X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/4231113a7be907539052ce59df44e23c54d21d38..e22397a1c5329e12f3719961c9456e378f94dbb1:/youtube_dl/extractor/gamespot.py diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 02804d2..4236a5e 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|review)s/(?:[^/]+/\d+-|embed/)(?P\d+)' _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -35,6 +35,15 @@ class GameSpotIE(OnceIE): '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, + }, { + 'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/', + 'only_matching': True, }] def _real_extract(self, url): @@ -52,7 +61,7 @@ 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( @@ -60,7 +69,7 @@ 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( r'/([^/]+)\.csmil/', @@ -105,7 +114,8 @@ 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))) + r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url), + http_formats_preference=-1)) if not formats: for quality in ['sd', 'hd']: