scrapy爬虫完整的代码实例

    新建工程

scrapy startproject tutorial

    进入tutorial目录，在spider下面新建quotes_spider.py

import scrapy
from ..items import QuotesItem

#coding:utf-8

class QuotesSpider(scrapy.Spider):
    name = "quotes"
    allowed_domain = "toscrape.com"

    def start_requests(self):
        for i in range(1,2):
            url = "http://quotes.toscrape.com/page/" + str(i) + "/"
            yield scrapy.Request(url=url,callback=self.parse)


    def parse(self, response):
        item = QuotesItem()
        for quote in response.css('div.quote'):
            item['text'] = quote.css('span.text::text').get(),
            item['author'] = quote.css('small.author::text').get(),
            item['tags'] = quote.css('div.tags a.tag::text').getall()
            yield item