X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Futils.py;h=4be3239268fd66e11bce4c2efd1cb26565e60883;hb=5f0d813d9395848e92a1c6d83335360652d654c1;hp=764474c3301695f77b6421b67b745d3c157d0937;hpb=b55ee18ff3a9642fe25a977e1152472877294493;p=youtube-dl diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 764474c33..4be323926 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -411,25 +411,9 @@ def make_HTTPS_handler(params, **kwargs): pass if sys.version_info < (3, 2): - import httplib - - class HTTPSConnectionV3(httplib.HTTPSConnection): - def __init__(self, *args, **kwargs): - httplib.HTTPSConnection.__init__(self, *args, **kwargs) - - def connect(self): - sock = socket.create_connection((self.host, self.port), self.timeout) - if getattr(self, '_tunnel_host', False): - self.sock = sock - self._tunnel() - try: - self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1) - except ssl.SSLError: - self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23) - - return YoutubeDLHTTPSHandler(params, https_conn_class=HTTPSConnectionV3, **kwargs) + return YoutubeDLHTTPSHandler(params, **kwargs) else: # Python < 3.4 - context = ssl.SSLContext(ssl.PROTOCOL_SSLv23) + context = ssl.SSLContext(ssl.PROTOCOL_TLSv1) context.verify_mode = (ssl.CERT_NONE if opts_no_check_certificate else ssl.CERT_REQUIRED) @@ -560,7 +544,9 @@ def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs): sock = compat_socket_create_connection( (self.host, self.port), self.timeout, sa) if is_https: - self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file) + self.sock = ssl.wrap_socket( + sock, self.key_file, self.cert_file, + ssl_version=ssl.PROTOCOL_TLSv1) else: self.sock = sock hc.connect = functools.partial(_hc_connect, hc) @@ -612,7 +598,9 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): def http_request(self, req): for h, v in std_headers.items(): - if h not in req.headers: + # Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275 + # The dict keys are capitalized because of this bug by urllib + if h.capitalize() not in req.headers: req.add_header(h, v) if 'Youtubedl-no-compression' in req.headers: if 'Accept-encoding' in req.headers: @@ -1631,3 +1619,23 @@ def age_restricted(content_limit, age_limit): if content_limit is None: return False # Content available for everyone return age_limit < content_limit + + +def is_html(first_bytes): + """ Detect whether a file contains HTML by examining its first bytes. """ + + BOMS = [ + (b'\xef\xbb\xbf', 'utf-8'), + (b'\x00\x00\xfe\xff', 'utf-32-be'), + (b'\xff\xfe\x00\x00', 'utf-32-le'), + (b'\xff\xfe', 'utf-16-le'), + (b'\xfe\xff', 'utf-16-be'), + ] + for bom, enc in BOMS: + if first_bytes.startswith(bom): + s = first_bytes[len(bom):].decode(enc, 'replace') + break + else: + s = first_bytes.decode('utf-8', 'replace') + + return re.match(r'^\s*<', s)