selenium爬取豆瓣电影top250

最近在看selenium相关，练练手

#!/usr/bin/python
#coding=utf-8

'''
    selenium spider
    https://movie.douban.com/top250
'''

from selenium import webdriver
import time
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )

url = 'https://movie.douban.com/top250'

f = open('D:\douban_movie.txt','w')

#打开豆瓣电影
driver = webdriver.Firefox()
driver.get(url)
driver.implicitly_wait(3)
driver.maximize_window()

#获取所有包含电影简介的元素
for i in range(10):
    content = driver.find_elements_by_class_name('info')
    # 遍历每一页元素内容，并提取电影名
    for i in content:
        movie = i.text
        print movie.split('\n')[0]
        f.write(movie.split('\n')[0] + '\n')
    #跳转页面到下一页，重新遍历
    driver.find_element_by_class_name('next').click()
    driver.implicitly_wait(5)

f.close()
time.sleep(3)

#关闭浏览器
driver.close()

　　

转载于:https://www.cnblogs.com/zhazi/p/11046486.html