-
Notifications
You must be signed in to change notification settings - Fork 0
/
LinkAnalysisAlgo.py
525 lines (410 loc) · 18.5 KB
/
LinkAnalysisAlgo.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
"""
Page_Rank_Link_Analysis
"""
import pickle
import networkx as nx
import numpy
import matplotlib.pyplot as plt
from tkinter import messagebox
import tkinter as tk
from tkinter import filedialog
from tkinter import *
from urllib.request import urlopen
import os
from urllib.parse import urlparse
class Page_Rank_Link_Analysis:
def __init__(self):
self.title = "PageRank algorithm"
self.root = tk.Tk()
self.root.title(self.title)
w = 390 # width for the Tk root
h = 220 # height for the Tk root
# get screen width and height
ws = self.root.winfo_screenwidth() # width of the screen
hs = self.root.winfo_screenheight() # height of the screen
# calculate x and y coordinates for the Tk root window
x = (ws / 2) - (w / 2)
y = (hs / 2) - (h / 2)
# set the dimensions of the screen
# and where it is placed
self.root.geometry('%dx%d+%d+%d' % (w, h, x, y))
self.frame = Frame(self.root)
self.frame.grid()
self.path = None
self.newWebsite = Entry(self.root)
self.flag_pickle = False
self.numberOfitterations = 1
self.link_Dic = {}
self.page_rank_vector = {}
self.temp_link_Dic = {}
self.directiory = None
def start(self):
text = tk.Label(self.root, text="Click 'Browse' and choose whice website you want to rank:")
text.grid(row=0, column=1)
browseButton = Button(command=self.Path, text="Browse", fg="black")
browseButton.grid(row = 1, column=1)
text2 = tk.Label(self.root, text="Enter new website(url):")
text2.grid(row=2, column=1)
self.newWebsite.grid(row=3, column=1)
text3 = tk.Label(self.root,text = "Start Data-Analysis")
text3.grid(row=4,column=1)
buildButton = Button(command=self.Build, text="Build", fg="black")
buildButton.grid(row=5, column=1)
pageRankButton = Button(command=self.PageRank, text="PageRank", fg="black")
pageRankButton.grid(row=6, column=1)
self.root.mainloop()
def Path(self):
file_path = tk.filedialog.askdirectory()
self.path = file_path + "/LinkAnalysis.pkl"
self.flag_pickle = True
pass
def Build(self):
def fixAddress(list):
list2 = []
for address in list:
if (address.startswith("http")):
list2.append(address)
else:
temp = add_http + address
address = temp
list2.append(address)
return list2
def removeUnwanted(source_Code):
tempList = []
for x in source_Code:
if "http:" in x:
temp = x[x.find("http:"):]
temp = list(temp.split(chr(34)))
temp = list(temp[0].split(chr(39)))
if not (temp[0].endswith(";")):
tempList.append(temp[0])
elif "www" in x:
temp = x[x.find('www'):]
temp = list(temp.split(chr(34)))
temp = list(temp[0].split(chr(39)))
if not (temp[0].endswith(";")):
tempList.append(temp[0])
elif "https:" in x:
temp = x[x.find("https:"):]
temp = list(temp.split(chr(34)))
temp = list(temp[0].split(chr(39)))
if not (temp[0].endswith(";")):
tempList.append(temp[0])
return fixAddress(tempList)
def cleanAddress(Address): # http://www.walla.co.il
list1 = Address.split("/")
return "http://" + list1[2]
def itterFunc(address_test):
numberOfErrors = 0
allowedCounter = 0
for x in address_test:
temp_link = urlparse(x)
# dead end solution
if temp_link.netloc != full_link:
continue
if x in dictionary:
if (dictionary[x][2] == "GREEN"):
print("Already Visited - ", x)
continue
try:
html = urlopen(x)
except Exception as e:
numberOfErrors += 1
continue
try:
content = html.read().decode()
except Exception as e:
numberOfErrors += 1
continue
allowedCounter += 1
tempSTR = ""
for k in content:
tempSTR += k
tempList2 = list(tempSTR.split())
innerAddresses = removeUnwanted(tempList2)
innerAddresses = (list(set(innerAddresses)))
for y in innerAddresses:
try:
new_link = urlparse(y)
except ValueError as e:
continue
if y in dictionary:
dictionary[y][0] = dictionary[y][0] + 1
dictionary[y][3].append(x) # add to list-in
else:
if new_link.netloc == full_link: # add to dict
dictionary[y] = [1, 0, "RED", [x], []]
else: # add external website to dict
other_website = new_link.scheme +"://"+ new_link.netloc
if other_website in dictionary:
dictionary[other_website][0] = dictionary[other_website][0] + 1
dictionary[other_website][3].append(x) # add to list-in
else:
dictionary[other_website] = [1, 0, "RED", [x], []]
dictionary[x][1] = len(innerAddresses)
dictionary[x][2] = "GREEN"
dictionary[x][4] = innerAddresses
messagebox._show("Program", "Building data base...this may take a while...")
self.flag_pickle = False
myAddress = str(self.newWebsite.get())
LinkName2 = str(self.newWebsite.get())
full_link = LinkName2.split('//')[1]
try:
html = urlopen(myAddress)
except Exception as e:
messagebox.showerror(title="Error", message="illegal address,try again..")
pass
try:
content = html.read().decode()
except Exception as e:
messagebox.showerror(title="Error", message="Something went wrong.." + e)
pass
tempSTR = ""
for x in content:
tempSTR += x
tempList = list(tempSTR.split())
add_http = "http://"
add_https = "https://"
address_test = removeUnwanted(tempList)
address_test.append(myAddress)
address_test = (list(set(address_test))) # remove duplicates
dictionary = {} ## dictionary - [ IN , OUT , STATUS(GREEN - Already visited , RED - Not Visited) , LISTIN , LISTOUT ]
for x in address_test: # enter the first list of links to the dict..
temp_link = urlparse(x)
if full_link == temp_link.netloc: # legit netloc (example: wwww.ynet.co.il )
dictionary[x] = [1, 0, "RED", [myAddress], []]
else: # other website
other_website = temp_link.scheme + "://" + temp_link.netloc
if other_website not in dictionary:
dictionary[other_website] = [1, 0, "RED", [myAddress], []]
dictionary[myAddress] = [1, len(address_test), "GREEN", [], address_test] # add the user input website to the dict..
itterFunc(address_test)
for _ in range (self.numberOfitterations):
tmpDict = {}
for link in dictionary:
tmpDict[link] = dictionary[link]
tmplist = tmpDict.keys()
itterFunc(tmplist)
self.temp_link_Dic = dictionary
messagebox.showinfo(title="Success",message="The build of the data structure succeeded")
messagebox.showinfo(title="Pickle output", message="Saving the data structure to pickle file.")
LinkName=str(self.newWebsite.get())
tempoLink=LinkName.split('.')
LinkName=tempoLink[1]
current_directory = os.getcwd()
final_directory = os.path.join(current_directory, LinkName)
if not os.path.exists(final_directory):
os.makedirs(final_directory)
filename=LinkName+"/"+ "LinkAnalysis.pkl"
dictionary["mainSite"] = full_link
output = open(filename, "wb")
pickle.dump(dictionary, output)
output.close
pass
def PageRank(self):
messagebox._show("Program","Running...this may take a few moments...")
def removeNodes(dict2):
link_Dic2 = {}
for x in dict2:
if x.endswith("pdf") or x.endswith("JPEG") or x.endswith("png") or x.endswith("jpg") or x.endswith("footer"):
continue
link_Dic2[x] = dict2[x]
return link_Dic2
def probability_x_to_y(linkRow, linkCol): # get the probability for the transition matrix
if linkCol not in self.link_Dic[linkRow][3]:
return 0
divNum = 1 / self.link_Dic[linkCol][1]
return divNum
def transition_matrix_input(keyList, matrix, probability_x_to_y):
for row in range(len(keyList)):
for col in range(len(keyList)):
matrix[row][col] = probability_x_to_y(keyList[row], keyList[col]) # transition matrix input
if self.flag_pickle is True:
filename = self.path
with open(filename, 'rb') as f:
# The protocol version used is detected automatically, so we do not
# have to specify it.
self.temp_link_Dic = pickle.load(f)
self.newWebsite = self.temp_link_Dic["mainSite"]
del self.temp_link_Dic["mainSite"]
else:
if not self.temp_link_Dic:
messagebox.showerror(title="Error",message="Browse or Enter new url first")
else:
self.newWebsite = self.temp_link_Dic["mainSite"]
del self.temp_link_Dic["mainSite"]
pass
self.link_Dic = removeNodes(self.temp_link_Dic) ## [ IN , OUT , STATUS(GREEN - Already visited , RED - Not Visited) , LISTIN , LISTOUT ]
numberDic = {}
index = 1
for key in self.link_Dic: ## set dictionary with running index for our Graph input.
print(key," ",self.link_Dic[key])
numberDic[key] = index
index += 1
matrix = numpy.zeros(shape=(len(self.link_Dic), len(self.link_Dic))) # Build NxN matrix ( N = number of links )
key_list = []
for key in self.link_Dic.keys():
key_list.append(key)
# this way we have no 'dict_keys' at the start
transition_matrix_input(key_list, matrix, probability_x_to_y)
sum_vector = {}
multiply_vector = {}
for link in key_list: # represent vectors with dictionary
multiply_vector[link] = 1 # our first vector initialize to 1
sum_vector[link] = 0 # our sum vector
sum_matrix = 0
for _ in range(50): # iterate Random walks
index1 = 0 # our x in the matrix
for x in key_list:
index2 = 0 # our y in the matrix
for y in key_list:
sum_matrix = sum_matrix + (matrix[index1][index2] * multiply_vector[y])
index2 += 1
sum_vector[x] = (sum_matrix * 0.8) + 0.2 # avoid spider trap with 20% tax.
sum_matrix = 0
index1 += 1
for k in sum_vector:
multiply_vector[k] = sum_vector[k] # our new multiply vector.
maximum = max(multiply_vector.values()) # our highest page rank
minimum = min(multiply_vector.values()) # out lowest page rank
for link in multiply_vector: # The Vector dictionary after normalization
self.page_rank_vector[link] = (multiply_vector[link] - minimum) / (maximum - minimum)
def mergeSort(arr):
if len(arr) > 1:
mid = len(arr) // 2 # Finding the mid of the array
left = arr[:mid] # Dividing the array elements
right = arr[mid:] # into 2 halves
mergeSort(left) # Sorting the first half
mergeSort(right) # Sorting the second half
i = j = k = 0
# Copy the data to temp lists left[] and right[]
while i < len(left) and j < len(right):
if left[i][1] < right[j][1]:
arr[k] = left[i]
i += 1
else:
arr[k] = right[j]
j += 1
k += 1
# Checking if any element was left
while i < len(left):
arr[k] = left[i]
i += 1
k += 1
while j < len(right):
arr[k] = right[j]
j += 1
k += 1
rankList = []
for x in self.page_rank_vector:
rankList.append([x, self.page_rank_vector[x]]) # set list of our page rank [ link , pageRank(float) ]
mergeSort(rankList) # sort the list
print("website: ", self.newWebsite)
temp = self.newWebsite.split(".")
LinkName = temp[1]
current_directory = os.getcwd()
final_directory = os.path.join(current_directory, LinkName)
if not os.path.exists(final_directory):
os.makedirs(final_directory)
# ---------------------- write to file 1------------------------
i = len(rankList) - 1
myPath = os.path.join( LinkName , 'output1.txt')
with open(myPath, 'w',encoding="utf-8") as f: # write the result to file [ linkName(str) , pageRank(float) ]
for _ in range(len(rankList)):
f.write(rankList[i][0] + " ")
f.write(str(rankList[i][1]) + '\n')
i -= 1
if (i < 0):
break
messagebox.showinfo(title="Success",message="You can find the result(output1.txt) at the project library at: "+LinkName)
f.close()
# ---------------------- write to file 1 end------------------------
# ---------------------- write to file 2------------------------
i = len(rankList) - 1
myPath = os.path.join( LinkName , 'output2.txt')
with open(myPath, 'w',encoding="utf-8") as f: # write the result to file [ linkName(str) , pageRank(float) ]
for _ in range(len(rankList)):
temp_address = urlparse(rankList[i][0])
if temp_address.netloc == self.newWebsite:
f.write(rankList[i][0] + " ")
f.write(str(rankList[i][1]) + '\n')
i -= 1
if (i < 0):
break
messagebox.showinfo(title="Success", message="You can find the result(output2.txt) at the project library at: "+LinkName)
f.close()
# ---------------------- write to file 2 end------------------------
if messagebox.askquestion(title=None,message = "Would you like to draw the graph?") == 'yes':
messagebox.showinfo(title="Graph Drawing",message="Drawing...this may take a few moments...")
# ---------------------- draw to Graph ------------------------
blueCounter = 0
redCounter = 0
color_map = []
node_size_map = []
for node in key_list:
if self.page_rank_vector[node] == 1:
color_map.append("red")
redCounter += 1
node_size_map.append(30)
else:
color_map.append("blue")
node_size_map.append(10)
blueCounter += 1
G = nx.Graph()
nodeCounter = 0
edgeCounter = 0
for xx in numberDic:
G.add_node(numberDic[xx])
nodeCounter += 1
for link in key_list:
if link not in numberDic:
continue
for outLink in self.link_Dic[link][3]:
if outLink not in numberDic:
continue
if (G.has_edge(numberDic[link], numberDic[outLink]) or G.has_edge(numberDic[outLink],
numberDic[link])):
continue
else:
G.add_edge(numberDic[link], numberDic[outLink], weight=1)
edgeCounter += 1
options = {
# 'node_color': 'black',
# 'node_size': 20,
'line_color': 'grey',
'linewidths': 0,
'width': 0.1,
'edgelist': None,
'edge_color': 'grey',
'style': 'solid',
'alpha': 1.0,
'arrowstyle': '-|>',
'arrowsize': 10,
'edge_cmap': None,
'edge_vmin': None,
'edge_vmax': None,
'ax': None,
'arrows': True,
'label': None,
'nodelist': None,
'node_shape': "o",
}
#pos = nx.random_layout(G)
print("nodeCounter ", nodeCounter)
print("edgeCounter ", edgeCounter)
print("red(Strong) : ", redCounter)
print("blue(Weeker) : ", blueCounter)
nx.draw(G,node_color=color_map, node_size=node_size_map, **options)
plt.figure(num=None, figsize=(1000, 1000), dpi=1)
# plt.figure(num=None, figsize=(10,10) , dpi=1200)
plt.axis('off')
plt.show()
self.link_Dic = {}
self.page_rank_vector = {}
self.temp_link_Dic = {}
messagebox._show("Graph", "The drawing is finished")
pass
def main():
program = Page_Rank_Link_Analysis()
program.start()
main()