Python自带网页解析器

willsonlincake · 发表于 2022-4-8 00:59:56| 字数 670

马上注册，结交更多好友，享用更多功能，让你轻松玩转社区。

您需要登录才可以下载或查看，没有账号？立即注册

x

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

class MyHTMLParser(HTMLParser):
def handle_starttag(self, tag, attrs):
      print("Start tag:", tag)
      for attr in attrs:
         print("    attr:", attr)

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

def handle_data(self, data):
      print("Data    :", 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)

parser = MyHTMLParser()