一、介绍
本例子用scrapy-splash爬取梅花网(http://www.meihua.info/a/list/today)的资讯信息,输入给定关键字抓取微信资讯信息。
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
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('//li[@class="item"]')
2、抓取标题
抓取代码:titles = sel.xpath('.//div[@class="first"]/div[1]/a[1]/text()')
3、抓取链接
抓取代码:url = 'http://www.meihua.info' + str(sel.xpath('.//div[@class="first"]/div[1]/a[1]/@href')[0].extract())
4、抓取日期
抓取代码:strdate = sel.xpath('.//span[@class="desc-font date"]/span/text()')
5、抓取来源
抓取代码:sources = site.xpath('//a[@rel="nofollow"]/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 scrapy_ott.items import SplashTestItem
from scrapy_ott.mongoDB import mongoDbBase
import scrapy_ott.IniFile
from scrapy_ott.LogFile import LogFile
import sys
import os
import re
import time reload(sys)
sys.setdefaultencoding('utf-8') # sys.stdout = open('output.txt', 'w') class meihuaSpider(Spider):
log = LogFile(time.strftime('%Y-%m-%d') + '.txt')
name = 'meihua' db = mongoDbBase() configfile = os.path.join(os.getcwd(), 'scrapy_ott\setting.conf')
cf = scrapy_ott.IniFile.ConfigFile(configfile)
information_wordlist = cf.GetValue("section", "information_keywords").split(';')
websearch_urls = cf.GetValue("meihua", "websearchurl").split(';')
start_urls = []
for url in websearch_urls:
start_urls.append(url) # request需要封装成SplashRequest
def start_requests(self):
self.log.WriteLog(u'抓取梅花网资讯数据')
for url in self.start_urls:
yield SplashRequest(url
, self.parse
, args={'wait': ''}
) 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):
'''
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: 四种格式 '今天'; '前天' ; '昨天' ;'06月12日 '
:return: True:合法;False:不合法
'''
currentDate = time.strftime('%Y-%m-%d')
if strDateText.find('今天') > -1 :
return True, currentDate
return False, ''
def parse(self, response): site = Selector(response)
sels = site.xpath('//li[@class="item"]') for sel in sels:
strdate = sel.xpath('.//span[@class="desc-font date"]/span/text()')
flag, date = self.date_isValid(strdate[0].extract())
if flag:
titles = sel.xpath('.//div[@class="first"]/div[1]/a[1]/text()')
title = str(titles[0].extract())
url = 'http://www.meihua.info' + str(sel.xpath('.//div[@class="first"]/div[1]/a[1]/@href')[0].extract())
for keyword in self.information_wordlist:
if title.find(keyword) > -1:
yield SplashRequest(url
, self.parse_item
, args={'wait': ''},
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('//div[@class="art-content"]/p[27]/strong/a/text()')
sources = site.xpath('//a[@rel="nofollow"]/text()')
if len(sources)>0:
it['source'] = sources[0].extract()
else:
it['source'] = '梅花网' # sources = site.xpath('//div[@style="text-align: center;"]/font/text()')
# if len(sources) > 1:
# it['source'] = str(sources[1].extract()).replace('消息源:','')
# else:
# it['source']='梅花网'
self.db.SaveInformation(it)
return it