-
Notifications
You must be signed in to change notification settings - Fork 0
/
Crawler.py
executable file
·532 lines (451 loc) · 22.1 KB
/
Crawler.py
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
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
import sqlite3
import threading
from Model import *
import urllib.parse
import urllib.request
from datetime import *
from time import sleep
from random import randint
import urllib.response
import urllib.robotparser
from html.parser import HTMLParser
#Number of pages to crawl for per run.
NUMOFPAGES = 200
class Crawler(threading.Thread):
numberOfThreads = 0
webpagesSaved = 0
dbLock = threading.Lock()
webpagesLock = threading.Lock()
linksLock = threading.Lock()
listOfLinks = []
assignedLock = threading.Lock()
assignedList = []
def __init__(self, cID):
try:
threading.Thread.__init__(self)
self.crawlerID = cID
for seed in Seeds.select():
if UncrawledTable.select().where(UncrawledTable.uncrawledURL == seed.pageURL).exists():
continue
timeDifference = datetime.now() - seed.lastCrawl
timeDifferenceInHours = timeDifference.days * 24 + timeDifference.seconds // 3600
pass #for quick testing
#timeDifferenceInHours = 100
if timeDifferenceInHours >= seed.crawlFrequency:
UncrawledTable.get_or_create(uncrawledURL = seed.pageURL)
seed.lastCrawl = datetime.now()
seed.save()
except (OperationalError, sqlite3.OperationalError):
print("Database already open by something")
def run(self):
tryTwice = 0
while True:
try:
print('Thread ' + str(self.crawlerID) + ': Getting link.')
Crawler.webpagesLock.acquire()
if Crawler.webpagesSaved >= NUMOFPAGES:
print('Thread ' + str(self.crawlerID) + ': Target reached, ending crawl')
Crawler.webpagesLock.release()
break
Crawler.webpagesLock.release()
exists = None
while True:
try:
linkQuery = UncrawledTable.select().limit(1) # just to check if table is empty #rawshana
exists = linkQuery.exists()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. UNCrawledTable')
except:
break
if not exists:
#if table is empty
if tryTwice == 2:
print('Thread ' + str(self.crawlerID) + ': No links available. Ending crawl.')
break
print('Thread ' + str(self.crawlerID) + ': No links available. Sleeping for 60 seconds. Attempt: ' + str(tryTwice + 1))
sleep(60)
tryTwice = tryTwice + 1
continue
tryTwice = 0
link = self._getALink()
### i am here
if link == 'ALLLINKSASSIGNED':
#if table is empty
print('Thread ' + str(self.crawlerID) + ': All links assigned.')
sleep(1)
continue
x = None
while True:
try:
x = CrawledTable.select().where(CrawledTable.crawledURL == link).exists()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. CrawledTable')
except:
break
if x: #if link already exists in CrawledTable
print('Thread ' + str(self.crawlerID) + ': Link already visited.' + ' ' + link)
#increment this page rank
while True:
try:
selectQuery = PageRank.select().where(PageRank.pageURL == link)
if (selectQuery.exists()):
PageRank.update(pageInLinks = PageRank.pageInLinks + 1).where(
PageRank.pageURL == link).execute()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. PageRankTable')
except:
break
Crawler.linksLock.acquire()
Crawler.assignedLock.acquire()
Crawler.assignedList.remove(link)
try:
Crawler.listOfLinks.remove(link)
except:
pass
Crawler.assignedLock.release()
Crawler.linksLock.release()
while True:
try:
UncrawledTable.delete().where(UncrawledTable.uncrawledURL == link).execute()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. Del UnCrawled Table')
except:
break
continue
Crawler.webpagesLock.acquire()
while True:
try:
print("CRAWLED URLS = ", CrawledTable.select().count(), ' Thread ' + str(self.crawlerID))
break
except (OperationalError, sqlite3.OperationalError)as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. print CrawledTable')
except:
break
print("Actual pages = ", Crawler.webpagesSaved, ' Thread ' + str(self.crawlerID))
Crawler.webpagesLock.release()
print('Thread ' + str(self.crawlerID) + ': Done getting link.')
print('Thread ' + str(self.crawlerID) + ': Crawling link: ' + link)
self.crawl(link)
while True:
try:
UncrawledTable.delete().where(UncrawledTable.uncrawledURL == link).execute()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. del UnCrawledTable')
sleep(1)
pass
except:
break
Crawler.linksLock.acquire()
Crawler.assignedLock.acquire()
Crawler.assignedList.remove(link)
try:
Crawler.listOfLinks.remove(link)
except:
pass
Crawler.assignedLock.release()
Crawler.linksLock.release()
while True:
try:
CrawledTable.create(crawledURL=link).update()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. CrawledTable')
sleep(1)
pass
except:
break
print('Thread ' + str(self.crawlerID) + ': Done crawling link: ' + link)
# Just in case, but these 2 exceptions should never happen
except IntegrityError:
print("IntegrityError has occurred by thread " + str(self.crawlerID) + " !")
except (OperationalError, sqlite3.OperationalError):
print("DatabaseError: DB is locked while thread " + str(self.crawlerID) + " tried to access it!")
print("Thread:", self.crawlerID, "is Exiting...")
def _getALink(self):
Crawler.linksLock.acquire()
Crawler.assignedLock.acquire()
listOfLinksQuery = None
if len(Crawler.listOfLinks) == 0:
while True:
try:
listOfLinksQuery = UncrawledTable.select().limit(Crawler.numberOfThreads)
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. UnCrawledTable')
except:
break
while True:
try:
for link in listOfLinksQuery:
Crawler.listOfLinks.append(link.uncrawledURL)
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. UnCrawledTable')
except:
break
if len(Crawler.listOfLinks) == 0:
retVal = "ALLLINKSASSIGNED"
else:
retVal = Crawler.listOfLinks.pop()
acquired = False
breaked = False
while True:
if retVal not in Crawler.assignedList:
break
if len(Crawler.listOfLinks) == 0:
if acquired == True:
breaked = True
break
acquired = True
while True:
try:
listOfLinksQuery = UncrawledTable.select().limit(Crawler.numberOfThreads)
break
except (OperationalError, sqlite3.OperationalError)as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying.UnCrawledTable')
except:
break
while True:
try:
for link in listOfLinksQuery:
Crawler.listOfLinks.append(link.uncrawledURL)
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. UnCrawledTable')
except:
break
if len(Crawler.listOfLinks) == 0:
retVal = "ALLLINKSASSIGNED"
else:
retVal = Crawler.listOfLinks.pop()
if breaked:
Crawler.assignedLock.release()
Crawler.linksLock.release()
return 'ALLLINKSASSIGNED'
else:
Crawler.assignedList.append(retVal)
Crawler.assignedLock.release()
Crawler.linksLock.release()
return retVal
def crawl(self, link):
tryOnce = 0
robotParser = self.setupRobotParser(link)
if robotParser.can_fetch("*", link):
while True:
try:
response = urllib.request.urlopen(link)
break
except urllib.error.HTTPError as e:
if e.code == 429:
if tryOnce == 1:
print(
'Thread ' + str(self.crawlerID) + ': Too many requests: ' + link + ' returning.')
return
print('Thread ' + str(self.crawlerID) + ': Too many requests: ' + link + ' trying again in 120 seconds.')
sleep(120)
tryOnce = 1
else:
return
# for handling any other url errors
except:
print('Error opening link: ',link, " by thread : ", self.crawlerID)
return
returnedLink = response.geturl()
if returnedLink != link:
print('Thread ' + str(self.crawlerID) + ': Redirection:' + link + ' to ' + returnedLink + ' returning.')
return
urlInfo = response.info()
dataType = urlInfo.get_content_type()
if 'html' not in dataType:
print('Thread ' + str(self.crawlerID) + ': Not HTML ' + link + ' returning.')
return
try:
webContent = response.read().decode(response.headers.get_content_charset('utf-8'))
except:
print("Incomplete Read of web content due to a defective http server.")
webContent = None
if(webContent):
Crawler.webpagesLock.acquire()
if Crawler.webpagesSaved < NUMOFPAGES:
Crawler.webpagesSaved += 1
else:
print('Thread ' + str(self.crawlerID) + ': Page number limit reached ')
Crawler.webpagesLock.release()
return
Crawler.webpagesLock.release()
selector = None
while True:
try:
selector = WebPages.select().where(WebPages.pageURL == returnedLink).exists()
break
except (OperationalError , sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. WebPagesTable')
except:
break
if selector:
print('Thread ' + str(self.crawlerID) + ': Updating webpage ' + link)
while True:
try:
WebPages.update(pageContent=webContent).where(
WebPages.pageURL == returnedLink).execute()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. WebPagesTable')
except:
break
else:
print('Thread ' + str(self.crawlerID) + ': Saving webpage ' + link )
try:
inserted = False
while True:
try:
if not inserted:
WebPages(pageURL=returnedLink, pageContent=webContent).save()
inserted = True
...
PageRank.create(pageURL=returnedLink).update()
...
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. WebPagesTable & PageRank')
sleep(randint(1,5))
except:
break
#should never happen
except:
print('UnexpectedException: In saving webpage WEEEEEEEEEEEEEEEEEEEEEEE')
print('Thread ' + str(self.crawlerID) + ': Done saving webpage and starting link extraction ' + link)
try:
parser = MyHTMLParser(link)
parser.feed(str(webContent))
#should never happen
except:
print('UnexpectedException: in parser WEEEEEEEEEEEEEEEEEEEEEEE')
size = 999
while True:
try:
for i in range(0, len(parser.links), size):
UncrawledTable.insert_many(parser.links[i:i + size]).upsert().execute()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. UnCrawledTable')
except:
break
while True:
try:
print("UNCRAWLED URLS = ", UncrawledTable.select().count(), ' Thread ' + str(self.crawlerID))
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. print UnCrawledTable')
except:
break
print('Thread ' + str(self.crawlerID) + ': Done inserting links ' + link)
def setupRobotParser(self, url):
rp = urllib.robotparser.RobotFileParser()
robotData = None
currentUrlComponents = urllib.parse.urlparse(url)
robotLocation = urllib.parse.urljoin(currentUrlComponents.scheme + '://' + currentUrlComponents.netloc, 'robots.txt')
while True:
try:
robotQuery = RobotTxts.select().where(RobotTxts.netLoc == robotLocation)
if (robotQuery.exists()):
robotData = robotQuery.get()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. RobotTable')
except:
break
if robotData:
rp.parse(str(robotData.robotContent))
else:
try:
robotContentFromInternet = str(urllib.request.urlopen(robotLocation).read())
except:
robotContentFromInternet = ''
rp.parse(robotContentFromInternet)
while True:
try:
RobotTxts(netLoc=robotLocation, robotContent=robotContentFromInternet).save()
break
except (OperationalError, sqlite3.OperationalError) as e:
if 'binding' in str(e):
break
print('Thread ', self.crawlerID, ': Database busy, retrying. RobotTable')
sleep(1)
pass
except:
break
return rp
'''---------------------------------------------HTML Parser----------------------------------------------------------'''
class MyHTMLParser(HTMLParser):
def __init__(self, currentLink):
HTMLParser.__init__(self)
self.links = []
self.parsingLink = currentLink
def handle_starttag(self, tag, attrs):
# Only parse the 'anchor' tag.
if tag == "a":
# Check the list of defined attributes.
for name, value in attrs:
# If href is defined, print it.
if name == "href":
link = value
# check if not none
if(link):
if link.startswith('//'):
link = 'http:' + link
elif link.startswith('/'):
link = urllib.parse.urljoin(self.parsingLink, link)
if '#' in link:
continue
elif link.startswith('ftp'):
continue
elif link.startswith('javascript'):
continue
parsedLink = urllib.parse.urlparse(link)
'''this option lets us crawl deeper into the current host'''
#link = urllib.parse.urljoin(parsedLink.scheme + '://' + parsedLink.netloc, parsedLink.path)
'''this option only lets us crawl the main pages of the hosts'''
link = parsedLink.scheme + '://' + parsedLink.netloc
if link[-1] != '/':
link = link + '/'
self.links.append({'uncrawledURL': link})