How to use the urlextract.URLExtract function in urlextract

To help you get started, we’ve selected a few urlextract examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github crabcamp / lexrank / lexrank / utils / text.py View on Github external
import regex
from urlextract import URLExtract

EMAIL_REGEX = regex.compile(
    r'[\p{L}0-9]+[\p{L}0-9_.+-]*[\p{L}0-9_+-]+@[\p{L}0-9]+[\p{L}0-9.-]*\.\p{L}+'  # noqa
)
PUNCTUATION_SIGNS = set('.,;:¡!¿?…⋯&‹›«»\"“”[]()⟨⟩}{/|\\')

url_extractor = URLExtract()


def clean_text(text, allowed_chars='- '):
    text = ' '.join(text.lower().split())
    text = ''.join(ch for ch in text if ch.isalnum() or ch in allowed_chars)

    return text


def contains_letters(word):
    return any(ch.isalpha() for ch in word)


def contains_numbers(word):
    return any(ch.isdigit() for ch in word)
github karlicoss / promnesia / src / promnesia / common.py View on Github external
def _get_extractor(syntax: Syntax):
    from urlextract import URLExtract # type: ignore
    u = URLExtract()
    # https://github.com/lipoja/URLExtract/issues/13
    if syntax in {'org', 'orgmode', 'org-mode'}: # TODO remove hardcoding..
        u._stop_chars_right |= {'[', ']'}
        u._stop_chars_left  |= {'[', ']'}
    elif syntax in {'md', 'markdown'}:
        pass
    # u._stop_chars_right |= {','}
    # u._stop_chars_left  |= {','}
    return u
github microsoft / NimbusML / src / python / tools / find_http_urls.py View on Github external
def findHttpUrls(searchRootDirectory):
    alterableUrlsStore = {}
    nonAlterableUrlsStore = {}
    invalidUrlsStore = {}
    extractor = URLExtract()
    lengthOfOriginalRootPath = -1
    for root, _, files in os.walk(searchRootDirectory, onerror=None):
        if lengthOfOriginalRootPath == -1:
             lengthOfOriginalRootPath = len(root)
        for filename in files:
            if pathlib.Path(filename).suffix in ['.props', '.pyproj', '.vcxproj', '.snk'] or '.git' in root:
                continue 
            absoluteFilePath = os.path.join(root, filename)
            relativeFilePath = '.' + absoluteFilePath[lengthOfOriginalRootPath:]
            try:
                with open(absoluteFilePath, "rb") as f:
                    data = f.read()
                    try:
                        data = data.decode("utf-8")  
                    except Exception as e:
                        print("Unable to decodefile: {} in UTF-8 Encoding.".format(relativeFilePath))
github rapid7 / insightconnect-plugins / proofpoint_tap / komand_proofpoint_tap / actions / parse_tap_alert / action.py View on Github external
def run(self, params={}):
        p = HTMLTableParser()
        p.feed(params.get(Input.TAP_ALERT))
        data = p.tables
        clean_data = TAP(data).data

        # Get the Threat details URL which is NOT an HTML table element, but instead the <a> link of the
        #    table element
        extractor = URLExtract()
        cleaned_input_for_extractor = params.get(Input.TAP_ALERT)
        cleaned_input_for_extractor.replace('\n', '')
        urls_from_input = extractor.find_urls(cleaned_input_for_extractor)
        threat_details_urls = list(filter(lambda u: r'threat/email' in u and r'threatinsight.proofpoint.com' in u[:40],
                                     urls_from_input))
        if threat_details_urls:
            clean_data['threat']['threat_details_url'] = threat_details_urls[0]

        return {Output.RESULTS: clean_data}
</a>

urlextract

Collects and extracts URLs from given text.

MIT
Latest version published 10 months ago

Package Health Score

65 / 100
Full package analysis

Similar packages