Saverr/svtplay-dl
1
0
Fork 0
mirror of https://github.com/spaam/svtplay-dl.git synced 2024-11-27 21:54:17 +01:00
Code Issues Projects Releases Wiki Activity

Improve title to filename conversion.

Browse Source 
Does unicode NFD decomposition on the string before stripping non ascii chars.

This means that chars like 'ü' is decomposed into 'u' and '¨', which mean that
when non-ascii chars are dropped we will still keep the 'u'.

Fixes #60
This commit is contained in:
Anders Waldenborg 2014-01-05 17:02:48 +01:00
parent 712901cc8e
commit d6ab73679e
2 changed files with 27 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
lib/svtplay_dl/__init__.py
View File

@ -8,7 +8,7 @@ import logging
from optparse import OptionParser
from svtplay_dl.log import log
from svtplay_dl.utils import get_http_data, is_py3, is_py2, decode_html_entities
from svtplay_dl.utils import get_http_data, decode_html_entities, filenamify
from svtplay_dl.service import service_handler, Generic
@ -64,16 +64,11 @@ def get_media(url, options):
match = re.search(r"(?i)<title[^>]*>\s*(.*?)\s*</title>", data, re.S)
if match:
title_tag = decode_html_entities(match.group(1))
if is_py3:
title = re.sub(r'[^\w\s-]', '', title_tag).strip().lower()
tmp = re.sub(r'[-\s]+', '-', title)
if not options.output:
options.output = filenamify(title_tag)
else:
title = unicode(re.sub(r'[^\w\s-]', '', title_tag).strip().lower())
tmp = unicode(re.sub(r'[-\s]+', '-', title))
if options.output and os.path.isdir(options.output):
options.output += "/%s" % tmp
else:
options.output = tmp
# output is a directory
os.path.join(options.output, filenamify(title_tag))
stream.get(options, url)

22
lib/svtplay_dl/utils/__init__.py
View File

@ -8,6 +8,7 @@ import re
import xml.etree.ElementTree as ET
import json
import time
import unicodedata
try:
import HTMLParser
except ImportError:
@ -306,3 +307,24 @@ def decode_html_entities(s):
def unesc(m):
return parser.unescape(m.group())
return re.sub(r'(&[^;]+;)', unesc, ensure_unicode(s))
def filenamify(title):
"""
Convert a string to something suitable as a file name.
"""
# ensure it is unicode
title = ensure_unicode(title)
# NFD decomposes chars into base char and diacritical mark, which means that we will get base char when we strip out non-ascii.
title = unicodedata.normalize('NFD', title)
# Drop any non ascii letters/digits
title = re.sub(r'[^a-zA-Z0-9 -]', '', title)
# Drop any leading/trailing whitespace that may have appeared
title = title.strip()
# Lowercase
title = title.lower()
# Replace whitespace with dash
title = re.sub(r'[-\s]+', '-', title)
return title