From 150f20828be552763dddce1c45b9a4e642cff599 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Wed, 4 Sep 2013 22:06:50 +0200 Subject: [PATCH] Add extractor for daum.net (closes #1330) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/daum.py | 71 ++++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) create mode 100644 youtube_dl/extractor/daum.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a96b62d37..caef53b73 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -18,6 +18,7 @@ from .condenast import CondeNastIE from .criterion import CriterionIE from .cspan import CSpanIE from .dailymotion import DailymotionIE, DailymotionPlaylistIE +from .daum import DaumIE from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py new file mode 100644 index 000000000..9b4566999 --- /dev/null +++ b/youtube_dl/extractor/daum.py @@ -0,0 +1,71 @@ +# encoding: utf-8 +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + determine_ext, +) + + +class DaumIE(InfoExtractor): + _VALID_URL = r'https?://tvpot\.daum\.net/.*?clipid=(?P\d+)' + IE_NAME = u'daum.net' + + _TEST = { + u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', + u'file': u'52554690.mp4', + u'info_dict': { + u'title': u'DOTA 2GETHER μ‹œμ¦Œ2 6회 - 2λΆ€', + u'upload_date': u'20130831', + u'duration': 3868, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1) + webpage = self._download_webpage(url, video_id) + full_id = self._search_regex(r'