[Python] Parse html by using python3

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

class MyHTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.anchors = []
        self.record = False


    def handle_starttag(self, tag, attrs):
        print("Start tag:", tag)
        for attr in attrs:
            print("     attr:", attr)
        if tag == "span":
            for k, v in attrs:
                if k == 'style' and v == 'color: #263645; font-weight: normal;' :
                    self.record = True
                    #self.anchors.append(v)
                    break

    def handle_endtag(self, tag):
        print("End tag  :", tag)

        if tag =="span":
            self.record = False

    def handle_data(self, data):
        print("Data     :", data)
        if self.record == True:
            self.anchors.append(data)

    def handle_comment(self, data):
        print("Comment  :", data)
    def handle_entityref(self, name):
        c = chr(name2codepoint[name])
        print("Named ent:", c)
    def handle_charref(self, name):
        if name.startswith('x'):
            c = chr(int(name[1:], 16))
        else:
            c = chr(int(name))
        print("Num ent  :", c)
    def handle_decl(self, data):
        print("Decl     :", data)


f = open("1.html")

p = MyHTMLParser()
p.feed(f.read())
p.close()

print (p.anchors)

Result

['Date', 'Scan Information']

Refernece:

• python的html.parser问题