import os
import urllib.request
import requests
from fake_useragent import UserAgent
from bs4 import BeautifulSoup
ua = UserAgent()
download_path = './电影总览'
if not os.path.exists(download_path):
#创建文件夹
os.makedirs(download_path)
def download_picture(url):
headers = {'User-Agent' :
'Mozilla/5.0 (Windows NT 10.0; Win64 x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
r = requests.get(url, headers = headers)
soup = BeautifulSoup(r.text, 'lxml')
content = soup.find('div', class_ = 'article')
images = content.find_all('img')
picture_http_list = [image['src'] for image in images]
picture_name_list = [image['alt'] for image in images]
for picture_name, picture_http in zip (picture_name_list, picture_http_list):
html = requests.get(picture_http)
with open(f'{download_path}/{picture_name}.jpg','wb') as f:
f.write(html.content)
def main():
start_urls = ["https://movie.douban.com/tag/#/"]
for url in start_urls:
download_picture(url)
main()
