python 下载多线程回调函数显示进度 和 文件名（不然分不清是谁卡死）

一、Python request 库 urllib模块

urllib.urlretrieve(url, filename, reporthook=None,data=None)
参数说明：
url：外部或者本地url
filename：指定了保存到本地的路径（如果未指定该参数，urllib会生成一个临时文件来保存数据）；
reporthook：是一个回调函数，当连接上服务器、以及相应的数据块传输完毕的时候会触发该回调。我们可以利用这个回调函数来显示当前的下载进度。
data：指post到服务器的数据。该方法返回一个包含两个元素的元组(filename, headers)，filename表示保存到本地的路径，header表示服务器的响应头。

下面通过例子来演示一下这个方法的使用，这个例子将新浪首页的html抓取到本地，保存在D:/sina.html文件中，同时显示下载的进度。

import urllib
def callbackfunc(blocknum, blocksize, totalsize):
    '''回调函数
    @blocknum: 已经下载的数据块
    @blocksize: 数据块的大小
    @totalsize: 远程文件的大小
    '''
    percent = 100.0 * blocknum * blocksize / totalsize
    if percent > 100:
        percent = 100
    print "%.2f%%"% percent
url = 'http://www.sina.com.cn'
local = 'd:\\sina.html'
urllib.urlretrieve(url, local, callbackfunc)

二、魔改

liburllibrequest.py
修改
133行添加'zjsurlretrieve'
'urlretrieve','zjsurlretrieve', 'urlcleanup', 'URLopener', 'FancyURLopener',

229行 添加自定义函数

zjs_url_tempfiles = []

def zjsurlretrieve(url, filename=None, reporthook=None, data=None):
    """
    Retrieve a URL into a temporary location on disk.

    Requires a URL argument. If a filename is passed, it is used as
    the temporary file location. The reporthook argument should be
    a callable that accepts a block number, a read size, and the
    total file size of the URL target. The data argument should be
    valid URL encoded data.

    If a filename is passed and the URL points to a local resource,
    the result is a copy from local file to new file.

    Returns a tuple containing the path to the newly created
    data file as well as the resulting HTTPMessage object.
    """
    url_type, path = splittype(url)
   
    with contextlib.closing(urlopen(url, data)) as fp:
        headers = fp.info()

        # Just return the local path and the "headers" for file://
        # URLs. No sense in performing a copy unless requested.
        if url_type == "file" and not filename:
            return os.path.normpath(path), headers

        # Handle temporary file setup.
        if filename:
            tfp = open(filename, 'wb')
        else:
            tfp = tempfile.NamedTemporaryFile(delete=False)
            filename = tfp.name
            _url_tempfiles.append(filename)

        with tfp:
            result = filename, headers
            bs = 1024*8
            size = -1
            read = 0
            blocknum = 0
            if "content-length" in headers:
                size = int(headers["Content-Length"])

            if reporthook:
                reporthook(blocknum, bs, size,url,filename)

            while True:
                block = fp.read(bs)
                if not block:
                    break
                read += len(block)
                tfp.write(block)
                blocknum += 1
                if reporthook:
                    reporthook(blocknum, bs, size,url,filename)

    if size >= 0 and read < size:
        raise ContentTooShortError(
            "retrieval incomplete: got only %i out of %i bytes"
            % (read, size), result)

    return result

三、使用



import urllib

def callbackfunc(blocknum, blocksize, totalsize,url,filename):
    '''回调函数
    @blocknum: 已经下载的数据块
    @blocksize: 数据块的大小
    @totalsize: 远程文件的大小
    '''
    percent = 100.0 * blocknum * blocksize / totalsize
    if percent > 100:
        percent = 100
    print "%.2f%%"% percent + filename

url = 'http://www.sina.com.cn'
local = 'd:\\sina.html'
urllib.zjsurlretrieve(url, local, callbackfunc)
发表新评论