diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/__init__.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/aftenposten.py | 11 | ||||
| -rw-r--r-- | youtube_dl/options.py | 9 | ||||
| -rw-r--r-- | youtube_dl/postprocessor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/postprocessor/ffmpeg.py | 6 | ||||
| -rw-r--r-- | youtube_dl/postprocessor/metadatafromtitle.py | 47 |
6 files changed, 71 insertions, 9 deletions
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index a08ddd670..852b2fc3d 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -213,6 +213,11 @@ def _real_main(argv=None): # PostProcessors postprocessors = [] # Add the metadata pp first, the other pps will copy it + if opts.metafromtitle: + postprocessors.append({ + 'key': 'MetadataFromTitle', + 'titleformat': opts.metafromtitle + }) if opts.addmetadata: postprocessors.append({'key': 'FFmpegMetadata'}) if opts.extractaudio: diff --git a/youtube_dl/extractor/aftenposten.py b/youtube_dl/extractor/aftenposten.py index 2b257ede7..e15c015fb 100644 --- a/youtube_dl/extractor/aftenposten.py +++ b/youtube_dl/extractor/aftenposten.py @@ -14,10 +14,10 @@ from ..utils import ( class AftenpostenIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html' + _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)' _TEST = { - 'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=§ion=webtv_serierogprogrammer_sweatshop_sweatshopenglish', + 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more', 'md5': 'fd828cd29774a729bf4d4425fe192972', 'info_dict': { 'id': '21039', @@ -30,12 +30,7 @@ class AftenpostenIE(InfoExtractor): } def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - video_id = self._html_search_regex( - r'data-xs-id="(\d+)"', webpage, 'video id') + video_id = self._match_id(url) data = self._download_xml( 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id) diff --git a/youtube_dl/options.py b/youtube_dl/options.py index eefe008d5..4e6e47d6f 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -736,6 +736,15 @@ def parseOpts(overrideArguments=None): action='store_true', dest='addmetadata', default=False, help='write metadata to the video file') postproc.add_option( + '--metadata-from-title', + metavar='FORMAT', dest='metafromtitle', + help='parse additional metadata like song title / artist from the video title. ' + 'The format syntax is the same as --output, ' + 'the parsed parameters replace existing values. ' + 'Additional templates: %(album), %(artist). ' + 'Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like ' + '"Coldplay - Paradise"') + postproc.add_option( '--xattrs', action='store_true', dest='xattrs', default=False, help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)') diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index 708df3dd4..f39acadce 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -15,6 +15,7 @@ from .ffmpeg import ( ) from .xattrpp import XAttrMetadataPP from .execafterdownload import ExecAfterDownloadPP +from .metadatafromtitle import MetadataFromTitlePP def get_postprocessor(key): @@ -34,5 +35,6 @@ __all__ = [ 'FFmpegPostProcessor', 'FFmpegSubtitlesConvertorPP', 'FFmpegVideoConvertorPP', + 'MetadataFromTitlePP', 'XAttrMetadataPP', ] diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 30094c2f3..b6f51cfd5 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -545,7 +545,9 @@ class FFmpegMetadataPP(FFmpegPostProcessor): metadata['title'] = info['title'] if info.get('upload_date') is not None: metadata['date'] = info['upload_date'] - if info.get('uploader') is not None: + if info.get('artist') is not None: + metadata['artist'] = info['artist'] + elif info.get('uploader') is not None: metadata['artist'] = info['uploader'] elif info.get('uploader_id') is not None: metadata['artist'] = info['uploader_id'] @@ -554,6 +556,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor): metadata['comment'] = info['description'] if info.get('webpage_url') is not None: metadata['purl'] = info['webpage_url'] + if info.get('album') is not None: + metadata['album'] = info['album'] if not metadata: self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add') diff --git a/youtube_dl/postprocessor/metadatafromtitle.py b/youtube_dl/postprocessor/metadatafromtitle.py new file mode 100644 index 000000000..5019433d3 --- /dev/null +++ b/youtube_dl/postprocessor/metadatafromtitle.py @@ -0,0 +1,47 @@ +from __future__ import unicode_literals + +import re + +from .common import PostProcessor +from ..utils import PostProcessingError + + +class MetadataFromTitlePPError(PostProcessingError): + pass + + +class MetadataFromTitlePP(PostProcessor): + def __init__(self, downloader, titleformat): + super(MetadataFromTitlePP, self).__init__(downloader) + self._titleformat = titleformat + self._titleregex = self.format_to_regex(titleformat) + + def format_to_regex(self, fmt): + """ + Converts a string like + '%(title)s - %(artist)s' + to a regex like + '(?P<title>.+)\ \-\ (?P<artist>.+)' + """ + lastpos = 0 + regex = "" + # replace %(..)s with regex group and escape other string parts + for match in re.finditer(r'%\((\w+)\)s', fmt): + regex += re.escape(fmt[lastpos:match.start()]) + regex += r'(?P<' + match.group(1) + '>.+)' + lastpos = match.end() + if lastpos < len(fmt): + regex += re.escape(fmt[lastpos:len(fmt)]) + return regex + + def run(self, info): + title = info['title'] + match = re.match(self._titleregex, title) + if match is None: + raise MetadataFromTitlePPError('Could not interpret title of video as "%s"' % self._titleformat) + for attribute, value in match.groupdict().items(): + value = match.group(attribute) + info[attribute] = value + self._downloader.to_screen('[fromtitle] parsed ' + attribute + ': ' + value) + + return True, info |