From f58487b392f7943c31e41b200bef8e97822529db Mon Sep 17 00:00:00 2001 From: Thijs Vermeir Date: Fri, 2 Jan 2015 13:13:18 +0100 Subject: [PATCH] [vier] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vier.py | 75 ++++++++++++++++++++++++++++++++ 2 files changed, 76 insertions(+) create mode 100644 youtube_dl/extractor/vier.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9848ff611..9ccd1b32e 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -474,6 +474,7 @@ from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE from .vidzi import VidziIE +from .vier import VierIE, VierVideosIE from .vimeo import ( VimeoIE, VimeoAlbumIE, diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py new file mode 100644 index 000000000..e3f1b4714 --- /dev/null +++ b/youtube_dl/extractor/vier.py @@ -0,0 +1,75 @@ +from .common import InfoExtractor +from ..utils import escape_url + +import re + +class VierIE (InfoExtractor): + _VALID_URL = r'(?:http://)?www.vier.be/(?P.*)/videos/(.+?)/(?P\d*)' + _TEST = { + 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'md5': 'bf48f4eb998cbde44ecd02fc42c51149', + 'info_dict': { + 'id': '16129', + 'ext': 'mp4', + 'title': 'Het wordt warm in De Moestuin', + 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + }, + } + + def _real_extract (self, url): + mobj = re.match (self._VALID_URL, url) + + program = mobj.group ('program') + video_id = mobj.group ('id') + + webpage = self._download_webpage (url, video_id) + + title = self._html_search_regex(r'', webpage, u'title') + description = self._html_search_regex (r'', webpage, u'description') + vod_id = self._html_search_regex(r'"filename" : "(.+?)"', webpage, u'playlist URL') + url = escape_url ("http://vod.streamcloud.be/vier_vod/mp4:_definst_/" + vod_id + ".mp4/playlist.m3u8") + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'formats': self._extract_m3u8_formats(url, video_id, 'mp4'), + } + +class VierVideosIE (InfoExtractor): + _VALID_URL = r'http://www.vier.be/(?P.*)/videos(\?page=(?P\d*))?$' + _TESTS = [{ + 'url': 'http://www.vier.be/demoestuin/videos', + 'info_dict': { + 'id': 'demoestuin page(0)', + }, + 'playlist_mincount': 20, + }, + { + 'url': 'http://www.vier.be/demoestuin/videos?page=6', + 'info_dict': { + 'id': 'demoestuin page(6)', + }, + 'playlist_mincount': 20, + }] + + def _real_extract (self, url): + mobj = re.match (self._VALID_URL, url) + + program = mobj.group ('program') + page = mobj.group ('page') + if page == None: + page = 0 + + videos_id = program + " page(" + str (page) + ")" + videos_page = self._download_webpage (url, videos_id, note='Retrieving videos page') + + return { + '_type': 'playlist', + 'id': videos_id, + 'entries': [{ + '_type': 'url', + 'url': "http://www.vier.be/" + eurl[0], + 'ie_key': 'Vier', + } for eurl in re.findall (r'

(.+?)

', videos_page)] + } -- 2.22.2