从0开始学爬虫11之使用requests库下载图片

Posted 2022-05-05 reblue520

从0开始学爬虫11之使用requests库下载图片

# coding=utf-8
import requests

def download_imgage():
    ‘‘‘
    demo: 下载图片
    ‘‘‘
    headers = "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
    url = "https://ss0.bdstatic.com/94oJfD_bAAcT8t7mm9GUKT-xh_/timg?image&quality=100&size=b4000_4000&sec=1563595148&di=1239a9121c930e1ab892faa7cd0b8f8a&src=http://m.360buyimg.com/pop/jfs/t23434/230/1763906670/10667/55866a07/5b697898N78cd1466.jpg"
    response = requests.get(url,headers=headers, stream=True)
    with open(‘demo.jpg‘, ‘wb‘) as fd:
        for chunk in response.iter_content(128):
            fd.write(chunk)

    print response.content


def download_image_improved():
    # 伪造headers信息
    headers = 
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"
    # 限定url
    url = "https://ss0.bdstatic.com/94oJfD_bAAcT8t7mm9GUKT-xh_/timg?image&quality=100&size=b4000_4000&sec=1563595148&di=1239a9121c930e1ab892faa7cd0b8f8a&src=http://m.360buyimg.com/pop/jfs/t23434/230/1763906670/10667/55866a07/5b697898N78cd1466.jpg"
    response = requests.get(url, headers=headers, stream=True)
    # contextlib 管理上下文信息
    from contextlib import closing
    # 可以关闭文件流
    with closing(requests.get(url, headers=headers, stream=True)) as response:
        # 打开文件
        with open(‘demo1.jpg‘, ‘wb‘) as fd:
            # 每128字节写入一次
            for chunk in response.iter_content(128):
                fd.write(chunk)


if __name__ == ‘__main__‘:
    # download_imgage()
    download_image_improved()