获取网页上图片的下载地址

2015/09/02 32099

清华大佬耗费三个月吐血整理的几百G的资源，免费分享！....>>> 

#!/user/bin/python3
import urllib2
from HTMLParser import HTMLParser

class MyHtmlParser(HTMLParser):
    links = []

    def handle_starttag(self, tag, attrs):
        if tag == "img":
            if len(attrs) == 0:
                pass
            else:
                for name, value in attrs:
                    if name == "src":
                        self.links.append(value)

if __name__ == "__main__":
    uri = "http://dy.163.com/v2/article/T1374483113516/AGSNE9L000964K4O"
    file = urllib2.urlopen(uri).read()
    # file = "<html><h1>Title</h1><p>I'm a paragraph!</p></html>"
    hy = MyHtmlParser()
    hy.feed(file)
    hy.close()
    print(hy.links)