本文實例講述了Python實現(xiàn)提取谷歌音樂搜索結(jié)果的方法。分享給大家供大家參考。具體如下：
Python的簡單腳本，用于提取谷歌音樂搜索頁面中的歌曲信息，包括歌曲名，作者，專輯名，現(xiàn)在鏈接等，最多只提取10頁結(jié)果。
|
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
|
#! /usr/bin/env python#coding=utf-8'''Created on 2011-8-19@author: yaoboyuan'''from urllib import request,parseimport re,sysdef extractSongRawData(text): '抓取每一首歌的原始數(shù)據(jù)' text = re.sub('\n+','',text) songList = re.findall('\<tbody.*?\</tbody>',text) nums = len(songList) print('search ' + str(nums) + ' songs') return songListdef translate(text): '去掉text中的無用字符，轉(zhuǎn)換unicode碼' text = re.sub('\<b>','',text) text = re.sub('\</b>','',text) #find the 成 and translate into chinese s = re.findall('&#([0-9]+);',text) if len(s)<=0: return text else: text = '' for i in range(len(s)): value = int(s[i],10) #from str'123' to 10 base's int 124 text += chr(value) #from value to char return textdef extractSongName(song): '提取歌曲名字' td = re.findall('(?:\<td class\="Title).*(?:\</td>)',song) name = re.findall('.+?\<a.+?>(.*?)\</a>',td[0]) songName = translate(name[0]) return songNamedef extractAuthorName(song): '提取作者名字' td = re.findall('(?:\<td class\="Artist).*(?:\</td>)',song) name = re.findall('.+?\<a.+?>(.*?)\</a>',td[0]) authorName = name[0] authorName = translate(authorName) return authorNamedef extrackAlbumName(song): '提取專輯名字' td = re.findall('(?:\<td class\="Album).*(?:\</td>)',song) name = re.findall('.+?\<a.+?>(.*?)\</a>',td[0]) albumName = translate(name[0]) return albumNamedef extractID(song): '提取歌曲id' td = re.findall('''\<tbody id\="([a-zA-Z0-9]+)"''',song) if len(td)>0: return td[0] else: return songdef extractLink(song): '提取歌曲下載鏈接' td = re.findall('''\<td class\="Icon.*?(?=title\="下載").*?onclick\="(.*?)>''',song) if len(td) == 0: return 'NULL' s = str(td[0]) rawLink = re.findall('http.*?(?=\?)',s) if len(rawLink) == 0: return s link = rawLink[0] link = re.sub('%3D','=',link) id = extractID(song) return link + '?id=' + iddef extractPageNums(text): '提取返回結(jié)果的頁數(shù)，最多要10頁' pageList = re.findall('page_link',text) return len(pageList)def extractSongInfo(song): '提取歌曲信息，返回歌曲列表' songList = [] for i in range(len(song)): songName = extractSongName(song[i]) authorName = extractAuthorName(song[i]) albumName = extrackAlbumName(song[i]) link = extractLink(song[i]) songItem = [songName,authorName,albumName,link] songList.append(songItem) index = '' if i<9: index = '0' + str(i+1) else: index = str(i + 1) #print(index + ' ' + songName + ' ' + authorName + ' ' + albumName + ' ' + link) return songListdef main(): while True: url = 'http://www.google.cn/music/search?q=' key = input('請輸入歌曲名字或關(guān)鍵字:') key = parse.quote(key) #統(tǒng)一編碼成utf-8 url += key mf = request.urlopen(url) c = mf.readall() c = str(c,encoding = 'utf-8') num = extractPageNums(c) print(str(num+1) + ' pages found') song = extractSongRawData(c) songList = extractSongInfo(song) #if the result great than 2 pages, then request all pages if num>0: for i in range(num): start = (i+1)*20 next_page = '&cat=song&start=%d'%(start) #next_page = parse.quote(next_page) #統(tǒng)一編碼成utf-8 url += next_page mf = request.urlopen(url) c = mf.readall() c = str(c,encoding = 'utf-8') song = extractSongRawData(c) songList += extractSongInfo(song) #find all results for i in range(len(songList)): #print the result index = '' if i<9: index = '0' + str(i+1) else: index = str(i + 1) print(index + ' ' + str(songList[i]))if __name__ == '__main__': main() |
希望本文所述對大家的Python程序設(shè)計有所幫助。
