python获取网页上图片下载地址的方法
在网站内容采集代码中,用到的获取网页上图片的下载地址的方法。
例子:
复制代码 代码示例:
#!/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)