爬取鬥魚網頁（selenium+chromedriver得到網頁，用Beasutiful Soup提取資訊）

=============================

=================================

=======================================

#self.driver.page_source 得到頁面原始碼用 xml解析
soup = BeautifulSoup(self.driver.page_source, 'xml')

結果示例：

================================

 1 ''''
 2 任務：
 3 爬去鬥魚直播內容
 4 https://www.douyu.com/directory/all
 5 思路：
 6 1. 利用selenium得到頁面內容
 7 2. 利用xpath或者bs等在頁面中進行資訊提取
 8 '''
 9 
10 from selenium import webdriver
11 from bs4 import BeautifulSoup
12 
13 
14 class Douyu():
15     #初始化方法
16     def setUp(self):
17         self.driver = webdriver.Chrome()
 
18         self.url = 'https://www.douyu.com/directory/all'
19 
20 
21     def douyu(self):
22         self.driver.get(self.url)
23 
24         while True:
25             soup = BeautifulSoup(self.driver.page_source, 'xml')
26 
27             # 返回當前頁面所有放假標題列表和觀眾人數
28             titles = soup.find_all('h3
 
', {'class':'ellipsis'})
29             nums = soup.find_all('span', {'class':'dy-num fr'})
30 
31             for title, num in zip(titles, nums):
32                 print("房間{0} 總共觀賞人數{1}".format(title.get_text().strip(), num.get_text().strip()))
33 
34     def destr(self):
35         self.driver.quit()
36 
37 if __name__ == '__main__':
38     douyu = Douyu()
39     douyu.setUp()
40     douyu.douyu()
41     douyu.destr()