爬取妹子图系列3

import requests
from bs4 import BeautifulSoup
import shutil

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0',
           'Referer': 'http://www.mzitu.com'}
url = 'https://www.mzitu.com/'
resp = requests.get(url, headers=headers).text
# print(resp)
# <img class='lazy' src='https:/xx'/>
# 爬取图片连接
soup = BeautifulSoup(resp, 'html.parser')
img_src = soup.findAll('img', class_='lazy')
# 返回 标签对象
# for img in img_src:
#     # print(img)
#     # print(img.get('src'))

import os
import time


def download(img_path, my_dir_path):
    resp = requests.get(img_path, headers=headers,stream=True)
    file_name = os.path.basename(img_path)
    real_path = os.path.join(my_dir_path, file_name)
    # print(resp.status_code)
    if resp.status_code == 200:
        # print(real_path)
        with open(real_path, 'wb') as f:
            shutil.copyfileobj(resp.raw, f)


print("开始下载")
i = 0
for img in img_src:
    time.sleep(2)
    # 记得睡一下，不然被反爬了
    # print(requests.get(img.get('src'), headers=headers,stream=True).status_code)
    download(img.get('data-original'), "f:/妹子/")
    i += 1
    print(img.get('data-original'))
print("下载结束")

对于 requests库，指定 stream =True ,然后配合 shutil工具直接下载图片即可