pyhton 爬图片网站并保存oss

from lxml import etree
import datetime
import io
import random
import string
import uuid
 
import requests
import oss2
 

def parser(img, imageName, dirpath):
    endpoint='<>'	# oss url
    access_key_id=''
    access_key_secret=''
    bucket_name=''
    bucket=oss2.Bucket(oss2.Auth(access_key_id, access_key_secret), endpoint, bucket_name)
    result=bucket.put_object(f'{dirpath}/{imageName}', img.getvalue())
    return result.status
 

def save_oss_img(url):

    dirpath='img'
 
    now=datetime.datetime.now()
    nonce=str(uuid.uuid4())
 
    imageName='{}.jpg'.format(nonce)

    img=io.BytesIO(requests.get(url).content)
 
    statusCode=parser(img, imageName, dirpath)



def crawling():
	# 爬虫这里不是很详细可以根据具体的业务来爬取
    url = '<爬取的url>'
    text = requests.get(url).text
    html = etree.HTML(text)
    html_data = html.xpath("//div[@class='slist']/ul/li/a/img/@src")
    url_list = []
    for i in html_data:
        save_oss_img(i)


def run():
    crawling()