本帖最后由 xiaoye 于 2015-9-30 10:52 编辑
最近在看scrapy,然后就有福利了，源码参考网上现有源代码，如果有想直接看源代码的请直接百度之
核心源码
[Python] 纯文本查看 复制代码 # This package will contain the spiders of your Scrapy project
#
# Please refer to the documentation for information on how to create and manage
# your spiders.
#encoding:utf8
from scrapy.spider import BaseSpider
from scrapy.selector import Selector
import scrapy
from scrapy.contrib.loader import ItemLoader,Identity
from meizitu.items import MeizituItem
class MeizituSpider(BaseSpider):
name="meizitu"
allowed_domains=["meizitu.com"]
start_urls={
'http://www.meizitu.com',
}
def parse(self,response):
sel=Selector(response)
for link in sel.xpath('//h2/a/@href').extract():
request=scrapy.Request(link,callback=self.parse_item)
yield request
pages=sel.xpath("//div[@class='navigation']/div[@id='wp_page_numbers']/ul/li/a/@href").extract()
print "pages:%s"%pages
if len(pages)>2:
page_link=pages[-2]
page_link=page_link.replace('/a/','')
request=scrapy.Request('http://www.meizitu.com/a/%s' % page_link, callback=self.parse)
yield request
def parse_item(self,response):
l = ItemLoader(item=MeizituItem(), response=response)
l.add_xpath('name', '//h2/a/text()')
l.add_xpath('tags', "//div[@id='maincontent']/div[@class='postmeta clearfix']/div[@class='metaRight']/p")
l.add_xpath('image_urls', "//div[@id='picture']/p/img/@src", Identity())
l.add_value('url', response.url)
return l.load_item()
依赖scrapy，运行之前请先安装scrapy
源码下载地址
https://github.com/i3esn0w/fun_craw.git
貌似没有图片不好说话
| 
发表于 2015-4-20 21:07:00
