Python 爬虫-图片的爬取

2017-07-25 22:49:21

import requests
import os

url = ‘https://wallpapers.wallhaven.cc/wallpapers/full/wallhaven-278989.jpg‘
root = ‘E://pics//‘
path = root + url.split(‘/‘)[-1]

def gethtml(url):
    # 打开网页有风险，需要使用try-except语句进行风险控制
    kv = {‘user-agent‘:‘Chrome/10‘}
    try:
        r = requests.get(url,headers=kv)
        r.raise_for_status()   # 如果打开失败，则会抛出一个HttpError异常
        # encoding是从header中分析出来的编码方式，apparent_encoding是 从内容分析出的编码方式
        #r.encoding=r.apparent_encoding
        return r.content
    except:
        print("打开失败")

if __name__ ==‘__main__‘:
    if not os.path.exists(root):
        os.mkdir(root)
    r = gethtml(url)
    with open(path,‘wb‘) as f:
        f.write(r)
        f.close()
        print(‘图片已存储‘)