From 76beff70a8899651b40a664a63ed2e4586145328 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?M=2EYasoob=20Ullah=20Khalid=20=E2=98=BA?= Date: Fri, 22 Aug 2014 01:30:49 +0500 Subject: [PATCH] Added an IE for Dump.com --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/dump.py | 39 ++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) create mode 100644 youtube_dl/extractor/dump.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index be7616edcf..7ad5d93188 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -69,6 +69,7 @@ from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE from .drtv import DRTVIE +from .dump import DumpIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .divxstage import DivxStageIE diff --git a/youtube_dl/extractor/dump.py b/youtube_dl/extractor/dump.py new file mode 100644 index 0000000000..cfa71bd38d --- /dev/null +++ b/youtube_dl/extractor/dump.py @@ -0,0 +1,39 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, +) + +class DumpIE(InfoExtractor): + _VALID_URL = r'^https?://(?:www\.)?dump\.com/(?P[a-zA-Z0-9]+)/' + + def _real_extract(self, url): + m = re.match(self._VALID_URL, url) + video_id = m.group('id') + + # Note: There is an easier-to-parse configuration at + # http://www.aparat.com/video/video/config/videohash/%video_id + # but the URL in there does not work + + webpage = self._download_webpage(url, video_id) + + try: + video_url = re.findall(r'file","(.+?.flv)"', webpage)[-1] + except IndexError: + raise ExtractorError(u'No video URL found') + + thumb = re.findall('([^"]+)', webpage, u'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': 'flv', + 'thumbnail': thumb, + }