diff options
author | James Taylor <user234683@users.noreply.github.com> | 2018-07-11 01:31:44 -0700 |
---|---|---|
committer | James Taylor <user234683@users.noreply.github.com> | 2018-07-11 01:31:44 -0700 |
commit | aea11c407f7be904037183da152c4cdf561cd65e (patch) | |
tree | 5fad52326feee68c3771becee44fdf24ceebca05 /youtube_dl/postprocessor/metadatafromtitle.py | |
parent | 2b308ec9f0fd1ba296db7bcdcea9f93aebf6eaa1 (diff) | |
download | yt-local-aea11c407f7be904037183da152c4cdf561cd65e.tar.lz yt-local-aea11c407f7be904037183da152c4cdf561cd65e.tar.xz yt-local-aea11c407f7be904037183da152c4cdf561cd65e.zip |
track custom youtube-dl distribution
Diffstat (limited to 'youtube_dl/postprocessor/metadatafromtitle.py')
-rw-r--r-- | youtube_dl/postprocessor/metadatafromtitle.py | 48 |
1 files changed, 48 insertions, 0 deletions
diff --git a/youtube_dl/postprocessor/metadatafromtitle.py b/youtube_dl/postprocessor/metadatafromtitle.py new file mode 100644 index 0000000..f5c14d9 --- /dev/null +++ b/youtube_dl/postprocessor/metadatafromtitle.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +import re + +from .common import PostProcessor + + +class MetadataFromTitlePP(PostProcessor): + def __init__(self, downloader, titleformat): + super(MetadataFromTitlePP, self).__init__(downloader) + self._titleformat = titleformat + self._titleregex = (self.format_to_regex(titleformat) + if re.search(r'%\(\w+\)s', titleformat) + else titleformat) + + def format_to_regex(self, fmt): + r""" + 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:]) + return regex + + def run(self, info): + title = info['title'] + match = re.match(self._titleregex, title) + if match is None: + self._downloader.to_screen( + '[fromtitle] Could not interpret title of video as "%s"' + % self._titleformat) + return [], info + for attribute, value in match.groupdict().items(): + info[attribute] = value + self._downloader.to_screen( + '[fromtitle] parsed %s: %s' + % (attribute, value if value is not None else 'NA')) + + return [], info |