Spaces:
Running
Running
Commit
•
610e92c
1
Parent(s):
dd7b091
Upload azapi.py
Browse files
azapi.py
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from .requester import Requester
|
2 |
+
from .tools import *
|
3 |
+
|
4 |
+
class AZlyrics(Requester):
|
5 |
+
"""
|
6 |
+
Fast and Secure API for AZLyrics.com.
|
7 |
+
|
8 |
+
Attributes:
|
9 |
+
title (str): song title.
|
10 |
+
artist (str): artist name.
|
11 |
+
search_engine (str): search engine used to assist scraping lyrics.
|
12 |
+
- currently available: 'google', 'duckduckgo'.
|
13 |
+
accuracy (float): used to determine accuracy via jaro algorithm.
|
14 |
+
proxies (dict): if you want to use proxy while connecting to 'AZLyrics.com'.
|
15 |
+
"""
|
16 |
+
|
17 |
+
def __init__(self, search_engine='', accuracy=0.6, proxies={}):
|
18 |
+
self.title = ''
|
19 |
+
self.artist = ''
|
20 |
+
self.search_engine = search_engine
|
21 |
+
|
22 |
+
self.accuracy = accuracy
|
23 |
+
if not 0 < accuracy <= 1:
|
24 |
+
self.accuracy = 0.6
|
25 |
+
|
26 |
+
self.proxies = proxies
|
27 |
+
|
28 |
+
self.lyrics_history = []
|
29 |
+
self.lyrics = ''
|
30 |
+
self.songs = {}
|
31 |
+
|
32 |
+
def getLyrics(self, url=None, ext='txt', save=False, path='', sleep=3):
|
33 |
+
"""
|
34 |
+
Retrieve Lyrics for a given song details.
|
35 |
+
|
36 |
+
Parameters:
|
37 |
+
url (str): url of the song's Azlyrics page.
|
38 |
+
ext (str): extension of the lyrics saved file, default is ".txt".
|
39 |
+
save (bool): allow to or not to save lyrics in a file.
|
40 |
+
sleep (float): cooldown before next request.
|
41 |
+
|
42 |
+
Returns:
|
43 |
+
lyrics (str): Lyrics of the detected song.
|
44 |
+
"""
|
45 |
+
|
46 |
+
# Best cooldown is 5 sec
|
47 |
+
time.sleep(sleep)
|
48 |
+
|
49 |
+
link = url
|
50 |
+
|
51 |
+
if not url:
|
52 |
+
# v3.0.5: No need for artist and title if url is found
|
53 |
+
if not self.artist + self.title:
|
54 |
+
raise ValueError("Both artist and title can't be empty!")
|
55 |
+
if self.search_engine:
|
56 |
+
# If user can't remember the artist,
|
57 |
+
# he can search by title only
|
58 |
+
|
59 |
+
# Get AZlyrics url via Google Search
|
60 |
+
link = googleGet(
|
61 |
+
self.search_engine,
|
62 |
+
self.accuracy,
|
63 |
+
self.get,
|
64 |
+
self.artist,
|
65 |
+
self.title,
|
66 |
+
0,
|
67 |
+
self.proxies
|
68 |
+
)
|
69 |
+
if not link:
|
70 |
+
return 0
|
71 |
+
else:
|
72 |
+
# Sometimes search engines block you
|
73 |
+
# If happened use the normal get method
|
74 |
+
link = normalGet(
|
75 |
+
self.artist,
|
76 |
+
self.title,
|
77 |
+
0)
|
78 |
+
|
79 |
+
page = self.get(link, self.proxies)
|
80 |
+
if page.status_code != 200:
|
81 |
+
if not self.search_engine:
|
82 |
+
print('Failed to find lyrics. Trying to get link from Google')
|
83 |
+
self.search_engine = 'google'
|
84 |
+
lyrics = self.getLyrics(url=url, ext=ext, save=save, path=path, sleep=sleep)
|
85 |
+
self.search_engine = ''
|
86 |
+
return lyrics
|
87 |
+
else:
|
88 |
+
print('Error',page.status_code)
|
89 |
+
return 1
|
90 |
+
|
91 |
+
# Getting Basic metadata from azlyrics
|
92 |
+
metadata = [elm.text for elm in htmlFindAll(page)('b')]
|
93 |
+
|
94 |
+
# if metadata is empty, then it's not a valid page
|
95 |
+
if not metadata:
|
96 |
+
print('Error', 'no metadata')
|
97 |
+
return 1
|
98 |
+
|
99 |
+
# v3.0.4: Update title and artist attributes with exact names
|
100 |
+
self.artist = filtr(metadata[0][:-7], True)
|
101 |
+
self.title = filtr(metadata[1][1:-1], True)
|
102 |
+
|
103 |
+
lyrics = parseLyric(page)
|
104 |
+
self.lyrics = lyrics.strip()
|
105 |
+
|
106 |
+
# Saving Lyrics
|
107 |
+
if lyrics:
|
108 |
+
if save:
|
109 |
+
# v3.0.2: Adding custom path
|
110 |
+
p = os.path.join(
|
111 |
+
path,
|
112 |
+
'{} - {}.{}'.format(
|
113 |
+
self.title.title(),
|
114 |
+
self.artist.title(),
|
115 |
+
ext
|
116 |
+
)
|
117 |
+
)
|
118 |
+
|
119 |
+
with open(p, 'w', encoding='utf-8') as f:
|
120 |
+
f.write(lyrics.strip())
|
121 |
+
|
122 |
+
# Store lyrics for later usage
|
123 |
+
self.lyrics_history.append(self.lyrics)
|
124 |
+
return self.lyrics
|
125 |
+
|
126 |
+
self.lyrics = 'No lyrics found :('
|
127 |
+
return 2
|
128 |
+
|
129 |
+
def getSongs(self, sleep=3):
|
130 |
+
"""
|
131 |
+
Retrieve a dictionary of songs with their links.
|
132 |
+
|
133 |
+
Parameters:
|
134 |
+
sleep (float): cooldown before next request.
|
135 |
+
|
136 |
+
Returns:
|
137 |
+
dict: dictionary of songs with their links.
|
138 |
+
"""
|
139 |
+
|
140 |
+
if not self.artist:
|
141 |
+
raise Exception("Artist can't be empty!")
|
142 |
+
|
143 |
+
# Best cooldown is 5 sec
|
144 |
+
time.sleep(sleep)
|
145 |
+
|
146 |
+
if self.search_engine:
|
147 |
+
link = googleGet(
|
148 |
+
self.search_engine,
|
149 |
+
self.accuracy,
|
150 |
+
self.get,
|
151 |
+
self.artist,
|
152 |
+
'',
|
153 |
+
1,
|
154 |
+
self.proxies
|
155 |
+
)
|
156 |
+
if not link:
|
157 |
+
return {}
|
158 |
+
else:
|
159 |
+
link = normalGet(
|
160 |
+
self.artist,
|
161 |
+
'',
|
162 |
+
1)
|
163 |
+
|
164 |
+
albums_page = self.get(link, self.proxies)
|
165 |
+
if albums_page.status_code != 200:
|
166 |
+
if not self.search_engine:
|
167 |
+
print('Failed to find songs. Trying to get link from Google')
|
168 |
+
self.search_engine = 'google'
|
169 |
+
songs = self.getLyrics(sleep=sleep)
|
170 |
+
self.search_engine = ''
|
171 |
+
return songs
|
172 |
+
else:
|
173 |
+
print('Error',albums_page.status_code)
|
174 |
+
return {}
|
175 |
+
|
176 |
+
# Store songs for later usage
|
177 |
+
self.songs = parseSongs(albums_page)
|
178 |
+
return self.songs
|