From 7df286540f893f7fbba07da8ba3b09dd7c9027c4 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Sat, 26 Oct 2013 21:57:10 +0200 Subject: [PATCH 1/2] [YouPornIE] Extract all encrypted links and remove doubles at the end --- youtube_dl/YoutubeDL.py | 2 +- youtube_dl/extractor/youporn.py | 78 +++++++++++---------------------- 2 files changed, 27 insertions(+), 53 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index e2332f9b8..d4654cc05 100644 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -462,7 +462,7 @@ def process_video_result(self, info_dict, download=True): info_dict['playlist_index'] = None # This extractors handle format selection themselves - if info_dict['extractor'] in [u'youtube', u'Youku', u'YouPorn', u'mixcloud']: + if info_dict['extractor'] in [u'youtube', u'Youku', u'mixcloud']: if download: self.process_info(info_dict) return info_dict diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index e3b56cece..704ee89dc 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -31,20 +31,6 @@ class YouPornIE(InfoExtractor): } } - def _print_formats(self, formats): - """Print all available formats""" - print(u'Available formats:') - print(u'ext\t\tformat') - print(u'---------------------------------') - for format in formats: - print(u'%s\t\t%s' % (format['ext'], format['format'])) - - def _specific(self, req_format, formats): - for x in formats: - if x["format"] == req_format: - return x - return None - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') @@ -71,27 +57,22 @@ def _real_extract(self, url): except KeyError: raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1]) - # Get all of the formats available + # Get all of the links from the page DOWNLOAD_LIST_RE = r'(?s)' download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, u'download list').strip() - - # Get all of the links from the page - LINK_RE = r'(?s)' + LINK_RE = r'' links = re.findall(LINK_RE, download_list_html) - - # Get link of hd video if available - mobj = re.search(r'var encryptedQuality720URL = \'(?P[a-zA-Z0-9+/]+={0,2})\';', webpage) - if mobj != None: - encrypted_video_url = mobj.group(u'encrypted_video_url') - video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8') - links = [video_url] + links + + # Get all encrypted links + encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage) + for encrypted_link in encrypted_links: + link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8') + links.append(link) if not links: raise ExtractorError(u'ERROR: no known formats available for video') - self.to_screen(u'Links found: %d' % len(links)) - formats = [] for link in links: @@ -103,39 +84,32 @@ def _real_extract(self, url): path = compat_urllib_parse_urlparse( video_url ).path extension = os.path.splitext( path )[1][1:] format = path.split('/')[4].split('_')[:2] + # size = format[0] # bitrate = format[1] format = "-".join( format ) # title = u'%s-%s-%s' % (video_title, size, bitrate) formats.append({ - 'id': video_id, 'url': video_url, - 'uploader': video_uploader, - 'upload_date': upload_date, - 'title': video_title, 'ext': extension, 'format': format, - 'thumbnail': thumbnail, - 'description': video_description, - 'age_limit': age_limit, + 'format_id': format, }) - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return - - req_format = self._downloader.params.get('format', 'best') - self.to_screen(u'Format: %s' % req_format) - - if req_format is None or req_format == 'best': - return [formats[0]] - elif req_format == 'worst': - return [formats[-1]] - elif req_format in ('-1', 'all'): - return formats - else: - format = self._specific( req_format, formats ) - if format is None: - raise ExtractorError(u'Requested format not available') - return [format] + # Sort and remove doubles + formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-')))) + for i in range(len(formats)-1,0,-1): + if formats[i]['format_id'] == formats[i-1]['format_id']: + del formats[i] + + return { + 'id': video_id, + 'uploader': video_uploader, + 'upload_date': upload_date, + 'title': video_title, + 'thumbnail': thumbnail, + 'description': video_description, + 'age_limit': age_limit, + 'formats': formats, + } From 6e76104d66624a8f742d1e0d210a35452a79aec8 Mon Sep 17 00:00:00 2001 From: rzhxeo Date: Sat, 26 Oct 2013 23:33:32 +0200 Subject: [PATCH 2/2] [YouPornIE] Make webpage download more robust --- youtube_dl/extractor/youporn.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 704ee89dc..e46a9b4d6 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -17,7 +17,7 @@ ) class YouPornIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P[0-9]+)/(?P[^/]+)' + _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))' _TEST = { u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', u'file': u'505835.mp4', @@ -34,6 +34,7 @@ class YouPornIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') + url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1')