X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/fe979149c83b5a935f7d28baf75848a9137316fd..75e3f4edaae1eaeba293fd8bcccd747d70e8155a:/youtube_dl/extractor/gamespot.py diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 621257c..ab647dd 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -14,7 +14,7 @@ from ..utils import ( class GameSpotIE(OnceIE): - _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P\d+)/?' + _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article)s/(?:[^/]+/\d+-|embed/)(?P\d+)' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -28,10 +28,19 @@ class GameSpotIE(OnceIE): 'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/', 'info_dict': { 'id': 'gs-2300-6424837', - 'ext': 'flv', - 'title': 'The Witcher 3: Wild Hunt [Xbox ONE] - Now Playing', + 'ext': 'mp4', + 'title': 'Now Playing - The Witcher 3: Wild Hunt', 'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.', }, + 'params': { + 'skip_download': True, # m3u8 downloads + }, + }, { + 'url': 'https://www.gamespot.com/videos/embed/6439218/', + 'only_matching': True, + }, { + 'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/', + 'only_matching': True, }] def _real_extract(self, url): @@ -49,7 +58,7 @@ class GameSpotIE(OnceIE): manifest_url = f4m_url formats.extend(self._extract_f4m_formats( f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False)) - m3u8_url = streams.get('m3u8_stream') + m3u8_url = dict_get(streams, ('m3u8_stream', 'adaptive_stream')) if m3u8_url: manifest_url = m3u8_url m3u8_formats = self._extract_m3u8_formats( @@ -57,10 +66,10 @@ class GameSpotIE(OnceIE): m3u8_id='hls', fatal=False) formats.extend(m3u8_formats) progressive_url = dict_get( - streams, ('progressive_hd', 'progressive_high', 'progressive_low')) + streams, ('progressive_hd', 'progressive_high', 'progressive_low', 'other_lr')) if progressive_url and manifest_url: qualities_basename = self._search_regex( - '/([^/]+)\.csmil/', + r'/([^/]+)\.csmil/', manifest_url, 'qualities basename', default=None) if qualities_basename: QUALITIES_RE = r'((,\d+)+,?)' @@ -75,8 +84,7 @@ class GameSpotIE(OnceIE): if m3u8_formats: self._sort_formats(m3u8_formats) m3u8_formats = list(filter( - lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', - m3u8_formats)) + lambda f: f.get('vcodec') != 'none', m3u8_formats)) if len(qualities) == len(m3u8_formats): for q, m3u8_format in zip(qualities, m3u8_formats): f = m3u8_format.copy() @@ -103,7 +111,8 @@ class GameSpotIE(OnceIE): onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri') if onceux_url: formats.extend(self._extract_once_formats(re.sub( - r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url).replace('ads/vmap/', ''))) + r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url), + http_formats_preference=-1)) if not formats: for quality in ['sd', 'hd']: