from bs4 import BeautifulSoup
import requests
import lxml
def request_douban(url):
try:
headers = {'user-agent': 'my-app/0.0.1'} # 僞裝成瀏覽器,避免403,被禁止訪問
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
except requests.RequestException:
return None
def main(url):
html = request_douban(url)
soup = BeautifulSoup(html, 'lxml') # 源碼
moives_list = soup.find(class_="").find_all('tr')
# print(moives_list)
for item in moives_list:
# print(item)
# item_name = item.find(class_='title').string
try:
item_name = item.find(class_='nbg').get('title')
item_img = item.find('a').find('img').get('src')
item_score = item.find(class_="rating_nums").string
item_comment = item.find(class_="star clearfix").find(class_="pl").string
print('電影名:{:<10}評分:{:<5}評價人數:{:<10}封面:{}'.format(item_name, item_score, item_comment, item_img))
print('-'*50)
except:
print('Error')
if __name__ == "__main__":
url = 'https://movie.douban.com/chart'
main(url)
爬蟲1_2019年豆瓣新片排行榜
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.