diff --git a/youtube_dl/extractor/amp.py b/youtube_dl/extractor/amp.py index b573b92808..dcc3c97f14 100644 --- a/youtube_dl/extractor/amp.py +++ b/youtube_dl/extractor/amp.py @@ -9,23 +9,21 @@ class AMPIE(InfoExtractor): - def _get_media_node(self, item, name, default=None): - media_name = 'media-%s' % name - media_group = item.get('media-group') or item - return media_group.get(media_name) or item.get(media_name) or item.get(name, default) - # parse Akamai Adaptive Media Player feed def _extract_feed_info(self, url): item = self._download_json( - url, None, - 'Downloading Akamai AMP feed', - 'Unable to download Akamai AMP feed' - )['channel']['item'] + url, None, 'Downloading Akamai AMP feed', + 'Unable to download Akamai AMP feed')['channel']['item'] video_id = item['guid'] - + + def get_media_node(name, default=None): + media_name = 'media-%s' % name + media_group = item.get('media-group') or item + return media_group.get(media_name) or item.get(media_name) or item.get(name, default) + thumbnails = [] - media_thumbnail = self._get_media_node(item, 'thumbnail') + media_thumbnail = get_media_node('thumbnail') if media_thumbnail: if isinstance(media_thumbnail, dict): media_thumbnail = [media_thumbnail] @@ -38,7 +36,7 @@ def _extract_feed_info(self, url): }) subtitles = {} - media_subtitle = self._get_media_node(item, 'subTitle') + media_subtitle = get_media_node('subTitle') if media_subtitle: if isinstance(media_subtitle, dict): media_subtitle = [media_subtitle] @@ -48,26 +46,28 @@ def _extract_feed_info(self, url): subtitles[lang] = [{'url': subtitle['href']}] formats = [] - media_content = self._get_media_node(item, 'content') + media_content = get_media_node('content') if isinstance(media_content, dict): media_content = [media_content] for media_data in media_content: media = media_data['@attributes'] media_type = media['type'] if media_type == 'video/f4m': - f4m_formats = self._extract_f4m_formats(media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id, f4m_id='hds', fatal=False) + f4m_formats = self._extract_f4m_formats( + media['url'] + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', + video_id, f4m_id='hds', fatal=False) if f4m_formats: formats.extend(f4m_formats) elif media_type == 'application/x-mpegURL': - m3u8_formats = self._extract_m3u8_formats(media['url'], video_id, m3u8_id='hls', fatal=False) + m3u8_formats = self._extract_m3u8_formats( + media['url'], video_id, 'mp4', m3u8_id='hls', fatal=False) if m3u8_formats: formats.extend(m3u8_formats) else: formats.append({ 'format_id': media_data['media-category']['@attributes']['label'], 'url': media['url'], - 'preference': 1, - 'vbr': int_or_none(media.get('bitrate')), + 'tbr': int_or_none(media.get('bitrate')), 'filesize': int_or_none(media.get('fileSize')), }) @@ -75,8 +75,8 @@ def _extract_feed_info(self, url): return { 'id': video_id, - 'title': self._get_media_node(item, 'title'), - 'description': self._get_media_node(item, 'description'), + 'title': get_media_node('title'), + 'description': get_media_node('description'), 'thumbnails': thumbnails, 'timestamp': parse_iso8601(item.get('pubDate'), ' '), 'duration': int_or_none(media_content[0].get('@attributes', {}).get('duration')), diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py index a55e696d21..bd2a6340bb 100644 --- a/youtube_dl/extractor/bleacherreport.py +++ b/youtube_dl/extractor/bleacherreport.py @@ -26,7 +26,7 @@ class BleacherReportIE(InfoExtractor): 'uploader': 'Team Stream Now ', }, 'add_ie': ['Ooyala'], - },{ + }, { 'url': 'http://bleacherreport.com/articles/2586817-aussie-golfers-get-fright-of-their-lives-after-being-chased-by-angry-kangaroo', 'md5': 'af5f90dc9c7ba1c19d0a3eac806bbf50', 'info_dict': { @@ -35,25 +35,11 @@ class BleacherReportIE(InfoExtractor): 'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo', 'timestamp': 1446839961, 'uploader': 'Sean Fay', - 'description': 'md5:e95afafa43619816552723878b3b0a84', + 'description': 'md5:825e94e0f3521df52fa83b2ed198fa20', 'uploader_id': 6466954, 'upload_date': '20151011', }, 'add_ie': ['Youtube'], - },{ - 'url': 'http://bleacherreport.com/articles/2496438-fsu-stat-projections-is-jalen-ramsey-best-defensive-player-in-college-football', - 'md5': 'a3ffc3dc73afdbc2010f02d98f990f20', - 'info_dict': { - 'id': '2496438', - 'ext': 'mp4', - 'title': 'FSU Stat Projections: Is Jalen Ramsey Best Defensive Player in College Football?', - 'upload_date': '20150615', - 'uploader': 'Team Stream Now ', - 'timestamp': 1434380212, - 'description': 'CFB, ACC, Florida State', - 'uploader_id': 3992341, - }, - 'add_ie': ['Vine'], }] def _real_extract(self, url): @@ -115,7 +101,6 @@ class BleacherReportCMSIE(AMPIE): def _real_extract(self, url): video_id = self._match_id(url) - info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id) info['id'] = video_id return info diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index 80a928827c..2a43107548 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -13,9 +13,6 @@ from ..utils import ( ExtractorError, clean_html, - determine_ext, - int_or_none, - parse_iso8601, ) @@ -91,7 +88,8 @@ def _real_extract(self, url): video_id = self._match_id(url).replace('/', '.') try: - info = self._extract_feed_info('http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) + info = self._extract_feed_info( + 'http://www.dramafever.com/amp/episode/feed.json?guid=%s' % video_id) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError): raise ExtractorError( diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 0cd0f9fa83..318ac013d4 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -3,10 +3,6 @@ import re from .amp import AMPIE -from ..utils import ( - parse_iso8601, - int_or_none, -) class FoxNewsIE(AMPIE): @@ -22,8 +18,8 @@ class FoxNewsIE(AMPIE): 'title': 'Frozen in Time', 'description': '16-year-old girl is size of toddler', 'duration': 265, - #'timestamp': 1304411491, - #'upload_date': '20110503', + # 'timestamp': 1304411491, + # 'upload_date': '20110503', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -36,8 +32,8 @@ class FoxNewsIE(AMPIE): 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal", 'description': "Congressman discusses president's plan", 'duration': 292, - #'timestamp': 1417662047, - #'upload_date': '20141204', + # 'timestamp': 1417662047, + # 'upload_date': '20141204', 'thumbnail': 're:^https?://.*\.jpg$', }, }, @@ -52,10 +48,9 @@ class FoxNewsIE(AMPIE): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - host = mobj.group('host') + host, video_id = re.match(self._VALID_URL, url).groups() - info = self._extract_feed_info('http://%s/v/feed/video/%s.js?template=fox' % (host, video_id)) + info = self._extract_feed_info( + 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id)) info['id'] = video_id return info