<slenium爬虫>斗鱼

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import unittest
from selenium import webdriver
from bs4 import BeautifulSoup as bs
import time

class douyu(unittest.TestCase):
    # 初始化方法，必须是setUp()
    def setUp(self):
        self.driver = webdriver.PhantomJS()
        self.num = 0
        self.count = 0

    # 测试方法必须有test字样开头
    def testDouyu(self):
        self.driver.get("https://www.douyu.com/directory/all")

        while True:
            soup = bs(self.driver.page_source, "lxml")
            # 房间名, 返回列表
            names = soup.find_all("h3", {"class" : "DyListCover-intro"})
            # 直播间热度, 返回列表
            numbers = soup.find_all("span", {"class" :"DyListCover-hot"})

            for name, number in zip(names, numbers):
                self.num += 1
                print(u"直播间热度: -" + number.get_text().strip() + u"-\t房间名: " + name.get_text().strip() + u‘-\t直播数量‘+ str(self.num))

                #self.count += int(number.get_text().strip())

            # 如果在页面源码里找到"下一页"为隐藏的标签，就退出循环 
            if self.driver.page_source.find("dy-Pagination-disabled dy-Pagination-next") != -1:
                    break

            # 一直点击下一页
            self.driver.find_element_by_class_name("dy-Pagination-next").click()
            time.sleep(1)

    # 测试结束执行的方法
    def tearDown(self):
        # 退出PhantomJS()浏览器
        print("当前网站直播人数" + str(self.num))
        print("当前网站总热度" + str(self.count))
        self.driver.quit()

if __name__ == "__main__":
    # 启动测试模块
    unittest.main()