你知道html最常使用的标签有多少个

Q：你知道html最常使用的标签有多少个吗

A：30个左右

from bs4 import BeautifulSoup
import urllib.request
import urllib.parse


def html_download(url):
    if url is None:
        return None

    response = urllib.request.urlopen(url)
    if 200 == response.status:
        html = response.read()
        return html


def html_parse(url, html):
    soup = BeautifulSoup(html, "lxml")
    tags_all = set()
    tags_special = set()
    tags_normal = {"html", "head", "body", "meta",
                   "title", "link", "script", "div",
                   "img", "span", "a", "p"}   #基本上会用到的标签有12个
    for tag in soup.find_all(True):
        tags_all.add(tag.name)
        if tag.name not in tags_normal:
            tags_special.add(tag.name)
    print("tags_all=%s" % tags_all)
    print("url=%s, tags_all_length=%s" % (url, len(tags_all)))
    tags_len.append(len(tags_all))
    print("tags_special=%s" % tags_special)
    print("url=%s, tags_special_length=%s" % (url, len(tags_special)))
    print("---------------------------------------------------------------------\n")

if __name__ == "__main__":
    root_urls = ["https://www.360.cn/",
                 "https://www.apple.com/cn/",
                 "https://www.taobao.com/",
                 "https://www.microsoftstore.com.cn/",
                 "https://www.amazon.cn",
                 "https://github.com/",
                 "https://en.wikipedia.org/wiki/Main_Page",
                 "https://developer.mozilla.org/zh-CN/"]
    # 存放使用标签个数
    tags_len = []
    for url_item in root_urls:
        html_content = html_download(url_item)
        html_parse(url_item, html_content)

    print(tags_len)
    print(sum(tags_len)/len(tags_len))
    print("crawler end")from bs4 i