一、介紹

　　　　本例子用scrapy-splash抓取界面網站給定關鍵字抓取咨詢信息。

　　　　給定關鍵字：個性化；融合；電視

　　　　抓取信息內如下：

　　　　　　1、資訊標題

　　　　　　2、資訊鏈接

　　　　　　3、資訊時間

　　　　　　4、資訊來源

　　二、網站信息

　　三、數據抓取

　　　　針對上面的網站信息，來進行抓取

　　　　1、首先抓取信息列表

　　　　　　抓取代碼：sels = site.xpath(‘//div[contains(@class,"news-view")]‘)

　　　　2、抓取標題

　　　　　　抓取代碼：title = sel.xpath(‘.//div[@class="news-header"][email protected])[0].extract()

　　　　3、抓取鏈接

　　　　　　抓取代碼：it[‘url‘] = sel.xpath(‘.//div[@class="news-header"][email protected])[0].extract()

　　　　4、抓取日期

　　　　　　抓取代碼：dates = sel.xpath(‘.//div[@class="news-footer"]/p/span[2]/text()‘)

　　　　5、抓取來源

　　　　　　抓取代碼：sources =sel.xpath(‘.//div[@class="news-footer"]/p/span[1]/a/text()‘)

　　四、完整代碼

# -*- 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 jiemianSpider(Spider):
    name = ‘jiemian‘

    configfile = os.path.join(os.getcwd(), ‘splash_test\spiders\setting.conf‘)

    cf = IniFile.ConfigFile(configfile)
    information_keywords = cf.GetValue("section", "information_keywords")
    information_wordlist = information_keywords.split(‘;‘)
    websearchurl = cf.GetValue("jiemian", "websearchurl")
    start_urls = []
    for word in information_wordlist:
        print websearchurl + word
        start_urls.append(websearchurl + word)

    # request需要封裝成SplashRequest
    def start_requests(self):
        for url in self.start_urls:
            index = url.rfind(‘=‘)
            yield SplashRequest(url
                                , self.parse
                                , args={‘wait‘: ‘2‘},
                                meta={‘keyword‘: url[index + 1:]}
                                )

    def Comapre_to_days(self,leftdate, rightdate):
        ‘‘‘
        比較連個字符串日期，左邊日期大於右邊日期多少天
        :param leftdate: 格式：2017-04-15
        :param rightdate: 格式：2017-04-15
        :return: 天數
        ‘‘‘
        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}‘)
        dt = strDateText.replace(‘/‘, ‘-‘)
        strDate = re.findall(datePattern, dt)
        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[contains(@class,"news-view")]‘)
        keyword = response.meta[‘keyword‘]
        item_list = []
        for sel in sels:
            dates = sel.xpath(‘.//div[@class="news-footer"]/p/span[2]/text()‘)
            flag,date =self.date_isValid(dates[0].extract())
            title = sel.xpath(‘.//div[@class="news-header"][email protected]‘)[0].extract()
            if  flag and title.find(keyword)>-1:
                it = SplashTestItem()
                it[‘title‘] = title
                it[‘url‘] = sel.xpath(‘.//div[@class="news-header"][email protected]‘)[0].extract()
                it[‘date‘] = date
                it[‘keyword‘] = keyword
                sources =sel.xpath(‘.//div[@class="news-footer"]/p/span[1]/a/text()‘)
                if len(sources)>0:
                    it[‘source‘] = sources[0].extract()
                item_list.append(it)
        return item_list

scrapy-splash抓取動態數據例子八