class ParsingHandle(object):
"""
Structure of handle that is used to do one thing only, parse a soup object.
Parsing of the soup object must take place in the handle method which must
be defined explictly.
"""
name = None
url = None
soup = None
def __init__(self, url='', soup=None):
self.name = validate_attribute_name(get_class_name(self))
if url: self.set_url(url)
if soup: self.set_soup(soup)
def __repr__(self):
return '<Handle: %s>' % self.name
def set_url(self, url):
if is_lazy_url(url, ignore=True):
self.url = url
elif is_str(url):
self.url = LazyUrl(url)
def set_url_path(self, path):
self.url.clear_full_path()
self.url.set_path(path)
def has_url(self, raise_error=False):
has = False
has = (self.url == True)
if not has and raise_error:
raise ValueError('%r is a false LazyUrl' % self.url)
return has
def set_soup(self, soup):
""" Set the instance soup object to be used in handle """
is_soup(soup)
self.soup = soup
def has_soup(self, raise_error=False):
return has_soup(self, raise_error)
def handle(self):
""" Override with your own HTML parsing logic """
pass # Do something with the soup object
def set_url(self, url): if is_lazy_url(url, ignore=True): self.url = url elif is_str(url): self.url = LazyUrl(url)
