MovieSpider.py 文件源码

def parse(self, response):
        try:
            l = ItemLoader(item=MovieItem(), response=response)
            l.add_value('name',
                        response.css('div#content h1 [property="v:itemreviewed"]::text').extract_first().strip())
            year = response.css('div#content h1 span.year::text').extract_first()
            if year.startswith('('):
                year = year[1:-1]
            l.add_value('year', year)

            newStrL = []
            for val in response.css('div#info::text').extract():
                newStr = val.strip().strip('/')
                if newStr != '':
                    newStrL.append(newStr)
                    if len(newStrL) == 2:
                        break

            if len(newStrL) == 2:
                l.add_value('region', newStrL[0].split('/'))
                l.add_value('language', newStrL[1].split('/'))

            l.add_value('duration', response.css('div#info [property="v:runtime"]::attr(content)').extract_first())
            l.add_value('types', response.css('div#info [property="v:genre"]::text').extract())
            l.add_value('directors', response.css('div#info [rel="v:directedBy"]::text').extract())
            l.add_value('actors', response.css('div#info [rel="v:starring"]::text').extract())
            l.add_value('runtime', response.css('div#info [property="v:initialReleaseDate"]::text').extract())
            l.add_value('detailurl', response.url)
            l.add_value('IMDburl', response.css('div#info [rel="nofollow"]::attr(href)').extract())
            l.add_value('stars', response.css('strong[property="v:average"]::text').extract_first())
            return l.load_item()
        except Exception:
            pass