Scrapy 教程

import scrapy


class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://quotes.toscrape.com/page/1/',
        'http://quotes.toscrape.com/page/2/',
    ]

    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(),
            }

2016-09-19 18:57:19 [scrapy.core.scraper] DEBUG: Scraped from <200 http://quotes.toscrape.com/page/1/>
{'tags': ['life', 'love'], 'author': 'André Gide', 'text': '“It is better to be hated for what you are than to be loved for what you are not.”'}
2016-09-19 18:57:19 [scrapy.core.scraper] DEBUG: Scraped from <200 http://quotes.toscrape.com/page/1/>
{'tags': ['edison', 'failure', 'inspirational', 'paraphrased'], 'author': 'Thomas A. Edison', 'text': "“I have not failed. I've just found 10,000 ways that won't work.”"}