scrapy入门例子

import scrapy

class Myscrapy1Item(scrapy.Item):
    # define the fields for your item here like:
    text = scrapy.Field()
    author = scrapy.Field()
    tags = scrapy.Field()

# -*- coding: utf-8 -*-
import scrapy
from myscrapy1.items import Myscrapy1Item

class QuotesSpider(scrapy.Spider):
    name = ‘quotes‘
    allowed_domains = [‘quotes.toscrape.com‘]
    start_urls = [‘http://quotes.toscrape.com/‘]

    def parse(self, response):
        quotes = response.css(‘.quote‘)
        for quote in quotes:
            item = Myscrapy1Item()

            item[‘text‘] = quote.css(‘.text::text‘).extract_first()
            item[‘author‘] = quote.css(‘.author::text‘).extract_first()
            item[‘tags‘] = quote.css(‘.tags .tag::text‘).extract()
            yield item

        #获取多页内容
        next = response.css(‘.pager .next a::attr("href")‘).extract_first()
        url = response.url.join(next) #生成绝对URL
        yield scrapy.Request(url=url, callback=self.parse) #构造请求时需要用scrapy.Request