def main(): wf = Web2Feed(sys.argv[1]) wf.set_caching(True) wf.set_robot_rules_policy(True, False) print wf.get_feed() sys.exit() content = get_page(uri) print "Content len: %d" % 0 if not content else len(content) sc = get_scraper(content, uri) #print sc.get_feed() print sc.get_plaintext(80)
def get_feed(self):
"""Scrape the page for semantic content."""
def get_formatted(scraper):
return {
'meta': scraper.get_meta(),
'feed': scraper.get_feed(),
}
if self.scraper:
return get_formatted(self.scraper)
if not self.contents and self.do_auto_fetch:
print "Web2Feed.get_feed() Attempting to fetch..."
self.fetch()
if not self.contents:
#raise Exception, "No content to scrape!"
print "Web2Feed.get_feed() unable to parse: no contents!"
return False
# TODO: Cache the scraper.
self.scraper = get_scraper(self.contents, self.uri)
return get_formatted(self.scraper)
