Python rfc3987.parse方法代码示例

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def _apply_icon(app, icon):
    app_path = osx.path_for_app(app)
    if not app_path:
        raise AppMissingError("Application not found: '{0}'".format(app))

    try:
        components = urlparse(icon)
        if not components["scheme"] or components['scheme'] == "file":
            icon_path = components["path"]
        else:
            tmpdir = mkdtemp()
            icon_path = os.path.join(tmpdir,
                                     os.path.basename(components["path"]))
            print(tty.progress("Downloading {0} icon: {1}".format(app, icon)))
            curl(icon, icon_path)
    except ValueError:
        icon_path = icon

    osx.set_icon(app_path, os.path.expanduser(icon_path)) 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def ld_object(attribute_name, entity_id):
    out = entity_id
    try:
        d = parse(entity_id, rule='URI')
        scheme = d['scheme']
        if scheme != 'urn' and scheme != 'http' and scheme != 'https':
            raise ValueError
    except ValueError:
        entity_type = ''
        if attribute_name.startswith('ref'):
            entity_type = attribute_name[3:]

        out = ngsild_uri(entity_type, entity_id)

    return out


# Do all the transformation work 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def is_uri(instance):
        if not isinstance(instance, str_types):
            return True
        return rfc3987.parse(instance, rule="URI") 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def uri_validator(value, **kwargs):
    try:
        parts = rfc3987.parse(value, rule='URI')
    except ValueError:
        raise ValidationError(MESSAGES['format']['invalid_uri'].format(value))

    if not parts['scheme'] or not parts['authority']:
        raise ValidationError(MESSAGES['format']['invalid_uri'].format(value)) 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def checker(url):
    '''
    Check if the url is a valid one or not.
    '''
    try:
        parse(url)
        return True
    except ValueError:
        return False
    return False 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def _uri(s):
    if rfc3987.parse(s).get("scheme") in ["http", "https"]:
        return s
    raise ValueError 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def ld_id(entity_id, entity_type):
    out = entity_id
    try:
        d = parse(entity_id, rule='URI')
        scheme = d['scheme']
        if scheme != 'urn' and scheme != 'http' and scheme != 'https':
            raise ValueError
    except ValueError:
        out = ngsild_uri(entity_type, entity_id)

    return out


# Generates a Relationship's object as a URI 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def IsUri(text):
    try:
        rfc3987.parse(text, rule='URI')
    except:
        return False
    return True 

# 需要导入模块: import rfc3987 [as 别名]
# 或者: from rfc3987 import parse [as 别名]
def spider(base_urls, target):
    '''
        Loop through the initial links found in the given page. Each new link
        discovered will be added to the list if it's not already there, and thus
        crawled aswell looking for more links.

        wannabe list works as the placeholder for the urls that are yet to crawl.
        base_urls is a list with all the already crawled urls.
    '''
    global target_
    target_ = parse(target)
    p = Pool(arguments.process)
    wannabe = [url for url in base_urls if target_['authority'] in parse(url)['authority']]

    while True:
        #retrieve all the urls returned by the workers
        new_urls = p.map(worker, wannabe)
        #flatten them and remove repeated ones
        new_urls = list(set(itertools.chain(*new_urls)))
        wannabe = []
        i = 0

        #if new_urls is empty meaning no more urls are being discovered, exit the loop
        if new_urls == []:
            break
        
        else:
            for url in new_urls:
                if url not in base_urls:
                    '''
                    For each new url, check if it hasn't been crawled. If it's 
                    indeed new and contains the target domain it gets appended to 
                    the wannabe list so in the next iteration it will be crawled. 
                    '''
                    i += 1
                    if target_['authority'] in parse(url)['authority']:
                        wannabe.append(url)
                    base_urls.append(url)
        
        print(colored('\nNew urls appended: {}\n'.format(i), 'green', attrs=['bold']))

    #once all the links for the given depth have been analyzed, execute the parser
    parser(base_urls)