Python现在非常火,语法简单而且功能强大,很多同学都想学Python!所以小的给各位看官们准备了高价值Python学习视频教程及相关电子版书籍,欢迎前来领取!
爬虫脚本把这个小说网上的几乎所有小说都下载到了本地,一共27000+本小说,一共40G。
完整代码:
#coding=utf-8
2 import urllib
3 import urllib2
4 import re
5 import os
6
7 webroot = 'http://www.xuanshu.com'
8
9 for page in range(20,220):
10 print '正在下载第'+str(page)+'页小说'
11
12 url = 'http://www.xuanshu.com/soft/sort02/index_'+str(page)+'.html'
13 headers = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6' }
14 try:
15 request = urllib2.Request(url,headers=headers)
16 response = urllib2.urlopen(request,timeout=180)
17 #print response.read()
18 except urllib2.URLError, e:
19 if hasattr(e,"code"):
20 print e.code
21 if hasattr(e,"reason"):
22 print e.reason
23
24 html = response.read().decode('utf-8')
25 #print html
26 pattern = re.compile(u'<li>.*?<div class="s">.*?target="_blank">(.*?)</a><br />大小:(.*?)<br>.*?</em><br>更新:(.*?)</div>.*?<a href="(.*?)"><img.*?>(.*?)</a>.*?<div class="u">(.*?)</div>',re.S)
27 items = re.findall(pattern,html)
28 #print items
29
30 for item in items:
31 try:
32 book_auther = item[0].encode('gbk')
33 book_size = item[1].encode('gbk')
34 book_updatetime = item[2].encode('gbk')
35 book_link = item[3].encode('gbk')
36 book_name = item[4].encode('gbk')
37 book_note = item[5].encode('gbk')
38
39 book_full_link = webroot + book_link # 构建书的绝对地址
40
41 #请求地址
42 try:
43 request = urllib2.Request(book_full_link,headers=headers)
44 response = urllib2.urlopen(request,timeout=180)
45 except urllib2.URLError, e:
46 if hasattr(e,"code"):
47 print e.code
48 if hasattr(e,"reason"):
49 print e.reason
50 html = response.read().decode('utf-8')
51 #print html
52 pattern = re.compile('<a class="downButton.*?<a class="downButton" href=\'(.*?)\'.*?Txt.*?</a>',re.S)
53 down_link = re.findall(pattern,html)
54 print book_name
55 print down_link
56
57 # down txt
58 try:
59 request = urllib2.Request(down_link[0].encode('utf-8'),headers=headers)
60 response = urllib2.urlopen(request,timeout=180)
61 except urllib2.URLError, e:
62 if hasattr(e,"code"):
63 print e.code
64 if hasattr(e,"reason"):
65 print e.reason
66 try:
67 fp = open(book_name+'.txt','w')
68 except IOError,e:
69 pattern = re.compile('<strong>.*?>(.*?)<.*?</strong>',re.S)
70 book_name = re.findall(pattern,book_name)
71 fp = open(book_name[0]+'.txt','w')
72 print 'start download'
73 fp.write(response.read())
74 print 'down finish\n'
75 fp.close()
76 except Exception,e:
77 print '该条目解析出现错误,忽略'
78 print e
79 print ''
80 fp = open('error.log','a')
81 fp.write('page:'+str(page)+'\n')
82 fp.write(item[4].encode('gbk'))
83 #fp.write(e)
84 fp.write('\nThere is an error in parsing process.\n\n')
85 fp.close()
该脚本只定向抓取“选书网”小说站,“玄幻奇幻”分类下的小说。供网友们参考,可自行修改。
写得比较粗糙,勿喷……
·END·