Find file
Fetching contributors…
Cannot retrieve contributors at this time
26 lines (21 sloc) 1.03 KB
import scrapy
# This spider is using the SeleniumDownloader to fetch the pages transparently.
# Check the middleware at ..middlewares.SeleniumDownloader
class QuotesSeleniumDownloaderSpider(scrapy.Spider):
name = 'quotes-selenium-downloader'
start_urls = ['']
custom_settings = {
def parse(self, response):
for quote in response.css("div.quote"):
yield {
'text': quote.css("span.text::text").extract_first(),
'author': quote.css("").extract_first(),
'tags': quote.css("div.tags > a.tag::text").extract()
next_page_url = response.css(" > a::attr(href)").extract_first()
if next_page_url is not None:
# To disable Selenium for a specific request, just pass a meta argument:
# yield scrapy.Request(response.urljoin(next_page_url), meta={'nojs': 1})
yield scrapy.Request(response.urljoin(next_page_url))