不太了解scrapy框架的可以看看

带你了解scrapy框架

这是scrapy的基本数据模型

这是我个人写的一个小实例 小白可以看一下基本流程

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


class BkSpider(scrapy.Spider):
    name = 'bk'
    # allowed_domains = ['bai.com']
    start_urls = ['https://www.oschina.net/blog']

    def img_parse(self, response):
        item = response.meta['item']
        with open('./img/%s' % item['imgname'], 'wb') as f:
            f.write(response.body)
        yield item

    def blog_parse(self, response):
        typ = response.meta['typ']
        div_list = response.xpath('//div[contains(@class,"blog-item")]')
        for div in div_list:
            try:
                title = div.xpath('.