Scrapy持久化

一、items保存爬取的文件

items.py

import scrapy


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

quote.py

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


class QuoteSpider(scrapy.Spider):
    name = 'quote'
    allowed_domains = ['quotes.toscrape.com']
    start_urls = ['http://quotes.toscrape.com/']
    """
    知识点
        1. text()获取标签的text
        2. @属性  获取属性的值
        3. extract()查找多个    extract_first() 查找一个
        4. response.urljoin     url拼接
        5. scrapy.Request(url=_next, callback=self.parse)   回调
    """
    def parse(self, response):
        # print(response.text)
        quotes = response.xpath('//div[@class="col-md-8"]/div[@class="quote"]')
        # print(quotes)''
        for quote in quotes:
            # print('=' * 20)
            # print(quote)
            item = QuoteItem()
            # extract_first() 查找一个
            text = quote.xpath('.//span[@class="text"]/text()').extract_first()
            # print(text)
            item['text'] = text
            author = quote.xpath('.//span/small[@class="author"]/text()').extract_first()
            # print(author)
            item['author'] = author
            # extract()查找多个
            tags = quote.xpath('.//div[@class="tags"]/a[@class="tag"]/@href').extract()
            item['tags'] = tags
            # print(tags)
            yield item
        # print('>' * 40)
        next_url = response.xpath('//div[@class="col-md-8"]/nav/ul[@class="pager"]/li[@class="next"]/a/@href').extract_first()
        # print(next_url)
        # 拼接url
        _next = response.urljoin(next_url)
        # print(_next)
        # callback 回调函数
        yield scrapy.Request(url=_next, callback=self.parse)

产生文件命令

scrapy crawl quote -o qutoes.json

文件类型：qutoes.xml　　qutoes.jl　　qutoes.csv等

二、

待续