Python爬虫URL管理器实现：基于deque的去重与防循环机制

from collections import deque
class URLQueue():
  def __init__(self):
    self.queue = deque() # 待抓取的网页
    self.visited = set() # 已经抓取过的网页
 
  def new_url_size(self):
    '''''
    获取未爬取URL集合的大小
    :return: 
    '''
    return len(self.queue)
 
  def old_url_size(self):
    '''''
    获取已爬取URL的大小
    :return: 
    '''
    return len(self.visited)
 
  def has_new_url(self):
    '''''
    判断是否有未爬取的URL
    :return: 
    '''
    return self.new_url_size() != 0
 
  def get_new_url(self):
    '''''
    获取一个未爬取的URL
    :return: 
    '''
    new_url = self.queue.popleft()#从左侧取出一个链接
    self.old_urls.add(new_url)#记录已经抓取
    return new_url
 
  def add_new_url(self, url):
    '''''
    将新的URL添加到未爬取的URL集合
    :param url: 单个url
    :return: 
    '''
    if url is None:
      return False
    if url not in self.new_urls and url not in self.old_urls:
      self.new_urls.append(url)
 
  def add_new_urls(self, urlset):
    '''''
    将新的URL添加到未爬取的URL集合
    :param urlset: url集合
    :return: 
    '''
    if urlset is None or len(urlset) == 0:
      return
    for url in urlset:
       self.add_new_url(url)