一、介绍
本例子用Selenium +phantomjs爬取活动行(http://www.huodongxing.com/search?qs=数字&city=全国&pi=1)的资讯信息,输入给定关键字抓取资讯信息。
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:Elements = doc('ul[class="event-horizontal-list-new"]').find('li')
2、抓取标题
抓取代码:title = element('h3').find('a').text().encode('utf8').strip()
3、抓取链接
抓取代码:url = 'http://www.huodongxing.com' + element('a').attr('href')
4、抓取日期
抓取代码:strdate = element.find('div').eq(0).text().encode('utf8').strip()
5、抓取主办方
抓取代码:orgnizer = element('div').eq(2).find('a').eq(1).find('span').text().encode('utf8').strip()
四、完整代码
# coding=utf-8 import os import re from selenium import webdriver import selenium.webdriver.support.ui as ui import time from datetime import datetime from selenium.webdriver.common.action_chains import ActionChains import IniFile # from threading import Thread from pyquery import PyQuery as pq import LogFile import mongoDB import urllib class huodongxingSpider(object): def __init__(self): logfile = os.path.join(os.path.dirname(os.getcwd()), time.strftime('%Y-%m-%d') + '.txt') self.log = LogFile.LogFile(logfile) configfile = os.path.join(os.path.dirname(os.getcwd()), 'setting.conf') cf = IniFile.ConfigFile(configfile) self.db = mongoDB.mongoDbBase() self.keyword_list = cf.GetValue("section", "meeting_keywords").split(';') websearch_url = cf.GetValue("huodongxing", "websearchurl") self.start_urls = [] for keyword in self.keyword_list: for i in xrange(1,4): url = websearch_url + '&pi=' + str(i) + '&qs=' + urllib.quote(keyword) self.start_urls.append(url) self.driver = webdriver.PhantomJS() self.wait = ui.WebDriverWait(self.driver, 2) self.driver.maximize_window() def scroll_foot(self): ''' 滚动条拉到底部 :return: ''' js = "" # 如何利用chrome驱动或phantomjs抓取 if self.driver.name == "chrome" or self.driver.name == 'phantomjs': js = "var q=document.body.scrollTop=10000" # 如何利用IE驱动抓取 elif self.driver.name == 'internet explorer': js = "var q=document.documentElement.scrollTop=10000" return self.driver.execute_script(js) 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: 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 ''' currentDate = time.strftime('%Y-%m-%d') datePattern = re.compile(r'd{4}-d{1,2}-d{1,2}') strDate = re.findall(datePattern, strDateText) if len(strDate) == 1: if self.Comapre_to_days(strDate[0], currentDate) > 0: return True, strDate[0] return False, '' def log_print(self, msg): ''' # 日志函数 # :param msg: 日志信息 # :return: # ''' print '%s: %s' % (time.strftime('%Y-%m-%d %H-%M-%S'), msg) def scrapy_date(self): strsplit = '------------------------------------------------------------------------------------' for link in self.start_urls: self.driver.get(link) selenium_html = self.driver.execute_script("return document.documentElement.outerHTML") doc = pq(selenium_html) infoList = [] self.log.WriteLog(strsplit) self.log_print(strsplit) Elements = doc('ul[class="event-horizontal-list-new"]').find('li') for element in Elements.items(): strdate = element.find('div').eq(0).text().encode('utf8').strip() flag, date = self.date_isValid(strdate) if flag: title = element('h3').find('a').text().encode('utf8').strip() for keyword in self.keyword_list: if title.find(keyword) > -1: url = 'http://www.huodongxing.com' + element('a').attr('href') orgnizer = element('div').eq(2).find('a').eq(1).find('span').text().encode('utf8').strip() dictM = {'title': title, 'date': date, 'url': url, 'keyword': keyword, 'startdate': date, 'enddate': date, 'area': '', 'organizer': orgnizer} infoList.append(dictM) break if len(infoList)>0: for item in infoList: url =item['url'] self.driver.get(url) htext = self.driver.execute_script("return document.documentElement.outerHTML") dochtml = pq(htext) area = dochtml('div[class="address"]').find('a').text().encode('utf8').strip() item['area'] = area # self.log.WriteLog('title:%s' % title) # self.log.WriteLog('url:%s' % url) # self.log.WriteLog('orgnizer:%s' % orgnizer) # self.log.WriteLog('kword:%s' % keyword) # self.log.WriteLog('area:%s' % area) # self.log.WriteLog('-----------------------------------') self.log_print('title:%s' % item['title']) self.log_print('url:%s' % item['url']) self.log_print('date:%s' % item['date']) self.log_print('orgnizer:%s' % item['organizer']) self.log_print('kword:%s' % item['keyword']) self.log_print('area:%s' % area) self.log_print('--------------------------') self.db.SaveMeetings(infoList) self.driver.close() self.driver.quit() # obj = huodongxingSpider() # obj.scrapy_date()