URL管理器的代码

###### url_manager.py ######

class UrlManager:
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

    def add_new_url(self, url):
        if url is None or len(url) == 0:
            return
        if url in self.new_urls or url in self.old_urls:
            return
        self.new_urls.add(url)

    def add_new_urls(self, urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)

    def get_url(self):
        if self.has_new_url():
            url = self.new_urls.pop()
            self.old_urls.add(url)
            return url
        else:
            return None

    def has_new_url(self):
        return len(self.new_urls) > 0


posted on 2024-07-23 18:46  星火splanet0  阅读(26)  评论(0)    收藏  举报