Question

def getSize(f):
    print StringIO(f)
    im = Image.open(StringIO(f))
    size = im.size[0], im.size[1]
    return size

def download(source_url, g = False, correct_url = True):
    try:
        socket.setdefaulttimeout(10)
        agents = ['Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0)','Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.1)','Microsoft Internet Explorer/4.0b1 (Windows 95)','Opera/8.00 (Windows NT 5.1; U; en)']
        ree = urllib2.Request(source_url)
        ree.add_header('User-Agent',random.choice(agents))
        ree.add_header('Accept-encoding', 'gzip')
        opener = urllib2.build_opener()
        h = opener.open(ree).read()
        if g:
            compressedstream = StringIO(h)
            gzipper = gzip.GzipFile(fileobj=compressedstream)
            data = gzipper.read()
            return data
        else:
            return h
    except Exception, e:
        return ""



pic = download("http://media2.ct.yelpcdn.com/photo/2MdauidaMUazuew2h0pdgQ/l")
s = getSize(pic)

当我这样做时，出现错误：

print StringIO(f)
File "/usr/lib/python2.6/dist-packages/PIL/Image.py", line 1980, in open
raise IOError("cannot identify image file")
IOError: cannot identify image file

Answer 1

问题在于您的Accept-Encoding状态gzip因此您可能会获得一张gzip图像。

我刚刚尝试使用gzip解压缩代码，并且没有任何问题。

    pic = download("http://media2.ct.yelpcdn.com/photo/2MdauidaMUazuew2h0pdgQ/l", g=True)
    s = getSize(pic)

将'Accept-Encoding'从'gzip'更改为'image.*'

也是如此

    ree.add_header('User-Agent',random.choice(agents))
    ree.add_header('Accept-Encoding', 'image.*')

第2部分：

你可以随时询问gzip并使用try / except来包装，以便在gzip抱怨时不加改变地返回数据。

    try:
        compressedstream = StringIO(h)
        gzipper = gzip.GzipFile(fileobj=compressedstream)
        data = gzipper.read()
        return data
    except IOError: # not gzip
        return h

为什么我的python代码不起作用？

1 个答案: