Python爬虫正则表达式示例

import requests
import re
from multiprocessing import Pool

# 正则表达式解析
'''
正则表达式贪婪匹配步骤：
    1、re.compile书写正则表达式
    2、re.finditer对整个目标文本进行迭代搜索匹配
    3、循环：在匹配完后把所需要的信息进行提取
'''


def parse(response):
    # step:1
    resp = re.compile(r'title="(?P<name>.*?)class="image-link".*?'
                      r'<p class="star">(?P<star>.*?)</p>.*?', re.S)
    # step:2
    items = resp.finditer(response)
    # step:3
    for item in items:
        print(item.group('name').strip())
        print(item.group('star').strip())


# 主函数
'''
requests爬虫基本框架：
    1.url网址
    2.头文件：cookie、headers
    3.params参数
    4.get/post请求获取json格式或text文本
'''


def main(offset):
    # step:1
    url = 'https://www.maoyan.com/board/4'
    # step:2
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.64'
    }
    # step:3
    params = {
        'requestCode': '5fcc2cff819df07687a41ed0dada9239pduxy',
        'offset': offset
    }
    # step:4
    response = requests.get(url, headers=headers, params=params).text
    parse(response)


# 程序入口
if __name__ == '__main__':
    # 快速爬取：多进程
    pool = Pool()
    pool.map(main, [i * 10 for i in range(11)])