def parse_cdbaby_album(album_id):
url = 'http://www.cdbaby.com/cd/%s' % (album_id,)
page = fetch_page(url, html=True)
release = {}
album = guess_case_title(page.find('span', {'id': 'ctl00_rightColumn_lblAlbumName'}).text)
album_id = extract_album_id(url)
artist = guess_case(page.find('div', {'id': 'ctl00_rightColumn_pnlArtists'}).find('span').text)
artist_id = extract_artist_id(page.find('a', {'id': 'ctl00_breadCrumb_lnkArtist'})['href'])
barcode = page.find('span', {'id': 'ctl00_rightColumn_lblBarcode'})
if barcode:
barcode = extract_barcode(barcode.text)
release_date = int(page.find('span', {'id': 'ctl00_leftColumn_lblAlbumRelease'}).text)
record_label = page.find('span', {'id': 'ctl00_rightColumn_lblRecordLabel'})
if record_label:
record_label = re.sub(r'^Record Label: ', '', record_label.text)
if artist.lower() == record_label.lower():
record_label = None
release = {
'cdbaby_id': album_id,
'title': album,
'artist': artist,
'artist_cdbaby_id': artist_id,
'barcode': barcode,
'date': str(release_date),
}
if record_label:
release['label'] = record_label
medium = {
'position': 1,
'tracks': [],
}
release['mediums'] = [medium]
for tr in page.find('table', {'id': 'tracks-display'}).findAll('tr'):
tds = tr.findAll('td')
if len(tds) != 4:
continue
track_no, track_title = parse_track_title(tds[1].text)
track_length = parse_track_length(tds[2].find('span').text)
medium['tracks'].append({
'position': track_no,
'title': track_title,
'length': track_length,
})
if page.find('input', {'class': 'cd-buynow-button'}):
medium['format'] = 'CD'
else:
medium['format'] = 'Digital Media'
return release
def parse_track_title(s):
m = re.match(r'^(\d+). (.+)$', s)
track_no, track_title = m.groups()
return int(track_no), guess_case_title(track_title)
