From 7adcbe759419320bf6224247640e2cc9f058fa8a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 25 Aug 2014 12:59:53 +0200 Subject: [PATCH] [rtlnl] Extract duration --- test/test_utils.py | 1 + youtube_dl/extractor/rtlnl.py | 6 +++++- youtube_dl/utils.py | 4 +++- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index e26cc5b0c..0953db371 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -219,6 +219,7 @@ def test_parse_duration(self): self.assertEqual(parse_duration('0h0m0s'), 0) self.assertEqual(parse_duration('0m0s'), 0) self.assertEqual(parse_duration('0s'), 0) + self.assertEqual(parse_duration('01:02:03.05'), 3723.05) def test_fix_xml_ampersands(self): self.assertEqual( diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py index 190c8f226..2d9511d5e 100644 --- a/youtube_dl/extractor/rtlnl.py +++ b/youtube_dl/extractor/rtlnl.py @@ -3,6 +3,7 @@ import re from .common import InfoExtractor +from ..utils import parse_duration class RtlXlIE(InfoExtractor): @@ -20,6 +21,7 @@ class RtlXlIE(InfoExtractor): 'onze mobiele apps.', 'timestamp': 1408051800, 'upload_date': '20140814', + 'duration': 576.880, }, 'params': { # We download the first bytes of the first fragment, it can't be @@ -35,6 +37,7 @@ def _real_extract(self, url): info = self._download_json( 'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid, uuid) + material = info['material'][0] episode_info = info['episodes'][0] @@ -44,8 +47,9 @@ def _real_extract(self, url): return { 'id': uuid, - 'title': '%s - %s' % (progname, subtitle), + 'title': '%s - %s' % (progname, subtitle), 'formats': self._extract_f4m_formats(f4m_url, uuid), 'timestamp': material['original_date'], 'description': episode_info['synopsis'], + 'duration': parse_duration(material.get('duration')), } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2b05fd7b7..53977cd2a 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1338,7 +1338,7 @@ def parse_duration(s): return None m = re.match( - r'(?:(?:(?P[0-9]+)[:h])?(?P[0-9]+)[:m])?(?P[0-9]+)s?(?::[0-9]+)?$', s) + r'(?:(?:(?P[0-9]+)[:h])?(?P[0-9]+)[:m])?(?P[0-9]+)s?(?::[0-9]+)?(?P\.[0-9]+)?$', s) if not m: return None res = int(m.group('secs')) @@ -1346,6 +1346,8 @@ def parse_duration(s): res += int(m.group('mins')) * 60 if m.group('hours'): res += int(m.group('hours')) * 60 * 60 + if m.group('ms'): + res += float(m.group('ms')) return res