scrapy之小试身手

要爬取的网址是：http://quotes.toscrape.com/

磕磕绊绊的写完了

spiders

import scrapy
from kkk.items import *

class QuoteSpider(scrapy.Spider):
    name = 'quote'
    allowed_domains = ['quotes.toscrape.com/']
    start_urls = ['http://quotes.toscrape.com//']

    def parse(self, response):
        quotes = response.css('.quote')
        for quote in quotes:               #这是一个很好的方向，页面由重复的构造组成是，拿到大的框架组成的列表，然后循环，依次拿每个框架内的详细信息，yield。
            item = QuoteItem()                 #
            text = quote.css('span.text::text').extract_first()
            author = quote.css('small.author::text').extract_first()
            tags = quote.css('div.tags > a.tag::text').extract()
            item['text'] = text
            item['author'] = author
            item['tags'] = tags
            yield item
        url = response.css('li.next > a::attr(href)').extract_first()
        next_url = response.urljoin(url)                           # response.urljoin()
        yield scrapy.Request(url=next_url,callback=self.parse)     # yield Request对象

 

　　Pipeline

　　收获：

　　　1 这里都是类，完全可以定义__init__，完全可以把一些数据 添加到其静态属性。　

import pymongo
from scrapy.exceptions import DropItem

class QuotePipeline1(object):
    def __init__(self):
        self.limit = 40
    def process_item(self,item,spider):
        if item:
            if len(item['text'])>self.limit:
                item['text'] = item['text'][:self.limit]+'...'
            return item
        else:
            return DropItem('{}扔掉'.format(item))

class QuotePipeline2(object):
    def __init__(self,uri,port,db):
        self.uri = uri
        self.port = port
        self.db = db
    @classmethod
    def from_crawler(cls,crawler):                             # from_crawler(cls,crawler) 类方法，可以从settings中获取 值。
        mongo_uri = crawler.settings.get('MONGO_URI')
        mongo_port = crawler.settings.get('MONGO_PORT')
        mongo_db = crawler.settings.get('MONGO_DB')
        return cls(
            mongo_uri,
            mongo_port,
            mongo_db,
        )
    def process_item(self,item,spider):
        name = item.__class__.__name__                # __class__.__name__返回的是 这个数据的 类 的名成。即在items 中定义的 class QuoteItem()：
        self.db[name].insert(dict(item))
        return item
    def open_spider(self,spider):
        self.client = pymongo.MongoClient(self.uri,self.port)
        self.db = self.client[self.db]
    def close_spider(self,spider):
        self.client.close()