zooqle.py 文件源码

def retrieve_url_nodecode(url):
    """ Return the content of the url page as a string """
    req = Request(url, headers = headers)
    try:
        response = urlopen(req)
    except URLError as errno:
        print(" ".join(("Connection error:", str(errno.reason))))
        print(" ".join(("URL:", url)))
        return ""
    dat = response.read()
    # Check if it is gzipped
    if dat[:2] == '\037\213':
        # Data is gzip encoded, decode it
        compressedstream = StringIO(dat)
        gzipper = gzip.GzipFile(fileobj=compressedstream)
        extracted_data = gzipper.read()
        dat = extracted_data
        return dat
    return dat