python模拟浏览器webdriver登陆网站后抓取页面并输出
2014-04-13 13:01
806 查看
关键在于以下两行代码 特别是find_element_by_xpath写法 很多写成 findElementsByXpath不知道是写错了 还是高级版本是这么写的...
#webElement = self.dr.find_element_by_xpath("//*");
#print(webElement.get_attribute("outerHTML"))
import os
from selenium import webdriver
import time
class Firefox_webdriver:
dr=webdriver.Chrome()
def autosend(self,my_username,my_password,interval,num):
self.dr.get("http://cas.baidu.com/?tpl=www2&fromu=http%3A%2F%2Fwww2.baidu.com%2F")
self.dr.implicitly_wait(1)
time.sleep(40)
#self.dr.find_element_by_id("TANGRAM__3__userName").send_keys("xxx@qq.com")
#self.dr.find_element_by_id("TANGRAM__3__password").send_keys("xxx")
#self.dr.find_element_by_name("pass-button pass-button-submit").click()
#self.dr.find_element_by_id("TANGRAM__3__submit").click()
#time.sleep(5)
self.dr.get("http://fengchao.baidu.com/nirvana/main.html?userid=5365496&%20%20userid=5365496&t=1397266614555&castk=62a4dmj7728a3a6aed231#/~pkgId=5&target=aoPk%20%20g")
time.sleep(30)
webElement = self.dr.find_element_by_xpath("//*");
print(webElement.get_attribute("outerHTML"))
'''for i in range(1,num):
url="http://test2.tieba.baidu.com/d/c/addPost?gid=258&content="+str(i)+"&sign=*****"
self.dr.get(url)
time.sleep(interval)
#self.dr.close()
'''
if __name__ == "__main__":
browser = Firefox_webdriver()
browser.autosend("*****","****",2,10)
#webElement = self.dr.find_element_by_xpath("//*");
#print(webElement.get_attribute("outerHTML"))
import os
from selenium import webdriver
import time
class Firefox_webdriver:
dr=webdriver.Chrome()
def autosend(self,my_username,my_password,interval,num):
self.dr.get("http://cas.baidu.com/?tpl=www2&fromu=http%3A%2F%2Fwww2.baidu.com%2F")
self.dr.implicitly_wait(1)
time.sleep(40)
#self.dr.find_element_by_id("TANGRAM__3__userName").send_keys("xxx@qq.com")
#self.dr.find_element_by_id("TANGRAM__3__password").send_keys("xxx")
#self.dr.find_element_by_name("pass-button pass-button-submit").click()
#self.dr.find_element_by_id("TANGRAM__3__submit").click()
#time.sleep(5)
self.dr.get("http://fengchao.baidu.com/nirvana/main.html?userid=5365496&%20%20userid=5365496&t=1397266614555&castk=62a4dmj7728a3a6aed231#/~pkgId=5&target=aoPk%20%20g")
time.sleep(30)
webElement = self.dr.find_element_by_xpath("//*");
print(webElement.get_attribute("outerHTML"))
'''for i in range(1,num):
url="http://test2.tieba.baidu.com/d/c/addPost?gid=258&content="+str(i)+"&sign=*****"
self.dr.get(url)
time.sleep(interval)
#self.dr.close()
'''
if __name__ == "__main__":
browser = Firefox_webdriver()
browser.autosend("*****","****",2,10)
相关文章推荐
- (转)Python-详解抓取网站,模拟登陆,抓取动态网页的原理和实现
- python自动化--mock、webservice及webdriver模拟手机浏览器
- 如何用Python,C#等语言去实现抓取静态网页+抓取动态网页+模拟登陆网站
- 如何用Python,C#等语言去实现抓取静态网页+抓取动态网页+模拟登陆网站
- Python模拟浏览器登陆网站
- python 爬虫利用webdriver 跳过登陆 进行小规模抓取信息
- python模拟浏览器登陆人人网站
- 如何用Python去实现抓取静态网页+抓取动态网页+模拟登陆网站
- 详解抓取网站,模拟登陆,抓取动态网页的原理和实现(Python,C#等)
- Python Post and Get 登陆web后台系统并抓取页面
- python模拟登陆网站抓取数据
- 用python写了一个简单的模拟浏览器抓取网页的库webclient
- python requests 模拟登陆网站,抓取数据
- 【转】详解抓取网站,模拟登陆,抓取动态网页的原理和实现(Python,C#等)
- Python模拟浏览器登陆网站
- 如何用Python,C#等语言去实现抓取静态网页+抓取动态网页+模拟登陆网站
- 详解抓取网站,模拟登陆,抓取动态网页的原理和实现(Python,C#等)
- Python利用selenium模拟浏览器抓取异步加载等难爬页面信息
- Python Post and Get 登陆web后台系统并抓取页面
- 使用C#的HttpWebRequest模拟登陆网站