From 9f5809b3e80674a7d3e4afbfc3e790849cf17cad Mon Sep 17 00:00:00 2001 From: fiocfun Date: Sun, 23 Mar 2014 00:16:35 +0600 Subject: [PATCH] [xtube] user playlist extractor --- test/test_playlists.py | 9 ++++++++ youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/xtube.py | 38 +++++++++++++++++++++++++++++++- 3 files changed, 47 insertions(+), 2 deletions(-) diff --git a/test/test_playlists.py b/test/test_playlists.py index 4c9c34057..2b1a7e849 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -38,6 +38,7 @@ from youtube_dl.extractor import ( GenericIE, TEDIE, ToypicsUserIE, + XTubeUserIE, ) @@ -278,5 +279,13 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['id'], 'Mikey') self.assertTrue(len(result['entries']) >= 17) + def test_xtube_user(self): + dl = FakeYDL() + ie = XTubeUserIE(dl) + result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers') + self.assertIsPlaylist(result) + self.assertEqual(result['id'], 'greenshowers') + self.assertTrue(len(result['entries']) >= 155) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index b8c843515..35f6e3358 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -288,7 +288,7 @@ from .worldstarhiphop import WorldStarHipHopIE from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE -from .xtube import XTubeIE +from .xtube import XTubeUserIE, XTubeIE from .yahoo import ( YahooIE, YahooNewsIE, diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 033a9d893..b293e2665 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -75,4 +75,40 @@ class XTubeIE(InfoExtractor): 'comment_count': comment_count, 'formats': formats, 'age_limit': 18, - } \ No newline at end of file + } + +class XTubeUserIE(InfoExtractor): + IE_DESC = 'XTube user profile' + _VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P[^&#]+)(?:$|[&#])' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + username = mobj.group('username') + + profile_page = self._download_webpage( + url, username, note='Retrieving profile page') + + video_count = int(self._search_regex( + r'%s\'s Videos \(([0-9]+)\)'%username, profile_page, + 'video count')) + + PAGE_SIZE = 25 + urls = [] + page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE + for n in range(1, page_count + 1): + lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username) + lpage = self._download_webpage( + lpage_url, username, + note='Downloading page %d/%d' % (n, page_count)) + urls.extend( + re.findall(r'addthis:url="([^"]+)"', lpage)) + + return { + '_type': 'playlist', + 'id': username, + 'entries': [{ + '_type': 'url', + 'url': eurl, + 'ie_key': 'XTube', + } for eurl in urls] + }