re 与 BeautifulSoup 速度对比

测试代码

import requests
import re

from time import time    
from bs4 import BeautifulSoup

headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
    'Cache-Control': 'no-cache',
    'DNT': '1',
    'Host': 'dict.cn',
    'Pragma': 'no-cache',
    'Proxy-Connection': 'keep-alive',
    'Referer': 'http://dict.cn/',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}


def get_translation(word):
    response = requests.get('http://dict.cn/{}'.format(word))
    text = response.text

    a = ''
    start_time = time()
    for i in range(10):
        a = re.findall(
            r'<li>\s*?<\w+>(\w+\.)</\w+>\s*?<\w+>(.*?)</\w+>\s*?</li>',
            re.search(
                '<div class="basic clearfix">(.*?)</div>', text, re.S
            ).group()
        )
    print(a)
    print('re: ', time() - start_time, '\n')

    start_time = time()
    html1 = BeautifulSoup(text, 'lxml')
    for i in range(10):
        a = [i.text for i in html1.select('#content div.main div.word div.basic.clearfix li')[:-1]]
    print(a)
    print('BeautifulSoup without split and strip: ', time() - start_time, '\n')

    start_time = time()
    html2 = BeautifulSoup(text, 'lxml')
    for i in range(10):
        a = [i.text.strip().split('\n') for i in html2.select('#content div.main div.word div.basic.clearfix li')[:-1]]
    print(a)
    print('BeautifulSoup with split and strip: ', time() - start_time, '\n')


if __name__ == '__main__':
    get_translation('at')

运行结果

[('prep.', '在；向；达'), ('n.', '基普(老挝货币基本单位)(=att)；[化]砹(极不稳定放射性元素)'), ('abbr.', '密封的(=airtight)'), ('abbr.', '气温(=air temperature)')]
re:  0.002012014389038086 

['\nprep.\n在；向；达\n', '\nn.\n基普(老挝货币基本单位)(=att)；[化]砹(极不稳定放射性元素)\n', '\nabbr.\n密封的(=airtight)\n', '\nabbr.\n气温(=air temperature)\n']
BeautifulSoup without split and strip:  1.0653910636901855 

[['prep.', '在；向；达'], ['n.', '基普(老挝货币基本单位)(=att)；[化]砹(极不稳定放射性元素)'], ['abbr.', '密封的(=airtight)'], ['abbr.', '气温(=air temperature)']]
BeautifulSoup with split and strip:  0.8744978904724121 

总结: re快