Python formalize_html Examples

Example #1

File: test_template_extractor.py Project: dingjoey/py_project

def do_template_extract(url, template_id):
	#load web page
	page = template_extractor.load_page(url)
	formal_page = minidom.formalize_html(page)	
	doc = minidom.parse_xml_to_document(formal_page)
	
	#load template
	template = template_extractor.load_template(template_id)
	
	#do extract
	page_result = template_extractor.extract(doc, template)

	#print result
	print "page url:%s" %url
	print "extract result:-------"
	for field_result in page_result:
		print field_result
	print "----------------------"

Example #2

File: listdetail_extractor.py Project: dingjoey/py_project

def extract(url):
	#load web page
	page = load_page(url)
	formal_page = minidom.formalize_html(page)	
	doc = minidom.parse_xml_to_document(formal_page)

	#get list candidate nodes
	list_candidate_nodes = get_list_candidate_nodes(doc) 

	#get one list node which is judged as the most important list
	list_node = get_list_node(list_candidate_nodes)

	#get the need list item infos
	list_item_infos =get_list_item_info(list_node)

	#print extract info
	print "page url : %s" %url
	print "extract list item infos : "
	for info in list_item_infos:
		print info
	print "-------------"