def parse(self, response):
hxs = HtmlXPathSelector(response)
titles = hsx.select('//td[@class="title"]')
item = []
for title in titles:
item = HackernewsItem()
item["title"] = title.select("a/text()").extract()
item["url"] = title.select("a/href").extract()
item.append(item)
return items
def parse(self, response):
titles = Selector(response).xpath('//tr[@class="athing"]/td[3]')
for title in titles:
item = HackernewsItem()
item['title'] = title.xpath("a[@href]/text()").extract()
item['url'] = title.xpath("a/@href").extract()
yield item
def parse(self, response):
hxs = HtmlXPathSelector(response)
titles = hxs.select('//td[@class="title"]')
items = []
for title in titles:
item = HackernewsItem()
item['title'] = title.select('a/text()').extract()
item['url'] = title.select('a/@href').extract()
items.append(title)
return items
def parse(self, response):
sel = Selector(response)
# find all <td>'s where class = title
titles = sel.xpath('//td[@class="title"]')
items = []
for title in titles:
item = HackernewsItem()
# find all <a>'s within each <td> that extracts the text
item["title"] = title.xpath("a/text()").extract()
# find all <a>'s within each <td> that extracts the url
item["url"] = title.xpath("a/@href").extract()
items.append(item)
return items