从照片网站pexels批量爬取照片

调试中,未成功。

from bs4 import BeautifulSoup
import requests
headers={    
    #'User-Agent':'Nokia6600/1.0 (3.42.1) SymbianOS/7.0s Series60/2.0 Profile/MIDP-2.0 Configuration/CLDC-1.0'
    'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
urls=['https://www.pexels.com/search/book/page={}'.format(i) for i in range(1,10)]
list=[]
for url in urls:
    wb_data=requests.get(url,headers=headers)
    #print(wb_data)
    soup=BeautifulSoup(wb_data.text,'lxml')
    imgs=soup.select('body>div.page-wrap>div.l-container>div.photos>article>a.js-photo-link>img')
    print(imgs)
    for img in imgs:
        photo=img.get('src')
        print(photo)
        list.append(photo)
    path='C://Users/Administrator/Desktop/aa'
    for item in list:
        data=requests.get(item,headers=headers)
        print(data)
        fp=open(path+item.split('?')[0][-10:],'wb')
        fp.write(data.content)
        fp.close()
    

 

posted @ 2018-04-20 17:21  蓝勃斐重新开始  阅读(997)  评论(0编辑  收藏  举报