def xpath_for_categories(self): text, root = wget_root(self.categories_url) grouped_hrefs = grouped_hrefs_from_page_sets(root) grouped_hrefs = map_list_list(lambda x: x[-1], grouped_hrefs) #pprint(grouped_hrefs) grouped_hrefs = filter( lambda x: is_grouped_hrefs_has_urls(x, self.products), grouped_hrefs) self.categories_xpath = map(lambda es: xpath_for_es(es, root), grouped_hrefs)
def xpath_for_categories(self): text, root = wget_root(self.categories_url) grouped_hrefs = grouped_hrefs_from_page_sets(root) grouped_hrefs = map_list_list(lambda x: x[-1], grouped_hrefs) #pprint(grouped_hrefs) grouped_hrefs = filter(lambda x: is_grouped_hrefs_has_urls(x, self.products), grouped_hrefs) self.categories_xpath = map(lambda es: xpath_for_es(es, root), grouped_hrefs)
def print_ess(ess, root=None): print "Traverse: detected %s structures:\n" % len(ess) if not ess: return pprint(ess) print "\nDetailed:" for es in ess: print "=" * 20 if root: xpath, errstring = xpath_for_es(es, root) print "%s items." % len(es), "NOT Suggested: %s." % errstring if errstring else "", "calculated XPATH: ", xpath print_es(es) #print construct_parentpath_for_tree(e) print
def print_ess(ess, root=None): print "Traverse: detected %s structures:\n" % len(ess) if not ess: return pprint(ess) print "\nDetailed:" for es in ess: print "=" * 20 if root: xpath, errstring = xpath_for_es(es, root) print "%s items." % len( es ), "NOT Suggested: %s." % errstring if errstring else "", "calculated XPATH: ", xpath print_es(es) #print construct_parentpath_for_tree(e) print