Merge branch 'master' of github.com:rg3/youtube-dl

diff --git a/test/helper.py b/test/helper.py
index 22d7638606841bc0250665402e09fb49655e5d89..01b11f6612dae53ae08bf397db89182c92ae4666 100644 (file)
--- a/test/helper.py
+++ b/test/helper.py
@@ -102,7 +102,10 @@ def expect_info_dict(self, expected_dict, got_dict):
             match_rex = re.compile(match_str)
 
             self.assertTrue(
-                isinstance(got, compat_str) and match_rex.match(got),
+                isinstance(got, compat_str),
+                'Expected a %r object, but got %r' % (compat_str, type(got)))
+            self.assertTrue(
+                match_rex.match(got),
                 u'field %s (value: %r) should match %r' % (info_field, got, match_str))
         elif isinstance(expected, type):
             got = got_dict.get(info_field)

diff --git a/test/test_download.py b/test/test_download.py
index c8d4ec2c87c97773d60c52ffb342809b8e2a0ffb..6422ef1197d226e8b7f098e7cb415ef58c187fed 100644 (file)
--- a/test/test_download.py
+++ b/test/test_download.py
@@ -7,6 +7,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
+    assertGreaterEqual,
     get_params,
     gettestcases,
     expect_info_dict,
@@ -136,12 +137,18 @@ def generator(test_case):
                 self.assertEqual(res_dict['_type'], 'playlist')
                 expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
             if 'playlist_mincount' in test_case:
-                self.assertGreaterEqual(
+                assertGreaterEqual(
+                    self,
                     len(res_dict['entries']),
                     test_case['playlist_mincount'],
                     'Expected at least %d in playlist %s, but got only %d' % (
                         test_case['playlist_mincount'], test_case['url'],
                         len(res_dict['entries'])))
+            if 'playlist_count' in test_case:
+                self.assertEqual(
+                    len(res_dict['entries']),
+                    test_case['playlist_count'],
+                    'Expected at %d in playlist %s, but got %d.')
 
             for tc in test_cases:
                 tc_filename = get_tc_filename(tc)

diff --git a/test/test_playlists.py b/test/test_playlists.py
index 3f79a7d6a5f7d33ce64750c0f4c3d752547c59dc..0137b8399c1e01318a9c1ce9d143c8487d761e7b 100644 (file)
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -310,24 +310,6 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'Always/Never: A Little-Seen Movie About Nuclear Command and Control : The New Yorker')
         self.assertEqual(len(result['entries']), 3)
 
-    def test_GoogleSearch(self):
-        dl = FakeYDL()
-        ie = GoogleSearchIE(dl)
-        result = ie.extract('gvsearch15:python language')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'python language')
-        self.assertEqual(result['title'], 'python language')
-        self.assertEqual(len(result['entries']), 15)
-
-    def test_generic_rss_feed(self):
-        dl = FakeYDL()
-        ie = GenericIE(dl)
-        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
-        self.assertEqual(result['title'], 'Zero Punctuation')
-        self.assertTrue(len(result['entries']) > 10)
-
     def test_ted_playlist(self):
         dl = FakeYDL()
         ie = TEDIE(dl)

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 59cc8a5ffe515ef26a21a1bcc84e9701ffb6c9fc..3a908d01f23dbfac41ea124c65336cc12eb79e86 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -341,6 +341,16 @@ class GenericIE(InfoExtractor):
                 'uploader': 'www.handjobhub.com',
                 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
             }
+        },
+        # RSS feed
+        {
+            'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+            'info_dict': {
+                'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
+                'title': 'Zero Punctuation',
+                'description': 're:'
+            },
+            'playlist_mincount': 11,
         }
     ]
 

diff --git a/youtube_dl/extractor/googlesearch.py b/youtube_dl/extractor/googlesearch.py
index 383032d81b1c9bd965be9caee8adefd79547b208..469e1f9357eaf66ef48b3bed6c3d464c48f2b5dc 100644 (file)
--- a/youtube_dl/extractor/googlesearch.py
+++ b/youtube_dl/extractor/googlesearch.py
@@ -14,6 +14,14 @@ class GoogleSearchIE(SearchInfoExtractor):
     _MAX_RESULTS = 1000
     IE_NAME = 'video.google:search'
     _SEARCH_KEY = 'gvsearch'
+    _TEST = {
+        'url': 'gvsearch15:python language',
+        'info_dict': {
+            'id': 'python language',
+            'title': 'python language',
+        },
+        'playlist_count': 15,
+    }
 
     def _get_n_results(self, query, n):
         """Get a specified number of results for a query"""

diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
index 53977cd2a35c0c829b40cb12e3d61b0efac091f3..16bc7408a74a535fa55a013866a096bec387d564 100644 (file)
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@@ -1458,6 +1458,12 @@ def urlencode_postdata(*args, **kargs):
     return compat_urllib_parse.urlencode(*args, **kargs).encode('ascii')
 
 
+try:
+    etree_iter = xml.etree.ElementTree.Element.iter
+except AttributeError:  # Python <=2.6
+    etree_iter = lambda n: n.findall('.//*')
+
+
 def parse_xml(s):
     class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
         def doctype(self, name, pubid, system):
@@ -1465,7 +1471,14 @@ def parse_xml(s):
 
     parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
     kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
-    return xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
+    # Fix up XML parser in Python 2.x
+    if sys.version_info < (3, 0):
+        for n in etree_iter(tree):
+            if n.text is not None:
+                if not isinstance(n.text, compat_str):
+                    n.text = n.text.decode('utf-8')
+    return tree
 
 
 if sys.version_info < (3, 0) and sys.platform == 'win32':