From d1feb308116f57ceae3888db5e1b93394300f564 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 8 May 2015 20:07:53 +0600 Subject: [PATCH] [mlb] Fallback to extracting video id from webpage for all URLs that does not contain it explicitly (Closes #5630) --- youtube_dl/extractor/mlb.py | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py index ee9ff73bf..109eecefd 100644 --- a/youtube_dl/extractor/mlb.py +++ b/youtube_dl/extractor/mlb.py @@ -10,7 +10,21 @@ class MLBIE(InfoExtractor): - _VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/(?:embed|m-internal-embed)\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?Pn?\d+)' + _VALID_URL = r'''(?x) + https?:// + m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/ + (?: + (?: + (?:.*?/)?video/(?:topic/[\da-z_-]+/)?v| + (?: + shared/video/embed/(?:embed|m-internal-embed)\.html| + [^/]+/video/play\.jsp + )\?.*?\bcontent_id= + ) + (?Pn?\d+)| + (?P.+?) + ) + ''' _TESTS = [ { 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', @@ -95,6 +109,12 @@ def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + if not video_id: + video_path = mobj.group('path') + webpage = self._download_webpage(url, video_path) + video_id = self._search_regex( + r'data-videoid="(\d+)"', webpage, 'video id') + detail = self._download_xml( 'http://m.mlb.com/gen/multimedia/detail/%s/%s/%s/%s.xml' % (video_id[-3], video_id[-2], video_id[-1], video_id), video_id)