Python抓取网易云 歌词，热评，热评用户的头像

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
import requests
import json
import os
from urllib.request import urlretrieve
def GetConment(kw):
url = 'http://120.79.36.48/search?keywords=%20'+kw
resp = requests.get(url)
resp.encoding = 'utf8'
hjson = resp.json()
# if
not 'songs' in hjson:
#
return 'No Lyric'
songs = []
for x in range(0,len(hjson['result']['songs'])):
# print(hjson['result']['songs'][x]['id'])
songs.append(hjson['result']['songs'][x]['id'])
# print(songs)
if len(songs)==0:
return 'No Songs'
cnt = 0
for s in songs:
commenturl = 'http://120.79.36.48/comment/music?id='+str(s)+'&limit=1'
# print(liricsurl)
r = requests.get(commenturl)
r.encoding = 'utf8'
json = r.json()
comment = json['hotComments']
for i in range(0,len(comment)-1):
print('『'+str(cnt)+'』'+comment[i]['content'])
cnt = cnt +1
print(comment[i]['user']['avatarUrl'])
# cont = cont + comment[i]['content']
def DawnloadHeader(kw):
url = 'http://120.79.36.48/search?keywords=%20'+kw
resp = requests.get(url)
resp.encoding = 'utf8'
hjson = resp.json()
# if
not 'songs' in hjson:
#
return 'No Lyric'
songs = []
for x in range(0,len(hjson['result']['songs'])):
# print(hjson['result']['songs'][x]['id'])
songs.append(hjson['result']['songs'][x]['id'])
# print(songs)
if len(songs)==0:
return 'No Songs'
cnt = 0
dirname = kw+'Header'
if not os.path.exists(dirname):
os.makedirs(dirname)
for s in songs:
commenturl = 'http://120.79.36.48/comment/music?id='+str(s)+'&limit=1'
# print(liricsurl)
r = requests.get(commenturl)
r.encoding = 'utf8'
json = r.json()
comment = json['hotComments']
for i in range(0,len(comment)-1):
print('正在下载：'+comment[i]['user']['avatarUrl'])
filename=os.path.join(dirname,str(cnt)+comment[i]['user']['nickname']+'.jpg')
with open(filename,'w') as f:
urlretrieve(comment[i]['user']['avatarUrl'],filename)
cnt = cnt +1
print('已下载完！')
def Getlirics(kw,cnt):
url = 'http://120.79.36.48/search?keywords=%20'+kw
resp = requests.get(url)
resp.encoding = 'utf8'
hjson = resp.json()
# if
not 'songs' in hjson:
#
return 'No Lyric'
songs = []
for x in range(0,cnt):
# print(hjson['result']['songs'][x]['id'])
songs.append(hjson['result']['songs'][x]['id'])
# print(songs)
if len(songs)==0:
return 'No Lyric'
lir = ''
for s in songs:
liricsurl = 'http://120.79.36.48/lyric?id='+str(s)
# print(liricsurl)
r = requests.get(liricsurl)
r.encoding = 'utf8'
json = r.json()
lyric = json['lrc']['lyric']
lyricUser = 'No User'
if 'lyricUser' in json:
lyricUser = json['lyricUser']['nickname']
# print('['+lyricUser+']n'+lyric)
lir = lir + '『'+lyricUser+'』n'+lyric+'n'
if lir == '':
return ''
return lir
DawnloadHeader('你的名字')