scrapy-splash抓取動態數據例子十一
阿新 • • 發佈:2017-06-12
tel ems 網站 tput findall spi 來源 標題 end
一、介紹
本例子用scrapy-splash抓取活動樹網站給定關鍵字抓取活動信息。
給定關鍵字:數字;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[@id =‘eventList‘]/div[@class =‘list‘]")
2、抓取標題
抓取代碼:title = str(sel.xpath(‘.//div[2]/h2/a/text()‘)[0].extract())
3、抓取鏈接
抓取代碼:url = ‘http://www.huodongshu.com‘ + str(sel.xpath(‘.//div[1][email protected])[0].extract())
4、抓取日期
抓取代碼:dates = sel.xpath(‘.//div[@class="info time"]/text()‘)
5、抓取來源
抓取代碼:sources = sel.xpath(‘.//div[@class="info title"]/a/text()‘)
6、地點
抓取代碼:areas = sel.xpath(‘.//div[@class="info site"]/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 importRequest, HtmlResponse from scrapy.selector import Selector from scrapy_splash import SplashRequest from splash_test.items import SplashMeetingItem import IniFile import sys import os import re import time reload(sys) sys.setdefaultencoding(‘utf-8‘) import urllib # sys.stdout = open(‘output.txt‘, ‘w‘) class huodongshuSpider(Spider): name = ‘huodongshu‘ configfile = os.path.join(os.getcwd(), ‘splash_test\spiders\setting.conf‘) cf = IniFile.ConfigFile(configfile) meeting_wordlist = cf.GetValue("section", "meeting_keywords").split(‘;‘) websearch_url = cf.GetValue("huodongshu", "websearchurl") start_urls = [] for keyword in meeting_wordlist: url = websearch_url +keyword start_urls.append(url) # 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 compareDate(self, dateLeft, dateRight): ‘‘‘ 比較倆個日期的大小 :param dateLeft: 日期 格式2017-03-04 :param dateRight:日期 格式2017-03-04 :return: 1:左大於右,0:相等,-1:左小於右 ‘‘‘ dls = dateLeft.split(‘-‘) drs = dateRight.split(‘-‘) if len(dls) > len(drs): return 1 if int(dls[0]) == int(drs[0]) and int(dls[1]) == int(drs[1]) and int(dls[2]) == int(drs[2]): return 0 if int(dls[0]) > int(drs[0]): return 1 elif int(dls[0]) == int(drs[0]) and int(dls[1]) > int(drs[1]): return 1 elif int(dls[0]) == int(drs[0]) and int(dls[1]) == int(drs[1]) and int(dls[2]) > int(drs[2]): return 1 return -1 def date_isValid(self, strDateText): ‘‘‘ 判斷日期時間字符串是否合法:如果給定時間大於當前時間是合法,或者說當前時間給定的範圍內 :param strDateText: 三種格式 ‘2017.04.27 ~ 04.28‘; ‘2017.04.20 08:30 ~ 12:30‘ ; ‘2015.12.29 ~ 2016.01.03‘ :return: True:合法;False:不合法 ‘‘‘ datePattern = re.compile(r‘\d{4}-\d{2}-\d{2}‘) date = strDateText.replace(‘.‘, ‘-‘) strDate = re.findall(datePattern, date) currentDate = time.strftime(‘%Y-%m-%d‘) flag = False startdate = ‘‘ enddate = ‘‘ if len(strDate) == 2: if self.compareDate(strDate[1], currentDate) > 0: flag = True startdate = strDate[0] enddate = strDate[1] elif len(strDate) == 1: # 2017.07.13 ~ 07.15 if date.find(‘:‘) > 0: if self.compareDate(strDate[0], currentDate) >= 0: flag = True startdate = strDate[0] enddate = strDate[0] else: startdate = strDate[0] enddate = date[0:5] + date[len(date) - 5:] if self.compareDate(enddate, currentDate) >= 0: flag = True return flag, startdate, enddate def parse(self, response): site = Selector(response) sels = site.xpath("//div[@id =‘eventList‘]/div[@class =‘list‘]") keyword = response.meta[‘keyword‘] it_list = [] for sel in sels: dates = sel.xpath(‘.//div[@class="info time"]/text()‘) if len(dates) > 0: strdate = str(dates[0].extract()) flag, startdate, enddate = self.date_isValid(strdate) if flag: title = str(sel.xpath(‘.//div[2]/h2/a/text()‘)[0].extract()) if title.find(keyword) > -1: url = ‘http://www.huodongshu.com‘ + str(sel.xpath(‘.//div[1][email protected]‘)[0].extract()) it = SplashMeetingItem() it[‘title‘] = title it[‘url‘] = url it[‘date‘] = strdate it[‘startdate‘] = startdate it[‘enddate‘] = enddate it[‘keyword‘] = keyword areas = sel.xpath(‘.//div[@class="info site"]/text()‘) if len(areas) > 0: it[‘area‘]=areas[0].extract() sources = sel.xpath(‘.//div[@class="info title"]/a/text()‘) if len(sources)>0: it[‘source‘] = sources[0].extract() it_list.append(it) return it_list
scrapy-splash抓取動態數據例子十一