莫烦 爬虫 下载图片

我的视频学习笔记

视频地址：https://www.bilibili.com/video/av17920849?p=9
讲解地址：https://morvanzhou.github.io/tutorials/data-manipulation/scraping/3-03-practice-download-image/

from bs4 import BeautifulSoup
from urllib.request import urlopen
import os
import requests

URL = "http://www.ngchina.com.cn/animals/"

# 找到图片所在的块
html = urlopen(URL).read().decode('utf-8')
soup = BeautifulSoup(html, features='lxml')
img_ul = soup.find_all('ul', {"class": "img_list"})

# 创建文件夹用来存放图片
os.makedirs('./img/', exist_ok=True)

for ul in img_ul:
    imgs = ul.find_all('img')
    for img in imgs:
        url = img['src']
        r = requests.get(url, stream=True)
        img_name = url.split('/')[-1]
        with open('./img/%s' % img_name, 'wb') as f:
            for chunk in r.iter_content(chunk_size=128):  # 每次放入128个字节
                f.write(chunk)
        print('Save %s' % img_name)