from html.parser import HTMLParser
from html.entities import name2codepoint

class MyHTMLParser(HTMLParser):
    def __init__(self):
        super(MyHTMLParser, self).__init__()
        self.vdm = []

        # self.article = False
        # self.panel = False
        # self.panelBody = False
        # self.panelContent = False
        # self.p = False
        # self.a = False

        # self.skip = []

    # @classmethod
    # def _hasClass(cls, list_tuple, class_name):
    #     for name_value in list_tuple:
    #         array_class = name_value[1].strip().split(" ")
    #         array_class = [ x.strip() for x in array_class ]
    #         contain_all = set(array_class).issubset(class_name)

    #         if name_value[0] == 'class' and contain_all:
    #             return True
    #     return False

    # def handle_starttag(self, tag, attrs):
    #     # print(self.get_starttag_text())
    #     if tag == "article" and self._hasClass(attrs, ["art-panel", "col-xs-12"]):
    #         self.article = True
    #         self.skip = []            
    #     else:
    #         if tag == "div" and self._hasClass(attrs, ["panel", "panel-default"]) and self.article:
    #             self.panel = True
    #         else:
    #             if tag == "div" and self._hasClass(attrs, ["panel-body"]) and self.article and self.panel:
    #                 self.panelBody = True
    #             else:
    #                 if tag == "div" and self._hasClass(attrs, ["panel-content"]) and self.article  and self.panel and self.panelBody:
    #                     self.panelContent = True
    #                 else:
    #                     if tag == "p" and self._hasClass(attrs, ["block", "hidden-xs"]) and self.article  and self.panel and self.panelBody and self.panelContent:
    #                         self.p = True
    #                     else:
    #                         if tag == "a" and self.article  and self.panel and self.panelBody and self.panelContent and self.p:
    #                             self.a = True
    #                         else:
    #                             self.skip.append(self.get_starttag_text())

    # def handle_endtag(self, tag):
    #     if len(self.skip) == 0:
    #         if tag == "a" and self.a:
    #             self.a = False
    #         else:
    #             if tag == "p" and self.p:
    #                 self.p = False
    #             else:
    #                 if tag == "div" and self.panelContent:
    #                     self.panelContent = False
    #                 else:
    #                     if tag == "div" and self.panelBody:
    #                         self.panelBody = False
    #                     else:
    #                         if tag == "div" and self.panel:
    #                             self.panel = False
    #                         else:
    #                             if tag == "article" and self.article:
    #                                 self.article = False
    #     else:
    #         self.skip.pop()

    def handle_data(self, data):
        # print("#"+data+"#")

        # if self.article and self.panel and self.panelBody and self.panelContent and self.p and self.a:
        #     self.vdm.append(data.strip())

        data = data.strip()
        if data.startswith("Aujourd'hui,") and data.endswith("VDM"):
            self.vdm.append(data.strip())
        

    def getText(self):
        return self.vdm