youtube-dl

commit 0980426559741bb9a8b2ea39b581073cf2738f5a
parent b1c9c669365cea4fb94babd66076665685abc453
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Fri, 22 Nov 2013 16:05:14 +0100

[bandcamp] add support for albums (reported in #1270)

Diffstat:
M
test/test_playlists.py
 | 
9
+++++++++
M
youtube_dl/extractor/__init__.py
 | 
2
+-
M
youtube_dl/extractor/bandcamp.py
 | 
24
++++++++++++++++++++++++
M
youtube_dl/extractor/generic.py
 | 
3
++-

4 files changed, 36 insertions(+), 2 deletions(-)
diff --git a/test/test_playlists.py b/test/test_playlists.py
@@ -22,6 +22,7 @@ from youtube_dl.extractor import (
     LivestreamIE,
     NHLVideocenterIE,
     BambuserChannelIE,
+    BandcampAlbumIE
 )
 
 
@@ -103,5 +104,13 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], u'pixelversity')
         self.assertTrue(len(result['entries']) >= 66)
 
+    def test_bandcamp_album(self):
+        dl = FakeYDL()
+        ie = BandcampAlbumIE(dl)
+        result = ie.extract('http://mpallante.bandcamp.com/album/nightmare-night-ep')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], u'Nightmare Night EP')
+        self.assertTrue(len(result['entries']) >= 4)
+
 if __name__ == '__main__':
     unittest.main()
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -11,7 +11,7 @@ from .arte import (
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
-from .bandcamp import BandcampIE
+from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
 from .breakcom import BreakIE
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
@@ -3,11 +3,13 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_urlparse,
     ExtractorError,
 )
 
 
 class BandcampIE(InfoExtractor):
+    IE_NAME = u'Bandcamp'
     _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
     _TEST = {
         u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
@@ -61,3 +63,25 @@ class BandcampIE(InfoExtractor):
                       }
 
         return [track_info]
+
+
+class BandcampAlbumIE(InfoExtractor):
+    IE_NAME = u'Bandcamp:album'
+    _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        title = mobj.group('title')
+        webpage = self._download_webpage(url, title)
+        tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
+        if not tracks_paths:
+            raise ExtractorError(u'The page doesn\'t contain any track')
+        entries = [
+            self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
+            for t_path in tracks_paths]
+        title = self._search_regex(r'album_title : "(.*?)"', webpage, u'title')
+        return {
+            '_type': 'playlist',
+            'title': title,
+            'entries': entries,
+        }
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -199,7 +199,8 @@ class GenericIE(InfoExtractor):
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
         if mobj is not None:
             burl = unescapeHTML(mobj.group(1))
-            return self.url_result(burl, 'Bandcamp')
+            # Don't set the extractor because it can be a track url or an album
+            return self.url_result(burl)
 
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)