質問編集履歴
1
追記しました
test
CHANGED
File without changes
|
test
CHANGED
@@ -37,3 +37,1333 @@
|
|
37
37
|
tmpファイルは作成されていてその中にコメントは入っています。
|
38
38
|
|
39
39
|
他にも気になる部分があればお尋ねください
|
40
|
+
|
41
|
+
|
42
|
+
|
43
|
+
### 追記
|
44
|
+
|
45
|
+
編集できる事については初めて知りましたありがとうございます。
|
46
|
+
|
47
|
+
|
48
|
+
|
49
|
+
エラーが起こった部分は
|
50
|
+
|
51
|
+
```
|
52
|
+
|
53
|
+
cmnd = ['./CatFiles.sh', tmpHeadFile, tmpMainFile, headlessFile, pediLogFileName]
|
54
|
+
|
55
|
+
```
|
56
|
+
|
57
|
+
だと思います
|
58
|
+
|
59
|
+
|
60
|
+
|
61
|
+
コードは以下の通りです
|
62
|
+
|
63
|
+
```
|
64
|
+
|
65
|
+
# coding: UTF-8
|
66
|
+
|
67
|
+
|
68
|
+
|
69
|
+
import requests
|
70
|
+
|
71
|
+
|
72
|
+
|
73
|
+
from bs4 import BeautifulSoup
|
74
|
+
|
75
|
+
|
76
|
+
|
77
|
+
import re
|
78
|
+
|
79
|
+
|
80
|
+
|
81
|
+
from time import sleep
|
82
|
+
|
83
|
+
|
84
|
+
|
85
|
+
from pprint import pprint
|
86
|
+
|
87
|
+
|
88
|
+
|
89
|
+
import os.path
|
90
|
+
|
91
|
+
|
92
|
+
|
93
|
+
from datetime import datetime, timedelta, timezone
|
94
|
+
|
95
|
+
|
96
|
+
|
97
|
+
import subprocess
|
98
|
+
|
99
|
+
|
100
|
+
|
101
|
+
import sys
|
102
|
+
|
103
|
+
|
104
|
+
|
105
|
+
import shutil
|
106
|
+
|
107
|
+
|
108
|
+
|
109
|
+
from functools import partial
|
110
|
+
|
111
|
+
|
112
|
+
|
113
|
+
|
114
|
+
|
115
|
+
|
116
|
+
|
117
|
+
RES_IN_SINGLEPAGE = 30
|
118
|
+
|
119
|
+
|
120
|
+
|
121
|
+
LOG_STORE_DIRECTORY = 'logs'
|
122
|
+
|
123
|
+
|
124
|
+
|
125
|
+
SCRAPING_INTERVAL_TIME = 3
|
126
|
+
|
127
|
+
|
128
|
+
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
|
133
|
+
|
134
|
+
|
135
|
+
|
136
|
+
|
137
|
+
NICOPEDI_URL_HEAD_A = "https://dic.nicovideo.jp/a/"
|
138
|
+
|
139
|
+
|
140
|
+
|
141
|
+
|
142
|
+
|
143
|
+
|
144
|
+
|
145
|
+
|
146
|
+
|
147
|
+
|
148
|
+
|
149
|
+
def CheckCreateDirectory(location, dirName) :
|
150
|
+
|
151
|
+
|
152
|
+
|
153
|
+
|
154
|
+
|
155
|
+
|
156
|
+
|
157
|
+
relativePath = location + '/' + dirName
|
158
|
+
|
159
|
+
|
160
|
+
|
161
|
+
|
162
|
+
|
163
|
+
|
164
|
+
|
165
|
+
if not os.path.exists(relativePath) :
|
166
|
+
|
167
|
+
|
168
|
+
|
169
|
+
|
170
|
+
|
171
|
+
|
172
|
+
|
173
|
+
os.mkdir(relativePath)
|
174
|
+
|
175
|
+
|
176
|
+
|
177
|
+
# print('Create',relativePath)
|
178
|
+
|
179
|
+
|
180
|
+
|
181
|
+
|
182
|
+
|
183
|
+
|
184
|
+
|
185
|
+
return relativePath
|
186
|
+
|
187
|
+
|
188
|
+
|
189
|
+
|
190
|
+
|
191
|
+
|
192
|
+
|
193
|
+
|
194
|
+
|
195
|
+
|
196
|
+
|
197
|
+
def GetSearchTargetURLs(baseURL, latestId) :
|
198
|
+
|
199
|
+
|
200
|
+
|
201
|
+
|
202
|
+
|
203
|
+
|
204
|
+
|
205
|
+
pageUrls = []
|
206
|
+
|
207
|
+
|
208
|
+
|
209
|
+
|
210
|
+
|
211
|
+
|
212
|
+
|
213
|
+
|
214
|
+
|
215
|
+
|
216
|
+
|
217
|
+
tgtPage = requests.get(baseURL)
|
218
|
+
|
219
|
+
|
220
|
+
|
221
|
+
soup = BeautifulSoup(tgtPage.content, "html.parser")
|
222
|
+
|
223
|
+
|
224
|
+
|
225
|
+
|
226
|
+
|
227
|
+
|
228
|
+
|
229
|
+
|
230
|
+
|
231
|
+
|
232
|
+
|
233
|
+
if not soup.find('div', class_='st-pg_contents') :
|
234
|
+
|
235
|
+
|
236
|
+
|
237
|
+
print_red('Nothing any response in this article.', is_bold=True)
|
238
|
+
|
239
|
+
|
240
|
+
|
241
|
+
return None
|
242
|
+
|
243
|
+
|
244
|
+
|
245
|
+
|
246
|
+
|
247
|
+
|
248
|
+
|
249
|
+
|
250
|
+
|
251
|
+
|
252
|
+
|
253
|
+
if soup.find('a', class_='navi') :
|
254
|
+
|
255
|
+
|
256
|
+
|
257
|
+
|
258
|
+
|
259
|
+
|
260
|
+
|
261
|
+
soup.find('a', class_='navi').decompose()
|
262
|
+
|
263
|
+
|
264
|
+
|
265
|
+
|
266
|
+
|
267
|
+
|
268
|
+
|
269
|
+
|
270
|
+
|
271
|
+
|
272
|
+
|
273
|
+
pagers = soup.select("div.st-pg_contents")
|
274
|
+
|
275
|
+
|
276
|
+
|
277
|
+
|
278
|
+
|
279
|
+
|
280
|
+
|
281
|
+
|
282
|
+
|
283
|
+
|
284
|
+
|
285
|
+
pager = pagers[0]
|
286
|
+
|
287
|
+
|
288
|
+
|
289
|
+
|
290
|
+
|
291
|
+
|
292
|
+
|
293
|
+
|
294
|
+
|
295
|
+
|
296
|
+
|
297
|
+
pager = pager.getText()
|
298
|
+
|
299
|
+
|
300
|
+
|
301
|
+
|
302
|
+
|
303
|
+
|
304
|
+
|
305
|
+
|
306
|
+
|
307
|
+
|
308
|
+
|
309
|
+
splitedTxt = pager.strip()
|
310
|
+
|
311
|
+
|
312
|
+
|
313
|
+
|
314
|
+
|
315
|
+
|
316
|
+
|
317
|
+
splitedTxts = splitedTxt.split('\n')
|
318
|
+
|
319
|
+
|
320
|
+
|
321
|
+
|
322
|
+
|
323
|
+
|
324
|
+
|
325
|
+
txts = []
|
326
|
+
|
327
|
+
|
328
|
+
|
329
|
+
|
330
|
+
|
331
|
+
|
332
|
+
|
333
|
+
|
334
|
+
|
335
|
+
|
336
|
+
|
337
|
+
for txt in splitedTxts :
|
338
|
+
|
339
|
+
|
340
|
+
|
341
|
+
v = re.sub(r'\D', '', txt)
|
342
|
+
|
343
|
+
|
344
|
+
|
345
|
+
if v == '' : continue
|
346
|
+
|
347
|
+
|
348
|
+
|
349
|
+
txts.append(int(v))
|
350
|
+
|
351
|
+
|
352
|
+
|
353
|
+
|
354
|
+
|
355
|
+
|
356
|
+
|
357
|
+
|
358
|
+
|
359
|
+
|
360
|
+
|
361
|
+
if len(txts) == 0 :
|
362
|
+
|
363
|
+
|
364
|
+
|
365
|
+
print('Nothing any response to get.')
|
366
|
+
|
367
|
+
|
368
|
+
|
369
|
+
return None
|
370
|
+
|
371
|
+
|
372
|
+
|
373
|
+
|
374
|
+
|
375
|
+
|
376
|
+
|
377
|
+
|
378
|
+
|
379
|
+
|
380
|
+
|
381
|
+
# print(len(txts), txts[-1])
|
382
|
+
|
383
|
+
|
384
|
+
|
385
|
+
finalPage = int((txts[-1] - 1) / RES_IN_SINGLEPAGE)
|
386
|
+
|
387
|
+
|
388
|
+
|
389
|
+
finalPage += 1
|
390
|
+
|
391
|
+
|
392
|
+
|
393
|
+
|
394
|
+
|
395
|
+
|
396
|
+
|
397
|
+
|
398
|
+
|
399
|
+
|
400
|
+
|
401
|
+
startPage = latestId // RES_IN_SINGLEPAGE
|
402
|
+
|
403
|
+
|
404
|
+
|
405
|
+
|
406
|
+
|
407
|
+
|
408
|
+
|
409
|
+
|
410
|
+
|
411
|
+
|
412
|
+
|
413
|
+
baseBbsUrl = baseURL.replace('/a/', '/b/a/')
|
414
|
+
|
415
|
+
|
416
|
+
|
417
|
+
|
418
|
+
|
419
|
+
|
420
|
+
|
421
|
+
print(startPage * RES_IN_SINGLEPAGE, 'To', finalPage * RES_IN_SINGLEPAGE)
|
422
|
+
|
423
|
+
|
424
|
+
|
425
|
+
# pprint(txts)
|
426
|
+
|
427
|
+
|
428
|
+
|
429
|
+
|
430
|
+
|
431
|
+
|
432
|
+
|
433
|
+
|
434
|
+
|
435
|
+
|
436
|
+
|
437
|
+
for i in range(startPage, finalPage) :
|
438
|
+
|
439
|
+
|
440
|
+
|
441
|
+
pageNum = i * RES_IN_SINGLEPAGE + 1
|
442
|
+
|
443
|
+
|
444
|
+
|
445
|
+
pageUrl = baseBbsUrl + '/' + str(pageNum) + '-'
|
446
|
+
|
447
|
+
|
448
|
+
|
449
|
+
pageUrls.append(pageUrl)
|
450
|
+
|
451
|
+
|
452
|
+
|
453
|
+
|
454
|
+
|
455
|
+
|
456
|
+
|
457
|
+
|
458
|
+
|
459
|
+
|
460
|
+
|
461
|
+
estSec = len(pageUrls) * SCRAPING_INTERVAL_TIME
|
462
|
+
|
463
|
+
|
464
|
+
|
465
|
+
estMin = estSec // 60
|
466
|
+
|
467
|
+
|
468
|
+
|
469
|
+
estHrs = estMin // 60
|
470
|
+
|
471
|
+
|
472
|
+
|
473
|
+
|
474
|
+
|
475
|
+
|
476
|
+
|
477
|
+
estSec = str(estSec) + 's / '
|
478
|
+
|
479
|
+
|
480
|
+
|
481
|
+
estMin = str(estMin) + 'm / '
|
482
|
+
|
483
|
+
|
484
|
+
|
485
|
+
estHrs = str(estHrs) + 'h'
|
486
|
+
|
487
|
+
|
488
|
+
|
489
|
+
|
490
|
+
|
491
|
+
|
492
|
+
|
493
|
+
print('Minimum estimation time =', estSec, estMin, estHrs)
|
494
|
+
|
495
|
+
|
496
|
+
|
497
|
+
|
498
|
+
|
499
|
+
|
500
|
+
|
501
|
+
return pageUrls
|
502
|
+
|
503
|
+
|
504
|
+
|
505
|
+
|
506
|
+
|
507
|
+
|
508
|
+
|
509
|
+
|
510
|
+
|
511
|
+
def GetAllResInPage(tgtUrl) :
|
512
|
+
|
513
|
+
|
514
|
+
|
515
|
+
|
516
|
+
|
517
|
+
|
518
|
+
|
519
|
+
r = requests.get(tgtUrl)
|
520
|
+
|
521
|
+
|
522
|
+
|
523
|
+
|
524
|
+
|
525
|
+
|
526
|
+
|
527
|
+
|
528
|
+
|
529
|
+
|
530
|
+
|
531
|
+
soup = BeautifulSoup(r.content, "html.parser")
|
532
|
+
|
533
|
+
|
534
|
+
|
535
|
+
|
536
|
+
|
537
|
+
|
538
|
+
|
539
|
+
|
540
|
+
|
541
|
+
|
542
|
+
|
543
|
+
resheads = soup.find_all("dt", class_="st-bbs_reshead")
|
544
|
+
|
545
|
+
|
546
|
+
|
547
|
+
resbodys = soup.find_all("dd", class_="st-bbs_resbody")
|
548
|
+
|
549
|
+
|
550
|
+
|
551
|
+
|
552
|
+
|
553
|
+
|
554
|
+
|
555
|
+
formattedHead = []
|
556
|
+
|
557
|
+
|
558
|
+
|
559
|
+
formattedBody = []
|
560
|
+
|
561
|
+
|
562
|
+
|
563
|
+
resCount = 0
|
564
|
+
|
565
|
+
|
566
|
+
|
567
|
+
|
568
|
+
|
569
|
+
|
570
|
+
|
571
|
+
|
572
|
+
|
573
|
+
|
574
|
+
|
575
|
+
for rhead in resheads:
|
576
|
+
|
577
|
+
|
578
|
+
|
579
|
+
h = rhead
|
580
|
+
|
581
|
+
|
582
|
+
|
583
|
+
|
584
|
+
|
585
|
+
|
586
|
+
|
587
|
+
|
588
|
+
|
589
|
+
|
590
|
+
|
591
|
+
hObj = BeautifulSoup(str(h), 'html.parser')
|
592
|
+
|
593
|
+
|
594
|
+
|
595
|
+
|
596
|
+
|
597
|
+
|
598
|
+
|
599
|
+
|
600
|
+
|
601
|
+
|
602
|
+
|
603
|
+
bbs_resNo = hObj.find('span', class_='st-bbs_resNo').getText()
|
604
|
+
|
605
|
+
|
606
|
+
|
607
|
+
bbs_name = hObj.find('span', class_='st-bbs_name').getText()
|
608
|
+
|
609
|
+
|
610
|
+
|
611
|
+
bbs_resInfo = hObj.find('div', class_='st-bbs_resInfo').getText()
|
612
|
+
|
613
|
+
|
614
|
+
|
615
|
+
|
616
|
+
|
617
|
+
bbs_resInfo = bbs_resInfo.strip()
|
618
|
+
|
619
|
+
|
620
|
+
|
621
|
+
bbs_resInfo = bbs_resInfo.strip('\n')
|
622
|
+
|
623
|
+
|
624
|
+
|
625
|
+
bbs_resInfo = bbs_resInfo.replace('\n', ' ')
|
626
|
+
|
627
|
+
|
628
|
+
|
629
|
+
|
630
|
+
|
631
|
+
|
632
|
+
|
633
|
+
|
634
|
+
|
635
|
+
|
636
|
+
|
637
|
+
pattern = r' +'
|
638
|
+
|
639
|
+
|
640
|
+
|
641
|
+
bbs_resInfo = re.sub(pattern, ' ', bbs_resInfo)
|
642
|
+
|
643
|
+
|
644
|
+
|
645
|
+
# print(bbs_resNo, bbs_name, bbs_resInfo)
|
646
|
+
|
647
|
+
|
648
|
+
|
649
|
+
|
650
|
+
|
651
|
+
|
652
|
+
|
653
|
+
resHeaders = [bbs_resNo, bbs_name, bbs_resInfo]
|
654
|
+
|
655
|
+
|
656
|
+
|
657
|
+
h = ' '.join(resHeaders)
|
658
|
+
|
659
|
+
|
660
|
+
|
661
|
+
|
662
|
+
|
663
|
+
|
664
|
+
|
665
|
+
formattedHead.append(h)
|
666
|
+
|
667
|
+
|
668
|
+
|
669
|
+
|
670
|
+
|
671
|
+
|
672
|
+
|
673
|
+
|
674
|
+
|
675
|
+
|
676
|
+
|
677
|
+
for rbody in resbodys:
|
678
|
+
|
679
|
+
|
680
|
+
|
681
|
+
|
682
|
+
|
683
|
+
|
684
|
+
|
685
|
+
b = str(rbody)
|
686
|
+
|
687
|
+
|
688
|
+
|
689
|
+
b = b.replace("<br>", "\n")
|
690
|
+
|
691
|
+
|
692
|
+
|
693
|
+
b = b.replace("<br/>", "\n")
|
694
|
+
|
695
|
+
|
696
|
+
|
697
|
+
b = BeautifulSoup(b, "html.parser").getText()
|
698
|
+
|
699
|
+
|
700
|
+
|
701
|
+
|
702
|
+
|
703
|
+
|
704
|
+
|
705
|
+
b = b.strip()
|
706
|
+
|
707
|
+
|
708
|
+
|
709
|
+
b = b.strip('\n')
|
710
|
+
|
711
|
+
|
712
|
+
|
713
|
+
formattedBody.append(b)
|
714
|
+
|
715
|
+
|
716
|
+
|
717
|
+
|
718
|
+
|
719
|
+
|
720
|
+
|
721
|
+
resCount += 1
|
722
|
+
|
723
|
+
|
724
|
+
|
725
|
+
|
726
|
+
|
727
|
+
|
728
|
+
|
729
|
+
return resCount, formattedHead, formattedBody
|
730
|
+
|
731
|
+
|
732
|
+
|
733
|
+
|
734
|
+
|
735
|
+
|
736
|
+
|
737
|
+
|
738
|
+
|
739
|
+
|
740
|
+
|
741
|
+
def TeeOutput(text, file) :
|
742
|
+
|
743
|
+
|
744
|
+
|
745
|
+
# print(text + '\n', end="")
|
746
|
+
|
747
|
+
|
748
|
+
|
749
|
+
file.write(text + '\n')
|
750
|
+
|
751
|
+
|
752
|
+
|
753
|
+
return
|
754
|
+
|
755
|
+
|
756
|
+
|
757
|
+
|
758
|
+
|
759
|
+
|
760
|
+
|
761
|
+
|
762
|
+
|
763
|
+
|
764
|
+
|
765
|
+
def GetLatestID(fName):
|
766
|
+
|
767
|
+
|
768
|
+
|
769
|
+
try:
|
770
|
+
|
771
|
+
|
772
|
+
|
773
|
+
cmnd = ['head', '-1', fName]
|
774
|
+
|
775
|
+
|
776
|
+
|
777
|
+
subResult = subprocess.check_output(cmnd)
|
778
|
+
|
779
|
+
|
780
|
+
|
781
|
+
except:
|
782
|
+
|
783
|
+
|
784
|
+
|
785
|
+
print("Error.")
|
786
|
+
|
787
|
+
|
788
|
+
|
789
|
+
|
790
|
+
|
791
|
+
|
792
|
+
|
793
|
+
heads = subResult.split()
|
794
|
+
|
795
|
+
|
796
|
+
|
797
|
+
id = int(heads[2])
|
798
|
+
|
799
|
+
|
800
|
+
|
801
|
+
|
802
|
+
|
803
|
+
|
804
|
+
|
805
|
+
return id
|
806
|
+
|
807
|
+
|
808
|
+
|
809
|
+
|
810
|
+
|
811
|
+
|
812
|
+
|
813
|
+
|
814
|
+
|
815
|
+
|
816
|
+
|
817
|
+
def print_colored(code, text, is_bold=False):
|
818
|
+
|
819
|
+
|
820
|
+
|
821
|
+
if is_bold:
|
822
|
+
|
823
|
+
|
824
|
+
|
825
|
+
code = '1;%s' % code
|
826
|
+
|
827
|
+
|
828
|
+
|
829
|
+
|
830
|
+
|
831
|
+
|
832
|
+
|
833
|
+
print('\033[%sm%s\033[0m' % (code, text))
|
834
|
+
|
835
|
+
|
836
|
+
|
837
|
+
|
838
|
+
|
839
|
+
|
840
|
+
|
841
|
+
print_red = partial(print_colored, '31')
|
842
|
+
|
843
|
+
|
844
|
+
|
845
|
+
|
846
|
+
|
847
|
+
|
848
|
+
|
849
|
+
|
850
|
+
|
851
|
+
|
852
|
+
|
853
|
+
def IsValidURL(targetURL) :
|
854
|
+
|
855
|
+
|
856
|
+
|
857
|
+
isValid = targetURL.startswith(NICOPEDI_URL_HEAD_A)
|
858
|
+
|
859
|
+
|
860
|
+
|
861
|
+
return isValid
|
862
|
+
|
863
|
+
|
864
|
+
|
865
|
+
|
866
|
+
|
867
|
+
|
868
|
+
|
869
|
+
# メイン処理スタート -----------------------------------------------------------------
|
870
|
+
|
871
|
+
|
872
|
+
|
873
|
+
args=sys.argv
|
874
|
+
|
875
|
+
if len(args)<=1:
|
876
|
+
|
877
|
+
print_red('Nothing Target URL',is_bold=True)
|
878
|
+
|
879
|
+
sys.exit(0)
|
880
|
+
|
881
|
+
tgtArtUrl = args[1]
|
882
|
+
|
883
|
+
|
884
|
+
|
885
|
+
|
886
|
+
|
887
|
+
|
888
|
+
|
889
|
+
|
890
|
+
|
891
|
+
|
892
|
+
|
893
|
+
if not IsValidURL(tgtArtUrl) :
|
894
|
+
|
895
|
+
|
896
|
+
|
897
|
+
print_red('This is not valid URL.', is_bold=True)
|
898
|
+
|
899
|
+
|
900
|
+
|
901
|
+
print('Target URL should be under', NICOPEDI_URL_HEAD_A)
|
902
|
+
|
903
|
+
|
904
|
+
|
905
|
+
sys.exit(0)
|
906
|
+
|
907
|
+
|
908
|
+
|
909
|
+
|
910
|
+
|
911
|
+
|
912
|
+
|
913
|
+
|
914
|
+
|
915
|
+
|
916
|
+
|
917
|
+
logDir = CheckCreateDirectory('.', LOG_STORE_DIRECTORY)
|
918
|
+
|
919
|
+
|
920
|
+
|
921
|
+
|
922
|
+
|
923
|
+
|
924
|
+
|
925
|
+
|
926
|
+
|
927
|
+
|
928
|
+
|
929
|
+
art_req = requests.get(tgtArtUrl)
|
930
|
+
|
931
|
+
|
932
|
+
|
933
|
+
art_soup = BeautifulSoup(art_req.content, 'html.parser')
|
934
|
+
|
935
|
+
|
936
|
+
|
937
|
+
|
938
|
+
|
939
|
+
|
940
|
+
|
941
|
+
|
942
|
+
|
943
|
+
|
944
|
+
|
945
|
+
art_soup.find('span', class_='st-label_title-category').decompose()
|
946
|
+
|
947
|
+
|
948
|
+
|
949
|
+
|
950
|
+
|
951
|
+
|
952
|
+
|
953
|
+
art_soup.find('div', class_='a-title-yomi').decompose()
|
954
|
+
|
955
|
+
|
956
|
+
|
957
|
+
|
958
|
+
|
959
|
+
|
960
|
+
|
961
|
+
titleTxt = art_soup.find('div', class_='a-title')
|
962
|
+
|
963
|
+
|
964
|
+
|
965
|
+
|
966
|
+
|
967
|
+
|
968
|
+
|
969
|
+
|
970
|
+
|
971
|
+
|
972
|
+
|
973
|
+
pageTitle = titleTxt.getText()
|
974
|
+
|
975
|
+
|
976
|
+
|
977
|
+
|
978
|
+
|
979
|
+
pageTitle = pageTitle.strip()
|
980
|
+
|
981
|
+
|
982
|
+
|
983
|
+
pageTitle = pageTitle.strip('\n')
|
984
|
+
|
985
|
+
|
986
|
+
|
987
|
+
|
988
|
+
|
989
|
+
|
990
|
+
|
991
|
+
pageTitle = pageTitle.replace(' ', '_')
|
992
|
+
|
993
|
+
|
994
|
+
|
995
|
+
|
996
|
+
|
997
|
+
|
998
|
+
|
999
|
+
|
1000
|
+
|
1001
|
+
|
1002
|
+
|
1003
|
+
pediLogFileName = pageTitle + ".log"
|
1004
|
+
|
1005
|
+
|
1006
|
+
|
1007
|
+
pediLogFileName = logDir + '/' + pediLogFileName
|
1008
|
+
|
1009
|
+
|
1010
|
+
|
1011
|
+
|
1012
|
+
|
1013
|
+
|
1014
|
+
|
1015
|
+
|
1016
|
+
|
1017
|
+
|
1018
|
+
|
1019
|
+
JST = timezone(timedelta(hours=+9), 'JST')
|
1020
|
+
|
1021
|
+
|
1022
|
+
|
1023
|
+
now = datetime.now(JST)
|
1024
|
+
|
1025
|
+
|
1026
|
+
|
1027
|
+
nowstamp = str(now.timestamp()).replace('.','')
|
1028
|
+
|
1029
|
+
|
1030
|
+
|
1031
|
+
|
1032
|
+
|
1033
|
+
|
1034
|
+
|
1035
|
+
|
1036
|
+
|
1037
|
+
|
1038
|
+
|
1039
|
+
tmpDir = CheckCreateDirectory('.', nowstamp)
|
1040
|
+
|
1041
|
+
|
1042
|
+
|
1043
|
+
|
1044
|
+
|
1045
|
+
|
1046
|
+
|
1047
|
+
|
1048
|
+
|
1049
|
+
|
1050
|
+
|
1051
|
+
tmpMainFile = tmpDir + '/' + nowstamp + '.main' + '.tmp'
|
1052
|
+
|
1053
|
+
|
1054
|
+
|
1055
|
+
|
1056
|
+
|
1057
|
+
|
1058
|
+
|
1059
|
+
|
1060
|
+
|
1061
|
+
|
1062
|
+
|
1063
|
+
|
1064
|
+
|
1065
|
+
|
1066
|
+
|
1067
|
+
print('Output log file = [', pediLogFileName, ']')
|
1068
|
+
|
1069
|
+
|
1070
|
+
|
1071
|
+
|
1072
|
+
|
1073
|
+
|
1074
|
+
|
1075
|
+
|
1076
|
+
|
1077
|
+
|
1078
|
+
|
1079
|
+
if os.path.exists(pediLogFileName) :
|
1080
|
+
|
1081
|
+
|
1082
|
+
|
1083
|
+
|
1084
|
+
|
1085
|
+
|
1086
|
+
|
1087
|
+
print("Found log file.")
|
1088
|
+
|
1089
|
+
|
1090
|
+
|
1091
|
+
latestId = GetLatestID(pediLogFileName)
|
1092
|
+
|
1093
|
+
|
1094
|
+
|
1095
|
+
openMode = 'a'
|
1096
|
+
|
1097
|
+
|
1098
|
+
|
1099
|
+
shutil.copyfile(pediLogFileName, tmpMainFile)
|
1100
|
+
|
1101
|
+
|
1102
|
+
|
1103
|
+
else :
|
1104
|
+
|
1105
|
+
|
1106
|
+
|
1107
|
+
|
1108
|
+
|
1109
|
+
|
1110
|
+
|
1111
|
+
print("Not found log file.")
|
1112
|
+
|
1113
|
+
|
1114
|
+
|
1115
|
+
latestId = 0
|
1116
|
+
|
1117
|
+
|
1118
|
+
|
1119
|
+
openMode = 'w'
|
1120
|
+
|
1121
|
+
|
1122
|
+
|
1123
|
+
|
1124
|
+
|
1125
|
+
|
1126
|
+
|
1127
|
+
writer = open(tmpMainFile, openMode)
|
1128
|
+
|
1129
|
+
|
1130
|
+
|
1131
|
+
|
1132
|
+
|
1133
|
+
|
1134
|
+
|
1135
|
+
if openMode == 'w' : TeeOutput(pageTitle + '\n', writer)
|
1136
|
+
|
1137
|
+
|
1138
|
+
|
1139
|
+
writer.close()
|
1140
|
+
|
1141
|
+
|
1142
|
+
|
1143
|
+
|
1144
|
+
|
1145
|
+
|
1146
|
+
|
1147
|
+
|
1148
|
+
|
1149
|
+
|
1150
|
+
|
1151
|
+
targetURLs = GetSearchTargetURLs(tgtArtUrl, latestId)
|
1152
|
+
|
1153
|
+
|
1154
|
+
|
1155
|
+
|
1156
|
+
|
1157
|
+
|
1158
|
+
|
1159
|
+
|
1160
|
+
|
1161
|
+
|
1162
|
+
|
1163
|
+
|
1164
|
+
|
1165
|
+
|
1166
|
+
|
1167
|
+
|
1168
|
+
|
1169
|
+
|
1170
|
+
|
1171
|
+
if targetURLs == None :
|
1172
|
+
|
1173
|
+
|
1174
|
+
|
1175
|
+
sys.exit(0)
|
1176
|
+
|
1177
|
+
|
1178
|
+
|
1179
|
+
|
1180
|
+
|
1181
|
+
|
1182
|
+
|
1183
|
+
print('Progress ... ', end='', flush=True)
|
1184
|
+
|
1185
|
+
|
1186
|
+
|
1187
|
+
|
1188
|
+
|
1189
|
+
|
1190
|
+
|
1191
|
+
for url in targetURLs:
|
1192
|
+
|
1193
|
+
|
1194
|
+
|
1195
|
+
|
1196
|
+
|
1197
|
+
|
1198
|
+
|
1199
|
+
|
1200
|
+
|
1201
|
+
|
1202
|
+
|
1203
|
+
with open(tmpMainFile, 'a') as writer:
|
1204
|
+
|
1205
|
+
|
1206
|
+
|
1207
|
+
|
1208
|
+
|
1209
|
+
|
1210
|
+
|
1211
|
+
|
1212
|
+
|
1213
|
+
|
1214
|
+
|
1215
|
+
resCount, formattedHead, formattedBody = GetAllResInPage(url)
|
1216
|
+
|
1217
|
+
|
1218
|
+
|
1219
|
+
|
1220
|
+
|
1221
|
+
|
1222
|
+
|
1223
|
+
|
1224
|
+
|
1225
|
+
|
1226
|
+
|
1227
|
+
mark = (latestId % RES_IN_SINGLEPAGE)
|
1228
|
+
|
1229
|
+
|
1230
|
+
|
1231
|
+
|
1232
|
+
|
1233
|
+
|
1234
|
+
|
1235
|
+
|
1236
|
+
|
1237
|
+
|
1238
|
+
|
1239
|
+
|
1240
|
+
|
1241
|
+
|
1242
|
+
|
1243
|
+
for i in range(mark, resCount):
|
1244
|
+
|
1245
|
+
|
1246
|
+
|
1247
|
+
TeeOutput(formattedHead[i], writer)
|
1248
|
+
|
1249
|
+
|
1250
|
+
|
1251
|
+
TeeOutput(formattedBody[i], writer)
|
1252
|
+
|
1253
|
+
|
1254
|
+
|
1255
|
+
TeeOutput("", writer)
|
1256
|
+
|
1257
|
+
|
1258
|
+
|
1259
|
+
latestId += 1
|
1260
|
+
|
1261
|
+
|
1262
|
+
|
1263
|
+
|
1264
|
+
|
1265
|
+
|
1266
|
+
|
1267
|
+
|
1268
|
+
|
1269
|
+
|
1270
|
+
|
1271
|
+
|
1272
|
+
|
1273
|
+
|
1274
|
+
|
1275
|
+
|
1276
|
+
|
1277
|
+
|
1278
|
+
|
1279
|
+
print(latestId, end=' ', flush=True)
|
1280
|
+
|
1281
|
+
|
1282
|
+
|
1283
|
+
|
1284
|
+
|
1285
|
+
|
1286
|
+
|
1287
|
+
|
1288
|
+
|
1289
|
+
|
1290
|
+
|
1291
|
+
if url != targetURLs[-1] : sleep(SCRAPING_INTERVAL_TIME)
|
1292
|
+
|
1293
|
+
|
1294
|
+
|
1295
|
+
|
1296
|
+
|
1297
|
+
|
1298
|
+
|
1299
|
+
print()
|
1300
|
+
|
1301
|
+
|
1302
|
+
|
1303
|
+
|
1304
|
+
|
1305
|
+
|
1306
|
+
|
1307
|
+
|
1308
|
+
|
1309
|
+
|
1310
|
+
|
1311
|
+
tmpHeadFile = tmpDir + '/' + nowstamp + '.head' + '.tmp'
|
1312
|
+
|
1313
|
+
|
1314
|
+
|
1315
|
+
|
1316
|
+
|
1317
|
+
|
1318
|
+
|
1319
|
+
with open(tmpHeadFile, 'w') as writer:
|
1320
|
+
|
1321
|
+
|
1322
|
+
|
1323
|
+
metaInfo = [pageTitle, str(now.strftime("%Y-%m-%d/%H:%M")), str(latestId)]
|
1324
|
+
|
1325
|
+
|
1326
|
+
|
1327
|
+
metaInfoLine = ' '.join(metaInfo)
|
1328
|
+
|
1329
|
+
|
1330
|
+
|
1331
|
+
TeeOutput(metaInfoLine, writer)
|
1332
|
+
|
1333
|
+
|
1334
|
+
|
1335
|
+
|
1336
|
+
|
1337
|
+
|
1338
|
+
|
1339
|
+
headlessFile = tmpDir + '/' + 'headless' + '.tmp'
|
1340
|
+
|
1341
|
+
|
1342
|
+
|
1343
|
+
cmnd = ['./CatFiles.sh', tmpHeadFile, tmpMainFile, headlessFile, pediLogFileName]
|
1344
|
+
|
1345
|
+
|
1346
|
+
|
1347
|
+
# pprint(cmnd)
|
1348
|
+
|
1349
|
+
|
1350
|
+
|
1351
|
+
|
1352
|
+
|
1353
|
+
subResult=subprocess.call(cmnd)
|
1354
|
+
|
1355
|
+
|
1356
|
+
|
1357
|
+
|
1358
|
+
|
1359
|
+
shutil.rmtree(tmpDir)
|
1360
|
+
|
1361
|
+
|
1362
|
+
|
1363
|
+
|
1364
|
+
|
1365
|
+
|
1366
|
+
|
1367
|
+
print("Output =", pediLogFileName, '(', latestId, ')' )
|
1368
|
+
|
1369
|
+
```
|