一、介绍
本例子用scrapy-splash抓取界面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[contains(@class,"news-view")]‘)
2、抓取标题
抓取代码:title = sel.xpath(‘.//div[@class="news-header"]/h3/a/@title‘)[0].extract()
3、抓取链接
抓取代码:it[‘url‘] = sel.xpath(‘.//div[@class="news-header"]/h3/a/@href‘)[0].extract()
4、抓取日期
抓取代码:dates = sel.xpath(‘.//div[@class="news-footer"]/p/span[2]/text()‘)
5、抓取来源
抓取代码:sources =sel.xpath(‘.//div[@class="news-footer"]/p/span[1]/a/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 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需要封装成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}‘) 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"]/h3/a/@title‘)[0].extract() if flag and title.find(keyword)>-1: it = SplashTestItem() it[‘title‘] = title it[‘url‘] = sel.xpath(‘.//div[@class="news-header"]/h3/a/@href‘)[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
时间: 2024-11-06 09:27:23