def parseintodict(file):
data = open(file).read()
links = {}
for type, html, link in parsers.links_in_article(data):
if not links.has_key(type):
links[type] = []
links[type].append((html, link))
return links
import urllib
import parsers
file = urllib.urlopen("http://www.nhs.uk/news/2010/03March/Pages/Impotence-is-a-warning-sign-for-heart-risk.aspx")
for tag in parsers.links_in_article(file.read()):
print tag
def scrape(self):
links = parsers.links_in_article(self.original_html())
self.update_links(links)
return self.scraped