def search(self, artist, files=None):
if files is not None and self.searchby:
keywords = format_value(files[0], self.searchby)
else:
keywords = artist
keywords = re.sub(r'\s+', self._separator, keywords)
if self.search_source is None:
album = self.retrieve(keywords)
return [album] if album else []
url = self._search_base.replace('%s', keywords)
write_log(translate('Mp3tag', 'Retrieving search page: %s') % url)
set_status(translate('Mp3tag', 'Retrieving search page...'))
if self.html is None:
page = get_encoding(urlopen(url), True, 'utf8')[1]
else:
page = get_encoding(self.html, True, 'utf8')[1]
write_log(translate('Mp3tag', 'Parsing search page.'))
set_status(translate('Mp3tag', 'Parsing search page...'))
infos = parse_search_page(self.indexformat, page, self.search_source,
url)
return [(info, []) for info in infos]
def retrieve_album(url, coverurl=None, id_field=ALBUM_ID):
write_log('Opening Album Page - %s' % url)
album_page, code = urlopen(url, False, True)
if album_page.find("featured new releases") >= 0:
raise OldURLError("Old AMG URL used.")
album_page = get_encoding(album_page, True, 'utf8')[1]
info, tracks = parse_albumpage(album_page)
info['#albumurl'] = url
info['amg_url'] = url
if 'album' in info:
info['#extrainfo'] = [
info['album'] + u' at AllMusic.com', info['#albumurl']
]
if coverurl:
try:
write_log('Retrieving Cover - %s' % info['#cover-url'])
cover = retrieve_cover(info['#cover-url'])
except KeyError:
write_log('No cover found.')
cover = None
except urllib2.URLError, e:
write_log(u'Error: While retrieving cover %s - %s' %
(info['#cover-url'], unicode(e)))
cover = None
def retrieve_album(url, coverurl=None, id_field=ALBUM_ID):
write_log('Opening Album Page - %s' % url)
album_page, code = urlopen(url, False, True)
if album_page.find("featured new releases") >= 0:
raise OldURLError("Old AMG URL used.")
album_page = get_encoding(album_page, True, 'utf8')[1]
info, tracks = parse_albumpage(album_page)
info['#albumurl'] = url
info['amg_url'] = url
if 'album' in info:
info['#extrainfo'] = [
info['album'] + u' at AllMusic.com', info['#albumurl']]
if coverurl:
try:
write_log('Retrieving Cover - %s' % info['#cover-url'])
cover = retrieve_cover(info['#cover-url'])
except KeyError:
write_log('No cover found.')
cover = None
except urllib2.URLError, e:
write_log(u'Error: While retrieving cover %s - %s' %
(info['#cover-url'], unicode(e)))
cover = None
def search(self, artist, files=None):
if files is not None and self.searchby:
keywords = format_value(files[0], self.searchby)
else:
keywords = artist
keywords = re.sub('\s+', self._separator, keywords)
if self.search_source is None:
album = self.retrieve(keywords)
return [album] if album else []
url = self._search_base.replace(u'%s', keywords)
write_log(translate('Mp3tag', u'Retrieving search page: %s') % url)
set_status(translate('Mp3tag', u'Retrieving search page...'))
if self.html is None:
page = get_encoding(urlopen(url), True, 'utf8')[1]
else:
page = get_encoding(self.html, True, 'utf8')[1]
write_log(translate('Mp3tag', u'Parsing search page.'))
set_status(translate('Mp3tag', u'Parsing search page...'))
infos = parse_search_page(self.indexformat, page, self.search_source, url)
return [(info, []) for info in infos]
def parse_searchpage(page, artist=None, album=None, id_field=ALBUM_ID):
"""Parses a search page and gets relevant info.
Arguments:
page -- html string with search page's html.
artist -- artist to to check for in results. If found only results
with that artist are returned.
album -- album to check for in results. If found only results with
with the album are returned.
id_field -- key to use for the album id found.
Return a tuple with the first element being == True if the list
was truncated with only matching artist/albums.
"""
page = get_encoding(page, True, 'utf8')[1]
soup = parse_html.SoupWrapper(parse_html.parse(page))
result_table = soup.find('ul', {'class': 'search-results'})
try:
results = result_table.find_all('div', {'class': 'info'})
except AttributeError:
return []
albums = [parse_search_element(result) for result in results]
d = {}
if artist and album:
d = {'artist': artist, 'album': album}
top = [album for album in albums if equal(d, album, True)]
elif album:
d = {'album': album}
top = [album for album in albums if equal(d, album, True, ['album'])]
if not top:
top = [
album for album in albums if equal(d, album, False, ['album'])
]
elif artist:
d = {'artist': artist}
top = [album for album in albums if equal(d, album, True, ['artist'])]
if not ret:
top = [
album for album in albums if equal(d, album, False, ['artist'])
]
else:
top = []
return False, albums
def parse_searchpage(page, artist=None, album=None, id_field=ALBUM_ID):
"""Parses a search page and gets relevant info.
Arguments:
page -- html string with search page's html.
artist -- artist to to check for in results. If found only results
with that artist are returned.
album -- album to check for in results. If found only results with
with the album are returned.
id_field -- key to use for the album id found.
Return a tuple with the first element being == True if the list
was truncated with only matching artist/albums.
"""
page = get_encoding(page, True, 'utf8')[1]
soup = parse_html.SoupWrapper(parse_html.parse(page))
result_table = soup.find('ul', {'class': 'search-results'})
try:
results = result_table.find_all('div',
{'class': 'info'})
except AttributeError:
return []
albums = [parse_search_element(result) for result in results]
d = {}
if artist and album:
d = {'artist': artist, 'album': album}
top = [album for album in albums if equal(d, album, True)]
elif album:
d = {'album': album}
top = [album for album in albums if equal(d, album, True, ['album'])]
if not top:
top = [album for album in albums if
equal(d, album, False, ['album'])]
elif artist:
d = {'artist': artist}
top = [album for album in albums if equal(d, album, True, ['artist'])]
if not ret:
top = [album for album in albums if
equal(d, album, False, ['artist'])]
else:
top = []
return False, albums
def retrieve(self, info):
if isinstance(info, str):
text = info.replace(' ', self._separator)
info = {}
else:
info = deepcopy(info)
text = info['#url']
try:
url = self.album_url % text
except TypeError:
url = self.album_url + text
info['#url'] = url
try:
write_log(translate('Mp3tag', 'Retrieving album page: %s') % url)
set_status(translate('Mp3tag', 'Retrieving album page...'))
page = get_encoding(urlopen(url), True, 'utf8')[1]
except:
page = ''
write_log(translate('Mp3tag', 'Parsing album page.'))
set_status(translate('Mp3tag', 'Parsing album page...'))
new_info, tracks = parse_album_page(page, self.album_source, url)
info.update(dict((k, v) for k, v in new_info.items() if v))
if self._get_cover and COVER in info:
cover_url = new_info[COVER]
if isinstance(cover_url, str):
info.update(retrieve_cover(cover_url))
else:
info.update(list(map(retrieve_cover, cover_url)))
if not tracks:
tracks = None
return info, tracks
def retrieve(self, info):
if isinstance(info, basestring):
text = info.replace(u' ', self._separator)
info = {}
else:
info = deepcopy(info)
text = info['#url']
try:
url = self.album_url % text
except TypeError:
url = self.album_url + text
info['#url'] = url
try:
write_log(translate('Mp3tag', u'Retrieving album page: %s') % url)
set_status(translate('Mp3tag', u'Retrieving album page...'))
page = get_encoding(urlopen(url), True, 'utf8')[1]
except:
page = u''
write_log(translate('Mp3tag', u'Parsing album page.'))
set_status(translate('Mp3tag', u'Parsing album page...'))
new_info, tracks = parse_album_page(page, self.album_source, url)
info.update(dict((k,v) for k,v in new_info.iteritems() if v))
if self._get_cover and COVER in info:
cover_url = new_info[COVER]
if isinstance(cover_url, basestring):
info.update(retrieve_cover(cover_url))
else:
info.update(map(retrieve_cover, cover_url))
if not tracks:
tracks = None
return info, tracks
set_status('Retrieving album.')
write_log('Retrieving album.')
write_log('Album URL - %s' % albuminfo['#albumurl'])
url = albuminfo['#albumurl']
try:
if self._useid:
info, tracks, cover = retrieve_album(url, self._getcover)
else:
info, tracks, cover = retrieve_album(url, self._getcover)
except urllib.error.URLError as e:
write_log('Error: While retrieving album URL %s - %s' %
(url, str(e)))
raise RetrievalError(str(e))
if cover:
info.update(cover)
albuminfo = albuminfo.copy()
albuminfo.update(info)
return albuminfo, tracks
def applyPrefs(self, args):
self._getcover = args[0]
self._useid = args[1]
info = AllMusic
if __name__ == '__main__':
f = get_encoding(open(sys.argv[1], 'r').read(), True)[1]
x = parse_albumpage(f)
print(x)
except KeyError:
set_status('Retrieving album.')
write_log('Retrieving album.')
write_log('Album URL - %s' % albuminfo['#albumurl'])
url = albuminfo['#albumurl']
try:
if self._useid:
info, tracks, cover = retrieve_album(url, self._getcover)
else:
info, tracks, cover = retrieve_album(url, self._getcover)
except urllib2.URLError, e:
write_log(u'Error: While retrieving album URL %s - %s' %
(url, unicode(e)))
raise RetrievalError(unicode(e))
if cover:
info.update(cover)
albuminfo = albuminfo.copy()
albuminfo.update(info)
return albuminfo, tracks
def applyPrefs(self, args):
self._getcover = args[0]
self._useid = args[1]
info = AllMusic
if __name__ == '__main__':
f = get_encoding(open(sys.argv[1], 'r').read(), True)[1]
x = parse_albumpage(f)
print x
