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
| #-*- coding: utf-8 -*-
import os
import requests
from bs4 import BeautifulSoup
import random
from faker import Factory
import Queue
import threading
fake = Factory.create()
luoo_site = 'http://www.luoo.net/music/'
luoo_site_mp3 = 'http://luoo-mp3.kssws.ks-cdn.com/low/luoo/radio%s/%s.mp3'
headers = {'Connection': 'keep-alive',
'User-Agent': fake.user_agent()
}
def random_proxies():
ip_index = random.randint(0, len(proxy_ips)-1)
res = { 'http': proxy_ips[ip_index] }
return res
def fix_characters(s):
for c in ['<', '>', ':', '"', '/', '\\\\', '|', '?', '*']:
s = s.replace(c, '')
return s
class LuooSpider(threading.Thread):
def __init__(self, url, vols, queue=None):
threading.Thread.__init__(self)
print '[luoo spider]'
print '=' * 20
self.url = url
self.queue = queue
self.vol = '1'
self.vols = vols
def run(self):
for vol in self.vols:
self.spider(vol)
print '\\ncrawl end\\n\\n'
def spider(self, vol):
url = luoo_site + vol
print 'crawling: ' + url + '\\n'
res = requests.get(url, proxies=random_proxies())
soup = BeautifulSoup(res.content, 'html.parser')
title = soup.find('span', attrs={'class': 'vol-title'}).text
cover = soup.find('img', attrs={'class': 'vol-cover'})['src']
desc = soup.find('div', attrs={'class': 'vol-desc'})
track_names = soup.find_all('a', attrs={'class': 'trackname'})
track_count = len(track_names)
tracks = []
for track in track_names:
_id = str(int(track.text[:2])) if (int(vol) < 12) else track.text[:2]
_name = fix_characters(track.text[4:])
tracks.append({'id': _id, 'name': _name})
phases = {
'phase': vol, # 期刊编号
'title': title, # 期刊标题
'cover': cover, # 期刊封面
'desc': desc, # 期刊描述
'track_count': track_count, # 节目数
'tracks': tracks # 节目清单(节目编号，节目名称)
}
self.queue.put(phases)
class LuooDownloader(threading.Thread):
def __init__(self, url, dist, queue=None):
threading.Thread.__init__(self)
self.url = url
self.queue = queue
self.dist = dist
self.__counter = 0
def run(self):
while True:
if self.queue.qsize() <= 0:
pass
else:
phases = self.queue.get()
self.download(phases)
def download(self, phases):
for track in phases['tracks']:
file_url = self.url % (phases['phase'], track['id'])
local_file_dict = '%s/%s' % (self.dist, phases['phase'])
if not os.path.exists(local_file_dict):
os.makedirs(local_file_dict)
local_file = '%s/%s.%s.mp3' % (local_file_dict, track['id'], track['name'])
if not os.path.isfile(local_file):
print 'downloading: ' + track['name']
res = requests.get(file_url, proxies=random_proxies(), headers=headers)
with open(local_file, 'wb') as f:
f.write(res.content)
f.close()
print 'done.\\n'
else:
print 'break: ' + track['name']
if __name__ == '__main__':
spider_queue = Queue.Queue()
luoo = LuooSpider(luoo_site, vols=['680', '721', '725', '720'],queue=spider_queue)
luoo.setDaemon(True)
luoo.start()
downloader_count = 5
for i in range(downloader_count):
luoo_download = LuooDownloader(luoo_site_mp3, '/home/luoo', queue=spider_queue)
luoo_download.setDaemon(True)
luoo_download.start()
|
