"""
import json
import logging
rdflib_logger = logging.getLogger('rdflib')
rdflib_logger.setLevel(logging.ERROR)
from lxml.html import fromstring
from rdflib import Graph, logger as rdflib_logger
from rdflib.plugins.parsers.pyRdfa import pyRdfa as PyRdfa, Options, logger as pyrdfa_logger
from rdflib.plugins.parsers.pyRdfa.initialcontext import initial_context
from extruct.xmldom import XmlDomHTMLParser
# silence rdflib/PyRdfa INFO logs
rdflib_logger.setLevel(logging.ERROR)
pyrdfa_logger.setLevel(logging.ERROR)
initial_context["http://www.w3.org/2011/rdfa-context/rdfa-1.1"].ns.update({
"twitter":
"https://dev.twitter.com/cards#",
"fb":
"http://ogp.me/ns/fb#"
})
class RDFaExtractor(object):
def extract(self,
htmlstring,
base_url=None,
encoding="UTF-8",
expanded=True):
Based on pyrdfa3 and rdflib
"""
import json
import logging
from xml.dom import Node
from xml.dom.minidom import Attr, NamedNodeMap
from lxml.etree import ElementBase, _ElementStringResult, _ElementUnicodeResult, XPath
from lxml.html import fromstring, HTMLParser, HtmlElementClassLookup
from rdflib import Graph, logger as rdflib_logger
from rdflib.plugins.parsers.pyRdfa import pyRdfa as PyRdfa, Options, logger as pyrdfa_logger
from rdflib.plugins.parsers.pyRdfa.initialcontext import initial_context
# silence rdflib/PyRdfa INFO logs
rdflib_logger.setLevel(logging.ERROR)
pyrdfa_logger.setLevel(logging.ERROR)
initial_context["http://www.w3.org/2011/rdfa-context/rdfa-1.1"].ns.update({
"twitter": "https://dev.twitter.com/cards#",
"fb": "http://ogp.me/ns/fb#"
})
class DomElementUnicodeResult(object):
CDATA_SECTION_NODE = Node.CDATA_SECTION_NODE
ELEMENT_NODE = Node.ELEMENT_NODE
TEXT_NODE = Node.TEXT_NODE
def __init__(self, text):
self.text = text
self.nodeType = Node.TEXT_NODE