def parse_item(self, response):
titles = Selector(response).xpath('//div[@itemscope="itemscope"]')
for title in titles:
item = SocrataItem()
item["text"] = title.xpath('.//div[@class="browse2-result-title"]/h2/a/text()').extract()[0]
item["url"] = title.xpath('.//div[@class="browse2-result-title"]/h2/a/@href').extract()[0]
item["views"] = title.xpath('.//div[@class="browse2-result-view-count-value"]/text()').extract()[0].strip()
yield item
def parse(self, response):
titles = response.xpath('//tr[@itemscope="itemscope"]')
for title in titles:
item = SocrataItem()
item["text"] = title.select("td[2]/div/span/text()").extract()
item["url"] = title.select("td[2]/div/a/@href").extract()
item["views"] = title.select("td[3]/span/text()").extract()
yield item
def parse_items(self, response):
hxs = HtmlXPathSelector(response)
titles = hxs.select('//tr[@itemscope="itemscope"]')
items = []
for t in titles:
item = SocrataItem()
item["text"] = t.select("td[2]/div/span/text()").extract()
item["url"] = t.select("td[2]/div/a/@href").extract()
item["views"] = t.select("td[3]/span/text()").extract()
items.append(item)
return (items)
def parse(self, response):
titles = scrapy.Selector(response).xpath(
"//div[@itemtype='http://schema.org/Dataset']")
for title in titles:
item = SocrataItem()
item['text'] = title.xpath(
"//a/span[@itemprop='name']/text()").extract()
item['url'] = title.xpath(
"//a[@href=contains('','https://opendata.socrata.com')]"
).extract()
item['views'] = title.xpath(
"//div[contains(@class,'view-count-value')]/text()").extract()
yield item