pyspider 示例

数据存放目录：

C:\Users\Administrator\data

升级版（可加载文章内所有多层嵌套的图片标签）

#!/usr/bin/env python

# -*- encoding: utf-8 -*-

# Created on 2019-04-08 14:24:34

# Project: qunaer

from pyspider.libs.base_handler import *

class Handler(BaseHandler):

    crawl_config = {

    }

    @every(minutes=24 * 60)

    def on_start(self):

        self.crawl('https://travel.qunar.com/travelbook/list.htm', callback=self.index_page,validate_cert=False)

    @config(age=10 * 24 * 60 * 60)

    def index_page(self, response):

        for each in response.doc('li > .tit>a').items():

            self.crawl(each.attr.href, callback=self.detail_page,validate_cert=False,fetch_type='js',js_viewport_height='')

        next1=response.doc('.next').attr.href

        self.crawl(next1,callback=self.index_page,validate_cert=False)

    @config(priority=2)

    def detail_page(self, response):

        imgs=response.doc('.js_memo_node').find('img')#获取id下的所有（包括多层嵌套的）img标签

        img_list=''                                  #必须事先声明，否则return,img_list时会报错：引用未事先声明的局部变量

        for img in imgs.items():

            img_list+=img.attr.src+','              #把所有图片用,组合在一起

                                                    #【复习】img_list=', '.join(['cats', 'rats', 'bats'])

        return {

            "url": response.url,

            "title": response.doc('title').text(),

            "date":response.doc('li.f_item.when > p > span.data').text(),

            "day":response.doc('li.f_item.howlong > p > span.data').text(),

            "text":response.doc('#b_panel_schedule').text(),

            "img":img_list

        }

#ele-3076663-2 > div.bottom > div.e_img_schedule > div > dl:nth-child(2) > dt > img

例子A

#!/usr/bin/env python

# -*- encoding: utf-8 -*-

# Created on 2019-04-08 14:24:34

# Project: qunaer

from pyspider.libs.base_handler import *

class Handler(BaseHandler):

    crawl_config = {

    }

    @every(minutes=24 * 60)

    def on_start(self):

        self.crawl('https://travel.qunar.com/travelbook/list.htm', callback=self.index_page,validate_cert=False)

    @config(age=10 * 24 * 60 * 60)

    def index_page(self, response):

        for each in response.doc('li > .tit>a').items():

            self.crawl(each.attr.href, callback=self.detail_page,validate_cert=False,fetch_type='js',js_viewport_height='')#用js加载，指定页面高度，防止懒加载图片只加载一半

        next1=response.doc('.next').attr.href

        self.crawl(next1,callback=self.index_page,validate_cert=False)

    @config(priority=2)

    def detail_page(self, response):

        #imgs=response.doc('#js_mainleft').find('img')

        #for img in imgs.items():

        #    img_list=img_list+img+','

        return {

            "url": response.url,

            "title": response.doc('title').text(),

            "date":response.doc('li.f_item.when > p > span.data').text(),

            "day":response.doc('li.f_item.howlong > p > span.data').text(),

            "text":response.doc('#b_panel_schedule').text(),

            "img":response.doc('#js_mainleft').find('img').attr.src

        }

#ele-3076663-2 > div.bottom > div.e_img_schedule > div > dl:nth-child(2) > dt > img