Bigquery function to simple normalize HTML into formated TEXT.

html_to_text.sql

CREATE OR REPLACE FUNCTION `project-id.dataset-id.html_to_text`(text STRING) AS (
TRIM(
    REGEXP_REPLACE(
      REGEXP_REPLACE(
        REGEXP_REPLACE(
          REGEXP_REPLACE(
            REGEXP_REPLACE(
              LOWER(text),
              r"<br>|<br\/>|<br\s+\/>|<\/p>", "\n"),
            r"<[^>]*>", ""),
          r"\n{2,}", "\n\n"),
        r"^\s+", ""),
      r"\n\s+", "\n")
  )
);