From: Jaime Marquínez Ferrándiz Date: Mon, 2 Sep 2013 09:54:09 +0000 (+0200) Subject: Add an extractor for VeeHD (closes #1359) X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=8e4e89f1c236e1bec38c5363c1c341930056211e;p=youtube-dl Add an extractor for VeeHD (closes #1359) --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 90f1a4418..9f56e427c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -89,6 +89,7 @@ from .tutv import TutvIE from .unistra import UnistraIE from .ustream import UstreamIE from .vbox7 import Vbox7IE +from .veehd import VeeHDIE from .veoh import VeohIE from .vevo import VevoIE from .videofyme import VideofyMeIE diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py new file mode 100644 index 000000000..3a99a29c6 --- /dev/null +++ b/youtube_dl/extractor/veehd.py @@ -0,0 +1,56 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + get_element_by_id, + clean_html, +) + +class VeeHDIE(InfoExtractor): + _VALID_URL = r'https?://veehd.com/video/(?P\d+)' + + _TEST = { + u'url': u'http://veehd.com/video/4686958', + u'file': u'4686958.mp4', + u'info_dict': { + u'title': u'Time Lapse View from Space ( ISS)', + u'uploader_id': u'spotted', + u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"', + webpage, u'player path') + player_url = compat_urlparse.urljoin(url, player_path) + player_page = self._download_webpage(player_url, video_id, + u'Downloading player page') + config_json = self._search_regex(r'value=\'config=({.+?})\'', + player_page, u'config json') + config = json.loads(config_json) + + video_url = compat_urlparse.unquote(config['clip']['url']) + title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) + uploader_id = self._html_search_regex(r'(.+?)', + webpage, u'uploader') + thumbnail = self._search_regex(r'(.*?)