page_spider.py 文件源码

def parse(self, response):
        content_info = response.css('div.contentinfo')
        symbol1 = u'?'
        symbol2 = u'?'

        rex = r'%s(.*)%s' % (symbol1, symbol2)
        logging.log(logging.INFO, "rex=" + rex)
        title = content_info.css('h1 a::text').re_first(rex)
        logging.log(logging.INFO, title)