def find_lyric(self, url):
pattern = 'item-([0-9]+)\.html'
song_id = common.get_first_group_by_pattern(url, pattern)
if not song_id:
logging.info('Failed to get id of url [%s]', url)
return False
song_url = 'http://www.kasi-time.com/item_js.php?no=' + song_id
data = common.get_url_content(song_url)
if not data:
logging.info('Failed to get content of url [%s]', song_url)
return False
lyric = data.decode('utf-8', 'ignore')
lyric = lyric.replace("document.write('", "")
lyric = lyric.replace("');", "")
lyric = lyric.replace("<br>", "\n")
lyric = lyric.replace(" ", " ")
lyric = common.htmlspecialchars_decode(lyric)
lyric = common.unicode2string(lyric)
lyric = common.strip_slash(lyric)
lyric = lyric.strip()
# test for half to full
lyric = common.half2full(lyric)
self.lyric = lyric
return True
def find_song_info(self, content):
prefix = "<div id='lyricBlock'>"
suffix = '</table>'
info_block = common.find_string_by_prefix_suffix(content, prefix, suffix, False)
prefix = '<h2>'
suffix = '</h2>'
title = common.find_string_by_prefix_suffix(info_block, prefix, suffix, False)
self.title = common.htmlspecialchars_decode(common.unicode2string(title))
patterns = {
'artist': u'>歌：(.*?)</td>',
'lyricist': u'>作詞：(.*?)</td>',
'composer': u'>作曲：(.*?)</td>'
}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(info_block, pattern)
if value:
value = common.strip_tags(common.htmlspecialchars_decode(value)).strip()
setattr(self, key, value)
else:
logging.debug('Failed to get %s, pattern: %s' % (key, pattern, ))
return True
def find_song_info(self, url):
ret = True
html = common.get_url_content(url)
encoding = 'sjis'
html = html.decode(encoding, 'ignore')
patterns = {
'title': u'<h2[^>]*>([^<]+)</h2>',
'artist': u'歌手：<h3.*?><a href="/artist/[0-9]+/".*?>(.+?)</a></h3>',
'lyricist': u'作詞：<h4.*?>([^<]+)</h4>',
'composer': u'作曲：<h4.*?>([^<]+)</h4>'
}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(html, pattern)
if not value:
logging.info('Failed to get %s of url [%s]', key, url)
ret = False
else:
value = common.unicode2string(common.strip_tags(value))
setattr(self, key, value)
return ret
def parse_artist_title(self, html):
startStr = '"description" content="'
endStr = u'の歌詞ページです'
infoStr = common.get_string_by_start_end_string(startStr, endStr, html)
if not infoStr:
return None
infoStr = infoStr.replace(startStr, '')
infoStr = infoStr.replace(endStr, '')
infoStr = infoStr.strip()
items = infoStr.split(' / ')
if len(items) == 2:
self.title = common.unicode2string(items[0])
self.artist = common.unicode2string(items[1])
def parse_composer(self, html):
prefix = '<b>作曲：</b>'
suffix = '\t'
raw_string = common.find_string_by_prefix_suffix(html, prefix, suffix, False)
if not raw_string:
logging.debug('Failed to find composer')
return False
self.composer = common.htmlspecialchars_decode(common.unicode2string(raw_string)).strip()
def find_lyric(self, content):
prefix = "<p id='lyricBody'>"
suffix = "</p>"
lyric = common.find_string_by_prefix_suffix(content, prefix, suffix, False)
lyric = lyric.replace('<br />', '')
lyric = common.htmlspecialchars_decode(common.unicode2string(lyric))
lyric = lyric.strip();
self.lyric = lyric
return True
def find_lyric(self, html):
prefix = '<div id="lyrics">'
suffix = '</div>'
rawLyric = common.get_string_by_start_end_string(prefix, suffix, html)
rawLyric = rawLyric.replace('<br/>', '\n')
rawLyric = common.unicode2string(rawLyric)
rawLyric = common.strip_tags(rawLyric).strip()
self.lyric = rawLyric
return True
def get_lyric_1st_part(self, html):
prefix = '<canvas id="lyrics" '
suffix = '</canvas>'
rawLyric = common.get_string_by_start_end_string(prefix, suffix, html)
if not rawLyric:
logging.info('Failed to get lyric string')
return None
encodedLyric = common.strip_tags(rawLyric)
lyric_1st = common.unicode2string(encodedLyric)
return lyric_1st
def parse_lyricist(self, html):
prefix = '<b>作詞：</b>'
suffix = '\t'
logging.debug('find me LYRICIST')
raw_string = common.find_string_by_prefix_suffix(html, prefix, suffix, False)
if not raw_string:
logging.debug('Failed to find lyricist')
return False
self.lyricist = common.htmlspecialchars_decode(common.unicode2string(raw_string)).strip()
def parse_lyric(self, url, html):
prefix = '<div id="lyric-trunk">'
suffix = '</div>'
lyric = common.get_string_by_start_end_string(prefix, suffix, html)
if not lyric:
logging.error('Failed to parse lyric')
return False
lyric = common.strip_tags(lyric)
lyric = common.unicode2string(lyric).strip()
self.lyric = lyric
return True
def find_lyric(self, html):
prefix = "<div class='lyricbox'>"
suffix = '<!--'
line = common.find_string_by_prefix_suffix(html, prefix, suffix, True)
prefix = '</script>'
suffix = '<!--'
lyric = common.find_string_by_prefix_suffix(line, prefix, suffix, False)
lyric = lyric.replace('<br />', '\n')
lyric = common.unicode2string(lyric).strip()
lyric = common.strip_tags(lyric).strip()
self.lyric = lyric
return True
def parse_lyric(self, html):
html = html.replace('\r\n', '')
prefix = "<div class='body'><p>"
suffix = '</p>'
lyric = common.find_string_by_prefix_suffix(html, prefix, suffix, False)
if not lyric:
logging.info('Failed to parse lyric from html [%s]', html)
return False
lyric = lyric.replace('<br />', '\n')
lyric = lyric.strip()
lyric = common.unicode2string(lyric)
lyric = common.half2full(lyric)
self.lyric = lyric
return True
def sanitize(self, src):
return common.unicode2string(common.htmlspecialchars_decode(src))