這是一個簡單的Python腳本，主要從懶人圖庫下載JavaScript特效模板，在腳本中使用了gevent這個第三方庫，使用的時候需要先安裝。
|
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
|
#!/usr/bin/python# -*- coding: utf-8 -*- import urllib,os,sysimport gevent,refrom gevent import monkeyfrom bs4 import BeautifulSoupgevent.monkey.patch_socket() '''Description：Python 爬蟲抓取懶人圖庫的JS腳本模板Author：adminCreate-Date：2015-05-25Version：1.0''' HTTP_URL = 'http://www.lanrentuku.com%s'DOWNLOAD_URL = HTTP_URL[:-2] + '/js/d%szip'reg=r'\d{1,}\.+' def encode(text): return text.encode("utf8") def createDirectory(curPath): myPath = os.path.join(getSubDirectory(), u'JS代碼模板') if not os.path.exists(myPath): os.mkdir(myPath) return os.path.join(myPath, curPath) def getSubDirectory(): return os.getcwd() def schedule(a, b, c): per = 100.0 * a * b / c if per > 100 : per = 100 sys.stdout.write('%.1f%%\r' % per) sys.stdout.flush() def geturllist(url): url_list = {} html = urllib.urlopen(url) content = html.read() html.close() # 用BeautifulSoup解析 decodeHtml = BeautifulSoup(content) try: aTags = decodeHtml.find_all('div', {'class':'list-pngjs'})[0].find_all('a') except IndexError, e: print e aTags = None # 獲取鏈接地址和標題 if aTags is not None: for a_tag in aTags: url_list[HTTP_URL % a_tag.get('href')] = a_tag.get_text() return url_list def download(down_url): try: m=re.search(reg,down_url[0]) name = DOWNLOAD_URL % m.group(0) urllib.urlretrieve(name,createDirectory(down_url[1] + name[-4:]),schedule) except Exception, e: print e.message def getpageurl(xUrl): # 進行列表頁循環(huán) return [xUrl % page for page in xrange(1,49)] if __name__ == '__main__': jobs = [] pageurl = getpageurl('http://www.lanrentuku.com/js/p%s.html') # 爬取所有鏈接 for i in pageurl: for k in geturllist(i).items(): jobs.append(gevent.spawn(download, k)) gevent.joinall(jobs) |
以上所述就是本文的全部內容了，希望大家能夠喜歡。
