honzakral/webpage.py

## webpage.py
class PageParserAndThumbnailer(object):
    def __init__(self, url, http_response):
        self.url = url
        self.headers, self.body = self.parse(http_response)

    @property
    def thumbnail(self):
        "create expensive thumbnail"

    def parse(self, http_response):
        "DO NOT TAKE SERIOUSLY"
        return http_response.split('\n\n', 1)

def simple_loader(url):
    return PageParserAndThumbnailer(urlopen(url))


class CachedLoader(object):
    def __init__(self, cache):
        self._cache = cache

    def __call__(self, url):
        try:
            out = self._cache.get(url)
        except Empty:
            out = simple_loader(url)
            self._cache.set(url, out)
        return out


class WebPage(object):
    """
    >>> wp = WebPage("http://example.com")
    >>> wp.body
    <HTML>
    <HEAD>
      <TITLE>Example Web Page</TITLE>
    </HEAD>
    <body>
    <p>You have reached this web page by typing &quot;example.com&quot;,
    &quot;example.net&quot;,
      or &quot;example.org&quot; into your web browser.</p>
    <p>These domain names are reserved for use in documentation and are not available
      for registration. See <a href="http://www.rfc-editor.org/rfc/rfc2606.txt">RFC
      2606</a>, Section 3.</p>
    </BODY>
    </HTML>
    >>> wp.thumbnail
    file:///tmp/thumbnails/http_example_com.png
    >>> wp = WebPage("http://example.com", loader=CachedLoader(memcache))
    """
    def __init__(self, url, loader=simple_loader):
        self._loader = loader
        self.url = url

    def _fetch(self):
        self._wrapped = self._loader(self.url)

    def __getattr__(self, attname):
        if not hasattr(self, '_wrapped'):
            self._fetch()
        return getattr(self._wrapped, attname)
	class PageParserAndThumbnailer(object):
	def __init__(self, url, http_response):
	self.url = url
	self.headers, self.body = self.parse(http_response)

	@property
	def thumbnail(self):
	"create expensive thumbnail"

	def parse(self, http_response):
	"DO NOT TAKE SERIOUSLY"
	return http_response.split('\n\n', 1)

	def simple_loader(url):
	return PageParserAndThumbnailer(urlopen(url))


	class CachedLoader(object):
	def __init__(self, cache):
	self._cache = cache

	def __call__(self, url):
	try:
	out = self._cache.get(url)
	except Empty:
	out = simple_loader(url)
	self._cache.set(url, out)
	return out


	class WebPage(object):
	"""
	>>> wp = WebPage("http://example.com")
	>>> wp.body
	<HTML>
	<HEAD>
	<TITLE>Example Web Page</TITLE>
	</HEAD>
	<body>
	<p>You have reached this web page by typing "example.com",
	"example.net",
	or "example.org" into your web browser.</p>
	<p>These domain names are reserved for use in documentation and are not available
	for registration. See <a href="http://www.rfc-editor.org/rfc/rfc2606.txt">RFC
	2606</a>, Section 3.</p>
	</BODY>
	</HTML>
	>>> wp.thumbnail
	file:///tmp/thumbnails/http_example_com.png
	>>> wp = WebPage("http://example.com", loader=CachedLoader(memcache))
	"""
	def __init__(self, url, loader=simple_loader):
	self._loader = loader
	self.url = url

	def _fetch(self):
	self._wrapped = self._loader(self.url)

	def __getattr__(self, attname):
	if not hasattr(self, '_wrapped'):
	self._fetch()
	return getattr(self._wrapped, attname)