[Python爬蟲] 之十九:Selenium +phantomjs 利用 pyquery抓取超級TV網數據
阿新 • • 發佈:2017-06-20
images 判斷 nco dex onf etc lac lin 利用
一、介紹
本例子用Selenium +phantomjs爬取超級TV(http://www.chaojitv.com/news/index.html)的資訊信息,輸入給定關鍵字抓取資訊信息。
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:Elements = doc(‘ul[class="la_list"]‘).find(‘li‘)
2、抓取標題
抓取代碼:title = element(‘h4‘).find(‘a‘).text().encode(‘utf8‘).strip()
3、抓取鏈接
抓取代碼:url = element(‘h4‘).find(‘a‘).attr(‘href‘)
4、抓取日期
抓取代碼:date = element(‘div[class="time"]‘).find(‘span‘).text().encode(‘utf8‘).strip()
5、抓取來源
抓取代碼:strSources = dochtml(‘span[class="wzof"]‘).text().encode(‘utf8‘).strip().split(‘:‘)
四、完整代碼
# coding=utf-8 import os import re from selenium import webdriver import selenium.webdriver.support.ui as ui import time from datetime import datetime import IniFile # from threading import Thread from pyquery import PyQuery as pq import LogFile import mongoDB class chaojitvSpider(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.webSearchUrl_list = cf.GetValue("chaojitv", "webSearchUrl").split(‘;‘) self.keyword_list = cf.GetValue("section", "information_keywords").split(‘;‘) self.db = mongoDB.mongoDbBase() self.start_urls = [] for url in self.webSearchUrl_list: self.start_urls.append(url) self.driver = webdriver.PhantomJS() self.wait = ui.WebDriverWait(self.driver, 2) self.driver.maximize_window() def Comapre_to_days(self,leftdate, rightdate): ‘‘‘ 比較連個字符串日期,左邊日期大於右邊日期多少天 :param leftdate: 格式:2017-04-15 :param rightdate: 格式:2017-04-15 :return: 天數 ‘‘‘ 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: ‘2017-06-20 10:22 ‘ :return: True:合法;False:不合法 ‘‘‘ currentDate = time.strftime(‘%Y-%m-%d‘) datePattern = re.compile(r‘\d{4}-\d{2}-\d{2}‘) strDate = re.findall(datePattern, strDateText) if len(strDate) == 1: if self.Comapre_to_days(currentDate, strDate[0]) == 0: return True, strDate[0] return False, ‘‘ def log_print(self, msg): ‘‘‘ # 日誌函數 # :param msg: 日誌信息 # :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="la_list"]‘).find(‘li‘) for element in Elements.items(): date = element(‘div[class="time"]‘).find(‘span‘).text().encode(‘utf8‘).strip() flag, strDate = self.date_isValid(date) if flag: title = element(‘h4‘).find(‘a‘).text().encode(‘utf8‘).strip() for keyword in self.keyword_list: if title.find(keyword) > -1: url = element(‘h4‘).find(‘a‘).attr(‘href‘) dictM = {‘title‘: title, ‘date‘: strDate, ‘url‘: url, ‘keyword‘: keyword, ‘introduction‘: title, ‘source‘: ‘‘} 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) strSources = dochtml(‘span[class="wzof"]‘).text().encode(‘utf8‘).strip().split(‘:‘) if len(strSources)>2: item[‘source‘] = strSources[2].replace(‘編輯‘,‘‘).replace(‘ ‘,‘‘) self.log_print(‘title:%s‘ % item[‘title‘]) self.log_print(‘url:%s‘ % item[‘url‘]) self.log_print(‘date:%s‘ % item[‘date‘]) self.log_print(‘source:%s‘ % item[‘source‘]) self.log_print(‘kword:%s‘ % item[‘keyword‘]) self.log_print(strsplit) self.db.SaveInformations(infoList) self.driver.close() self.driver.quit() obj = chaojitvSpider() obj.scrapy_date()
[Python爬蟲] 之十九:Selenium +phantomjs 利用 pyquery抓取超級TV網數據