1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-25 12:12:34 +01:00
gallery-dl/gallery_dl/text.py
2015-11-03 00:05:18 +01:00

101 lines
3.0 KiB
Python

# -*- coding: utf-8 -*-
# Copyright 2015 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Collection of functions that work in strings/text"""
import sys
import re
import os.path
import html.parser
import urllib.parse
import platform
def remove_html(text):
"""Remove html-tags from a string"""
return " ".join(re.sub("<[^>]+?>", " ", text).split())
def filename_from_url(url):
"""Extract the last part of an url to use as a filename"""
try:
path = urllib.parse.urlparse(url).path
pos = path.rindex("/")
return path[pos+1:]
except ValueError:
return url
def clean_path_windows(path):
"""Remove illegal characters from a path-segment (Windows)"""
try:
return re.sub(r'[<>:"\\/|?*]', "_", path)
except TypeError:
return path
def clean_path_posix(path):
"""Remove illegal characters from a path-segment (Posix)"""
try:
return path.replace("/", "_")
except AttributeError:
return path
def shorten_path(path, limit=255, encoding=sys.getfilesystemencoding()):
"""Shorten a path segment to at most 'limit' bytes"""
return (path.encode(encoding)[:limit]).decode(encoding, "ignore")
def shorten_filename(filename, limit=255, encoding=sys.getfilesystemencoding()):
"""Shorten a filename to at most 'limit' bytes while preserving extension"""
name, extension = os.path.splitext(filename)
bext = extension.encode(encoding)
bname = name.encode(encoding)[:limit-len(bext)]
return bname.decode(encoding, "ignore") + extension
def extract(txt, begin, end, pos=0):
"""Extract the text between 'begin' and 'end' from 'txt'
Args:
txt: String to search in
begin: First string to be searched for
end: Second string to be searched for after 'begin'
pos: Starting position for searches in 'txt'
Returns:
The string between the two search-strings 'begin' and 'end' beginning
with position 'pos' in 'txt' as well as the position after 'end'.
If at least one of 'begin' or 'end' is not found, None and the original
value of 'pos' is returned
Examples:
extract("abcde", "b", "d") -> "c" , 4
extract("abcde", "b", "d", 3) -> None, 3
"""
try:
first = txt.index(begin, pos) + len(begin)
last = txt.index(end, first)
return txt[first:last], last+len(end)
except ValueError:
return None, pos
def extract_all(txt, rules, pos=0, values=None):
"""Calls extract for each rule and returns the result in a dict"""
if values is None:
values = {}
for key, begin, end in rules:
result, pos = extract(txt, begin, end, pos)
if key:
values[key] = result
return values, pos
if platform.system() == "Windows":
clean_path = clean_path_windows
else:
clean_path = clean_path_posix
unquote = urllib.parse.unquote
unescape = html.parser.HTMLParser().unescape