一、介绍

    本例子用scrapy-splash抓取活动树网站给定关键字抓取活动信息。

    给定关键字:数字;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

    scrapy-splash抓取动态数据例子十一-LMLPHP

    scrapy-splash抓取动态数据例子十一-LMLPHP

      scrapy-splash抓取动态数据例子十一-LMLPHP

  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[@id ='eventList']/div[@class ='list']")

    2、抓取标题

      抓取代码:title = str(sel.xpath('.//div[2]/h2/a/text()')[0].extract())

    3、抓取链接

      抓取代码:url = 'http://www.huodongshu.com' + str(sel.xpath('.//div[1]/a/@href')[0].extract())

    4、抓取日期

      抓取代码:dates = sel.xpath('.//div[@class="info time"]/text()')

    5、抓取来源

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

    6、地点

      抓取代码:areas = sel.xpath('.//div[@class="info site"]/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 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需要封装成SplashRequest
def start_requests(self):
for url in self.start_urls:
index = url.rfind('=')
yield SplashRequest(url
, self.parse
, args={'wait': ''},
meta={'keyword': url[index + 1:]}
) def compareDate(self, dateLeft, dateRight):
'''
比较俩个日期的大小
:param dateLeft: 日期 格式2017-03-04
:param dateRight:日期 格式2017-03-04
:return: 1:左大于右,0:相等,-1:左小于右
'''
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):
'''
判断日期时间字符串是否合法:如果给定时间大于当前时间是合法,或者说当前时间给定的范围内
:param strDateText: 三种格式 '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]/a/@href')[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
05-11 22:23