wienerlinien_at.py 文件源码

def parse(self, response):
        # Wiener Linien returns HTML with an XML content type which creates an
        # XmlResponse.
        response = HtmlResponse(url=response.url, body=response.body)
        for item in response.css('.block-news-item'):
            il = FeedEntryItemLoader(response=response,
                                     timezone=self._timezone,
                                     base_url='http://{}'.format(self.name))
            link = response.urljoin(item.css('a::attr(href)').extract_first())
            il.add_value('link', link)
            il.add_value('title', item.css('h3::text').extract_first())
            il.add_value('updated', item.css('.date::text').extract_first())
            yield scrapy.Request(link, self.parse_item, meta={'il': il})