import scrapy
class QuotesSpider(scrapy.Spider):
name = "quotes"
def start_requests(self):
urls = [
'http://quotes.toscrape.com/page/1/',
'http://quotes.toscrape.com/page/2/',
]
for url in urls:
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
page = response.url.split("/")[-2]
filename = f'quotes-{page}.html'
with open(filename, 'wb') as f:
f.write(response.body)
self.log(f'Saved file {filename}')tutorial/
scrapy.cfg # deploy configuration file
tutorial/ # project's Python module, you'll import your code from here
__init__.py
items.py # project items definition file
middlewares.py # project middlewares file
pipelines.py # project pipelines file
settings.py # project settings file
spiders/ # a directory where you'll later put your spiders
__init__.py