写爬虫是一项复杂、枯噪、反复的工作,考虑的问题包括采集效率、链路异常处理、数据质量(与站点编码规范关系很大)等。整理自己写一个爬虫程序,单台服务器可以启用1~8个实例同时采集,然后将数据入库。
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
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
|
#-*- coding:utf-8 -*- #!/usr/local/bin/python import sys, time, os,string import mechanize import urlparse from BeautifulSoup import BeautifulSoup import re import MySQLdb import logging import cgi from optparse import OptionParser #----------------------------------------------------------------------------# # Name: TySpider.py # # Purpose: WebSite Spider Module # # Author: 刘天斯 # # Email: liutiansi@gamil.com # # Created: 2010/02/16 # # Copyright: (c) 2010 # #----------------------------------------------------------------------------# """ |-------------------------------------------------------------------------- | 定义 loging class; |-------------------------------------------------------------------------- | | 功能:记录系统相关日志信息。 | | """ class Pubclilog(): def __init__( self ): self .logfile = 'website_log.txt' def iniLog( self ): logger = logging.getLogger() filehandler = logging.FileHandler( self .logfile) streamhandler = logging.StreamHandler() fmt = logging.Formatter( '%(asctime)s, %(funcName)s, %(message)s' ) logger.setLevel(logging.DEBUG) logger.addHandler(filehandler) logger.addHandler(streamhandler) return [logger,filehandler] """ |-------------------------------------------------------------------------- | 定义 tySpider class; |-------------------------------------------------------------------------- | | 功能:抓取分类、标题等信息 | | """ class BaseTySpider: #初始化相关成员方法 def __init__( self ,X,log_switch): #数据库连接 self .conn = MySQLdb.connect(db = 'dbname' ,host = '192.168.0.10' , user = 'dbuser' ,passwd = 'SDFlkj934y5jsdgfjh435' ,charset = 'utf8' ) #分类及标题页面Community self .CLASS_URL = 'http://test.abc.com/aa/CommTopicsPage?' #发表回复页 self .Content_URL = 'http://test.bac.com/aa/CommMsgsPage?' #开始comm值 self .X = X #当前comm id取模,方面平均到表 self .mod = self .X % 5 #Community文件下载页 self .body = "" #self.bodySoup对象 self .soup = None #发表回复页下载内容变量 self .Contentbody = "" #发表回复页内容self.ContentbodySoup对象 self .Contentsoup = None #日志开关 self .log_switch = log_switch #======================获取名称及分类方法========================== def _SpiderClass( self ,nextpage = None ): if nextpage = = None : FIXED_QUERY = 'cmm=' + str ( self .X) else : FIXED_QUERY = nextpage[ 1 :] try : rd = mechanize.Browser() rd.addheaders = [( "User-agent" , "Tianya/2010 (compatible; MSIE 6.0;Windows NT 5.1)" )] rd. open ( self .CLASS_URL + FIXED_QUERY) self .body = rd.response().read() #rd=mechanize.Request(self.CLASS_URL + FIXED_QUERY) #response = mechanize.urlopen(rd) #self.body=response.read() except Exception,e: if self .log_switch = = "on" : logapp = Pubclilog() logger,hdlr = logapp.iniLog() logger.info( self .CLASS_URL + FIXED_QUERY + str (e)) hdlr.flush() logger.removeHandler(hdlr) return self .soup = BeautifulSoup( self .body) NextPageObj = self .soup( "a" , { 'class' : re. compile ( "fs-paging-item fs-paging-next" )}) self .cursor = self .conn.cursor() if nextpage = = None : try : Ttag = str ( self .soup.table) #print Ttag """ ------------------分析结构体----------------- <table cellspacing="0" cellpadding="0"> <tr> <td> <h1 id="codetool">
相关文章
热门资讯 |