def parse(self, response): sel = Selector(response) sites = sel.xpath('//ul') items = [] for site in sites: item = {} item['quotes'] = site.xpath('li/b/text()').extract() if len(item['quotes']) != 0: items.append(item) data.saveQuotes(self.start_urls, self.allowed_domains, items) return 0
def parse(self, response): sel = Selector(response) sites = sel.xpath('//div') items = [] for site in sites: item = {} item['body'] = str("".join(site.xpath('div[@class="quoteText"]/text()').extract()).encode('UTF-8')) item['author'] = str("".join(site.xpath('div[@class="quoteText"]/a/text()').extract()).encode('UTF-8')) item['work'] = str("".join(site.xpath('div[@class="quoteText"]/i/a/text()').extract()).encode('UTF-8')) if len(item['body']) != 0: items.append(item) data.saveQuotes(self.start_urls,self.allowed_domains,items) return 0
def parse(self, response): sel = Selector(response) sites = sel.xpath('//div') items = [] for site in sites: item = {} item['body'] = str("".join( site.xpath('div[@class="quoteText"]/text()').extract()). encode('UTF-8')) item['author'] = str("".join( site.xpath('div[@class="quoteText"]/a/text()').extract()). encode('UTF-8')) item['work'] = str("".join( site.xpath('div[@class="quoteText"]/i/a/text()').extract() ).encode('UTF-8')) if len(item['body']) != 0: items.append(item) data.saveQuotes(self.start_urls, self.allowed_domains, items) return 0