From 67abbe95273f59f4a04486172e6d422a10b6afb3 Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Wed, 17 Sep 2014 22:57:01 +0300 Subject: [PATCH] [videomega] Add new extractor. Closes #3775 --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/videomega.py | 59 +++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) create mode 100644 youtube_dl/extractor/videomega.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f715c3310..75831b40a 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -393,6 +393,7 @@ from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE +from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py new file mode 100644 index 000000000..1b6b65839 --- /dev/null +++ b/youtube_dl/extractor/videomega.py @@ -0,0 +1,59 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + remove_start, +) + + +class VideoMegaIE(InfoExtractor): + _VALID_URL = r'''(?x)https?:// + (?:www\.)?videomega\.tv/ + (?:iframe\.php)?\?ref=(?P[A-Za-z0-9]+) + ''' + _TEST = { + 'url': 'http://videomega.tv/?ref=GKeGPVedBe', + 'md5': '240fb5bcf9199961f48eb17839b084d6', + 'info_dict': { + 'id': 'GKeGPVedBe', + 'ext': 'mp4', + 'title': 'XXL - All Sports United', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) + webpage = self._download_webpage(url, video_id) + + escaped_data = self._search_regex( + 'unescape\("([^"]+)"\)', webpage, 'escaped data') + playlist = compat_urllib_parse.unquote(escaped_data) + + thumbnail = self._search_regex( + r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) + url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') + title = self._html_search_regex( + r'(.*?)', webpage, 'title') + if title: + title = remove_start(title, 'VideoMega.tv - ') + + formats = [] + formats.append({ + 'format_id': 'sd', + 'url': url, + }) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + }