爬虫# 只保留＜span＞＜p＞＜div＞标签，去除各种样式,将div、span、标签处理为p标签，

import re
import ssl
import requests
import urllib3
from w3lib.html import remove_tags

headers = {
   
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36"
}
ssl._create_default_https_context = ssl._create_unverified_context
urllib3.disable_warnings()

# 特殊字符替换
def replace_entity(str):
    CHAR_ENTITIES_dict = {
   
        " ": "",
        " ": "",
        " ": "",
        "&lt;": "<",
        "&gt;": ">",
        "&amp;": "&",
        "&quot;": '"',
        "&ldquo;": "“",
        "&rdquo;": "”",
        "&copy;": "©",
        "&reg;": "™",
        "&times;": "×",
        "&divide;": "÷",
    }
    for i in list(CHAR_ENTITIES_dict.keys