scrapy snippet

1. spider文件

from scrapy.contrib.spiders import CrawlSpider, Rule

from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor

from scrapy.selector import HtmlXPathSelector

item = DomzItem()

image_urls = hxs.select('//img/@src').extract()

item['image_urls'] = ["http:" + x for x in image_urls]

return item

from scrapy.selector import HtmlXPathSelector

hxs = HtmlXPathSelector(response)

class MySpider(CrawlSpider): #控制下载速度

    name = 'myspider'

    download_delay = 2

$ scrapy crawl somespider -s JOBDIR=crawls/somespider-1
 

#这样开始下载之后可以Ctrl + C停止，恢复下载还是同样的命令

$ scrapy crawl somespider -s JOBDIR=crawls/somespider-1

name = "wikipedia"

allowed_domains = ["wikipedia.org"]

start_urls = [

　　"http://en.wikipedia.org/wiki/Pune"

]

2. setting文件

ITEM_PIPELINES = ['scrapy.contrib.pipeline.images.ImagesPipeline']

IMAGES_STORE= '...'

3. item 文件

 image_urls = Field()

 images = Field()