pydataSpiderDetails.py 文件源码

def parse(self, response):
        hxs = scrapy.Selector(response)
        slots_tutorials = hxs.xpath('//td[@class="slot slot-tutorial"]')
        for slot in slots_tutorials:
            speakers_tutorials = slot.xpath('//span[@class="speaker"]/text()').extract()
            urls_tutorials = slot.xpath('//span[@class="title"]//@href').extract()
            talks_tutorials = slot.xpath('//span[@class="title"]//a/text()').extract()

        indexSpeaker=0
        for speaker in speakers_tutorials:
            yield Request(url=''.join(('http://www.pydata.org', urls_tutorials[indexSpeaker])),
                          callback=self.parse_details,
                          meta={'speaker': speaker.strip(), 'url': urls_tutorials[indexSpeaker], 
                          'talk': talks_tutorials[indexSpeaker]}
                          )       
            indexSpeaker=indexSpeaker+1