generated from S2-group/template-replication-package
-
Notifications
You must be signed in to change notification settings - Fork 3
/
scrapeRAA.py
231 lines (176 loc) · 8.04 KB
/
scrapeRAA.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
from lxml import etree
import csv
import code
DBLP_XML = './dblp-23-02-2023.xml'
DBLP_DTD = './dblp.dtd'
YEAR_MIN = 2012
YEAR_MAX = 2023
#I included the second / because otherwise if there is a conference e.g. icrac it will get included.
SA_VENUES = tuple([
'conf/icsa/',
'conf/ecsa/',
'conf/wicsa/',
'conf/qosa/',
'conf/cbse/',
'journals/jsa/'
])
RO_VENUES = tuple([
'conf/icra/',
'conf/iros/',
'conf/rss/',
'conf/irc/',
'journals/trob/',
'journals/ral/',
'journals/ijrr/',
'journals/scirobotics/'
])
SAS_VENUES = tuple([
'conf/acsos/',
'conf/saso/',
'conf/icac/',
'conf/seams/',
'journals/taas/'
])
venue_to_category = {
SA_VENUES : "Software_Architecture",
RO_VENUES : "Robotics",
SAS_VENUES : "Self-Adaptive_Systems"
}
ARCHITECTURE_KWORDS = ["architect"]
ROBOTICS_KWORDS = ["robot"]
SAS_KWORDS = ["self-", "adapt"]
FROM_ROBOTICS = ARCHITECTURE_KWORDS + SAS_KWORDS
FROM_SOFTWARE = ROBOTICS_KWORDS + SAS_KWORDS
FROM_SAS = ROBOTICS_KWORDS + ARCHITECTURE_KWORDS
venue_to_words = {
SA_VENUES : FROM_SOFTWARE,
RO_VENUES : FROM_ROBOTICS,
SAS_VENUES : FROM_SAS
}
# Iterate over a large-sized xml file without the need to store it in memory in
# full. Yields every next element. Source:
# https://stackoverflow.com/questions/9856163/using-lxml-and-iterparse-to-parse-a-big-1gb-xml-file
def iterate_xml(xmlfile):
etree.DTD(file=DBLP_DTD)
doc = etree.iterparse(xmlfile, events=('start', 'end'), load_dtd=True, resolve_entities=True, encoding='utf-8')
_, root = next(doc)
start_tag = None
for event, element in doc:
if event == 'start' and start_tag is None:
start_tag = element.tag
if event == 'end' and element.tag == start_tag:
yield element
start_tag = None
root.clear()
def title_criteria(key, venue_list, title, counter, explain=False, dblp_entry=None):
title_lowered = title.lower()
title_keywords = venue_to_words[venue_list]
category = ""
if explain:
print("keywords " + str(title_keywords) + "found in " + str(title) + "is " + str(any(keyword in title for keyword in title_keywords)))
print("key starts with " + str(venue_list) + "in " + str(key) + "is " + str(key.startswith(venue_list)))
return_value = ((key.startswith(venue_list) or ((True) and key.startswith("conf/icse") and (dblp_entry is not None) and ("SEAMS" in dblp_entry.find('booktitle').text)) ) and any(keyword in title_lowered for keyword in title_keywords))
if(return_value):
counter[0]+=1
category = venue_to_category[venue_list]
return category
def venue_criteria(key, venue_list, counter, explain=False, dblp_entry=None):
category = ""
if explain:
print("key starts with " + str(venue_list) + "in " + str(key) + "is " + str(key.startswith(venue_list)))
old_seams_check = (True) and key.startswith("conf/icse") and (dblp_entry is not None) and ("SEAMS" in dblp_entry.find('booktitle').text)
return_value = ( (key.startswith(venue_list) or (old_seams_check)) )
if(return_value):
counter[0]+=1
category = venue_to_category[venue_list]
return category
def filter_by_title():
HITS = 0
csv_file = open(input("csv file name? > ")+'.csv', 'w', encoding='utf-8', newline="")
writer = csv.writer(csv_file, delimiter=",")
header = ["hit num", "title", 'year', "authors", "key", "ee", "venue_category"]
writer.writerow(header)
# The db key should start with any of the venues we are interested in,
# as well as be within the desired year range.
ro_counter = [0]
sa_counter = [0]
sas_counter = [0]
for dblp_entry in iterate_xml(DBLP_XML):
key = dblp_entry.get('key')
year_subelem = dblp_entry.find('year')
if((year_subelem is not None) and (int(year_subelem.text) >= YEAR_MIN) and (int(year_subelem.text) <= YEAR_MAX)):
# Remove any potential HTML content (such as <i>) from the title.
title = ''.join(dblp_entry.find('title').itertext())
match_robotics = title_criteria(key,RO_VENUES, title, ro_counter)
match_software = title_criteria(key,SA_VENUES, title, sa_counter)
match_adaptive = title_criteria(key, SAS_VENUES, title, sas_counter, dblp_entry=dblp_entry)
matched_criteria = match_robotics or match_software or match_adaptive
if(matched_criteria): #an any with extra steps to get the return value in a variable.
# add to result.
# Merge the names of all authors of the work.
authors = ' & '.join(''.join(author.itertext()) for author in
dblp_entry.findall('author'))
# Obtain the source (usually in the form of a DOI link).
ee = dblp_entry.find('ee')
if ee is not None:
ee = ee.text
# Compile csv row.
row = [HITS,
title.replace(',', ';'),
dblp_entry.find('year').text,
authors,
key,
ee,
matched_criteria]
writer.writerow(row)
HITS += 1
print("\r TOTAL HITS : " + str(HITS) + " ROBOTICS HITS: " + str(ro_counter[0]) + " ARCHITECTURE HITS: " + str(sa_counter[0]) + " SAS HITS: " + str(sas_counter[0]), end="")
# Parse all entries in the DBLP database.
print("")
def get_all():
HITS = 0
csv_file = open(input("csv file name? > ")+'.csv', 'w', encoding='utf-8', newline="")
writer = csv.writer(csv_file, delimiter=",")
header = ["hit num", "title", 'year', "authors", "key", "ee", "venue_category"]
writer.writerow(header)
# The db key should start with any of the venues we are interested in,
# as well as be within the desired year range.
ro_counter = [0]
sa_counter = [0]
sas_counter = [0]
for dblp_entry in iterate_xml(DBLP_XML):
key = dblp_entry.get('key')
year_subelem = dblp_entry.find('year')
if((year_subelem is not None) and (int(year_subelem.text) >= YEAR_MIN) and (int(year_subelem.text) <= YEAR_MAX)):
# Remove any potential HTML content (such as <i>) from the title.
title = ''.join(dblp_entry.find('title').itertext())
match_robotics = venue_criteria(key,RO_VENUES, ro_counter)
match_software = venue_criteria(key,SA_VENUES, sa_counter)
match_adaptive = venue_criteria(key, SAS_VENUES, sas_counter, dblp_entry=dblp_entry)
matched_criteria = match_robotics or match_software or match_adaptive
if(matched_criteria): #an any with extra steps to get the return value in a variable.
# add to result.
# Merge the names of all authors of the work.
authors = ' & '.join(''.join(author.itertext()) for author in
dblp_entry.findall('author'))
# Obtain the source (usually in the form of a DOI link).
ee = dblp_entry.find('ee')
if ee is not None:
ee = ee.text
# Compile csv row.
row = [HITS,
title.replace(',', ';'),
dblp_entry.find('year').text,
authors,
key,
ee,
matched_criteria]
writer.writerow(row)
HITS += 1
print("\r TOTAL HITS : " + str(HITS) + " ROBOTICS HITS: " + str(ro_counter[0]) + " ARCHITECTURE HITS: " + str(sa_counter[0]) + " SAS HITS: " + str(sas_counter[0]), end="")
# Parse all entries in the DBLP database.
print("")
if __name__ == "__main__":
get_all()
input("done with get all")
filter_by_title()