import requests,urllib,os from bs4 import BeautifulSoup ans = 1 for page in range(58,69): url = 'http://bbs.fengniao.com/forum/pic/slide_101_6478020_768937' + str(page) + '.html' header = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.109 Safari/537.36'} source_code = requests.get(url,headers = header) plain_text = source_code.text soup = BeautifulSoup(plain_text,'lxml') download_link = [] file_name = '' for pic_tag in soup.find_all('a'): #get the name if pic_tag.get('href')=='/forum/6478020.html': file_name = pic_tag.get('title') if pic_tag.get('class')==['pictureDownload']: download_link.append(pic_tag.get('href')) #file setting folder_path = "D:/spider_things/2016.4.6/" + file_name +"/" if not os.path.exists(folder_path): os.makedirs(folder_path) for item in download_link: urllib.urlretrieve(item,folder_path + str(ans) + '.jpg') print 'download_',ans,'_pics' ans=ans+1
这次爬虫应用了创建文件夹的功能： #file setting folder_path = "D:/spider_things/2016.4.6/" + file_name +"/" if not os.path.exists(folder_path): os.makedirs(folder_path)上面代码块的意思是：
"os.path.exists(folder_path)"用来判断folder_path这个路径是否存在，如果不存在，就执行“os.makedirs(folder_path)”来创建这个路径