Python urllib.error.ContentTooShortError() Examples

def download_voice(filename: str, api_root: str, access_token: str):
    file = tempfile.NamedTemporaryFile()
    url = '{url}/data/record/{file}'.format(url=api_root, file=filename)
    try:
        opener = urllib.request.build_opener()
        opener.addheaders = [("Authorization", "Bearer {at}".format(at=access_token))]

        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(url, file.name)
    except (URLError, HTTPError, ContentTooShortError) as e:
        logging.getLogger(__name__).warning("Error occurs when downloading files: " + str(e))
        return _("Error occurs when downloading files: ") + str(e)
    if file.seek(0, 2) <= 0:
        raise EOFError('File downloaded is Empty')
    file.seek(0)
    return file 

def cq_get_image(image_link: str) -> tempfile:  # Download image from QQ
    file = tempfile.NamedTemporaryFile()
    try:
        urllib.request.urlretrieve(image_link, file.name)
    except (URLError, HTTPError, ContentTooShortError) as e:
        logging.getLogger(__name__).warning('Image download failed.')
        logging.getLogger(__name__).warning(str(e))
        return None
    else:
        if file.seek(0, 2) <= 0:
            raise EOFError('File downloaded is Empty')
        file.seek(0)
        return file 

def download_file_from_qzone(cookie: str, csrf_token: str, uin, group_id, file_id, filename, file_size):
    cookie_arr = param_spliter(cookie)
    url = "http://qun.qzone.qq.com/cgi-bin/group_share_get_downurl?uin=" + str(uin) + "&pa=/104/" + \
          str(file_id) + "&groupid=" + str(group_id) + "&bussinessid=0&charset=utf-8&g_tk=" + str(csrf_token) + "&r=888"
    ret = requests.get(url, cookies=cookie_arr)
    data = json.loads(ret.text.split("(")[1].split(")")[0])['data']
    cookie += "; FTN5K=" + str(data['cookie'])
    download_url = data['url']
    download_url += "/" + quote(filename)
    if file_size >= 50*1024*1024:  # File size is bigger than 50MiB
        return _("File is too big to be downloaded")
    file = tempfile.NamedTemporaryFile()
    try:
        opener = urllib.request.build_opener()
        opener.addheaders.append(('Cookie', cookie))
        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(download_url, file.name)
    except (URLError, HTTPError, ContentTooShortError) as e:
        logging.getLogger(__name__).warning("Error occurs when downloading files: " + str(e))
        return _("Error occurs when downloading files: ") + str(e)
    else:
        if file.seek(0, 2) <= 0:
            raise EOFError('File downloaded is Empty')
        file.seek(0)
        return file
    '''
    try:
        opener = urllib.request.build_opener()
        opener.addheaders.append(('Cookie', cookie))
        with opener.open(download_url) as response, tempfile.NamedTemporaryFile() as f:
            shutil.copyfileobj(response, f)
            if f.seek(0, 2) <= 0:
                raise EOFError('File downloaded is Empty')
            f.seek(0)
            return f
    except Exception as e:
        logging.getLogger(__name__).warning("Error occurs when downloading files" + str(e))
        return url
    ''' 

def download_user_avatar(uid: str):
    file = tempfile.NamedTemporaryFile()
    url = "https://q1.qlogo.cn/g?b=qq&nk={}&s=0".format(uid)
    try:
        opener = urllib.request.build_opener()
        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(url, file.name)
    except (URLError, HTTPError, ContentTooShortError) as e:
        logging.getLogger(__name__).warning("Error occurs when downloading files: " + str(e))
        return _("Error occurs when downloading files: ") + str(e)
    if file.seek(0, 2) <= 0:
        raise EOFError('File downloaded is Empty')
    file.seek(0)
    return file 

def download_group_avatar(uid: str):
    file = tempfile.NamedTemporaryFile()
    url = "https://p.qlogo.cn/gh/{}/{}/".format(uid, uid)
    try:
        opener = urllib.request.build_opener()
        urllib.request.install_opener(opener)
        urllib.request.urlretrieve(url, file.name)
    except (URLError, HTTPError, ContentTooShortError) as e:
        logging.getLogger(__name__).warning("Error occurs when downloading files: " + str(e))
        return _("Error occurs when downloading files: ") + str(e)
    if file.seek(0, 2) <= 0:
        raise EOFError('File downloaded is Empty')
    file.seek(0)
    return file 

def download(self):
        print("Downloading %s into: %s..." % (self.url, self.path))
        if os.path.isfile(self.path):
            print("File (%s) exists, so skipping." % self.path)
            return True
        else:
            if not os.path.exists(os.path.dirname(self.path)):
                os.makedirs(os.path.dirname(self.path))
            i = 1
            while i <= 5:
                try:
                    urllib.request.urlretrieve(self.url, filename=self.path)
                    break
                except HTTPError as err:
                    print("Error: %s, reason: %s. Retrying (%i).." % (err.code, err.reason, i))
                    i += 1
                except IOError as err:
                    print("Error: %s, reason: %s. Retrying (%i).." % (err.errno, err.strerror, i))
                    i += 1
                except socket.timeout as err:
                    print("Network error: %s. Retrying (%i).." % (err.strerror, i))
                    i += 1
                except socket.error as err:
                    print("Network error: %s. Retrying (%i).." % (err.strerror, i))
                    i += 1
                except ContentTooShortError as err:
                    print("Error: The downloaded data is less than the expected amount, so skipping.")
                    i += 1

            if i == 5:
                return False

        return True 

def get_zhaopin_html(jobarea_name, job_type):
    url_temp = "http://sou.zhaopin.com/jobs/searchresult.ashx?jl={jobarea_name}&kw={job_type}&sm=0&p=1&source=1"
    url = url_temp.format(jobarea_name=urllib.request.quote(jobarea_name),job_type=urllib.request.quote(job_type))
    headers = { 'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36' }


    logger.warning("-------->15-->02")
    try:
        time.sleep(2)
        req = urllib.request.Request(url, None, headers)
        response = urlopen(req)
        # response = urllib.request.urlopen(url) # 打开网址

    except HTTPError as e1:
        print("The (www.python.org)server couldn't fulfill the request.")
        logger.error('-------->15-->02->HTTPError-> %s' % ( e1.msg))
    except URLError as e2:
        print('We failed to reach a server.')
        logger.error('-------->15-->03->URLError->%s' % (e2.msg))
    except ContentTooShortError as e3:
        print('Reason: ', e3.reason)
        logger.error('-------->15-->04->ContentTooShortError-> %s' % (e3.msg))
    else:
        html = ""
        logger.warning("-------->15-->05")
        try:
            if response:
                logger.warning("-------->15-->05-->01a")
                html = response.read()   # 读取源代码并转为unicode
                logger.warning("-------->15-->05-->01b")
            else:
                logger.warning("-------->15-->05-->02")
        except Exception as e4:
            logger.error('-------->15-->06->URLError->%s' % (str(e4)))
        finally:
            logger.warning("-------->15-->07-->finally")
            response.close()

        logger.warning("-------->15-->08")


        if html:
            return html.decode('UTF-8')
        else:
            logger.error("-------->15-->09-> html is None")

    return ""


# 解析 智联招聘：zhaopin.com 页面的, css选择器