youtube-dl

commit 4fc946b546c2a471774646f7da291105f8a0cb99
parent 280bc5dad651728e493b3b25a672a9aaef590683
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Thu, 20 Feb 2014 13:14:05 +0100

[generic] Add support for RSS feeds (Fixes #667)

Diffstat:
M
test/test_playlists.py
 | 
9
+++++++++
M
youtube_dl/extractor/generic.py
 | 
28
++++++++++++++++++++++++++++

2 files changed, 37 insertions(+), 0 deletions(-)
diff --git a/test/test_playlists.py b/test/test_playlists.py
@@ -250,5 +250,14 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'python language')
         self.assertTrue(len(result['entries']) == 15)
 
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
+
 if __name__ == '__main__':
     unittest.main()
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 
 import os
 import re
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
@@ -159,6 +160,25 @@ class GenericIE(InfoExtractor):
             raise ExtractorError('Invalid URL protocol')
         return response
 
+    def _extract_rss(self, url, video_id, doc):
+        playlist_title = doc.find('./channel/title').text
+        playlist_desc_el = doc.find('./channel/description')
+        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+
+        entries = [{
+            '_type': 'url',
+            'url': e.find('link').text,
+            'title': e.find('title').text,
+        } for e in doc.findall('./channel/item')]
+
+        return {
+            '_type': 'playlist',
+            'id': url,
+            'title': playlist_title,
+            'description': playlist_desc,
+            'entries': entries,
+        }
+
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
@@ -219,6 +239,14 @@ class GenericIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        # Is it an RSS feed?
+        try:
+            doc = xml.etree.ElementTree.fromstring(webpage)
+            if doc.tag == 'rss':
+                return self._extract_rss(url, video_id, doc)
+        except xml.etree.ElementTree.ParseError:
+            pass
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name