100644 --- a/newshomepages/utils.py +++ b/newshomepages/utils.py @@ -544,12 +544,12 @@ def get_hyperlink_list() -> list[dict[str, typing.Any]]: return get_hyperlink_df().to_dict(orient="records") -def get_hyperlink_df() -> pd.DataFrame: +def get_hyperlink_df(verbose: bool = False) -> pd.DataFrame: """Get the full list of hyperlink files from our extracts. Returns a DataFrame. """ - return _get_extract_files_df("hyperlink-files.csv") + return _get_extract_files_df("hyperlink-files.csv", verbose=verbose) def get_lighthouse_list() -> list[dict[str, typing.Any]]: