diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-07-12 23:36:32 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-07-12 23:36:32 +0600 |
commit | 48607afac5ccff69d02ba8cfcfba9dd34bf1fa26 (patch) | |
tree | 239a019c8b72447625286cb33c982b01765c0035 | |
parent | c4f1fde75bf69e05be29283c9211089e6ab269ad (diff) | |
parent | b6ea9ef21ad3a43bddf24f5769bdf21a372381fa (diff) |
Merge branch 'fstirlitz-rdsca'
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/rds.py | 70 |
2 files changed, 71 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index cbaa07391..3f4f23521 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 .rds import RDSIE from .redtube import RedTubeIE from .restudy import RestudyIE from .reverbnation import ReverbNationIE diff --git a/youtube_dl/extractor/rds.py b/youtube_dl/extractor/rds.py new file mode 100644 index 000000000..fdd3f36a6 --- /dev/null +++ b/youtube_dl/extractor/rds.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class RDSIE(InfoExtractor): + IE_DESC = 'RDS.ca' + _VALID_URL = r'https?://(?:www\.)?rds\.ca/videos/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+\.\d+)' + + _TEST = { + 'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799', + 'info_dict': { + 'id': '3.1132799', + 'display_id': 'fowler-jr-prend-la-direction-de-jacksonville', + '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, + 'upload_date': '20150430', + 'duration': 154.354, + 'age_limit': 0, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + # TODO: extract f4m from 9c9media.com + video_url = self._search_regex( + r'<span[^>]+itemprop="contentURL"[^>]+content="([^"]+)"', + webpage, 'video url') + + title = self._og_search_title(webpage) or self._html_search_meta( + 'title', webpage, 'title', fatal=True) + description = self._og_search_description(webpage) or self._html_search_meta( + 'description', webpage, 'description') + thumbnail = self._og_search_thumbnail(webpage) or self._search_regex( + [r'<link[^>]+itemprop="thumbnailUrl"[^>]+href="([^"]+)"', + r'<span[^>]+itemprop="thumbnailUrl"[^>]+content="([^"]+)"'], + webpage, 'thumbnail', fatal=False) + timestamp = parse_iso8601(self._search_regex( + r'<span[^>]+itemprop="uploadDate"[^>]+content="([^"]+)"', + webpage, 'upload date', fatal=False)) + duration = parse_duration(self._search_regex( + r'<span[^>]+itemprop="duration"[^>]+content="([^"]+)"', + webpage, 'duration', fatal=False)) + age_limit = self._family_friendly_search(webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'age_limit': age_limit, + } |