|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
有大佬能来看一下嘛
pyspider框架下的
是用来爬取P站图片的 为什么运行不了
- from pyspider.libs.base_handler import *
- import os
- class Handler(BaseHandler):
- crawl_config = {
- }
- @every(minutes=24 * 60)
- def on_start(self):
- self.crawl('https://www.pixiv.net/', callback=self.index_page)
- @config(age=10 * 24 * 60 * 60)
- def index_page(self, response):
- for each in response.doc("div.rp5asc-0 bscYTy a").items():
- self.crawl(each.attr.href, callback=self.detail_page)
- @config(priority=2)
- def detail_page(self, response):
- for each in response.doc("rp5asc-10 leQnFG").items():
- self.crawl(each.attr.src, callback=self.detail_page2)
-
-
- @config(priority=2)
- def detail_page(self, response):
- f=open(os.path.join("D:\\图",response.url[-10:]),'wb')
- f.write(response.content)
- f.close()
复制代码 |
|