-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathextract_V1.5.py
250 lines (207 loc) · 8.35 KB
/
extract_V1.5.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
# Developed By :
# Syed Faizan Ali SP17-BSE-110
# Muhammad Hammad SP17-BSE-074
# Section : G2
# Submitted To : Dr Salman Khan
# Title : Web Of Science
import pyodbc
import os
def c1(research,cursor,author_dict,source_author,affliation,C1,r_id):
affliation = affliation.split('\n')
for one in affliation:
flag=0
if('[' in one):
ones = one.split(']')
if(';' in ones[0][1:]):
authors = ones[0][1:].split(';')
if('Dept' in ones[-1][1:]):
uni_dept = ones[-1][1:].split("Dept")
uni = uni_dept[0]
dept = uni_dept[-1]
else:
uni = ones[-1][1:].split(",")[0]
dept = "NO Dept"
else:
authors = ones[0][1:]
if('Dept' in ones[-1][1:]):
uni_dept = ones[-1][1:].split("Dept")
uni = uni_dept[0]
dept = uni_dept[-1]
else:
uni = ones[-1][1:].split(",")[0]
dept = "NO Dept"
flag=1
author = authors
if(author_dict.__contains__(author+uni)):
a_id = author_dict[author+uni]
cursor.execute("Insert into Research_Authors values(?,?)",(r_id,a_id))
else:
cursor.execute("Insert into Authors values(?,?,?,?)",(author,uni,dept,source_author))
cursor.execute("SELECT Author_ID AS LastID FROM Authors WHERE Author_ID = @@Identity")
a_id=int(cursor.fetchone()[0])
cursor.execute("Insert into Research_Authors values(?,?)",(r_id,a_id))
author_dict[author+uni]=a_id
else:
authors= fieldData(research,'AF ',['TI ']).split('\n')
if('Dept' in C1):
uni_dept = C1.split("Dept")
uni = uni_dept[0]
dept = uni_dept[-1]
else:
uni = C1.split(",")[0]
dept = "NO Dept"
if(uni==''):
uni="NO uni"
if(flag==0):
for author in authors:
if(author_dict.__contains__(author+uni)):
a_id = author_dict[author+uni]
cursor.execute("Insert into Research_Authors values(?,?)",(r_id,a_id))
else:
cursor.execute("Insert into Authors values(?,?,?,?)",(author,uni,dept,source_author))
cursor.execute("SELECT Author_ID AS LastID FROM Authors WHERE Author_ID = @@Identity")
a_id=int(cursor.fetchone()[0])
cursor.execute("Insert into Research_Authors values(?,?)",(r_id,a_id))
author_dict[author+uni]=a_id
def check(line,end):
for e in end:
if(line.startswith(e)):
return True
return False
def fieldData(research,start,end):
copy = False
data=''
for l in research:
if l.startswith(start):
copy = True
data = l[3:]
continue
elif check(l,end):
copy = False
break
elif copy:
data = data + l[3:]
return data[:-2]
def filterResearch(research,cursor,author_dict,source_author):
language="";doc_type="";no_of_ref=0;time_cited=0;download180=0;download2003=0
publish_year='';start_page=0;end_page=0;reprint_author='';email='';C1=''
for l in research:
if l.startswith('LA '):
language = l[3:].rstrip('\n')
continue
elif l.startswith('DT '):
doc_type = l[3:].rstrip('\n')
continue
elif l.startswith('NR '):
no_of_ref = l[3:].rstrip('\n')
continue
elif l.startswith('TC '):
time_cited = l[3:].rstrip('\n')
continue
elif l.startswith('U1 '):
download180 = l[3:].rstrip('\n')
continue
elif l.startswith('U2 '):
download2003 = l[3:].rstrip('\n')
continue
elif l.startswith('PY '):
publish_year = l[3:].rstrip('\n')
continue
elif l.startswith('BP '):
start_page = l[3:].rstrip('\n')
continue
elif l.startswith('EP '):
end_page = l[3:].rstrip('\n')
continue
elif l.startswith('RP '):
reprint_author = l[3:].rstrip('\n')
continue
elif l.startswith('EM '):
email = l[3:].rstrip('\n')
continue
elif l.startswith('C1 '):
C1 = l[3:]
continue
# authors_names = fieldData(research,"AF ",['TI'])
title = fieldData(research,'TI ',['SO '])
journal = fieldData(research,'SO ',['LA '])
authors_keyword = fieldData(research,'DE ',['ID '])
keywords_plus = fieldData(research,'ID ',['AB '])
abstract = fieldData(research,'AB ',['C1 '])
affliation = fieldData(research,'C1 ',['RP ','EM ','RI ','OI ','CR ','NR '])
web_science = fieldData(research,'WC ',['SC '])
research_areas = fieldData(research,'SC ',['GA '])
# Research Table------------
cursor.execute("INSERT INTO Research VALUES(?,?,?,?,?,?,?,?,?,?,?,?)",
(title,journal,language,doc_type,abstract,no_of_ref,time_cited,download180,download2003,publish_year,start_page,end_page))
cursor.execute("SELECT R_ID AS LastID FROM Research WHERE R_ID = @@Identity")
r_id=int(cursor.fetchone()[0])
# Research Area Table------------
research_areas = research_areas.split(';')
for area in research_areas:
cursor.execute("Insert into Research_Area values(?,?)",(r_id,area))
# Authors keywords Table------------
authors_keyword = authors_keyword.split(';')
for keyword in authors_keyword:
cursor.execute("Insert into Authors_Keywords values(?,?)",(r_id,keyword))
# Keywords pluus Table------------
keywords_plus = keywords_plus.split(';')
for keyword in keywords_plus:
cursor.execute("Insert into Keywords_Plus values(?,?)",(r_id,keyword))
# web of Science Table------------
web_science = web_science.split(';')
for keyword in web_science:
cursor.execute("Insert into web_of_science values(?,?)",(r_id,keyword))
# Reprint Author Table------------
author = reprint_author
author_dep = author.split('(reprint author)')
authors = author_dep[0]
if('Dept' in author_dep[-1][1:]):
uni_dept = author_dep[-1][1:].split("Dept")
uni = uni_dept[0]
dept = uni_dept[-1].split(",")[0]
else:
uni = author_dep[-1][1:].split(",")[0]
dept = "NO Dept"
if(uni==''):
uni='No University'
if(dept==''):
dept='No Dept'
if(email==''):
email='No Email'
cursor.execute("Insert into Reprint_Author values(?,?,?,?,?)",(r_id,authors,uni,dept,email))
# Authors Table------------
c1(research,cursor,author_dict,source_author,affliation,C1,r_id)
# start
author_dict = {}
for i in range(1,13):
path = r"B:\COMSATS_DATA\SEMESTER_6\Data_Warehousing\Web_of_Science_V1.2\data ("+str(i)+")"
dirListing = os.listdir(path)
length = len(dirListing)
length +=1
for j in range(1,length):
print("Folder "+str(i),": File "+str(j))
research = []
conn = pyodbc.connect('Driver={SQL Server};'
'Server=FAIZANSHAH;'
'Database=db_webscience;'
'Trusted_Connection=yes;')
cursor = conn.cursor()
# where Author_Name=? AND Institute_Name=?",(author,uni)
with open("B:\COMSATS_DATA\SEMESTER_6\Data_Warehousing\Web_of_Science_V1.2\data ("+str(i)+")/input("+str(j)+").txt", encoding="utf8") as infile:
copy = False
count = 1
for line in infile:
count +=1
if (line.startswith("PT J") or line.startswith("nullPT J")):
copy = True
continue
elif line.startswith("ER"):
copy = False
source_author = str(i)+"_"+str(j)+"_"+str(count)
filterResearch(research,cursor,author_dict,source_author)
research.clear()
continue
elif copy:
research.append(line)
conn.commit()