From b31756c18e708605f1ba0257f8a28234c229bf70 Mon Sep 17 00:00:00 2001 From: Filippo Valsorda Date: Mon, 20 May 2013 11:57:10 +0200 Subject: [PATCH] Python 2 compat fixes for MyVideo.de rtmpdump downloads --- youtube_dl/InfoExtractors.py | 38 +++++++++++++++++------------------- youtube_dl/utils.py | 4 ++++ 2 files changed, 22 insertions(+), 20 deletions(-) diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 2dd1c49f6..c38592e79 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -1982,27 +1982,27 @@ class MyVideoIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*' IE_NAME = u'myvideo' -# Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git -# Copyright (C) 2013 Tristan Fischer (sphere@dersphere.de) - GPLv3 + # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git + # Released into the Public Domain by Tristan Fischer on 2013-05-19 + # https://github.com/rg3/youtube-dl/pull/842 def __rc4crypt(self,data, key): x = 0 box = list(range(256)) for i in list(range(256)): - x = (x + box[i] + ord(key[i % len(key)])) % 256 + x = (x + box[i] + compat_ord(key[i % len(key)])) % 256 box[i], box[x] = box[x], box[i] x = 0 y = 0 - out = [] + out = '' for char in data: x = (x + 1) % 256 y = (y + box[x]) % 256 box[x], box[y] = box[y], box[x] -# out.append(chr(ord(char) ^ box[(box[x] + box[y]) % 256])) - out.append(chr(char ^ box[(box[x] + box[y]) % 256])) - return ''.join(out) + out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256]) + return out def __md5(self,s): - return hashlib.md5(s).hexdigest() + return hashlib.md5(s).hexdigest().encode() def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) @@ -2046,9 +2046,13 @@ class MyVideoIE(InfoExtractor): }] # try encxml + mobj = re.search('var flashvars={(.+?)}', webpage) + if mobj is None: + raise ExtractorError(u'Unable to extract video') + params = {} encxml = '' - sec = re.search('var flashvars={(.+?)}', webpage).group(1) + sec = mobj.group(1) for (a, b) in re.findall('(.+?):\'(.+?)\',?', sec): if not a == '_encxml': params[a] = b @@ -2067,11 +2071,11 @@ class MyVideoIE(InfoExtractor): # get enc data enc_data = self._download_webpage(xmldata_url, video_id).split('=')[1] enc_data_b = binascii.unhexlify(enc_data) - sk = self.__md5( - base64.b64decode(base64.b64decode(GK)) + - self.__md5( - str(video_id).encode('utf-8') - ).encode('utf-8') + sk = self.__md5( + base64.b64decode(base64.b64decode(GK)) + + self.__md5( + str(video_id).encode('utf-8') + ) ) dec_data = self.__rc4crypt(enc_data_b, sk) @@ -2098,11 +2102,6 @@ class MyVideoIE(InfoExtractor): raise ExtractorError(u'unable to extract swfobj') video_file = compat_urllib_parse.unquote(mobj.group(1)) -# mobj = re.search('path=\'(.*?)\'', dec_data) -# if mobj is None: -# raise ExtractorError(u'unable to extract filepath') -# video_filepath = mobj.group(1) - if not video_file.endswith('f4m'): ppath, prefix = video_file.split('.') video_playpath = '%s:%s' % (prefix, ppath) @@ -2133,7 +2132,6 @@ class MyVideoIE(InfoExtractor): 'ext': u'flv', 'play_path': video_playpath, 'video_file': video_file, -# 'file_path': video_filepath, 'video_hls_playlist': video_hls_playlist, 'player_url': video_swfobj, }] diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 616948e10..63d9d0ae5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -150,6 +150,10 @@ try: except NameError: compat_chr = chr +def compat_ord(c): + if type(c) is int: return c + else: return ord(c) + std_headers = { 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',