def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
title_tags = soup.find_all(is_entry_title)
regex = re.compile(ur'^(.*)\u2013(.*)$')
for title in title_tags:
title_text = title.a.text
matches = regex.findall(title_text)
if len(matches) == 0 or len(matches[0])<2:
print '\tno matches...?', matches
continue
artist = matches[0][0].strip()
album = matches[0][1].strip()
if album.lower() == 's/t' or album.lower() == 'self-titled':
album = artist
# print '\t', 'FOUND:', artist, '>', album
songs = []
albums = spotifier.fetch_album(album)
for album in albums:
album_artist = album['artist']
if album_artist.lower() != artist.lower():
continue
album_id = album['id']
tracks = spotifier.get_album_tracks(album_id)
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
print "{}: {}".format(album_artist, album['name'])
break
page_title = 'DOA'
return songs, page_title
def parse_for_songs(url):
r = requests.get(url)
soup = BeautifulSoup(r.content)
trs = soup.find_all('tr')
songs = []
for tr in trs:
row_raw_text = [text for text in tr.stripped_strings]
index = 0
# print row_raw_text
if len(row_raw_text) >=3:
artist = row_raw_text[1].encode('ascii', errors='replace').strip()
album = row_raw_text[2].encode('ascii', errors='replace').strip()
albums = spotifier.fetch_album(album)
for album in albums:
if not 'artist' in album:
continue
album_artist = album['artist']
if album_artist.lower() != artist.lower():
continue
album_id = album['id']
tracks = spotifier.get_album_tracks(album_id)
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
print "{}: {}".format(album_artist, album['name'])
break
page_title = 'KEXP'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
band_text = band.text.strip()
band_names = band_text.split(',')
for band_name in band_names:
#print band_name
band_name = band_name.strip()
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print 'Band: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'U_STREET'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
# print band
band_name_raw = band.text
if band_name_raw == 'Tickets' or band_name_raw == 'More Info':
continue
band_names = [name.strip() for name in band_name_raw.split(',')]
# artists = spotifier.fetch_artist(band_name)
# print artists
for band_name in band_names:
print band_name
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
# print 'Found {} albums'.format(len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'CATSCRADLE'
return songs, page_title
def parse_for_songs(url):
songs = []
page_title = 'skinny'
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
title_tags = soup.find_all(is_review_title)
for title in title_tags:
title_text = [text for text in title.stripped_strings]
regex = re.compile(ur'^(.*)\u2013(.*)$')
matches = regex.findall(title_text[0])
if len(matches) < 1 or len(matches[0]) < 2:
continue
artist = matches[0][0].strip()
album = matches[0][1].strip()
print artist, '>', album
albums = spotifier.fetch_album(album)
for album in albums:
album_artist = album['artist']
if album_artist.lower() != artist.lower():
continue
album_id = album['id']
tracks = spotifier.get_album_tracks(album_id)
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
band_text = band.text.strip()
band_names = band_text.split('|')
for band_name in band_names:
# print band_name
band_name = band_name.strip()
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print 'Band: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'ROCK_HOTEL'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
# print band
band_name_raw = band.text
if band_name_raw == 'Tickets' or band_name_raw =='More Info':
continue
band_names = [name.strip() for name in band_name_raw.split(',')]
# artists = spotifier.fetch_artist(band_name)
# print artists
for band_name in band_names:
print band_name
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
# print 'Found {} albums'.format(len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'CATSCRADLE'
return songs, page_title
def parse_for_songs(url):
songs = []
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
title_tags = soup.find_all(href=re.compile("/reviews/albums"))
for title_tag in title_tags:
matches = [text for text in title_tag.stripped_strings]
if len(matches)<2:
continue
artist = matches[0].encode('ascii', errors='replace').strip()
album = matches[1].encode('ascii', errors='replace').strip()
# print '\t', 'FOUND:', artist, '>', album
albums = spotifier.fetch_album(album)
for album in albums:
"""
if not 'artist' in album:
print "%s does NOT have key 'artist'" % str(album)
continue
album_artist = album['artist']
if album_artist.lower() != artist.lower():
continue
"""
album_id = album['id']
tracks = spotifier.get_album_tracks(album_id)
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
print "{}: {}".format(artist, album['name'])
break
page_title = 'PITCHFORK'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
title_tags = soup.find_all(is_entry_title)
regex = re.compile(ur'^(.*)\u2013(.*)$')
for title in title_tags:
title_text = title.a.text
matches = regex.findall(title_text)
if len(matches) == 0 or len(matches[0]) < 2:
print '\tno matches...?', matches
continue
artist = matches[0][0].strip()
album = matches[0][1].strip()
if album.lower() == 's/t' or album.lower() == 'self-titled':
album = artist
# print '\t', 'FOUND:', artist, '>', album
songs = []
albums = spotifier.fetch_album(album)
for album in albums:
album_artist = album['artist']
if album_artist.lower() != artist.lower():
continue
album_id = album['id']
tracks = spotifier.get_album_tracks(album_id)
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
print "{}: {}".format(album_artist, album['name'])
break
page_title = 'DOA'
return songs, page_title
def parse_for_songs(url):
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band)
songs = []
bands = []
for tag in band_tags:
band_name = tag.text.strip()
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print '\tBand: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'ROCKNESS'
return songs, page_title
def parse_for_songs(url):
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band)
songs = []
bands = []
for tag in band_tags:
band_name = tag.text.strip()
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print '\tBand: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'SXSW'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
cleaned_band_names = []
for band in band_tags:
band_text = band.text.strip()
band_names = band_text.split(',')
cleaned_band_names.extend(band_names)
for band_name in band_names:
band_name = band_name.strip()
if band_name.startswith('and '):
band_name = band_name[4:]
band_name = band_name.replace('(Record Release)', '')
band_name = band_name.strip()
cleaned_band_names.append(band_name)
more_names = band_name.split('w/')
for new_one in more_names:
cleaned_band_names.append(new_one)
#print '\t' + new_one
for band_name in set(cleaned_band_names):
band_name = band_name.strip()
#print band_name
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print '\tBand: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'COMET'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
cleaned_band_names = []
for band in band_tags:
band_text = band.text.strip()
band_names = band_text.split(',')
cleaned_band_names.extend(band_names)
for band_name in band_names:
band_name = band_name.strip()
if band_name.startswith('and '):
band_name = band_name[4:]
band_name = band_name.replace('(Record Release)', '')
band_name = band_name.strip()
cleaned_band_names.append(band_name)
more_names = band_name.split('w/')
for new_one in more_names:
cleaned_band_names.append(new_one)
#print '\t' + new_one
for band_name in set(cleaned_band_names):
band_name = band_name.strip()
#print band_name
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
print '\tBand: {} -- Found {} albums'.format(band_name, len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'COMET'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
band_name = band.text
#print band_name
# artists = spotifier.fetch_artist(band_name)
# print artists
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
# print 'Found {} albums'.format(len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'BLACKCAT'
return songs, page_title
def parse_for_songs(url):
print 'Getting songs from ', url
r = requests.get(url)
soup = BeautifulSoup(r.content)
band_tags = soup.find_all(is_band_tag)
songs = []
for band in band_tags:
band_name = band.text
#print band_name
# artists = spotifier.fetch_artist(band_name)
# print artists
albums = spotifier.get_albums_for_artist(band_name)
if len(albums) == 0:
continue
# print 'Found {} albums'.format(len(albums))
for album in albums:
tracks = spotifier.get_album_tracks(album['id'])
if len(tracks) < 1:
continue
songs.append({'uri': tracks[0]['uri']})
break
page_title = 'BLACKCAT'
return songs, page_title