scrapy-splash抓取动态数据例子九

  一、介绍

    本例子用scrapy-splash抓取众视网网站给定关键字抓取咨询信息。

    给定关键字:个性化;融合;电视

    抓取信息内如下:

      1、资讯标题

      2、资讯链接

      3、资讯时间

      4、资讯来源

  二、网站信息

    

    

    

    

    

  三、数据抓取

    针对上面的网站信息,来进行抓取

    1、首先抓取信息列表

      抓取代码:sels = site.xpath('//div[@class="topic overfl"]')

    2、抓取标题

      抓取代码:title = sel.xpath('.//div[@class="info"]/h3/a/text()')[0].extract()

    3、抓取链接

      抓取代码:url = 'http://www.dvbcn.com' + str(sel.xpath('.//div[@class="info"]/h3/a/@href')[0].extract())

    4、抓取日期

      抓取代码:strdate = sel.xpath('.//span[@class="time"]/text()')[0].extract()

    5、抓取来源

      抓取代码:sources = site.xpath('//span[@class="news_from"]/font/text()')

   

  四、完整代码

# -*- coding: utf-8 -*-
import scrapy
from scrapy import Request
from scrapy.spiders import Spider
from scrapy_splash import SplashRequest
from scrapy_splash import SplashMiddleware
from scrapy.http import Request, HtmlResponse
from scrapy.selector import Selector
from scrapy_splash import SplashRequest
from splash_test.items import SplashTestItem
import IniFile
import sys
import os
import re
import time

reload(sys)
sys.setdefaultencoding('utf-8')

# sys.stdout = open('output.txt', 'w')

class dvbcnSpider(Spider):
    name = 'dvbcn'

    configfile = os.path.join(os.getcwd(), 'splash_testspiderssetting.conf')

    cf = IniFile.ConfigFile(configfile)
    information_wordlist = cf.GetValue("section", "information_keywords").split(';')
    websearch_urls = cf.GetValue("dvbcn", "websearchurl").split(';')
    start_urls = []
    for url in websearch_urls:
        print url
        start_urls.append(url)

    # request需要封装成SplashRequest
    def start_requests(self):
        for url in self.start_urls:
            yield SplashRequest(url
                                , self.parse
                                , args={'wait': '2'}
                                )

    def Comapre_to_days(self,leftdate, rightdate):
        '''
        比较连个字符串日期,左边日期大于右边日期多少天
        :param leftdate: 格式:2017-04-15
        :param rightdate: 格式:2017-04-15
        :return: 天数
        '''
        l_time = time.mktime(time.strptime(leftdate, '%Y-%m-%d'))
        r_time = time.mktime(time.strptime(rightdate, '%Y-%m-%d'))
        result = int(l_time - r_time) / 86400
        return result

    def date_isValid(self, strDateText):
        currentDate = time.strftime('%Y-%m-%d')
        datePattern = re.compile(r'd{4}-d{1,2}-d{1,2}')
        strDate = re.findall(datePattern, strDateText)
        if len(strDate) == 1:
            if self.Comapre_to_days(currentDate,strDate[0])==0:
                return True,currentDate
        return False, ''
    def parse(self, response):

        site = Selector(response)
        sels = site.xpath('//div[@class="topic overfl"]')
        for sel in sels:
            strdate = sel.xpath('.//span[@class="time"]/text()')[0].extract()
            flag, date = self.date_isValid(strdate)
            if flag:
                title = sel.xpath('.//div[@class="info"]/h3/a/text()')[0].extract()
                url = 'http://www.dvbcn.com' + str(sel.xpath('.//div[@class="info"]/h3/a/@href')[0].extract())

                for keyword in self.information_wordlist:
                    if title.find(keyword) > -1:
                        yield SplashRequest(url
                                            , self.parse_item
                                            , args={'wait': '1'},
                                            meta={'date': date, 'url': url,
                                                  'keyword': keyword, 'title': title}
                                            )


    def parse_item(self, response):
        site = Selector(response)
        it = SplashTestItem()
        it['title'] = response.meta['title']
        it['url'] = response.meta['url']
        it['date'] = response.meta['date']
        it['keyword'] = response.meta['keyword']
        sources = site.xpath('//span[@class="news_from"]/font/text()')
        if len(sources)>0:
            it['source'] = sources[0].extract()
        return it
原文地址:https://www.cnblogs.com/shaosks/p/6972825.html