下载某个页面中的图片

用到了BeautifulSoup这个库,需要先下载安装.下载地址http://www.crummy.com/software/BeautifulSoup/

config.py

1 url = "http://www.baidu.com"
2 folder = "d:\test"

downloadPictrues.py

import config
from bs4 import BeautifulSoup
import urlparse
from urllib2 import urlopen
from urllib import urlretrieve
import os

###########################################
#to resolve the fucking character encoding problem
import sys
reload(sys)
sys.setdefaultencoding('utf8')

def main(url, out_folder):
    """Downloads all the images at 'url' to out_folder"""
    pageFile =  urlopen(url)                 #pageFile ---a file-liked object
    soup = BeautifulSoup(pageFile)           #get a BeatifulSoup Object
    #print soup.prettify()                    #
    elements = urlparse.urlparse(url)        #parse url into a 6-tuple
    print elements
    parsed = list(elements)                  #new list initialized from iterable items
    for image in soup.findAll("img"):        #find all "img"tag
        #print "Image: %(src)s" % image
        print image,image['src'],type(image)
        image_url = urlparse.urljoin(url, image['src'])  #construct a full url
        filename = image["src"].split("/")[-1]           
        outpath = os.path.join(out_folder, filename)     #
        #print out_folder,filename,outpath
        urlretrieve(image_url, outpath)                  #download pictrues

if __name__ == "__main__":
    url = config.url
    folder = config.folder
    if os.path.exists(folder):
        print 'ok'
        main(url,folder)
    else:
        os.makedirs(folder)
        main(url,folder)