def parse(self, response):
scrapedData = Selector(response).css('a.articleTitleListSmall')
for data in scrapedData:
item = DataItem()
item['title'] = data.css('a.articleTitleListSmall::text').get(),
item['source'] = 'IslamJesus.ws - Article - Abu Iyyad',
item['url'] = data.css('a.articleTitleListSmall::attr(href)').get()
yield item
def parse(self, response):
scrapedData = Selector(response).css('a.articleLinkOrange')
for data in scrapedData:
item = DataItem()
item['title'] = data.css('a.articleLinkOrange::text').get(),
item['source'] = 'HealthyMuslim.com - Article - Abu Iyyad',
item['url'] = data.css('a.articleLinkOrange::attr(href)').get()
yield item
def parse(self, response):
items = DataItem()
items['title'] = response.xpath(
'//h3[@class="info-name"]/a[1]/@title').extract()
items['precio'] = response.xpath(
'//div[@class="product-price "]/span[1]/text()').extract()
save(items)
yield items
def parse(self, response):
scrapedData = Selector(response).css('a.uk-link-reset')
for data in scrapedData:
item = DataItem()
item['title'] = data.css('a.uk-link-reset::text').get(),
item['source'] = 'Salafi Publications - Article',
item['url'] = "https://www.salafipubs.com/" + \
data.css('a.uk-link-reset::attr(href)').get()
yield item
def parse(self, response):
scrapedData = Selector(response).css('h3.mh-posts-list-title')
for data in scrapedData:
item = DataItem()
item['title'] = data.css(
'h3.mh-posts-list-title > a::attr(title)').get(),
item['source'] = 'Salafi Sounds - Audio',
item['url'] = data.css(
'h3.mh-posts-list-title > a::attr(href)').get()
yield item
def parse_datasets(self, response):
xpath = "//td[1]/p[1]/span[2]/a[1]/@href"
subSelector = response.xpath(xpath)
preurl = "http://archive.ics.uci.edu/ml"
for sub in subSelector:
item = sub.get()
url = preurl + item.replace("..", "")
ditem = DataItem()
ditem["tmpurl"] = url
yield scrapy.Request(url,
meta={"dataitem": ditem},
callback=self.parse_downloads)
def parse(self, response):
for rep in response.css('li.public'):
item = DataItem()
item['name'] = rep.xpath(
'.//a[@itemprop="name codeRepository"]/text()').re_first(
r'\n\s*(.*)')
item['update_time'] = rep.xpath(
'.//relative-time/@datetime').extract_first()
data_url = response.urljoin(
rep.xpath('.//h3/a/@href').extract_first())
request = scrapy.Request(data_url, callback=self.parse_data)
request.meta['item'] = item
yield request
def parse(self, response):
content = '//div[@class="content"]/article'
items = []
for con in response.xpath(content):
item = DataItem()
item['module'] = response.xpath(
'//div[@class="content"]/h1/strong/a/text()').extract()
item['title'] = con.xpath('h2/a/text()').extract()
item['note'] = con.xpath('p[@class="note"]/text()').extract()
item['more'] = con.xpath('p[@class="more"]/a/@href').extract()
items.append(item)
yield scrapy.http.Request(item['more'][0],
meta={'item': item},
callback=self.parse2)
nextPage = response.xpath(
'//li[@class="next-page"]/a/@href').extract()
if nextPage:
next = nextPage[0]
yield scrapy.http.Request(next, callback=self.parse)
