Function extract_text

searx/utils.py:136–164

Extract text from a lxml result * if xpath_results is list, extract the text from each result and concat the list * if xpath_results is a xml element, extract all the text node from it ( text_content() method from lxml ) * if xpath_results is a string element, then it's al

(xpath_results, allow_none=False)

def extract_text(xpath_results, allow_none=False):
    """Extract text from a lxml result

      * if xpath_results is list, extract the text from each result and concat the list
      * if xpath_results is a xml element, extract all the text node from it
        ( text_content() method from lxml )
      * if xpath_results is a string element, then it's already done
    """
    if isinstance(xpath_results, list):
        # it's list of result : concat everything using recursive call
        result = ''
        for e in xpath_results:
            result = result + extract_text(e)
        return result.strip()
    elif isinstance(xpath_results, ElementBase):
        # it's a element
        text = html.tostring(
            xpath_results, encoding='unicode', method='text', with_tail=False
        )
        text = text.strip().replace('\n', ' ')
        return ' '.join(text.split())
    elif isinstance(xpath_results, (_ElementStringResult, _ElementUnicodeResult, str, Number, bool)):
        return str(xpath_results)
    elif xpath_results is None and allow_none:
        return None
    elif xpath_results is None and not allow_none:
        raise ValueError('extract_text(None, allow_none=False)')
    else:
        raise ValueError('unsupported type')


def normalize_url(url, base_url):