python - Scrapy，使用不同的 XPathSelector 进行递归爬行

Question

晚上好，感谢您的帮助。

我正在挖掘 Scrappy，我的需要是从网站获取信息并重新创建该网站的相同树结构。 示例:

books [
python [
    first [
    title = 'Title'
    author = 'John Doe'
    price = '200'
    ]

    first [
    title = 'Other Title'
    author = 'Mary Doe'
    price = '100'
    ]
]

php [
    first [
        title = 'PhpTitle'
        author = 'John Smith'
        price = '100'
        ]

        first [
        title = 'Php Other Title'
        author = 'Mary Smith'
        price = '300'
    ]
]
]

从教程中我已经正确完成了我的基本蜘蛛:

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from pippo.items import PippoItem

class PippoSpider(BaseSpider):
    name = "pippo"
    allowed_domains = ["www.books.net"]
    start_urls = [
        "http://www.books.net/index.php"
    ]

    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        sites = hxs.select('//div[@id="28008_LeftPane"]/div/ul/li')
        items = []
        for site in sites:
        item = PippoItem()
        item['subject'] = site.select('a/b/text()').extract()
        item['link'] = site.select('a/@href').extract()
        items.append(item)
        return items

我的问题是，我的结构的任何级别在网站中都更深一层，因此如果在我的基础级别中我获得了我需要的书籍主题，则抓取相应的 itemitem['link'] 以获取其他项目。但在下一个网址中，我将需要一个不同的 HtmlXPathSelector 来正确提取我的数据，依此类推，直到结构结束。

您能基本上帮助我并让我走上正确的道路吗？ 谢谢。

Answer 1

您需要手动请求链接:(另请参阅 CrawlSpider )

from urlparse import urljoin

from scrapy.http import Request
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector

from pippo.items import PippoItem

class PippoSpider(BaseSpider):
    name = "pippo"
    allowed_domains = ["www.books.net"]
    start_urls = ["http://www.books.net/"]

    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        sites = hxs.select('//div[@id="28008_LeftPane"]/div/ul/li')

        for site in sites:
            item = PippoItem()
            item['subject'] = site.select('.//text()').extract()
            item['link'] = site.select('.//a/@href').extract()
            link = item['link'][0] if len(item['link']) else None
            if link:
                yield Request(urljoin(response.url, link),
                    callback=self.parse_link,
                    errback=lambda _: item,
                    meta=dict(item=item),
                    )
            else:
                yield item

    def parse_link(self, response):
        item = response.meta.get('item')
        item['alsothis'] = 'more data'
        return item