首先pip安装selenium
一、phantomjs
1、下载phantomjs压缩包,解压,把bin文件夹路径加入PATH环境变量
2、代码
#coding=utf-8
import requests
import re
from pyquery import PyQuery as pq
from lxml import etree
from bs4 import BeautifulSoup
import sys
from selenium import webdriver
reload(sys)
sys.setdefaultencoding("utf-8")
def getHtml(url):
driver = webdriver.PhantomJS(executable_path='/home/lhy/phantomjs-1.9.8-linux-x86_64/bin/phantomjs')
driver.get(url)
fo = open("phonesinfo2.txt", "wb")
fo.write(driver.page_source)
fo.close()
return driver.page_source
二、chrome浏览器
1、必须安装chrome浏览器
2、下载chrome驱动chromedriver
3、把驱动加如PATH环境变量(注意最好修改/etc/profile配置,永久生效)
4、代码
#coding=utf-8
import requests
import re
from pyquery import PyQuery as pq
from lxml import etree
from bs4 import BeautifulSoup
import sys
from selenium import webdriver
reload(sys)
sys.setdefaultencoding("utf-8")
def getHtml(url):
driver=webdriver.Chrome();
driver.get(url)
fo = open("phonesinfo2.txt", "wb")
fo.write(driver.page_source)
fo.close()
return driver.page_source
注意运行过程中会打开chrome浏览器