關於模擬瀏覽器登陸的header,能夠在相應網站按F12調取出編輯器,點擊netwook,以下:html
以便於不會被網站反爬蟲拒絕。python
1 import requests 2 from bs4 import BeautifulSoup 5 def get_movies(): 6 headers = { 7 'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.82 Safari/537.36', 8 'Host': 'movie.douban.com' 9 } 10 movie_list = [] #定義序列 11 for i in range(0, 10): 12 link = 'https://movie.douban.com/top250?start=' + str(i * 25) #經過循環,下載第二頁,第三頁 13 r = requests.get(link, headers=headers, timeout=10) #timeout=10,響應時長 14 print(str(i + 1), "頁響應狀態碼:", r.status_code) #顯示狀態碼,返回200,請求成功 15 16 soup = BeautifulSoup(r.text, "lxml") 17 div_list = soup.find_all('div', class_='hd') #以下圖顯示,電影名字在div標籤以後 18 for each in div_list: 19 movie = each.a.span.text.strip() #span後的文本 20 movie_list.append(movie) #append(movie),在movie_list中添加movie序列 21 return movie_list 24 movies = get_movies() 25 print(movies)