Python中scrapy框架的ltem和scrapy.Request详解

import scrapy
class Tutorial1tem(scrapy.Item):
    #define the fields for your item here 7ike:#参照下面这个参数定义你的字段
    #name = scrapy.Fie1d()
    pass

class Quotesspider(scrapy.spider):
    name = 'quotes'
    a1lowed_domains = ['toscrape.com']
    start_ur1s = ['http: //quotes.toscrape.com/']
def parse(self,response):
    quotes = response.css( '.quote ' )
    for quote in quotes :
        text = quote.css('.text: :text ').get()
        author = quote.css( '.author : :text ').get()
        tags = quote.css( '.tag : :text ' ).getall()
    yield {
    'text':text,
    'author':author,
    'tags ' : tags,
    }

#特殊的字典结构可以在scrapy中传递数据
class TutorialItem(scrapy.Item):
    #Field字段
    #就是类似于产生一个类似字典格式的数据拥有字典的一些属性
    #字段默认为空
    #我们可以通过实例化像着键赋值但是如果没有写这个键就不能赋值但是字典可以
    text = scrapy. Field()
    author = scrapy.Fie1d()
    tags = scrapy . Fie1d()

Request(url，ca11back=None，method='GET', headers=None，body=None,
        cookies=None，meta=None，encoding='utf-8 '，priority=O,
        dont_filter=False，errback=None，flags=None，cb_kwargs=None)

c1ass Quotesspider(scrapy.spider):
    name = 'quotes_3'
    allowed_domains = ['toscrape.com']
    start__ur1s = ['http://quotes.toscrape.com/']
def parse(self，response):
    quotes = response.css( '.quote ' )
    for quote in quotes:
        text = quote.css( '.text: :text ' ).get()
        author = quote.css( '.author : :text ' ).get()
        tags = quote.css( '.tag : :text ' ). geta11()
        yield Qd01QuotesItem(text=text，author=author，tags=tags)
    next_page = response.css( '.next a: :attr(href) ' ).get()
    if next_page:
        next__ur1 = 'http: //quotes.toscrape.com' + next_page
        yield scrapy. Request(next_url, cal7back=self.parse)