searx.results Namespace Reference

Classes
class	ResultContainer
class	Timing
class	UnresponsiveEngine

Functions
	result_content_len (content)
	compare_urls (url_a, url_b)
	merge_two_infoboxes (infobox1, infobox2)
	result_score (result, priority)

Variables
	CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile(r'[,;:!?\./\\\\ ()-_]', re.M | re.U)
	WHITESPACE_REGEX = re.compile('( |\t|\n)+', re.M | re.U)

Function Documentation

compare_urls()

searx.results.compare_urls	(		url_a,
			url_b )

Lazy compare between two URL.
"www.example.com" and "example.com" are equals.
"www.example.com/path/" and "www.example.com/path" are equals.
"https://www.example.com/" and "http://www.example.com/" are equals.

Args:
    url_a (ParseResult): first URL
    url_b (ParseResult): second URL

Returns:
    bool: True if url_a and url_b are equals

Definition at line 26 of file results.py.

def compare_urls(url_a, url_b):
    """Lazy compare between two URL.
    "www.example.com" and "example.com" are equals.
    "www.example.com/path/" and "www.example.com/path" are equals.
    "https://www.example.com/" and "http://www.example.com/" are equals.
 
    Args:
        url_a (ParseResult): first URL
        url_b (ParseResult): second URL
 
    Returns:
        bool: True if url_a and url_b are equals
    """
    # ignore www. in comparison
    if url_a.netloc.startswith('www.'):
        host_a = url_a.netloc.replace('www.', '', 1)
    else:
        host_a = url_a.netloc
    if url_b.netloc.startswith('www.'):
        host_b = url_b.netloc.replace('www.', '', 1)
    else:
        host_b = url_b.netloc
 
    if host_a != host_b or url_a.query != url_b.query or url_a.fragment != url_b.fragment:
        return False
 
    # remove / from the end of the url if required
    path_a = url_a.path[:-1] if url_a.path.endswith('/') else url_a.path
    path_b = url_b.path[:-1] if url_b.path.endswith('/') else url_b.path
 
    return unquote(path_a) == unquote(path_b)
 
 

Referenced by searx.results.merge_two_infoboxes().

Here is the caller graph for this function:

merge_two_infoboxes()

searx.results.merge_two_infoboxes	(		infobox1,
			infobox2 )

Definition at line 59 of file results.py.

def merge_two_infoboxes(infobox1, infobox2):  # pylint: disable=too-many-branches, too-many-statements
    # get engines weights
    if hasattr(engines[infobox1['engine']], 'weight'):
        weight1 = engines[infobox1['engine']].weight
    else:
        weight1 = 1
    if hasattr(engines[infobox2['engine']], 'weight'):
        weight2 = engines[infobox2['engine']].weight
    else:
        weight2 = 1
 
    if weight2 > weight1:
        infobox1['engine'] = infobox2['engine']
 
    infobox1['engines'] |= infobox2['engines']
 
    if 'urls' in infobox2:
        urls1 = infobox1.get('urls', None)
        if urls1 is None:
            urls1 = []
 
        for url2 in infobox2.get('urls', []):
            unique_url = True
            parsed_url2 = urlparse(url2.get('url', ''))
            entity_url2 = url2.get('entity')
            for url1 in urls1:
                if (entity_url2 is not None and url1.get('entity') == entity_url2) or compare_urls(
                    urlparse(url1.get('url', '')), parsed_url2
                ):
                    unique_url = False
                    break
            if unique_url:
                urls1.append(url2)
 
        infobox1['urls'] = urls1
 
    if 'img_src' in infobox2:
        img1 = infobox1.get('img_src', None)
        img2 = infobox2.get('img_src')
        if img1 is None:
            infobox1['img_src'] = img2
        elif weight2 > weight1:
            infobox1['img_src'] = img2
 
    if 'attributes' in infobox2:
        attributes1 = infobox1.get('attributes')
        if attributes1 is None:
            infobox1['attributes'] = attributes1 = []
 
        attributeSet = set()
        for attribute in attributes1:
            label = attribute.get('label')
            if label not in attributeSet:
                attributeSet.add(label)
            entity = attribute.get('entity')
            if entity not in attributeSet:
                attributeSet.add(entity)
 
        for attribute in infobox2.get('attributes', []):
            if attribute.get('label') not in attributeSet and attribute.get('entity') not in attributeSet:
                attributes1.append(attribute)
 
    if 'content' in infobox2:
        content1 = infobox1.get('content', None)
        content2 = infobox2.get('content', '')
        if content1 is not None:
            if result_content_len(content2) > result_content_len(content1):
                infobox1['content'] = content2
        else:
            infobox1['content'] = content2
 
 

References searx.results.compare_urls(), and searx.results.result_content_len().

Here is the call graph for this function:

result_content_len()

searx.results.result_content_len

(

content

)

Definition at line 20 of file results.py.

def result_content_len(content):
    if isinstance(content, str):
        return len(CONTENT_LEN_IGNORED_CHARS_REGEX.sub('', content))
    return 0
 
 

Referenced by searx.results.merge_two_infoboxes().

Here is the caller graph for this function:

result_score()

searx.results.result_score	(		result,
			priority )

Definition at line 131 of file results.py.

def result_score(result, priority):
    weight = 1.0
 
    for result_engine in result['engines']:
        if hasattr(engines.get(result_engine), 'weight'):
            weight *= float(engines[result_engine].weight)
 
    weight *= len(result['positions'])
    score = 0
 
    for position in result['positions']:
        if priority == 'low':
            continue
        if priority == 'high':
            score += weight
        else:
            score += weight / position
 
    return score
 
 

Variable Documentation

CONTENT_LEN_IGNORED_CHARS_REGEX

searx.results.CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile(r'[,;:!?\./\\\\ ()-_]', re.M | re.U)

Definition at line 15 of file results.py.

WHITESPACE_REGEX

searx.results.WHITESPACE_REGEX = re.compile('( |\t|\n)+', re.M | re.U)

Definition at line 16 of file results.py.