mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 13:52:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

[mtv] Extract more metadata and more

Browse source 
1. Remove MTVIggyIE. All www.mtviggy.com URLs now redirects to
   www.mtv.com
2. Fix MTVDEIE
3. Return multiple URLs from _transform_rtmp_url. This is for
   tosh.cc.com
This commit is contained in:
Yen Chi Hsuan 2016-07-26 11:03:43 +08:00
parent 0a147785e8
commit 712c7530ff
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
1 changed files with 30 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

58
youtube_dl/extractor/mtv.py
View file

@ -16,6 +16,7 @@
HEADRequest, HEADRequest,
sanitized_Request, sanitized_Request,
strip_or_none, strip_or_none,
timeconvert,
unescapeHTML, unescapeHTML,
url_basename, url_basename,
RegexNotFoundError, RegexNotFoundError,
@ -36,13 +37,13 @@ def _id_from_uri(uri):
return uri.split(':')[-1] return uri.split(':')[-1]
# This was originally implemented for ComedyCentral, but it also works here # This was originally implemented for ComedyCentral, but it also works here
@staticmethod @classmethod
def _transform_rtmp_url(rtmp_video_url): def _transform_rtmp_url(cls, rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url) m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m: if not m:
return rtmp_video_url return {'rtmp': rtmp_video_url}
base = 'http://viacommtvstrmfs.fplive.net/' base = 'http://viacommtvstrmfs.fplive.net/'
return base + m.group('finalid') return {'http': base + m.group('finalid')}
def _get_feed_url(self, uri): def _get_feed_url(self, uri):
return self._FEED_URL return self._FEED_URL
@ -86,14 +87,14 @@ def _extract_video_formats(self, mdoc, mtvn_id):
rtmp_video_url = rendition.find('./src').text rtmp_video_url = rendition.find('./src').text
if rtmp_video_url.endswith('siteunavail.png'): if rtmp_video_url.endswith('siteunavail.png'):
continue continue
new_url = self._transform_rtmp_url(rtmp_video_url) new_urls = self._transform_rtmp_url(rtmp_video_url)
formats.append({ formats.extend([{
'ext': 'flv' if new_url.startswith('rtmp') else ext, 'ext': 'flv' if new_url.startswith('rtmp') else ext,
'url': new_url, 'url': new_url,
'format_id': rendition.get('bitrate'), 'format_id': '-'.join([kind, rendition.get('bitrate')]),
'width': int(rendition.get('width')), 'width': int(rendition.get('width')),
'height': int(rendition.get('height')), 'height': int(rendition.get('height')),
}) } for kind, new_url in new_urls.items()])
except (KeyError, TypeError): except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.') raise ExtractorError('Invalid rendition field.')
self._sort_formats(formats) self._sort_formats(formats)
@ -136,6 +137,8 @@ def _get_video_info(self, itemdoc):
description = strip_or_none(xpath_text(itemdoc, 'description')) description = strip_or_none(xpath_text(itemdoc, 'description'))
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
title_el = None title_el = None
if title_el is None: if title_el is None:
title_el = find_xpath_attr( title_el = find_xpath_attr(
@ -168,6 +171,7 @@ def _get_video_info(self, itemdoc):
'thumbnail': self._get_thumbnail_url(uri, itemdoc), 'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description, 'description': description,
'duration': float_or_none(content_el.attrib.get('duration')), 'duration': float_or_none(content_el.attrib.get('duration')),
'timestamp': timestamp,
} }
def _get_feed_query(self, uri): def _get_feed_query(self, uri):
@ -186,8 +190,13 @@ def _get_videos_info_from_url(self, url, video_id):
idoc = self._download_xml( idoc = self._download_xml(
url, video_id, url, video_id,
'Downloading info', transform_source=fix_xml_ampersands) 'Downloading info', transform_source=fix_xml_ampersands)
title = xpath_text(idoc, './channel/title')
description = xpath_text(idoc, './channel/description')
return self.playlist_result( return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')]) [self._get_video_info(item) for item in idoc.findall('.//item')],
playlist_title=title, playlist_description=description)
def _extract_mgid(self, webpage): def _extract_mgid(self, webpage):
try: try:
@ -233,6 +242,8 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds', 'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.', 'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
'timestamp': 1400126400,
'upload_date': '20140515',
}, },
} }
@ -275,6 +286,8 @@ class MTVIE(MTVServicesInfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"', 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.', 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
'timestamp': 1352610000,
'upload_date': '20121111',
}, },
}, },
] ]
@ -301,20 +314,6 @@ def _real_extract(self, url):
return self._get_videos_info(uri) return self._get_videos_info(uri)
class MTVIggyIE(MTVServicesInfoExtractor):
IE_NAME = 'mtviggy.com'
_VALID_URL = r'https?://www\.mtviggy\.com/videos/.+'
_TEST = {
'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/',
'info_dict': {
'id': '984696',
'ext': 'mp4',
'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet',
}
}
_FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'
class MTVDEIE(MTVServicesInfoExtractor): class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de' IE_NAME = 'mtv.de'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$' _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
@ -322,7 +321,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum', 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
'info_dict': { 'info_dict': {
'id': 'music_video-a50bc5f0b3aa4b3190aa', 'id': 'music_video-a50bc5f0b3aa4b3190aa',
'ext': 'mp4', 'ext': 'flv',
'title': 'MusicVideo_cro-traum', 'title': 'MusicVideo_cro-traum',
'description': 'Cro - Traum', 'description': 'Cro - Traum',
}, },
@ -335,7 +334,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen', 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
'info_dict': { 'info_dict': {
'id': 'local_playlist-f5ae778b9832cc837189', 'id': 'local_playlist-f5ae778b9832cc837189',
'ext': 'mp4', 'ext': 'flv',
'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1', 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
}, },
'params': { 'params': {
@ -343,7 +342,6 @@ class MTVDEIE(MTVServicesInfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, { }, {
# single video in pagePlaylist with different id
'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3', 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
'info_dict': { 'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344', 'id': 'local_playlist-4e760566473c4c8c5344',
@ -355,6 +353,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
# rtmp download # rtmp download
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -367,11 +366,14 @@ def _real_extract(self, url):
r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'), r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
video_id) video_id)
def _mrss_url(item):
return item['mrss'] + item.get('mrssvars', '')
# news pages contain single video in playlist with different id # news pages contain single video in playlist with different id
if len(playlist) == 1: if len(playlist) == 1:
return self._get_videos_info_from_url(playlist[0]['mrss'], video_id) return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
for item in playlist: for item in playlist:
item_id = item.get('id') item_id = item.get('id')
if item_id and compat_str(item_id) == video_id: if item_id and compat_str(item_id) == video_id:
return self._get_videos_info_from_url(item['mrss'], video_id) return self._get_videos_info_from_url(_mrss_url(item), video_id)