diff options
| author | Leslie P. Polzer <polzer@gnu.org> | 2015-02-23 12:11:19 +0100 | 
|---|---|---|
| committer | Leslie P. Polzer <polzer@gnu.org> | 2015-02-23 12:11:19 +0100 | 
| commit | 93b5071f73738d788c878b38a57f2b6efe0da883 (patch) | |
| tree | a1eab4c779501627faadaff52479535e145584c8 | |
| parent | ddc369f073fda4ddd429c2d9a104e561cefd417f (diff) | |
[soundgasm] add profile IE.
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/soundgasm.py | 36 | 
2 files changed, 40 insertions, 1 deletions
| diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 94e150826..cf58f0800 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -425,7 +425,10 @@ from .soundcloud import (      SoundcloudUserIE,      SoundcloudPlaylistIE  ) -from .soundgasm import SoundgasmIE +from .soundgasm import ( +    SoundgasmIE, +    SoundgasmProfileIE +)  from .southpark import (      SouthParkIE,      SouthparkDeIE, diff --git a/youtube_dl/extractor/soundgasm.py b/youtube_dl/extractor/soundgasm.py index a4f8ce6c3..e568ff18c 100644 --- a/youtube_dl/extractor/soundgasm.py +++ b/youtube_dl/extractor/soundgasm.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals  import re  from .common import InfoExtractor +from ..utils import clean_html  class SoundgasmIE(InfoExtractor): @@ -38,3 +39,38 @@ class SoundgasmIE(InfoExtractor):              'title': audio_title,              'description': description          } + +class SoundgasmProfileIE(InfoExtractor): +    _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[0-9a-zA-Z_\-]+)/?$' +    _TEST = { +        'url': 'http://soundgasm.net/u/ytdl', +        'playlist_count': 1, +        'info_dict': { +            '_type': 'playlist', +            'id': 'ytdl', +            'title': 'ytdl' +        } +    } + +    def _real_extract(self, url): +        profile_id = self._match_id(url) +        webpage = self._download_webpage(url, profile_id) + +        ids = re.findall(r'''<a\s+href=".+?/u/%s/([^/]+)">''' % re.escape(profile_id), webpage) +        ids = [clean_html(id) for id in ids] + +        entries = [] +        for id in ids: +            entries.append({ +                '_type': 'url', +                'url': ('http://soundgasm.net/u/%s/%s' % (profile_id, id)) +            }) + +        info_dict = { +            '_type': 'playlist', +            'id': profile_id, +            'title': profile_id, +            'entries': entries +        } + +        return info_dict; | 
