youtube-dl

commit 019f4c03717bfd2b887309e5a4c96ea82cbedf34
parent 2ab2c0d1f53f66614eda4fefb042e851e78097f0
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date:   Sun,  5 Feb 2017 22:47:04 +0800

[bandcamp] Fix extraction for incomplete albums

Closes #11727

Diffstat:
M
ChangeLog
 | 
1
+
M
youtube_dl/extractor/bandcamp.py
 | 
19
++++++++++++++++---

2 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/ChangeLog b/ChangeLog
@@ -1,6 +1,7 @@
 version <unreleased>
 
 Extractors
+* [bandcamp] Fix extraction for incomplete albums (#11727)
 * [iwara] Fix extraction (#11781)
 * [googledrive] Fix extraction on Python 3.6
 
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
@@ -209,6 +209,15 @@ class BandcampAlbumIE(InfoExtractor):
             'id': 'entropy-ep',
         },
         'playlist_mincount': 3,
+    }, {
+        # not all tracks have songs
+        'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
+        'info_dict': {
+            'id': 'we-are-the-plague',
+            'title': 'WE ARE THE PLAGUE',
+            'uploader_id': 'insulters',
+        },
+        'playlist_count': 2,
     }]
 
     def _real_extract(self, url):
@@ -217,12 +226,16 @@ class BandcampAlbumIE(InfoExtractor):
         album_id = mobj.group('album_id')
         playlist_id = album_id or uploader_id
         webpage = self._download_webpage(url, playlist_id)
-        tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
-        if not tracks_paths:
+        track_elements = re.findall(
+            r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage)
+        if not track_elements:
             raise ExtractorError('The page doesn\'t contain any tracks')
+        # Only tracks with duration info have songs
         entries = [
             self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
-            for t_path in tracks_paths]
+            for elem_content, t_path in track_elements
+            if self._html_search_meta('duration', elem_content, default=None)]
+
         title = self._html_search_regex(
             r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
             webpage, 'title', fatal=False)