diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-07-12 23:35:56 +0600 | 
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-07-12 23:35:56 +0600 | 
| commit | b6ea9ef21ad3a43bddf24f5769bdf21a372381fa (patch) | |
| tree | 239a019c8b72447625286cb33c982b01765c0035 | |
| parent | b8dd44baa98467caa683b38f3857e5f3700b431a (diff) | |
[rds] Improve
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/rds.py | 70 | ||||
| -rw-r--r-- | youtube_dl/extractor/rdsca.py | 50 | 
3 files changed, 71 insertions, 51 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 73fa0e4ed..3f4f23521 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -460,7 +460,7 @@ from .radiobremen import RadioBremenIE  from .radiofrance import RadioFranceIE  from .rai import RaiIE  from .rbmaradio import RBMARadioIE -from .rdsca import RDScaIE +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, +        } diff --git a/youtube_dl/extractor/rdsca.py b/youtube_dl/extractor/rdsca.py deleted file mode 100644 index a8df927e4..000000000 --- a/youtube_dl/extractor/rdsca.py +++ /dev/null @@ -1,50 +0,0 @@ -# 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, -            }], -        }  | 
