From 165e3bb67a6d737f33d0aa2024c652b363d85ebe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Sat, 2 Nov 2013 19:50:57 +0100 Subject: [PATCH] [bambuser] Add an extractor for channels (closes #1702) --- test/test_playlists.py | 9 +++++++ youtube_dl/extractor/__init__.py | 2 +- youtube_dl/extractor/bambuser.py | 40 +++++++++++++++++++++++++++++++- 3 files changed, 49 insertions(+), 2 deletions(-) diff --git a/test/test_playlists.py b/test/test_playlists.py index d6a8d56df9..de1e8d88ed 100644 --- a/test/test_playlists.py +++ b/test/test_playlists.py @@ -20,6 +20,7 @@ from youtube_dl.extractor import ( SoundcloudUserIE, LivestreamIE, NHLVideocenterIE, + BambuserChannelIE, ) @@ -85,5 +86,13 @@ class TestPlaylists(unittest.TestCase): self.assertEqual(result['title'], u'Highlights') self.assertEqual(len(result['entries']), 12) + def test_bambuser_channel(self): + dl = FakeYDL() + ie = BambuserChannelIE(dl) + result = ie.extract('http://bambuser.com/channel/pixelversity') + self.assertIsPlaylist(result) + self.assertEqual(result['title'], u'pixelversity') + self.assertTrue(len(result['entries']) >= 66) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a1e35eb468..a69c08f51c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -9,7 +9,7 @@ from .arte import ( ArteTVFutureIE, ) from .auengine import AUEngineIE -from .bambuser import BambuserIE +from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index cf8da22e3b..f3b36f4733 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -1,10 +1,15 @@ import re import json +import itertools from .common import InfoExtractor +from ..utils import ( + compat_urllib_request, +) class BambuserIE(InfoExtractor): + IE_NAME = u'bambuser' _VALID_URL = r'https?://bambuser\.com/v/(?P\d+)' _API_KEY = '005f64509e19a868399060af746a00aa' @@ -33,10 +38,43 @@ class BambuserIE(InfoExtractor): 'id': video_id, 'title': info['title'], 'url': info['url'], - 'thumbnail': info['preview'], + 'thumbnail': info.get('preview'), 'duration': int(info['length']), 'view_count': int(info['views_total']), 'uploader': info['username'], 'uploader_id': info['uid'], } + +class BambuserChannelIE(InfoExtractor): + IE_NAME = u'bambuser:channel' + _VALID_URL = r'http://bambuser.com/channel/(?P.*?)(?:/|#|\?|$)' + # The maximum number we can get with each request + _STEP = 50 + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + user = mobj.group('user') + urls = [] + last_id = '' + for i in itertools.count(1): + req_url = ('http://bambuser.com/xhr-api/index.php?username={user}' + '&sort=created&access_mode=0%2C1%2C2&limit={count}' + '&method=broadcast&format=json&vid_older_than={last}' + ).format(user=user, count=self._STEP, last=last_id) + req = compat_urllib_request.Request(req_url) + # Without setting this header, we wouldn't get any result + req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) + info_json = self._download_webpage(req, user, + u'Downloading page %d' % i) + results = json.loads(info_json)['result'] + if len(results) == 0: + break + last_id = results[-1]['vid'] + urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) + + return { + '_type': 'playlist', + 'title': user, + 'entries': urls, + }