def download_link(self) -> str:
""" :returns: link where the file awaits to be downloaded """
data = Request.get(self.url).content
soup = BeautifulSoup(data, "html.parser")
track_meta = json.loads(BandcampJSON(soup).generate()[0])
if track_meta['trackinfo'][0]['file'] is None:
raise ValueError("could not find mp3 in %s" % self.url)
return "https:" + track_meta['trackinfo'][0]['file']['mp3-128']
def parse(self, url: str, art: bool=True, lyrics: bool=False, debugging: bool=False) -> dict or None:
"""Requests the page, cherry picks album info
:param url: album/track url
:param art: if True download album art
:param lyrics: if True fetch track lyrics
:param debugging: if True then verbose output
:return: album metadata
"""
if debugging:
logging.basicConfig(level=logging.DEBUG)
try:
response = requests.get(url, headers=self.headers)
except requests.exceptions.MissingSchema:
return None
try:
self.soup = BeautifulSoup(response.text, "lxml")
except FeatureNotFound:
self.soup = BeautifulSoup(response.text, "html.parser")
logging.debug(" Generating BandcampJSON..")
bandcamp_json = BandcampJSON(self.soup, debugging).generate()
album_json = json.loads(bandcamp_json[0])
embed_json = json.loads(bandcamp_json[1])
page_json = json.loads(bandcamp_json[2])
logging.debug(" BandcampJSON generated..")
logging.debug(" Generating Album..")
self.tracks = album_json['trackinfo']
album_release = album_json['album_release_date']
if album_release is None:
album_release = album_json['current']['release_date']
try:
album_title = embed_json['album_title']
except KeyError:
album_title = album_json['trackinfo'][0]['title']
try:
label = page_json['item_sellers']['{}'.format(album_json['current']['selling_band_id'])]['name']
except KeyError:
label = None
album = {
"tracks": [],
"title": album_title,
"artist": embed_json['artist'],
"label": label,
"full": False,
"art": "",
"date": str(dt.strptime(album_release, "%d %b %Y %H:%M:%S GMT").year),
"url":url
}
artist_url = album_json['url'].rpartition('/album/')[0]
for track in self.tracks:
if lyrics:
track['lyrics'] = self.get_track_lyrics("{}{}#lyrics".format(artist_url, track['title_link']))
if track['file'] is not None:
track = self.get_track_metadata(track)
album['tracks'].append(track)
album['full'] = self.all_tracks_available()
if art:
album['art'] = self.get_album_art()
logging.debug(" Album generated..")
print("ALBUM URL:", album["url"])
return album
def parse(self, url: str, art: bool = True) -> dict or None:
"""Requests the page, cherry picks album info
:param url: album/track url
:param art: if True download album art
:return: album metadata
"""
try:
response = requests.get(url)
except requests.exceptions.MissingSchema:
return None
try:
self.soup = BeautifulSoup(response.text, "lxml")
except FeatureNotFound:
self.soup = BeautifulSoup(response.text, "html.parser")
logger.debug('\n\tBeautifulSoup: {}\n'.format(self.soup))
bandcamp_json = BandcampJSON(self.soup).generate()
album_json = json.loads(bandcamp_json[0])
embed_json = json.loads(bandcamp_json[1])
page_json = json.loads(bandcamp_json[2])
self.tracks = album_json['trackinfo']
album_release = album_json['album_release_date']
if album_release is None:
album_release = album_json['current']['release_date']
try:
album_title = embed_json['album_title']
except KeyError:
album_title = album_json['trackinfo'][0]['title']
try:
label = page_json['item_sellers']['{}'.format(
album_json['current']['selling_band_id'])]['name']
except KeyError:
label = None
album = {
"tracks": [],
"title": album_title,
"artist": embed_json['artist'],
"label": label,
"full": False,
"art": "",
"date":
str(dt.strptime(album_release, "%d %b %Y %H:%M:%S GMT").year)
}
for track in self.tracks:
if track['file'] is not None:
track = self.get_track_metadata(track)
album['tracks'].append(track)
album['full'] = self.all_tracks_available()
if art:
album['art'] = self.get_album_art()
return album