From 1dba4a2185dda37fb4c22e65f5115abfea32e38e Mon Sep 17 00:00:00 2001 From: peugeot Date: Wed, 3 Sep 2014 14:10:06 +0200 Subject: [PATCH] Add support for TNAFlix --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/tnaflix.py | 68 ++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 youtube_dl/extractor/tnaflix.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6c7668fe2..ff5b9a29e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -348,6 +348,7 @@ from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE +from .tnaflix import TNAFlixIE from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py new file mode 100644 index 000000000..078e55483 --- /dev/null +++ b/youtube_dl/extractor/tnaflix.py @@ -0,0 +1,68 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + str_to_int, +) + +class TNAFlixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P[\w-]+)/(?P[\w-]+)/video(?P\d+)' + _TEST = { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'thumbnail': 're:https?://.*\.jpg$', + #'duration': 84, + 'age_limit': 18, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + redir_url = self._html_search_regex( + r'flashvars.config = escape\("([^"]+)"', webpage, 'redirection URL') + redirection_webpage = self._download_webpage(redir_url, display_id) + sources = self._search_regex( + r'(.+)', redirection_webpage, 'sources', flags=re.MULTILINE|re.DOTALL) + + formats = [] + for format_id, video_url in re.findall(r'([^<]+)\s*([^<]+)', sources, flags=re.MULTILINE|re.DOTALL): + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) + + title = self._og_search_title(webpage) + + #duration = self._html_search_regex(r'