selenium的webdriver.Chrome()模拟点击斗鱼页面
- #!/usr/bin/env python
- # coding=utf-8
-
- from bs4 import BeautifulSoup
- import unittest
- from selenium import webdriver
- import time
-
- class Douyu(unittest.TestCase):
- # 初始化方法,必须是setUp
- def setUp(self):
- self.driver = webdriver.Chrome()
- self.num = 0
- self.count = 0
- self.list = []
- # 具体的测试用例方法,一定要用test开头
- def testDouyu(self):
- self.driver.get("https://www.douyu.com/directory/all")
- while True:
- soup = BeautifulSoup(self.driver.page_source, 'lxml')
- # 返回页面的房间标题列表和观众人数
- titles = soup.find_all('h3', {'class': 'ellipsis'})
- nums = soup.find_all('span', {'class': 'dy-num fr'})
- # 使用zip()函数把列表合并,并创建一个元组对的列表[(1,2),(3,4)...]
- for title, num in zip(titles, nums):
- print(u"观众人数:" + num.get_text().strip(), u"\t房间标题:" + title.get_text().strip())
- self.num += 1
- i = num.get_text().strip()
- # print(type(i)) # str类型
- if i[-1] =='万':
- j = float(i.replace('万',''))*10000
- self.list.append(int(j))
- else:
- self.list.append(int(i))
- # 如果点击到最后找到了“shark-pager-disable-next”不会返回-1,终止循环,page_source.find()未找到内容则返回-1
- if self.driver.page_source.find("shark-pager-disable-next") != -1:
- break
- # 模拟点击下一页
- self.driver.find_element_by_class_name("shark-pager-next").click()
- time.sleep(4)
-
- def tearDown(self):
- # 退出
- print("加载完成。。。")
- # print(self.list)
- # print(len(self.list))
- for x in self.list:
- # print(type(x))
- # print(x)
- self.count += x
- print('总直播人数:'+str((self.num)))
- # print('总计%s人观看'%self.count)
- if self.count%10000%1000 != 0:
- if self.count%10000//1000!=0:
- print('合计%s人观看' % (str((self.count)//10000) + '万' + str(self.count%10000//1000) +'千' + str(self.count % 10000 % 1000)))
- else:
- print('合计%s人观看' % (str((self.count)//10000)+ '万' + str(self.count % 10000 % 1000)))
- else:
- print('合计%s人观看'%(str((self.count)//10000) + '万' + str(self.count%10000//1000)+'千'))
- self.driver.quit()
-
- if __name__ == "__main__":
- unittest.main()