| 1 | #!/usr/bin/python
|
|---|
| 2 | # -*- coding: utf-8 -*-
|
|---|
| 3 |
|
|---|
| 4 | from appscript import *
|
|---|
| 5 | from itertools import izip
|
|---|
| 6 | import htmlentitydefs
|
|---|
| 7 | import re
|
|---|
| 8 |
|
|---|
| 9 | # based on <http://sebsauvage.net/python/snyppets/>
|
|---|
| 10 | RE_ENTITY_CHR = re.compile(u'&(%s);' % u'|'.join(htmlentitydefs.name2codepoint))
|
|---|
| 11 | RE_ENTITY_DEC = re.compile(u'&#(\d+);')
|
|---|
| 12 | RE_ENTITY_HEX = re.compile(u'&#x(\w+);')
|
|---|
| 13 | def decode_entities(s):
|
|---|
| 14 | def entity2char(m):
|
|---|
| 15 | entity = m.group(1)
|
|---|
| 16 | if entity in htmlentitydefs.name2codepoint:
|
|---|
| 17 | return unichr(htmlentitydefs.name2codepoint[entity])
|
|---|
| 18 | return u' ' # Unknown entity: We replace with a space.
|
|---|
| 19 | replaced = 0
|
|---|
| 20 | s, n = RE_ENTITY_CHR.subn(entity2char, s)
|
|---|
| 21 | replaced += n
|
|---|
| 22 | s, n = RE_ENTITY_DEC.subn(lambda x: unichr(int(x.group(1))), s)
|
|---|
| 23 | replaced += n
|
|---|
| 24 | s, n = RE_ENTITY_HEX.subn(lambda x: unichr(int(x.group(1),16)), s)
|
|---|
| 25 | replaced += n
|
|---|
| 26 | return s, replaced
|
|---|
| 27 |
|
|---|
| 28 | OPEN_P = r'<[Pp][^>]*>'
|
|---|
| 29 | RE_OPEN_P = re.compile(OPEN_P)
|
|---|
| 30 | RE_MATCHED_P = re.compile(OPEN_P + r'(?!<[Pp])(.*)</[Pp]>')
|
|---|
| 31 | RE_TOO_MANY_CR = re.compile(r'\s*\n\s*\n\s*\n+', re.U)
|
|---|
| 32 | RE_TAG = re.compile(r'<[^>]*>')
|
|---|
| 33 | RE_WHITESPACE = re.compile(r'\s+', re.U)
|
|---|
| 34 | RE_LEADING_WHITESPACE = re.compile(r'^\s+(.*)', re.U)
|
|---|
| 35 | RE_TRAILING_WHITESPACE = re.compile(r'(.*)\s+$', re.U)
|
|---|
| 36 |
|
|---|
| 37 | def html_to_text(s):
|
|---|
| 38 | s, replaced = decode_entities(s)
|
|---|
| 39 | s = s.replace('\r\n', '\n')
|
|---|
| 40 | s = s.replace('\r', '\n')
|
|---|
| 41 | if replaced > 0 or RE_TAG.search(s): # HTML
|
|---|
| 42 | s = RE_WHITESPACE.sub(' ', s)
|
|---|
| 43 | s = RE_MATCHED_P.sub(r'\1\n\n', s)
|
|---|
| 44 | s = RE_OPEN_P.sub(r'\n\n', s)
|
|---|
| 45 | s = RE_TAG.sub('', s)
|
|---|
| 46 | s = RE_TOO_MANY_CR.sub(r'\n\n', s)
|
|---|
| 47 | s = RE_LEADING_WHITESPACE.sub(r'\1', s)
|
|---|
| 48 | s = RE_TRAILING_WHITESPACE.sub(r'\1', s)
|
|---|
| 49 | return s
|
|---|
| 50 |
|
|---|
| 51 | def podcasts_to_lyrics():
|
|---|
| 52 | iTunes = app('iTunes')
|
|---|
| 53 |
|
|---|
| 54 | podcasts = iTunes.tracks[its.podcast == True]
|
|---|
| 55 |
|
|---|
| 56 | ids = podcasts.id()
|
|---|
| 57 | descs = podcasts.description()
|
|---|
| 58 | longdescs = podcasts.long_description()
|
|---|
| 59 | lyricses = podcasts.lyrics()
|
|---|
| 60 |
|
|---|
| 61 | for id_, desc, longdesc, lyrics in izip(ids, descs, longdescs, lyricses):
|
|---|
| 62 | if lyrics == k.missing_value: # video
|
|---|
| 63 | continue
|
|---|
| 64 |
|
|---|
| 65 | if longdesc == k.missing_value:
|
|---|
| 66 | if desc == k.missing_value:
|
|---|
| 67 | continue
|
|---|
| 68 | longdesc = desc
|
|---|
| 69 | else:
|
|---|
| 70 | longdesc = html_to_text(longdesc)
|
|---|
| 71 |
|
|---|
| 72 | if lyrics == longdesc:
|
|---|
| 73 | continue
|
|---|
| 74 |
|
|---|
| 75 | iTunes.tracks[its.id == id_].lyrics.set(longdesc)
|
|---|
| 76 |
|
|---|
| 77 |
|
|---|
| 78 |
|
|---|
| 79 | if __name__ == '__main__':
|
|---|
| 80 | # sync_ipod()
|
|---|
| 81 | # - poll whether 'Sync' button is enabled
|
|---|
| 82 | # update_podcasts()
|
|---|
| 83 | # - poll '[queued for download]' on last podcast, then any remaining
|
|---|
| 84 | podcasts_to_lyrics()
|
|---|
| 85 | # sync_ipod()
|
|---|
| 86 |
|
|---|
| 87 | # write podcast entry replacing http://njr.sabi.net/2007/03/04/an-applescript-to-update-podcasts-and-your-ipod/ - now we can use accessibility
|
|---|
