Python学习--第八天

1.爬取豆瓣电影排行榜单https://movie.douban.com/chart的各电影海报到本地image文件夹下。

import os
import bs4
import requests
url = 'https://movie.douban.com/chart'
head = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
                      'AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/80.0.3987.132 Safari/537.36'
}
reqe = requests.get(url=url, headers=head)
reqe.encoding = 'utf-8'
soup = bs4.BeautifulSoup(reqe.text, 'html.parser')
div_items = []
folder = 'image'
g = 1
try:
    os.mkdir(folder)
except:
    folder = 'image(' + str(g) + ')'
    g += 1
    os.mkdir(folder)
    os.chdir(folder)
for each in soup.find_all(name='img', attrs={'class': 'm_sub_img'}):
    div_items.append(each['src'])
for i in range(0, 100):#需要爬取的图片数
    with open("./image"+str(i)+'.jpg', 'wb') as f:
        img_html = requests.get(div_items[i])
        f.write(img_html.content)
        i += 1