逛的时候太太太太喜欢某张图了 每日一次下下来的竟然还是位图 尝试爬下来什么格式
import reimport requestsfrom bs4 import BeautifulSoup as bsimport osdef url_open(url): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER'} res = requests.get(url, headers=headers) return resdef findlinks(res): soup = bs(res.text, 'lxml') target = soup.find_all('ul', class_="clearfix") list = re.findall(r'rel="external nofollow" href="(.*?\.html)"', str(target)) return listdef find_img(list): urlhead = 'http://pic.netbian.com' img = [] for each in list: img.append(urlhead + each) return imgdef save_img(img): urlhead = 'http://pic.netbian.com' for each in img: res = url_open(each) soup = bs(res.content, 'lxml') link = re.findall(r'src="(/.*\.jpg)"', str(soup)) url = urlhead + link[0] filename = url.split('/')[-1].replace('.html', '') img = url_open(url) with open(filename, 'wb') as f: f.write(img.content)if __name__ == '__main__': # os.mkdir('彼岸图') os.chdir('彼岸图') url = 'http://pic.netbian.com/4kdongman/index.html' res = url_open(url) list = findlinks(res) img = find_img(list) save_img(img)学习参考@猫先生的早茶，大佬讲的很详细
以及[已解决]爬虫爬彼岸图网高清壁纸 有机会吗？？？
https://fishc.com.cn/thread-118301-1-1.html
(出处: 鱼C论坛)
