UrlManager

最新推荐文章于 2024-10-30 19:27:31 发布

qq_187352634

最新推荐文章于 2024-10-30 19:27:31 发布

阅读量74

点赞数

分类专栏： spider 文章标签： UrlManager python

本文链接：https://blog.csdn.net/qq_37755459/article/details/134532996

版权

spider 专栏收录该内容

13 篇文章 0 订阅

订阅专栏

创建一个类工具，管理url

class UrlManager:
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    # 添加一个新的网址
    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)

    # 添加多个新的网址
    def add_new_urls(self, urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)

    # 获取一个网址
    def get_url(self):
        if self.has_new_url():
            url = self.new_urls.pop()
            self.old_urls.add(url)
            return url
        else:
            return None

    # 是否还有网址，查看网址是否都被访问了
    def has_new_url(self):
        return len(self.new_urls) > 0


if __name__ == '__main__':
    url_manager = UrlManager()
    url_manager.add_new_url("url1")
    url_manager.add_new_urls(["url1", "url2"])
    print(url_manager.new_urls, url_manager.old_urls)
    print("*" * 30)

    url_manager.get_url()
    print(url_manager.new_urls, url_manager.old_urls)

    print("*" * 30)
    url_manager.get_url()
    print(url_manager.new_urls, url_manager.old_urls)

    print("*" * 30)
    print(url_manager.has_new_url())