今天在使用Selenuim+PhantomJS动态抓取网页时，出现如下报错信息：
C:\Python36\lib\site-packages\selenium-3.11.0-py3.6.egg\selenium\webdriver\phantomjs\webdriver.py:49: UserWarning: Selenium support for PhantomJS has been deprecated, please use headless versions of Chrome or Firefox instead
warnings.warn('Selenium support for PhantomJS has been deprecated, please use headless '
意思就是Selenuim已经放弃PhantomJS，了，建议使用火狐或者谷歌无界面浏览器。
要确保机器上安装谷歌浏览器
把chromedriver.exe放在C:\Python27\Scripts路径下
Chrome-headless 模式， Google 针对 Chrome 浏览器 59版 新增加的一种模式，可以让你不打开UI界面的情况下使用 Chrome 浏览器，所以运行效果与 Chrome 保持完美一致。
火狐驱动：https://github.com/mozilla/geckodriver/releases
https://github.com/mozilla/geckodriver/releases/download/v0.19.1/geckodriver-v0.19.1-linux64.tar.gz
Geckodriver版本与Firefox版本映射关系
https://blog.csdn.net/u013250071/article/details/78803230
下载驱动后，可以放在python27/scrpts目录下，也可以放在某个目录，设置在环境变量path里面
具体实现代码：
chrome_options = Options()
#Chrome-headless 模式， Google 针对 Chrome 浏览器 59版 新增加的一种模式，可以让你不打开UI界面的情况下使用 Chrome 浏览器，所以运行效果与 Chrome 保持完美一致。
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
self.driver = webdriver.Chrome(chrome_options=chrome_options)
self.driver.set_page_load_timeout(10)
self.driver.maximize_window()
其它使用同 phantomjs 一样
完整python代码
# coding=utf-8
import os
import re
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from datetime import datetime,timedelta
import time
from pyquery import PyQuery as pq
import reimport datetimeclass consumer: def __init__(self):
#通过配置文件获取IEDriverServer.exe路径
# IEDriverServer ='C:\Program Files\Internet Explorer\IEDriverServer.exe'
# self.driver = webdriver.Ie(IEDriverServer)
# self.driver.maximize_window()
# self.driver = webdriver.PhantomJS(service_args=['--load-images=false'])
# self.driver = driver = webdriver.Chrome() # chrome_options = Options()
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')
# self.driver = webdriver.Chrome(chrome_options=chrome_options) options = webdriver.FirefoxOptions()
options.set_headless()
# options.add_argument('-headless')
options.add_argument('--disable-gpu')
self.driver = webdriver.Firefox(firefox_options=options)
self.driver.set_page_load_timeout(10)
self.driver.maximize_window() def WriteLog(self, message,date):
fileName = os.path.join(os.getcwd(), 'consumer/' + date + '.txt')
with open(fileName, 'a') as f:
f.write(message)
# http://search.cctv.com/search.php?qtext=消费主张&type=video
def CatchData(self,url='http://search.cctv.com/search.php?qtext=%E6%B6%88%E8%B4%B9%E4%B8%BB%E5%BC%A0&type=video'):
error = ''
try:
self.driver.get(url) selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")
doc = pq(selenium_html) filename = datetime.datetime.now().strftime('%Y-%m-%d')
message = '{0},{1}'.format( '标题', '时间')
filename = datetime.datetime.now().strftime('%Y-%m-%d')
self.WriteLog(message, filename)
pages = doc("div[class='page']").find("a")
# 2018-06-05 00:12:21
pattern = re.compile("\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2}")
for index in range(1,6):
url = "get_data('{0}', '消费主张', 'relevance', 'video', '-1', '1', '', '20', '1')".format(index) self.driver.execute_script(url)
selenium_html = self.driver.execute_script("return document.documentElement.outerHTML")
doc = pq(selenium_html)
print(index)
try:
Elements = doc("div[class='jvedio']").find("a")
for sub in Elements.items():
title = sub.attr('title')
print(title)
ts = pattern.findall(title)
strtime = ''
if ts and len(ts) == 1:
strtime = ts[0]
if strtime:
index1 = title.index(strtime)
title = str(title[0:index1]).replace("•","") title = '\n{0},{1}'.format(title, strtime)
self.WriteLog(title, filename)
except Exception as e:
print("OS error: {0}".format(e)) except Exception as e1:
error = "ex"# python "C:\Program Files (x86)\JetBrains\PyCharm 2016.2.3\helpers\pydev\setup_cython.py" build_ext --inplaceobj = consumer()obj.CatchData()
# obj.CatchContent('')
# obj.export('')
