-
Notifications
You must be signed in to change notification settings - Fork 0
/
Crawler.py
564 lines (495 loc) · 21.4 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
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
import os
import re
import sys
import gc
import ConfigParser
import optparse
import requests
import urllib
import pickle
import getpass
import time
import glob
import cPickle as pickle
import traceback
import numbers
from datetime import date,timedelta
from lxml import html
from Profile import Profile,Group
from multiprocessing import Process, Lock
from threading import Thread
from Progress import Progress,StringMap
class CrawlerGroup(Group):
prefix = "groups"
def __init__(self,gid):
super(CrawlerGroup,self).__init__(gid)
self._page = None
self._link = None
def setLastActive(self,text):
year,month,day = re.split("/",text[0:text.find(" ")])
self.LastActivity = "%s/%s/%s" % (day,month,year)
def fill(self,session):
sys.stderr.write("Loading Group [%s]\n" % self.Id)
assert isinstance(self.Id,numbers.Number)
self._link = "https://fetlife.com/groups/%s" % self.Id
self._page = session.get(self._link)
if self._page.url != self._link or self._page.status_code == 500:
sys.stderr.write("Missing Profile [%s]\n" % self.Id)
return False
tree = html.fromstring(self._page.text)
self.Name = str(tree.xpath('//h2[@class="group_name bottom"]/a/text()')[0].encode('utf8'))
text = tree.xpath('//h2[@class="group_name bottom"]/following-sibling::p/text()')[0]
self.Membership = int(re.sub(r'[^0-9]','', text))
text = tree.xpath('//span[@class="last_comment"]/span/text()')
if len(text) > 0:
self.setLastActive(text[0])
for text in tree.xpath('//ul[@class="group_mods"]/li/a[@class="small"]/@href'):
self.Mods.add(int(re.sub(r'[^0-9]','', text)))
try:
self.Owner = int(re.sub(r'[^0-9]','',tree.xpath('//div[contains(text(),"(owner)")]/preceding::a/@href')[-1]))
except:
pass
#-----------------------------------------------------------------------------------------------
self._link = "https://fetlife.com/groups/%s/group_memberships" % self.Id
self._page = session.get(self._link)
tree = html.fromstring(self._page.text)
tell = tree.xpath('//div[contains(@class,"group_members")]/div[@class="clearfix"]')
if len(tell) == 0:
self.TooBig = True
else:
self.TooBig = False
pageNum = 1
while True:
self._link = "https://fetlife.com/groups/%s/group_memberships?page=%d" % (self.Id,pageNum)
self._page = session.get(self._link)
tree = html.fromstring(self._page.text)
urls = tree.xpath('//div[contains(@class,"user_in_list")]/div/a/@href')
for url in urls:
pid = int(re.sub(r'[^0-9 ]','', url))
self.Members.add(pid)
next = tree.xpath('//a[@class="next_page"]')
if len(next) == 1:
pageNum += 1
else:
break
self.setCrawlDate()
sys.stderr.write("Done Loading Group [%s]\n" % self.Id)
return True
class CrawlerProfile(Profile):
prefix = "users"
def __init__(self,pid):
super(CrawlerProfile,self).__init__(pid)
self._page = None
self._link = None
def setLastActive(self,text):
now = date.today()
try:
number = int(re.sub(r'[^0-9]','', text))
except ValueError:
self.LastActivity = Profile.NEVER_ACTIVE
return
if "hour" in text or "minute" in text:
then = now
elif "day" in text:
then = now - timedelta(number)
elif "month" in text:
day = 1
month = now.month
year = now.year
for i in range(number):
month -= 1
if month == 0:
year -= 1
month = 12
then = date(year,month,day)
elif "year" in text:
day = 1
month = 1
year = now.year - number
then = date(year,month,day)
else:
raise RuntimeError,"We can not process [%s] yet" % text
self.LastActivity = "%s/%s/%s" % (then.day,then.month,then.year)
def fill(self,session):
sys.stderr.write("Loading Profile [%s]\n" % self.Id)
assert isinstance(self.Id,numbers.Number)
self._link = "https://fetlife.com/users/%s" % self.Id
self._page = session.get(self._link)
if self._page.url != self._link:
sys.stderr.write("Missing Profile [%s]\n" % self.Id)
return False
tree = html.fromstring(self._page.text)
self.Name = tree.xpath('//h2[@class="bottom"]/text()')[0].strip()
rawPair = tree.xpath('//span[@class="small quiet"]/text()')[0].strip()
splitList = re.split(" ",rawPair)
if len(splitList) > 1:
self.Type = splitList[1]
try:
self.Age = int(re.sub(r'[^0-9]','', splitList[0]))
except ValueError:
self.Age = -1
if self.Age != splitList[0]:
self.Gender = re.sub(r'[0-9 ]','', splitList[0])
Location = tree.xpath('//div[@class="span-13 append-1"]/p/em/a/text()')
self.Location = [unicode(x) for x in Location]
table = tree.xpath('//div[@class="span-13 append-1"]/table/tr')
for item in table:
children = [x for x in item]
header = children[0]
if header.text == "relationship status:" or header.text == "D/s relationship status:":
assert len(children[1:]) == 1
td = children[1]
assert len(td.getchildren()) == 1
ul = td.getchildren()[0]
for li in ul:
if len(li.getchildren()) == 1:
a = li.getchildren()[0]
url = a.get("href")
rel = li.text.strip()
pid = int(re.sub(r'[^0-9 ]','', url))
self.Relationships.append(tuple([pid,rel]))
elif header.text == "orientation:":
assert len(children[1:]) == 1
td = children[1]
self.Orientation = td.text
elif header.text == "active:":
assert len(children[1:]) == 1
td = children[1]
self.Active = td.text
elif header.text == "is looking for:":
assert len(children[1:]) == 1
td = children[1]
for text in td.itertext():
self.LookingFor.append(text)
else:
raise RuntimeError,"Unknown table [%s]" % header.text
lastActive = tree.xpath('//ul[@id="mini_feed"]/li/span[@class="quiet small"]/text()')
if len(lastActive) != 0:
self.setLastActive(lastActive[0])
for groupURL in tree.xpath('//li/a[contains(@href,"/groups/")]/@href'):
try:
self.Groups.add(int(re.sub(r'[^0-9]','', groupURL)))
except ValueError:
pass
#---------------------------------------------------
# Fetishes
#---------------------------------------------------
stringMap = StringMap()
stuff = tree.xpath('//em[text()="Into:"]/ancestor::p')
if len(stuff) != 0:
#sys.stderr.write("Into [%s]\n" % stuff)
intoList = []
for item in stuff[0]:
if item.text is None:
continue
#sys.stderr.write("\t[%s][%s]\n" % (item,item.text))
try:
if "href" in item.keys():
fetishName = item.text
fetishId = int(re.sub(r'[^0-9 ]','', item.get("href")))
intoList.append( [fetishId,None] )
if not stringMap.hasString("Fetish",fetishId):
stringMap.addString("Fetish",fetishId,fetishName)
elif len(intoList) > 0:
intoList[-1][1] = item.text[1:-1]
except ValueError:
pass
#sys.stderr.write("\n%s\n" % intoList)
for (k,v) in intoList:
if v not in self.Into:
self.Into[v] = set()
self.Into[v].add(k)
stuff = tree.xpath('//em[text()="Curious about:"]/ancestor::p')
if len(stuff) != 0:
#sys.stderr.write("Curious About [%s]\n" % stuff)
curiousList = []
for item in stuff[0]:
if item.text is None:
continue
#sys.stderr.write("\t[%s][%s] - [%s]\n" % (item,item.text,item.keys()))
try:
if "href" in item.keys():
fetishName = item.text
fetishId = int(re.sub(r'[^0-9 ]','', item.get("href")))
curiousList.append( [fetishId,None] )
if not stringMap.hasString("Fetish",fetishId):
stringMap.addString("Fetish",fetishId,fetishName)
elif len(curiousList) > 0:
curiousList[-1][1] = item.text[1:-1]
except ValueError:
pass
#sys.stderr.write("\n%s\n" % curiousList)
for (k,v) in curiousList:
if v not in self.Curious:
self.Curious[v] = set()
self.Curious[v].add(k)
#---------------------------------------------------
# Now, friends
#---------------------------------------------------
pageNum = 1
while True:
self._link = "https://fetlife.com/users/%s/friends?page=%d" % (self.Id,pageNum)
self._page = session.get(self._link)
tree = html.fromstring(self._page.text)
urls = tree.xpath('//div[@class="clearfix user_in_list"]/div/a/@href')
for url in urls:
friend = int(re.sub(r'[^0-9 ]','', url))
self.Friends.append(friend)
next = tree.xpath('//a[@class="next_page"]')
if len(next) == 1:
pageNum += 1
else:
break
self.setCrawlDate()
sys.stderr.write("Done Loading Profile [%s]\n" % self.Id)
return True
class Crawler(object):
def __init__(self,session,progress,raise_on_failure=False):
self.__session = session
self.__progress = progress
self.__raiseOnFailure = raise_on_failure
self.__errorPath = "Error"
if not os.path.exists(self.__errorPath):
os.mkdir(self.__errorPath)
def getSession(self):
return self.__session
def saveError(self,eid,entity):
errorFile = os.path.join(self.__errorPath,"%s_%s.txt" % (entity.prefix,entity.Id))
with open(errorFile,'w') as fp:
fp.write("=========================\n")
traceback.print_exc(file=fp)
fp.write("=========================\n")
if entity is None:
fp.write("No Entity\n")
else:
fp.write("Requ URL - %s\n" % entity._link)
if entity._page is None:
fp.write("No Page\n")
else:
fp.write("Resp URL - %s\n" % entity._page.url)
fp.write("Status Code - %s\n" % entity._page.status_code)
fp.write("Reason - %s\n" % entity._page.reason)
htmlFile = os.path.join(self.__errorPath,"%s_%s.html" % (entity.prefix,entity.Id))
with open(htmlFile,'w') as hfp:
hfp.write(entity._page.text.encode('utf8'))
fp.write("=========================\n")
def doTick(self):
try:
nextId = self.__progress.nextProfile()
if nextId is not None:
entity = CrawlerProfile(nextId)
if entity.fill(self.getSession()):
pids = entity.getOtherProfiles()
gids = entity.getGroups()
entity.save()
self.__progress.completeProfile(nextId,pids,gids)
else:
self.__progress.missingProfile(nextId)
del entity
return True
except KeyboardInterrupt:
sys.stderr.write("Interrupting work.\n")
self.__progress.setExit()
return False
except Exception,e:
sys.stderr.write("Failed to load profile [%s].\n" % (nextId))
self.saveError(nextId,entity)
#traceback.print_exc(sys.stderr)
self.__progress.errorProfile(nextId)
if self.__raiseOnFailure:
self.__progress.setExit()
raise
return True
try:
nextId = self.__progress.nextGroup()
if nextId is not None:
entity = CrawlerGroup(nextId)
if entity.fill(self.getSession()):
pids = entity.getProfiles()
entity.save()
self.__progress.completeGroup(nextId,pids)
else:
self.__progress.missingGroup(nextId)
del entity
return True
except KeyboardInterrupt:
sys.stderr.write("Interrupting work.\n")
self.__progress.setExit()
return False
except Exception,e:
sys.stderr.write("Failed to load group [%s].\n" % (nextId))
traceback.print_exc(sys.stderr)
self.saveError(nextId,entity)
self.__progress.errorGroup(nextId)
if self.__raiseOnFailure:
self.__progress.setExit()
raise
return True
sys.stderr.write("No pending work.\n")
self.__progress.setExit()
return False
class Session(object):
def __init__(self):
self.__dataPath = "Data"
self.__sessionFile = os.path.join(self.__dataPath,"session.dat")
if not os.path.exists(self.__dataPath):
os.mkdir(self.__dataPath)
self.__session = requests.Session()
if os.path.exists(self.__sessionFile):
self.__session.cookies = self.__loadCookies()
def get(self,*args,**kwargs):
return self.__session.get(*args,**kwargs)
def getDataPath(self):
return self.__dataPath
def isLoggedIn(self):
page = self.__session.get("http://fetlife.com")
tree = html.fromstring(page.text)
login = tree.xpath('//a[@href="/login"]')
#sys.stderr.write("[%s]\n" % login)
if len(login) == 0:
return True
else:
return False
def __saveCookies(self,cookies):
with open(self.__sessionFile,'w') as fp:
pickle.dump(cookies,fp)
def __loadCookies(self):
with open(self.__sessionFile,'rb') as fp:
return pickle.load(fp)
def doLogin(self):
if self.isLoggedIn():
sys.stderr.write("Previous login still valid\n")
return True
sys.stderr.write("Not logged in yet\n")
userName = raw_input("Enter username: ")
passWord = getpass.getpass("Enter password for [%s]:" % userName)
page = self.__session.get("http://fetlife.com/login")
tree = html.fromstring(page.text)
token = tree.xpath('//div[@id="authenticity_token"]/text()')[0]
payload = {
"authenticity_token": token,
"nickname_or_email" : userName,
"password" : passWord,
"remember_me" : "1",
"commit" : "Login to FetLife"
}
payloadStr = urllib.urlencode(payload)
payloadStr += "&utf8=%E2%9C%93"
sys.stderr.write("%s\n" % payloadStr)
page = self.__session.post("https://fetlife.com/session",data=payloadStr)
if self.isLoggedIn():
self.__saveCookies(self.__session.cookies)
sys.stderr.write("Now logged in.\n")
return True
else:
sys.stderr.write("Still not logged in.\n")
if __name__ == "__main__":
usage = "usage: %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option('-p', '--profile', help="profile number to test scan", type='int', default=None)
parser.add_option('-g', '--group', help="group number to test scan", type='int', default=None)
parser.add_option('-t', '--threads', help="number of threads to spawn", type='int', default=1)
parser.add_option('-r', '--rebuild', help="rebuild the progress file",action="store_true",default=False)
parser.add_option('-i', '--init', help="init the progress file",action="store_true",default=False)
parser.add_option('-e', '--error', help="re-examine the error pages",action="store_true",default=False)
parser.add_option('-s', '--sequence', help="examine progress to find unvisited profiles",action="store_true",default=False)
options, args = parser.parse_args()
session = Session()
if not session.doLogin():
sys.stderr.write("Something went wrong, still not connected\n")
if options.init:
sys.stderr.write("Init Progress File\n")
if options.profile == None and options.group == None:
sys.stderr.write("\tMust select profile or group to init from\n")
sys.exit(0)
progress = Progress()
progress.initPending(options.profile,options.group)
progress.printProgress()
crawler = Crawler(session,progress)
sys.stderr.write("Starting Crawler\n")
crawler.doTick()
sys.stderr.write("Ending Crawler\n")
progress.setExit()
progress.saveProgress()
sys.exit(0)
elif options.rebuild:
sys.stderr.write("Rebuilding Progress File\n")
Progress(True)
progress.printProgress()
sys.exit(0)
elif options.sequence:
sys.stderr.write("Calculating Unvisted Profiles\n")
progress = Progress()
maxPid = progress.maxProfile()
sys.stderr.write("Max Profile Id [%s]\n" % maxPid)
for i in range(maxPid):
if i%1024 == 0:
sys.stderr.write("[%12s]\n" % i)
if not progress.knownProfile(i):
progress.pendingProfile(i)
progress.printProgress()
progress.saveProgress()
sys.exit(0)
if options.profile is not None:
profile = CrawlerProfile(options.profile)
if profile.fill(session):
sys.stderr.write("Loaded. Other Profiles [%d]\n" % (len(profile.getOtherProfiles())))
sys.stderr.write(unicode(profile))
sys.stderr.write("Valid : [%s]\n" % profile.validate())
profile.save()
profile.load()
sys.stderr.write("Valid : [%s]\n" % profile.validate())
else:
sys.stderr.write("Failed\n")
elif options.group is not None:
group = CrawlerGroup(options.group)
if group.fill(session):
sys.stderr.write("Loaded. Profiles [%d]\n" % (len(group.getProfiles())))
sys.stderr.write(unicode(group))
sys.stderr.write("Valid : [%s]\n" % group.validate())
group.save()
group.load()
sys.stderr.write("Valid : [%s]\n" % group.validate())
else:
sys.stderr.write("Failed\n")
elif options.error is True:
sys.stderr.write("Examining Error List\n")
progress = Progress()
progress.printProgress()
progress.resetErrorProfiles()
progress.resetErrorGroups()
progress.saveProgress()
progress.printProgress()
crawler = Crawler(session,progress,True)
sys.stderr.write("Starting Crawler\n")
while not progress.getExit():
crawler.doTick()
sys.stderr.write("Ending Crawler\n")
progress.saveProgress()
progress.setExit()
else:
def RunCrawler(num):
crawler = Crawler(session,progress)
sys.stderr.write("Starting Crawler [%d]\n" % num)
while not progress.getExit():
crawler.doTick()
sys.stderr.write("Ending Crawler [%d]\n" % num)
progress.setExit()
progress = Progress()
stringMap = StringMap()
progress.printProgress()
threads = []
for i in range(options.threads):
threads.append(Thread(None,target=RunCrawler,args=(i,)))
threads[-1].start()
try:
while not progress.getExit():
time.sleep(60)
progress.printProgress()
progress.saveProgress()
stringMap.save()
except:
sys.stderr.write("Shutting down from main thread\n")
progress.setExit()
for thread in threads:
thread.join()