#!/usr/bin/env python
# encoding: utf-8
from selenium import webdriverdriver = webdriver.Chrome()
url = 'http://www.toutiao.com/news_fashion/'driver.get(url)print driver.title

#!/usr/bin/env python
# encoding: utf-8
import time
from selenium import webdriver
import itertoolsdriver = webdriver.Chrome()
url = 'http://www.toutiao.com/news_fashion/'
driver.get(url)
print driver.get(url)for x in range(2):driver.refresh()titles = driver.find_elements_by_class_name("title-box")contents = driver.find_elements_by_class_name("abstract")imgs = driver.find_element_by_css_selector(".feedimg")for title, content, img in zip(titles, contents, itertools.repeat(imgs)):data = {'title': title.text,'content': content.text,'img': img.get_attribute('src')}print datatime.sleep(10)driver.close()

# coding:utf-8import requests
from bs4 import BeautifulSoup
from selenium import webdriver
import time
#有验证码
driver = webdriver.Chrome()
url = 'http://mp.sohu.com/'
driver.get(url)driver.find_element_by_id("userid").clear()
driver.find_element_by_id('userid').send_keys("username")
driver.find_element_by_id("pwd").clear()
driver.find_element_by_id("pwd").send_keys('password')
driver.find_element_by_id("loginbutton").click()time.sleep(2)
driver.close()

class judge(Spider):name = "judge"start_urls = ["http://wenshu.court.gov.cn/List/List?sorttype=1&conditions=searchWord+2+AJLX++%E6%A1%88%E4%BB%B6%E7%B1%BB%E5%9E%8B:%E6%B0%91%E4%BA%8B%E6%A1%88%E4%BB%B6"]def init_driver(self):driver = webdriver.Chrome()return driver def parse(self,response):driver = self.init_driver()driver.get(self.start_urls[0])sel = Selector(text=driver.page_source)self.logger.info(u'---------------Parsing----------------')print sel.xpath("//div[@class='dataItem'][1]/table/tbody/tr[1]/td/div[@class='wstitle']/a/text()").extract()self.logger.info(u'---------------success----------------')