pyspider使用

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2018-11-08 22:33:55
# Project: qsbk

from pyspider.libs.base_handler import *
from lxml import html
from urlparse import urljoin
import datetime
class Handler(BaseHandler):
    crawl_config = {
    }
    def __init__(self):
        self.start_url=‘https://www.qiushibaike.com/‘
    @every(minutes=24 * 60)
    def on_start(self):
        self.crawl(self.start_url, callback=self.index_page)

    @config(age=10 * 24 * 60 * 60)
    def index_page(self, response):
        root=html.fromstring(response.content.decode(‘utf-8‘))
        content_left_node = root.xpath("//div[@id=‘content-left‘]")
        div_node_list = content_left_node[0].xpath("./div")
        tasks=[]
        for div_node in div_node_list:
            title_node = div_node.xpath(
                ".//div[@class=‘author clearfix‘]/a[contains(@onclick,‘web-list-author-text‘)]/h2/text()")
            __content_url =div_node.xpath("./a[@class=‘contentHerf‘]/@href")
            content_url = urljoin(self.start_url, __content_url[0])
            content_node = div_node.xpath(".//div[@class=‘content‘]/span[1]")
            content = content_node[0].xpath(‘string(.)‘)
            name = title_node[0]
            info = ‘‘.join(content)
            crawldate = datetime.datetime.now().strftime(‘%Y-%m-%d %H:%M:%S‘)
            item = {}
            item[‘name‘] = name.strip() if name else name
            item[‘info‘] = info.strip() if info else info
            item[‘crawldate‘] = crawldate
            item[‘url‘] = content_url
            tasks.append(item)
        return {‘data‘:tasks}