crawler_shipinhao/xinshi/demo.py

# -*- coding: utf-8 -*-
# @Author: wangkun
# @Time: 2022/10/25
import difflib
import time

from selenium.webdriver import DesiredCapabilities
from selenium.webdriver.common.by import By
from seleniumwire import webdriver


class Demo:
    @classmethod
    def get_hotword(cls):
        # 打印请求配置
        ca = DesiredCapabilities.CHROME
        ca["goog:loggingPrefs"] = {"performance": "ALL"}

        # driver初始化
        driver = webdriver.Chrome(desired_capabilities=ca)
        # driver = webdriver.Chrome(desired_capabilities=ca, options=chrome_options)

        driver.implicitly_wait(10)
        print('打开百度网页')
        driver.get('https://www.baidu.com/')
        driver.maximize_window()
        driver.implicitly_wait(10)

        time.sleep(1)
        hot_words = driver.find_elements(By.XPATH, '//li[@class="hotsearch-item odd"]')
        for i in range(len(hot_words)):
            print(i)
            hot_word = hot_words[i].find_element(By.XPATH, '//span[@class="title-content-title"]')
            print(hot_word)

    # 比较字符串相似度
    @classmethod
    def str_similarity(cls):
        str1 = '男童不小心将玩具扔到姑父身上，姑父一耳光将男童扇倒地。目前家人已报警处理，孩子身体检查无大碍。#家庭 #监控下的惊险一幕 '
        str2 = '...姑父一耳光将男童扇倒地。目前家人已报警处理，孩子身体检查无大碍。#家庭 #监控下的惊险一幕'

        print(difflib.SequenceMatcher(None, str1, str2).quick_ratio())
        # print(type(difflib.SequenceMatcher(None, str1, str2).quick_ratio()))


if __name__ == '__main__':
    # Demo.get_hotword()
    Demo.str_similarity()
    pass