scrapy run spider code example
Example 1: genspider scrapy
scrapy genspider mydomain mydomain.com
Example 2: scrapy spider shell from spider
from scrapy.shell import inspect_response
def parse_details(self, response, item=None):
if item:
# populate more `item` fields
return item
else:
inspect_response(response, self)
Example 3: scrapy create project
scrapy startproject projectname
Example 4: simple scrapy spider file
import scrapy
class QuotesSpider(scrapy.Spider):
name = "quotes"
start_urls = [
'http://quotes.toscrape.com/page/1/',
]
def parse(self, response):
for quote in response.css('div.quote'):
yield {
'text': quote.css('span.text::text').get(),
'author': quote.css('small.author::text').get(),
'tags': quote.css('div.tags a.tag::text').getall(),
}
next_page = response.css('li.next a::attr(href)').get()
if next_page is not None:
next_page = response.urljoin(next_page)
yield scrapy.Request(next_page, callback=self.parse)