} catch (final Exception e) {
            return url;
        }
    }

    /**
     * Extracts anchor URLs from the HTML document.
     *
     * @param document the parsed HTML document
     * @param responseData the response data from crawling
     * @return list of anchor URLs found in the document
     */
    protected List<String> getAnchorList(final Document document, final ResponseData responseData) {

index.field.lang=lang
# Field name for cache status in the index.
index.field.has_cache=has_cache
# Field name for last modified date in the index.
index.field.last_modified=last_modified
# Field name for anchor in the index.
index.field.anchor=anchor
# Field name for segment in the index.
index.field.segment=segment
# Field name for role in the index.
index.field.role=role
# Field name for boost value in the index.
index.field.boost=boost