分页爬取斋藤飞鸟图片

#简单爬取斋藤飞鸟图片
import requests
import time
from lxml import etree
# from requests.exceptions import RequestException
def get_one_page(url):
    headers={
        'User - Agent':'Mozilla / 5.0(Windows NT 10.0;Win64;x64) AppleWebKit / 537.36(KHTML, likeGecko) Chrome / 75.0.3770.100Safari / 537.36',
}
    r=requests.get(url,headers=headers)
    #     if r.status_code==200:
    #         return r.text
    #     return None
    # except RecursionError:
    #     return None
    contend=r.text
    html=etree.HTML(contend)
    src_list=html.xpath('//img/@src')
    alt_list=html.xpath('//div[@class="prop"]/text()')
    for src,alt in zip(src_list,alt_list):
        filename=src[48:]
        print('正在爬取第%d页'%(d/30))
        print('正在保存图片'+filename)
        r = requests.get(src,headers=headers)
        with open('斋藤飞鸟图片//'+filename,'wb') as f:
            f.write(r.content)

def main(d):
    url='https://movie.douban.com/celebrity/1329640/photos/?type=C&start=%d&sortby=like&size=a&subtype=a' %(d)
    # print(r.text)
    print(get_one_page(url))

if __name__=='__main__':
    d = 0
    while True:
        d = d + 30
        if d >= 500:
            break
        main(d)
        time.sleep(0.5)