Python クローラー フレームワークのスクレイピーなサンプルの詳細な説明

from scrapy.spider import BaseSpider
class DmozSpider(BaseSpider):
    name = "dmoz"
    allowed_domains = ["dmoz.org"]
    start_urls = [
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
    ]
    def parse(self, response):
        filename = response.url.split("/")[-2]
        open(filename, 'wb').write(response.body)

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class DmozSpider(BaseSpider):
    name = "dmoz"
    allowed_domains = ["dmoz.org"]
    start_urls = [
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
        "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
    ]
    def parse(self, response):
        hxs = HtmlXPathSelector(response)
        sites = hxs.select('//ul/li')
        for site in sites:
            title = site.select('a/text()').extract()
            link = site.select('a/@href').extract()
            desc = site.select('text()').extract()
            print title, link, desc

from scrapy.item import Item, Field
class DmozItem(Item):
   title = Field()
   link = Field()
   desc = Field()
然后在spider的parse方法中，我们把解析出来的数据保存在DomzItem对象中。
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from tutorial.items import DmozItem
class DmozSpider(BaseSpider):
   name = "dmoz"
   allowed_domains = ["dmoz.org"]
   start_urls = [
       "http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
       "http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
   ]
   def parse(self, response):
       hxs = HtmlXPathSelector(response)
       sites = hxs.select('//ul/li')
       items = []
       for site in sites:
           item = DmozItem()
           item['title'] = site.select('a/text()').extract()
           item['link'] = site.select('a/@href').extract()
           item['desc'] = site.select('text()').extract()
           items.append(item)
       return items

class MySpider(BaseSpider):
    name = 'myspider'
    start_urls = (
        'http://example.com/page1',
        'http://example.com/page2',
        )
    def parse(self, response):
        # collect `item_urls`
        for item_url in item_urls:
            yield Request(url=item_url, callback=self.parse_item)
    def parse_item(self, response):
        item = MyItem()
        # populate `item` fields
        yield Request(url=item_details_url, meta={'item': item},
            callback=self.parse_details)
    def parse_details(self, response):
        item = response.meta['item']
        # populate more `item` fields
        return item

from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
class MininovaSpider(CrawlSpider):
    name = 'mininova.org'
    allowed_domains = ['mininova.org']
    start_urls = ['http://www.mininova.org/today']
    rules = [Rule(SgmlLinkExtractor(allow=['/tor/\d+'])),
             Rule(SgmlLinkExtractor(allow=['/abc/\d+']), 'parse_torrent')]
    def parse_torrent(self, response):
        x = HtmlXPathSelector(response)
        torrent = TorrentItem()
        torrent['url'] = response.url
        torrent['name'] = x.select("//h1/text()").extract()
        torrent['description'] = x.select("//div[@id='description']").extract()
        torrent['size'] = x.select("//div[@id='info-left']/p[2]/text()[2]").extract()
        return torrent