def find_song_info(self, content):
# content = content.decode('utf-8', 'ignore')
pattern = u'<meta property="og:title" content="(.*?) 歌詞 \|'
title = common.get_first_group_by_pattern(content, pattern)
title = common.htmlspecialchars_decode(title)
self.title = title
pattern = u'<meta property="og:description" content="(.*?)が歌う'
artist = common.get_first_group_by_pattern(content, pattern)
artist = common.htmlspecialchars_decode(artist)
self.artist = artist
prefixes = {
'lyricist': u'作詞</dt>',
'composer': u'作曲</dt>',
}
suffix = '</dd>'
for key in prefixes:
prefix = prefixes[key]
value = common.find_string_by_prefix_suffix(content, prefix, suffix, False)
if value:
value = common.strip_tags(value).strip()
value = common.htmlspecialchars_decode(value)
setattr(self, key, value)
return True
def parse_song_info(self, url, html):
ret = True
pattern = '<h1.*?>(.*)</h1>'
title = common.get_first_group_by_pattern(html, pattern)
if title:
title = common.htmlspecialchars_decode(common.strip_tags(title)).strip()
self.title = title
else:
logging.warning('Failed to parse title of url [%s]', url)
ret = False
patterns = {
'artist': '">([^<]*)</a></span></td></tr>',
'lyricist': 'td>([^<]*)<br></td></tr><tr>',
'composer': 'td>([^<]*)<br></td></tr></table>',
}
prefix = '<table class="lyric-data">'
suffix = '</table>'
info_table = common.find_string_by_prefix_suffix(html, prefix, suffix)
info_table = info_table.replace('\n', '')
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(info_table, pattern)
if value:
value = common.htmlspecialchars_decode(common.strip_tags(value)).strip()
setattr(self, key, value)
else:
logging.warning('Failed to get %s', key)
ret = False
return ret
def find_song_info(self, url):
ret = True
resp = common.get_url_content(url)
encoding = 'sjis'
html = resp.decode(encoding, 'ignore')
prefix = '<table border=0 cellpadding=0 cellspacing=5>'
suffix = '</td></table>'
infoString = common.get_string_by_start_end_string(prefix, suffix, html)
self.title = common.strip_tags(
common.get_string_by_start_end_string('<td>', '</td>', infoString)
)
self.artist = common.strip_tags(
common.get_string_by_start_end_string('<td><a href=', '</a></td>', infoString)
)
prefix = '<table border=0 cellpadding=0 cellspacing=0>'
suffix = '</td></table>'
lyricAndMusic = common.get_string_by_start_end_string(prefix, suffix, infoString)
pattern = u'作詞 ： (.*)<br>'
self.lyricist = common.get_first_group_by_pattern(lyricAndMusic, pattern)
pattern = u'作曲 ： (.*)</td>'
self.composer = common.get_first_group_by_pattern(lyricAndMusic, pattern)
return ret
def get_song_id(self, url):
if not url:
return None
pattern = '/lyrics/([0-9]+)'
id = common.get_first_group_by_pattern(url, pattern)
if not id:
pattern = '/kashi/([0-9]+)'
id = common.get_first_group_by_pattern(url, pattern)
return id
def get_csrf_token(self, html):
pattern = '(/lib/pl-lib.js[^"]+)'
pl_lib_js = common.get_first_group_by_pattern(html, pattern)
if not pl_lib_js:
return None
url = urlparse.urljoin(site_url, pl_lib_js)
r = self.s.get(url)
pattern = "'X-CSRF-Token', '(.*?)'"
token = common.get_first_group_by_pattern(r.text, pattern)
return token
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_lyric(self, url):
pattern = 'surl=([^&=]+)'
song_id = common.get_first_group_by_pattern(url, pattern)
if not song_id:
logging.error('Failed to get id of url [%s]', url)
return False
song_url = 'http://www.animap.jp/kasi/phpflash/flashphp.php?unum=' + song_id
data = common.get_url_content(song_url)
if not data:
logging.error('Failed to get content of url [%s]', song_url)
return False
prefix = 'test2='
pos = data.find(prefix)
if pos == -1:
logging.error('Failed to find lyric position of url [%s]', url)
return False
lyric = data[pos + len(prefix):]
lyric = lyric.decode('sjis').strip()
# test for half to full
lyric = common.half2full(lyric)
self.lyric = lyric
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 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 = 'euc_jp'
html = html.decode(encoding, 'ignore')
patterns = {
'title': 'title',
'artist': 'artist',
'lyricist': 'sakusi',
'composer': 'sakyoku',
}
for key in patterns:
key_for_pattern = patterns[key]
pattern = u'<INPUT type="hidden" name=%s value="([^"]*)">' % (key_for_pattern, )
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.htmlspecialchars_decode(value).strip()
setattr(self, key, value)
return ret
def get_xml_parameters(self, url):
bytes = common.get_url_content(url)
pattern = "query +: +'([^']+)'"
query = common.get_first_group_by_pattern(bytes, pattern)
return query
def find_song_info(self, html):
ret = True
prefix = '<font color="#FFFFFF"><b>'
suffix = "</b></font>"
title = common.strip_tags(common.find_string_by_prefix_suffix(html, prefix, suffix)).strip()
if title:
self.title = title
prefix = '<font size="-1" color="#FFFFFF">'
suffix = "</font>"
info = common.find_string_by_prefix_suffix(html, prefix, suffix)
info = re.sub(" +", "", info)
info = info.replace("\r", "").replace("\n", "")
patterns = {"artist": u"歌：(.*?)/", "lyricist": u"詞：(.*?)/", "composer": u"曲：(.*?)<"}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(info, pattern)
if value:
setattr(self, key, value)
else:
logging.info("Failed to get %s from info %s", key, info)
return False
return ret
def get_lyric_id(self, url):
pattern = 'lyrics/([0-9]+)'
lyric_id = common.get_first_group_by_pattern(url, pattern)
if not lyric_id:
logging.error('Failed to parse id of lyric from url')
return False
return lyric_id
def find_song_info(self, html):
pattern = '<meta property="og:title" content="([^"]+)" />'
ogTitle = common.get_first_group_by_pattern(html, pattern)
artist, title = ogTitle.split(':')
self.title = title
self.artist = artist
return True
def find_lyric(self, url):
pattern = '/[a-z]+/([0-9]+)/'
song_id = common.get_first_group_by_pattern(url, pattern)
if not song_id:
# try old pattern
# http://www.uta-net.com/user/phplib/view_0.php?ID=17248
pattern = 'ID=([0-9]+)'
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
showkasi_pattern = 'http://www.uta-net.com/user/phplib/swf/showkasi.php?ID=%s&WIDTH=530&HEIGHT=810'
song_url = showkasi_pattern % (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
prefix = '<\0\0'
suffix = '\0'
lyric = common.find_string_by_prefix_suffix(data, prefix, suffix, False)
if not lyric:
logging.error('Failed to get lyric of url [%s]', url)
return False
lyric = unicode(lyric, 'utf8')
lyric = lyric.strip()
# test for half to full
lyric = common.half2full(lyric)
self.lyric = lyric
return True
def parse_song_info(self, html):
pattern = u'<title>(.+?) 歌詞 / .*</title>'
self.title = common.get_first_group_by_pattern(html, pattern)
pattern = u"<div class='artists'>歌：(.*) 作詞：(.*) 作曲：(.*)</div>"
matches = common.get_matches_by_pattern(html, pattern)
if not matches:
return False
self.artist = matches.group(1)
self.lyricist = matches.group(2)
self.composer = matches.group(3)
return True
def find_song_info(self, content):
pattern = 'og:description" content="(.*)"'
og_desc = common.get_first_group_by_pattern(content, pattern)
if og_desc:
pattern = u'(.*?)「(.*?)」'
matches = common.get_matches_by_pattern(og_desc, pattern)
if matches:
artist = matches.group(1)
artist = artist.replace(u'歌詞サーチ ', '')
self.artist = artist
self.title = matches.group(2)
else:
logging.debug('og desc: %s' % (og_desc))
prefix = '="lyrics_info_text"'
suffix = '</div>'
info_text = common.find_string_by_prefix_suffix(content, prefix, suffix, False)
if not info_text:
logging.info('Failed to find lyrics info text')
one_line = info_text.replace('\n', '')
patterns = {
'lyricist': u'>作詞</p><p class="info_detail">(.*?)</p>',
'composer': u'>作曲</p><p class="info_detail">(.*?)</p>',
}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(one_line, 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, html):
ret = True
patterns = {
'title': '"musicSongTitle":"(.*?)"',
'artist': '"musicArtistName":"(.*?)"'
}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(html, pattern)
if value:
setattr(self, key, value)
return ret
def parse_lyric(self, html):
prefix = '<PRE>'
suffix = '</PRE>'
raw_lyric = common.find_string_by_prefix_suffix(html, prefix, suffix, False)
if not raw_lyric:
logging.info('Failed to parse lyric from html [%s]', html)
return False
raw_lyric = raw_lyric.strip()
pos = raw_lyric.find('\n\n')
if pos < 0:
logging.info('Failed to find two consecutive newlines')
return False
self.title = raw_lyric[0:pos]
raw_lyric = raw_lyric[pos+2:]
pos = raw_lyric.find('\n\n')
if pos < 0:
logging.info('Failed to find two consecutive newlines')
return False
info = raw_lyric[0:pos]
self.lyric = raw_lyric[pos+2:]
patterns = {
'artist': u'歌：(.+)',
'lyricist': u'作詞：(.+?)／',
'composer': u'作曲：(.+?)／',
'arranger': u'編曲：(.+?)／',
}
for key in patterns:
pattern = patterns[key]
value = common.get_first_group_by_pattern(info, pattern)
if not value:
logging.info('Failed to get %s of url [%s]', key, url)
else:
value = common.htmlspecialchars_decode(value).strip()
setattr(self, key, value)
return True
def find_song_info(self, url):
ret = True
html = common.get_url_content(url)
encoding = 'utf-8'
html = html.decode(encoding, 'ignore')
pattern = '<h1>(.*)</h1>'
value = common.get_first_group_by_pattern(html, pattern).strip()
if value:
self.title = value
else:
logging.error('Failed to find title of url [%s]', url)
ret = False
prefix = '<div class="person_list">'
suffix = '</div>'
info_table = common.find_string_by_prefix_suffix(html, prefix, suffix)
patterns = {
'artist': u'歌手',
'lyricist': u'作詞者',
'composer': u'作曲者',
'arranger': u'編曲者',
}
for key in patterns:
pattern = patterns[key]
prefix = u'<th>%s</th>' % (pattern)
suffix = '</td>'
value = common.find_string_by_prefix_suffix(info_table, prefix, suffix, False)
if not value:
continue
value = common.strip_tags(value).strip()
if value:
setattr(self, key, value)
return ret
def find_lyric(self, url):
pattern = '\?([0-9]+)'
song_id = common.get_first_group_by_pattern(url, pattern)
if not song_id:
logging.error('Failed to get id of url [%s]', url)
return False
params = self.get_hidden_params()
query = '%s%s&time=%s' % (params['query_prefix'], song_id, time.localtime(), )
logging.debug('query:%s' % (query, ))
post_url = 'http://www.kashinavi.com/cgi-bin/kashi.cgi'
resp = common.get_url_content(post_url, query)
if not resp:
logging.error('Failed to get content of url [%s], query [%s]', post_url, query)
return False
raw_lyric = resp.decode('utf-8', 'ignore')
# if parsing rule changed, return debug info
if raw_lyric.find(u'歌詞ナビTOPページより') > 0:
self.lyric = '''
Site rule changed!
Please contact franklai
LoadVars::%s::myLoadVars
''' % (params['middle_value'])
return True
# else remove the useless part and return lyric
front_str = 'kashi='
start = raw_lyric.find(front_str) + len(front_str)
lyric = raw_lyric[start:]
lyric = lyric.strip()
self.lyric = lyric
return True
def get_song_id(self, url):
pattern = '/song/([0-9]+)'
song_id = common.get_first_group_by_pattern(url, pattern)
return song_id
