Python 爬虫 “幼虫”

 初步爬虫框架

import requests
import re

class MyCrawler:
    def __init__(self, filename):
        self.filename = filename
        
    def download(self, url):
        r = requests.get(url)
        return r.text
    
    def extract(self, content, pattern):
        result = re.findall(pattern, content)
        return result
    
    def save(self, info):
        with open(self.filename, 'a') as f:
            for item in info:
                f.write(item[0] + ' ' + item[1] + 'n')
                
    def crawl(self, url, pattern):
        content = self.download(url)
        info = self.extract(content, pattern)
        self.save(info)