[Python爬虫] 之十四：Selenium +phantomjs抓取媒介360数据

　　具体代码如下：
# coding=utf-8
import os
import re
from selenium import webdriver
import selenium.webdriver.support.ui as ui
from selenium.webdriver.common.keys import Keys
import time
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.support.select import Select
import IniFile
from selenium.webdriver.common.keys import Keys
from threading import Thread
import thread
import LogFile
import urllib
import mongoDB
#抓取数据线程类
class ScrapyData_Thread(Thread):
    #抓取数据线程类
    def __init__(self,webSearchUrl,inputTXTIDLabel,searchlinkIDLabel,htmlLable,htmltime,keyword,invalid_day,db):
        '''
        构造函数
        :param webSearchUrl: 搜索页url
        :param inputTXTIDLabel: 搜索输入框的标签
        :param searchlinkIDLabel: 搜索链接的标签
        :param htmlLable: 要搜索的标签
        :param htmltime: 要搜索的时间
        :param invalid_day: 要搜索的关键字，多个关键字中间用分号(;)隔开
        :param keywords: #资讯发布的有效时间，默认是3天以内
        :param db: 保存数据库引擎
        '''
        Thread.__init__(self)

        self.webSearchUrl = webSearchUrl
        self.inputTXTIDLabel = inputTXTIDLabel
        self.searchlinkIDLabel = searchlinkIDLabel
        self.htmlLable = htmlLable
        self.htmltime = htmltime
        self.keyword = keyword
        self.invalid_day = invalid_day
        self.db = db

        self.driver = webdriver.PhantomJS()
        self.wait = ui.WebDriverWait(self.driver, 20)
        self.driver.maximize_window()

    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 run(self):
        print '关键字：%s' % self.keyword

        self.driver.get(self.webSearchUrl)
        time.sleep(1)

        # js = "var obj = document.getElementById('ctl00_ContentPlaceHolder1_txtSearch');obj.value='" + self.keyword + "';"
        # self.driver.execute_script(js)
        # 点击搜索链接
        ss_elements = self.driver.find_element_by_id(self.inputTXTIDLabel)
        ss_elements.send_keys(unicode(self.keyword,'utf8'))

        search_elements = self.driver.find_element_by_id(self.searchlinkIDLabel)
        search_elements.click()
        time.sleep(4)

        self.wait.until(lambda driver: self.driver.find_elements_by_xpath(self.htmlLable))
        Elements = self.driver.find_elements_by_xpath(self.htmlLable)

        timeElements = self.driver.find_elements_by_xpath(self.htmltime)
        urlList = []
        for hrefe in Elements:
            urlList.append(hrefe.get_attribute('href').encode('utf8'))

        index = 0
        strMessage = ' '
        strsplit = '\n------------------------------------------------------------------------------------\n'
        index = 0
        # 每页中有用记录
        recordCount = 0
        usefulCount = 0
        meetingList = []
        kword = self.keyword
        currentDate = time.strftime('%Y-%m-%d')

        for element in Elements:

            strDate = timeElements[index].text.encode('utf8')
            # 日期在3天内并且搜索的关键字在标题中才认为是复合要求的数据
            #因为搜索的记录是安装时间倒序，所以如果当前记录的时间不在3天以内，那么剩下的记录肯定是小于当前日期的，所以就退出
            if self.Comapre_to_days(currentDate,strDate) < self.invalid_day:
                usefulCount =  1
                txt = element.text.encode('utf8')
                if txt.find(kword) > -1:
                    dictM = {'title': txt, 'date': strDate,
                             'url': urlList[index], 'keyword': kword, 'info': txt}
                    meetingList.append(dictM)

                    # print ' '
                    # print '标题：%s' % txt
                    # print '日期：%s' % strDate
                    # print '资讯链接：' + urlList[index]
                    # print strsplit

                    # # log.WriteLog(strMessage)
                    recordCount = recordCount + 1
            else:
                usefulCount = 0

            if usefulCount:
                break
            index = index + 1

        self.db.SaveMeetings(meetingList)
        print "共抓取了: %d 个符合条件的资讯记录" % recordCount

        self.driver.close()
        self.driver.quit()

if __name__ == '__main__':

    configfile = os.path.join(os.getcwd(), 'chinaMedia.conf')
    cf = IniFile.ConfigFile(configfile)
    webSearchUrl = cf.GetValue("section", "webSearchUrl")
    inputTXTIDLabel = cf.GetValue("section", "inputTXTIDLabel")
    searchlinkIDLabel = cf.GetValue("section", "searchlinkIDLabel")
    htmlLable = cf.GetValue("section", "htmlLable")
    htmltime = cf.GetValue("section", "htmltime")

    invalid_day = int(cf.GetValue("section", "invalid_day"))

    keywords= cf.GetValue("section", "keywords")
    keywordlist = keywords.split(';')
    start = time.clock()
    db = mongoDB.mongoDbBase()
    for keyword in keywordlist:
        if len(keyword) > 0:
            t = ScrapyData_Thread(webSearchUrl,inputTXTIDLabel,searchlinkIDLabel,htmlLable,htmltime,keyword,invalid_day,db)
            t.setDaemon(True)
            t.start()
            t.join()

    end = time.clock()
    print "整个过程用时间: %f 秒" % (end - start)
巴特西

[Python爬虫] 之十四：Selenium +phantomjs抓取媒介360数据

最新文章

热门文章
