来写第一只爬虫
:
- from scrapy.spider import Spider
- class DmozSpider(Spider):
- name = "dmoz"
- allowed_domains = ["dmoz.org"]
- start_urls = [
- "http://www.baobaokuaizhangda.com/",
- "http://www.baobaokuaizhangda.com/"
- ]
- def parse(self, response):
- filename = response.url.split("/")[-2]
- open(filename, 'wb').write(response.body)