pyspider—爬取视频链接

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
# Created on 2015-03-20 09:46:20
# Project: fly_spider

import re
import time
#from pyspider.database.mysql.mysqldb import SQL
from pyspider.libs.base_handler import *
from pyquery import PyQuery as pq

class Handler(BaseHandler):

    headers= {
    "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "Accept-Encoding":"gzip, deflate, sdch",
    "Accept-Language":"zh-CN,zh;q=0.8",
    "Cache-Control":"max-age=0",
    "Connection":"keep-alive",
    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.101 Safari/537.36"
    }

    crawl_config = {
        "headers" : headers,
        "timeout" : 100
    }
    @every(minutes= 1)
    def on_start(self):
        self.crawl('http://www.zhanqi.tv/games',callback=self.index_page)

    @config(age=10 * 24 * 60 * 60)
    def index_page(self, response):
        print(response)
        for each in response.doc('a[href^="http://www.zhanqi.tv/games/"]').items():
            if re.match("http://www.zhanqi.tv/games/\w+", each.attr.href, re.U):
                self.crawl(each.attr.href, 
                fetch_type='js',                   
                js_script="""
                function() {
                    setTimeout(window.scrollTo(0,document.body.scrollHeight), 5000);         
                }
                """,callback=self.list_page)  

    @config(age=1*60*60, priority=2)                
    def list_page(self, response):
        for each in response.doc('.active > div.live-list-tabc > ul#hotList.clearfix > li > a').items():
            if re.match("http://www.zhanqi.tv/\w+", each.attr.href, re.U):
                self.crawl(each.attr.href,
                fetch_type='js',                   
                js_script="""
                function() {
                    setTimeout(window.scrollTo(0,document.body.scrollHeight), 5000);        
                }
                """,callback=self.detail_page)    

    @config(age=1*60*60, priority=2)
    def detail_page(self, response):
        for each in response.doc('.video-flash-cont').items():
            d = pq(each)
            print(d.html())

        return {
            "url": response.url,
            "author":response.doc('.meat > span').text(),
            "title":response.doc('.title-name').text(),
            "game-name":response.doc('span > .game-name').text(),
            "users2":response.doc('div.live-anchor-info.clearfix > div.sub-anchor-info > div.clearfix > div.meat-info > span.num.dv.js-onlines-panel > span.dv.js-onlines-txt > span').text(),
            "flash-cont":d.html(),
            "picture":response.doc('.active > img').text(),
            }
posted @ 2015-09-30 14:52 silianpan 阅读(...) 评论(...) 编辑 收藏