url.py 文件源码

def __init__(self, domains, urls, *args, **kwargs):
        """Constructor for FeedSpider.

        Parameters
        ----------
        domains : list
            A list of domains for the site.
        urls : list
            A list of feed URLs of the site.
        provider : string
            The provider of RSS feed.
        url_regex : string
            URL pattern regular expression.

        If you use this spider to store item into database, additional
        keywords are required:

        platform_id : int
            The id of a platform instance.
        session : object
            An instance of SQLAlchemy session.

        Other keywords are used to specify how to parse the XML, see
        http://doc.scrapy.org/en/latest/topics/spiders.html#scrapy.spiders\
        .XMLFeedSpider.
        """
        self.platform_id = kwargs.pop('platform_id', None)
        self.session = kwargs.pop('session', None)
        self.url_regex = kwargs.pop('url_regex', None)
        self.provider = kwargs.pop('provider', 'self')
        self.iterator = kwargs.pop('iterator', 'iternodes')
        self.itertag = kwargs.pop('iterator', 'item')
        self.allowed_domains = domains
        self.start_urls = urls
        super(FeedSpider, self).__init__(*args, **kwargs)