class LocalCoverSource(Source):
def __init__(self, args):
self.root = expanduser(expandvars(args["root"]))
Logger("coverfetcher").info("Created LocalCoverSource. Root={}",
self.root)
self.logger = Logger("coverfetcher.local")
COVER_FILENAMES = (
"cover.jpg",
"cover.png",
"folder.jpg",
"folder.png",
)
def _parse_file_path(self, albuminfo):
if "file" not in albuminfo:
return None
# Handle mopidy library file paths
file = albuminfo["file"]
if file.startswith("local:track:"):
file = unquote(re.sub("^local:track:", "", file))
u = urlparse(file)
if u.scheme == "":
return u.path if isabs(u.path) else join(self.root, u.path)
elif u.scheme == "file":
return unquote(u.path)
else:
self.logger.warning("Unknown URI scheme: {}. Ignoring it.", u)
# TODO: log warning
return None
def fetch(self, albuminfo):
path = self._parse_file_path(albuminfo)
if not path:
return None
dirpath = dirname(path)
for path in [join(dirpath, n) for n in self.COVER_FILENAMES]:
if isfile(path):
with open(path, "rb") as f:
self.logger.debug("Found cover: {}", path)
return {"extension": splitext(path)[1][1:],
"bytedata": f.read()}
return None
def __init__(self, args):
self.root = expanduser(expandvars(args["root"]))
Logger("coverfetcher").info("Created LocalCoverSource. Root={}",
self.root)
self.logger = Logger("coverfetcher.local")
def __init__(self, args):
Logger("coverfetcher").info("Created WikipediaCoverSource")
self.logger = Logger("coverfetcher.wiki")
class WikipediaCoverSource(Source):
def __init__(self, args):
Logger("coverfetcher").info("Created WikipediaCoverSource")
self.logger = Logger("coverfetcher.wiki")
DBPEDIA_URL = 'http://dbpedia.org/sparql'
WIKIPEDIA_URL = 'http://en.wikipedia.org/w/api.php'
SPARQL_QUERY = '''PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX dbpprop: <http://dbpedia.org/property/>
PREFIX owl: <http://dbpedia.org/ontology/>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT ?coverFilename WHERE {{
?subject dbpprop:name ?name .
?subject rdfs:label ?label .
{{ ?subject dbpprop:artist ?artist }}
UNION
{{ ?subject owl:artist ?artist }}
{{ ?artist rdfs:label "{artist}"@en }}
UNION
{{ ?artist dbpprop:name "{artist}"@en }}
?subject rdf:type <http://dbpedia.org/ontology/Album> .
?subject dbpprop:cover ?coverFilename .
FILTER ( regex(?name, "{album}", "i") )
}}
Limit 1'''
def get_url(self, albuminfo):
# Find the name of the cover art filename on DBpedia
cover_filename = None
dbpedia_response = requests.get(
self.DBPEDIA_URL,
params={
'format': 'application/sparql-results+json',
'timeout': 2500,
'query': self.SPARQL_QUERY.format(artist=albuminfo["artist"],
album=albuminfo["album"])
}, headers={'content-type': 'application/json'})
try:
data = dbpedia_response.json()
results = data['results']['bindings']
if results:
cover_filename = results[0]['coverFilename']['value']
self.logger.debug("Found album: %s" % cover_filename)
else:
self.logger.debug("Album not found on dbpedia") # TODO
except:
self.logger.error("Error scraping dbpedia album page")
# Ensure we have a filename before attempting to query wikipedia
if not cover_filename:
return None
# Find the absolute url of the cover art on Wikipedia
wikipedia_response = requests.get(self.WIKIPEDIA_URL, params={
'format': 'json',
'action': 'query',
'continue': '',
'prop': 'imageinfo',
'iiprop': 'url',
'titles': ('File:' + cover_filename).encode('utf-8')},
headers={'content-type': 'application/json'})
try:
data = wikipedia_response.json()
results = data['query']['pages']
for _, result in results.items():
image_url = result['imageinfo'][0]['url']
return image_url
except:
self.logger.error("Error scraping wikipedia imageinfo")
return None
def fetch(self, albuminfo):
url = self.get_url(albuminfo)
if url:
extension = url.split(".")[-1].lower()
bytedata = read(url)
return {"extension": extension, "bytedata": bytedata}
return None
