The branch, dharma has been updated
via 9e882ed965badd19eccfbb5d388465bd8cfdfeaa (commit)
from d10e1c453cf960dc5d68a96211479fdb30698ae4 (commit)
- Log -----------------------------------------------------------------
http://xbmc.git.sourceforge.net/git/gitweb.cgi?p=xbmc/scripts;a=commit;h=9e882ed965badd19eccfbb5d388465bd8cfdfeaa
commit 9e882ed965badd19eccfbb5d388465bd8cfdfeaa
Author: amet <[email protected]>
Date: Thu May 12 17:05:45 2011 +0400
[script.cu.lyrics] -v1.0.2
- fixed: decode Lyricsmode and Lyricstime pages using
'decode("ISO-8859-1")', thx Anssi
diff --git a/script.cu.lyrics/addon.xml b/script.cu.lyrics/addon.xml
index a5e1943..e5cd220 100644
--- a/script.cu.lyrics/addon.xml
+++ b/script.cu.lyrics/addon.xml
@@ -1,7 +1,7 @@
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<addon id="script.cu.lyrics"
name="CU Lyrics"
- version="1.0.1"
+ version="1.0.2"
provider-name="Amet">
<requires>
<import addon="xbmc.python" version="1.0"/>
diff --git a/script.cu.lyrics/changelog.txt b/script.cu.lyrics/changelog.txt
index 82a1622..d700935 100644
--- a/script.cu.lyrics/changelog.txt
+++ b/script.cu.lyrics/changelog.txt
@@ -1,3 +1,6 @@
+1.0.2
+- fixed: decode Lyricsmode and Lyricstime pages using 'decode("ISO-8859-1")',
thx Anssi
+
1.0.1
- added: two more scrapers Lyricsmode and Lyricstime
diff --git
a/script.cu.lyrics/resources/lib/scrapers/lyricsmode/lyricsScraper.py
b/script.cu.lyrics/resources/lib/scrapers/lyricsmode/lyricsScraper.py
index fb5632f..b4f2dab 100644
--- a/script.cu.lyrics/resources/lib/scrapers/lyricsmode/lyricsScraper.py
+++ b/script.cu.lyrics/resources/lib/scrapers/lyricsmode/lyricsScraper.py
@@ -136,9 +136,9 @@ class XmlUtils :
class LyricsFetcher:
def __init__( self ):
- self.clean_lyrics_regex = re.compile( "<.+?>" )
- self.normalize_lyrics_regex = re.compile( "&#[x]*(?P<name>[0-9]+);*" )
- self.clean_br_regex = re.compile( "<br[ /]*>[\s]*", re.IGNORECASE )
+ self.clean_lyrics_regex = re.compile( "<.+?>" )
+ self.normalize_lyrics_regex = re.compile( "&#[x]*(?P<name>[0-9]+);*" )
+ self.clean_br_regex = re.compile( "<br[ /]*>[\s]*", re.IGNORECASE )
def get_lyrics_start(self, *args):
lyricThread = threading.Thread(target=self.get_lyrics_thread,
args=args)
@@ -154,9 +154,9 @@ class LyricsFetcher:
print "Search url: %s" % (url)
song_search = urllib.urlopen(url).read()
lyr = song_search.split("<div id='songlyrics_h'
class='dn'>")[1].split('<!-- /SONG LYRICS -->')[0]
- lyr = self.clean_br_regex.sub( "\n", lyr ).strip()
- lyr = self.clean_lyrics_regex.sub( "", lyr ).strip()
- lyr = self.normalize_lyrics_regex.sub( lambda m: unichr( int(
m.group( 1 ) ) ), lyr ).encode( "UTF-8", "replace" ).decode( "UTF-8" )
+ lyr = self.clean_br_regex.sub( "\n", lyr ).strip()
+ lyr = self.clean_lyrics_regex.sub( "", lyr ).strip()
+ lyr = self.normalize_lyrics_regex.sub( lambda m: unichr( int(
m.group( 1 ) ) ), lyr.decode("ISO-8859-1") )
lyr = u"\n".join( [ lyric.strip() for lyric in lyr.splitlines() ]
)
l.lyrics = lyr
l.source = __title__
diff --git
a/script.cu.lyrics/resources/lib/scrapers/lyricstime/lyricsScraper.py
b/script.cu.lyrics/resources/lib/scrapers/lyricstime/lyricsScraper.py
index b803a97..4997ef6 100644
--- a/script.cu.lyrics/resources/lib/scrapers/lyricstime/lyricsScraper.py
+++ b/script.cu.lyrics/resources/lib/scrapers/lyricstime/lyricsScraper.py
@@ -133,9 +133,9 @@ class XmlUtils :
class LyricsFetcher:
def __init__( self ):
- self.clean_lyrics_regex = re.compile( "<.+?>" )
- self.normalize_lyrics_regex = re.compile( "&#[x]*(?P<name>[0-9]+);*" )
- self.clean_br_regex = re.compile( "<br[ /]*>[\s]*", re.IGNORECASE )
+ self.clean_lyrics_regex = re.compile( "<.+?>" )
+ self.normalize_lyrics_regex = re.compile( "&#[x]*(?P<name>[0-9]+);*" )
+ self.clean_br_regex = re.compile( "<br[ /]*>[\s]*", re.IGNORECASE )
self.clean_info_regex = re.compile( "\[[a-z]+?:.*\]\s" )
def get_lyrics_start(self, *args):
@@ -152,10 +152,10 @@ class LyricsFetcher:
url = "http://www.lyricstime.com/%s-%s-lyrics.html"; %
(song.artist.lower().replace(" ","-").replace(",","-"),
song.title.lower().replace(" ","-").replace(",","-"), )
song_search = urllib.urlopen(url.replace("--","-")).read()
print "Search url: %s" % (url)
- lyr = song_search.split('<div id="songlyrics"
>')[1].split('</div>')[0]#.replace("<p>","").replace("</p>","").replace("<br
/>","")
+ lyr = song_search.split('<div id="songlyrics"
>')[1].split('</div>')[0]
lyr = self.clean_br_regex.sub( "\n", lyr ).strip()
- lyr = self.clean_lyrics_regex.sub( "", lyr ).strip()
- lyr = self.normalize_lyrics_regex.sub( lambda m: unichr( int(
m.group( 1 ) ) ), lyr ).encode( "UTF-8", "replace" ).decode( "UTF-8" )
+ lyr = self.clean_lyrics_regex.sub( "", lyr ).strip()
+ lyr = self.normalize_lyrics_regex.sub( lambda m: unichr( int(
m.group( 1 ) ) ), lyr.decode("ISO-8859-1") )
lyr = u"\n".join( [ lyric.strip() for lyric in lyr.splitlines() ] )
lyr = self.clean_info_regex.sub( "", lyr )
l.lyrics = lyr
-----------------------------------------------------------------------
Summary of changes:
script.cu.lyrics/addon.xml | 2 +-
script.cu.lyrics/changelog.txt | 3 +++
.../lib/scrapers/lyricsmode/lyricsScraper.py | 12 ++++++------
.../lib/scrapers/lyricstime/lyricsScraper.py | 12 ++++++------
4 files changed, 16 insertions(+), 13 deletions(-)
hooks/post-receive
--
Scripts
------------------------------------------------------------------------------
Achieve unprecedented app performance and reliability
What every C/C++ and Fortran developer should know.
Learn how Intel has extended the reach of its next-generation tools
to help boost performance applications - inlcuding clusters.
http://p.sf.net/sfu/intel-dev2devmay
_______________________________________________
Xbmc-addons mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/xbmc-addons
