From 5537dce84da34110198fc9b46c1770e5eca0fa8b Mon Sep 17 00:00:00 2001 From: David Fabijan Date: Sun, 3 Aug 2014 10:50:25 +0200 Subject: [PATCH] [Mojvideo] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/mojvideo.py | 46 ++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+) create mode 100644 youtube_dl/extractor/mojvideo.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 66c873789..468c7dc29 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -181,6 +181,7 @@ from .mlb import MLBIE from .mpora import MporaIE from .mofosex import MofosexIE +from .mojvideo import MojvideoIE from .mooshare import MooshareIE from .morningstar import MorningstarIE from .motherless import MotherlessIE diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py new file mode 100644 index 000000000..db315c17e --- /dev/null +++ b/youtube_dl/extractor/mojvideo.py @@ -0,0 +1,46 @@ +import re + +from .common import InfoExtractor + +class MojvideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-.*/(?P[a-f0-9]+)' + _TEST = { + 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', + 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', + 'info_dict': { + 'id': '3d1ed4497707730b2906', + 'ext': 'mp4', + 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', + 'description':'Video: V avtu pred mano rdečelaska - Alfi Nipič', + 'height':378, + 'width':480 + # TODO more properties, either as: + # * A value + # * MD5 checksum; start the string with md5: + # * A regular expression; start the string with re: + # * Any Python type (for example int or float) + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + # TODO more code goes here, for example ... + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'(.*?)', webpage, 'title') + description = self._search_regex(r'', webpage, 'video description') + final_url = self._html_search_regex(r'mp4: \'(.*)\'', webpage, 'video url') + height=int(self._search_regex(r'',webpage,"video height")) + width=int(self._search_regex(r'',webpage,"video width")) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'ext': 'mp4', + 'url': final_url, + 'height':height, + 'width':width + # TODO more properties (see youtube_dl/extractor/common.py) + } \ No newline at end of file