From 64e7ad6045990f01b250b622b9934035f75da624 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 21 Mar 2014 14:38:37 +0100 Subject: [PATCH] [videolectures] (New extractor) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/videolecturesnet.py | 67 ++++++++++++++++++++++++ youtube_dl/utils.py | 4 ++ 3 files changed, 72 insertions(+) create mode 100644 youtube_dl/extractor/videolecturesnet.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 80b1e128a1..9cf73272fb 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -260,6 +260,7 @@ from .vice import ViceIE from .viddler import ViddlerIE from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE +from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE from .vimeo import ( diff --git a/youtube_dl/extractor/videolecturesnet.py b/youtube_dl/extractor/videolecturesnet.py new file mode 100644 index 0000000000..f8b946a883 --- /dev/null +++ b/youtube_dl/extractor/videolecturesnet.py @@ -0,0 +1,67 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + find_xpath_attr, + int_or_none, + parse_duration, + unified_strdate, +) + + +class VideoLecturesNetIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?videolectures\.net/(?P[^/#?]+)/' + IE_NAME = 'videolectures.net' + + _TEST = { + 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/', + 'info_dict': { + 'id': 'promogram_igor_mekjavic_eng', + 'ext': 'mp4', + 'title': 'Automatics, robotics and biocybernetics', + 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'upload_date': '20130627', + 'duration': 565, + 'thumbnail': 're:http://.*\.jpg', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + smil_url = 'http://videolectures.net/%s/video/1/smil.xml' % video_id + smil = self._download_xml(smil_url, video_id) + + title = find_xpath_attr(smil, './/meta', 'name', 'title').attrib['content'] + description = find_xpath_attr(smil, './/meta', 'name', 'abstract').attrib['content'] + upload_date = unified_strdate( + find_xpath_attr(smil, './/meta', 'name', 'date').attrib['content']) + + switch = smil.find('.//switch') + duration = parse_duration(switch.attrib.get('dur')) + thumbnail_el = find_xpath_attr(switch, './image', 'type', 'thumbnail') + thumbnail = ( + None if thumbnail_el is None else thumbnail_el.attrib.get('src')) + + formats = [{ + 'url': v.attrib['src'], + 'width': int_or_none(v.attrib.get('width')), + 'height': int_or_none(v.attrib.get('height')), + 'filesize': int_or_none(v.attrib.get('size')), + 'tbr': int_or_none(v.attrib.get('systemBitrate')) / 1000.0, + 'ext': v.attrib.get('ext'), + } for v in switch.findall('./video') + if v.attrib.get('proto') == 'http'] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'upload_date': upload_date, + 'duration': duration, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 7809c4e0b8..3574fc615c 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -763,6 +763,10 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): def unified_strdate(date_str): """Return a string with the date in the format YYYYMMDD""" + + if date_str is None: + return None + upload_date = None #Replace commas date_str = date_str.replace(',', ' ')