def search_song(self,
song_title="",
band_name="",
album_type="any",
excluded_album_types=None):
params = dict(bandName=band_name, songTitle=song_title)
url = self.site_url + self.url_search_songs
data = requests.get(url,
params=params,
headers={
'User-Agent': get_random_user_agent()
}).json()
songs = data['aaData']
excluded_album_types = excluded_album_types or []
for song in songs:
if album_type != "any":
if song[2] != album_type:
continue
if song[2] in excluded_album_types:
continue
data = {
"album_url":
song[0][song[0].find('href="') + 6:song[0].find('" title=')],
"band_name":
song[0][song[0].find('>') + 1:song[0].find('</a')],
"album_name":
song[1][song[1].find('">') + 2:song[1].find('</a')],
"album_type":
song[2],
"song_name":
song[3],
"song_id":
self.lyric_id_re.search(song[4]).group("id")
}
yield data
def search_band(self, band_name="", genre="", index=0):
params = dict(bandName=band_name, genre=genre, iDisplayStart=index)
url = self.site_url + self.url_search_bands
data = requests.get(url,
params=params,
headers={
'User-Agent': get_random_user_agent()
}).json()
bands, num = data['aaData'], data["iTotalRecords"]
for band in bands:
data = {
"url": band[0][band[0].find('href="') + 6:band[0].find('">')],
"name": band[0][band[0].find('">') + 2:band[0].find('</a>')],
"genre": band[1],
"country": band[2]
}
yield data
def get_band_data(url):
result = {}
response = requests.get(
url, headers={'User-Agent': get_random_user_agent()})
tree = html.fromstring(response.content)
result["name"] = \
tree.xpath('//*[@id="band_info"]/h1/a/text()')
result["url"] = \
tree.xpath('//*[@id="band_info"]/h1/a/@href')
result["genre"] = \
tree.xpath(".//*[@id='band_stats']/dl[2]/dd[1]/text()")
result["theme"] = \
tree.xpath(".//*[@id='band_stats']/dl[2]/dd[2]/text()")
result["label"] = \
tree.xpath(".//*[@id='band_stats']/dl[2]/dd[3]/text()")
result["country"] = \
tree.xpath(".//*[@id='band_stats']/dl[1]/dd[1]/a/text()")
result["location"] = \
tree.xpath(".//*[@id='band_stats']/dl[1]/dd[2]/text()")
result["status"] = \
tree.xpath(".//*[@id='band_stats']/dl[1]/dd[3]/text()")
result["date"] = \
tree.xpath(".//*[@id='band_stats']/dl[1]/dd[4]/text()")
years_active = \
tree.xpath(".//*[@id='band_stats']/dl[3]/dd/text()")
# result["years"] = years_active[0]
for r in result.keys():
if isinstance(result[r], list) and len(result[r]) == 1:
result[r] = result[r][0]
elif isinstance(result[r], list) and len(result[r]) == 0:
result[r] = None
if isinstance(result[r], str) and result[r] == 'N/A':
result[r] = None
if r == "years":
if "," in result[r]:
years = result[r].split(",")
result[r] = [y.rstrip().lstrip() for y in years]
else:
result[r] = [result[r].rstrip().lstrip()]
if r == "theme" and result[r] is not None:
result[r] = result[r].split(",")
return result
def get_lyrics_by_song_id(self, song_id):
url = self.site_url + self.url_lyrics + song_id
data = requests.get(url,
headers={'User-Agent': get_random_user_agent()})
lyrics = self.tags_re.sub('', data.text.strip())
return lyrics