def adapt(self, text, htmlpage=None):
if htmlpage is None:
return text
if text is None:
return
encoding = getattr(htmlpage, 'encoding', 'utf-8')
text = text.encode(encoding)
unquoted = unquote_markup(text, encoding=encoding)
cleaned = strip_url(disallowed.sub('', unquoted))
base = get_base_url(htmlpage).encode(encoding)
base_url = strip_url(unquote_markup(base, encoding=encoding))
joined = urljoin(base_url, cleaned)
return safe_download_url(joined)
def extract(self, text):
if text is not None:
return extract_image_url(strip_url(text))
return ''
def extract(self, text):
if text is not None:
return strip_url(text)
return ''
def extract(self, text):
return extract_image_url(strip_url(text))
