scrapy 學習

import scrapy

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

    def start_requests(self):
        urls = [
            'http://quotes.toscrape.com/page/1/',
            #'http://quotes.toscrape.com/page/2/',
        ]
        for url in urls:
            yield scrapy.Request(url=url, callback=self.parse)

    def parse(self, response):
        for quote in response.xpath('//div[@class="quote"]'):
            yield {
               'text': quote.xpath('.//span[@class="text"]/text()').extract(),
               'author': quote.xpath('.//small[@class="author"]/text()').extract(),
               'tags': quote.xpath('./div/meta/@content').extract(),
            }
 
        next_page = response.xpath('//li[@class="next"]/a/@href').extract_first()
        if next_page is not None:
            next_page = response.urljoin(next_page)
            yield scrapy.Request(next_page, callback=self.parse)

知識點：

1.xpath如何在循環中訪問當前節點下的內容（'.//

2.當前循環節點內容下的值能夠按照絕對路徑獲取    (./div/meta

3.當前頁面的url如何訪問    response.urljoin(