X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmlb.py;h=e369551c2fb5730377d863cf3bc2bdde31eb5f60;hb=ac0df2350a5ff4fcedd7502df127300361595d7e;hp=bfdb462ebaf663df7d7c4f3c1618988f0aa1d1e3;hpb=9b583dca4cf3b623323de8fadf6dc851b7111fd2;p=youtube-dl diff --git a/youtube_dl/extractor/mlb.py b/youtube_dl/extractor/mlb.py index bfdb462eb..e369551c2 100644 --- a/youtube_dl/extractor/mlb.py +++ b/youtube_dl/extractor/mlb.py @@ -6,12 +6,11 @@ from .common import InfoExtractor from ..utils import ( parse_duration, parse_iso8601, - find_xpath_attr, ) class MLBIE(InfoExtractor): - _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?Pn?\d+)' + _VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?Pn?\d+)' _TESTS = [ { 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', @@ -73,6 +72,18 @@ class MLBIE(InfoExtractor): 'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb', 'only_matching': True, }, + { + 'url': 'http://mlb.mlb.com/shared/video/embed/embed.html?content_id=36599553', + 'only_matching': True, + }, + { + 'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553', + 'only_matching': True, + }, + { + 'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728', + 'only_matching': True, + } ] def _real_extract(self, url): @@ -88,8 +99,9 @@ class MLBIE(InfoExtractor): duration = parse_duration(detail.find('./duration').text) timestamp = parse_iso8601(detail.attrib['date'][:-5]) - thumbnail = find_xpath_attr( - detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text + thumbnails = [{ + 'url': thumbnail.text, + } for thumbnail in detail.findall('./thumbnailScenarios/thumbnailScenario')] formats = [] for media_url in detail.findall('./url'): @@ -116,5 +128,5 @@ class MLBIE(InfoExtractor): 'duration': duration, 'timestamp': timestamp, 'formats': formats, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, }