diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-07-12 21:34:32 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-07-12 21:34:32 +0600 |
commit | b8dd44baa98467caa683b38f3857e5f3700b431a (patch) | |
tree | 35ba9cfca2e164baa8ca36270c7291eb564ee6b4 | |
parent | c4f1fde75bf69e05be29283c9211089e6ab269ad (diff) | |
parent | ac8f97f2b37115bf81a653360819b5d30eebda18 (diff) |
Merge branch 'rdsca' of https://github.com/fstirlitz/youtube-dl into fstirlitz-rdsca
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/rdsca.py | 50 |
2 files changed, 51 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index cbaa07391..73fa0e4ed 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -460,6 +460,7 @@ from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE +from .rdsca import RDScaIE from .redtube import RedTubeIE from .restudy import RestudyIE from .reverbnation import ReverbNationIE diff --git a/youtube_dl/extractor/rdsca.py b/youtube_dl/extractor/rdsca.py new file mode 100644 index 000000000..a8df927e4 --- /dev/null +++ b/youtube_dl/extractor/rdsca.py @@ -0,0 +1,50 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_iso8601, + url_basename, +) + + +class RDScaIE(InfoExtractor): + IE_NAME = 'RDS.ca' + _VALID_URL = r'http://(?:www\.)?rds\.ca/videos/(?P<id>.*)' + + _TESTS = [{ + 'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799', + 'info_dict': { + "ext": "mp4", + "title": "Fowler Jr. prend la direction de Jacksonville", + "description": "Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ", + "timestamp": 1430397346, + } + }] + + def _real_extract(self, url): + video_id = url_basename(url) + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex( + r'<span itemprop="name"[^>]*>([^\n]*)</span>', webpage, 'video title', default=None) + video_url = self._search_regex( + r'<span itemprop="contentURL" content="([^"]+)"', webpage, 'video URL') + upload_date = parse_iso8601(self._search_regex( + r'<span itemprop="uploadDate" content="([^"]+)"', webpage, 'upload date', default=None)) + description = self._search_regex( + r'<span itemprop="description"[^>]*>([^\n]*)</span>', webpage, 'description', default=None) + thumbnail = self._search_regex( + r'<span itemprop="thumbnailUrl" content="([^"]+)"', webpage, 'upload date', default=None) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': upload_date, + 'formats': [{ + 'url': video_url, + }], + } |