forked from jimbarnesrtp/pf2
-
Notifications
You must be signed in to change notification settings - Fork 0
/
buildStructures.py
218 lines (189 loc) · 6.88 KB
/
buildStructures.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
from bs4 import BeautifulSoup
import requests
import json
import datetime
import codecs
import time
structHolder = {}
structHolder['name'] = 'Pathfinder 2.0 Structures list'
structHolder['date'] = datetime.date.today().strftime("%B %d, %Y")
def get_multi(link):
items = []
res2 = requests.get(link)
res2.raise_for_status()
soup2 = BeautifulSoup(res2.text, 'lxml')
main = soup2.find("span", {'id':'ctl00_MainContent_DetailedOutput'})
traits = main.find_all("span", {"class" : lambda L: L and L.startswith('trai')})
traitHolder = []
for trait in traits:
traitHolder.append(trait.text)
children = main.contents
reachedBreak = False
reachedItem = False
detailHolder = []
notFirstH2 = False
inHeader = False
parentDetails = {}
parentDetails['traits'] = traitHolder
item = {}
item['link'] = link
tagType = ""
itemDetailHolder = []
for child in children:
stringContents = str(child)
if stringContents.startswith("<"):
#print(stringContents)
if child.name == "img":
parentDetails['actions'] = child['alt']
if child.name == "hr":
tagType = ""
reachedBreak = True
inHeader = False
if child.name == "img":
item['actions'] = child['alt']
if child.name == "h1":
inHeader = True
if child.name == "h2":
#print(child.text)
className = ""
try:
className = child['class'][0]
except:
className = ""
if className == "title":
if notFirstH2:
item['text'] = detailHolder + itemDetailHolder
for key in parentDetails.keys():
item[key] = parentDetails[key]
items.append(item)
item = {}
item['link'] = link
itemDetailHolder = []
else:
notFirstH2 = True
reachedBreak = False
reachedItem = True
inHeader = False
name = child.text
start = child.text.find("Item")
item['name'] = child.text[0:start]
if child.name == "b":
if(child.text != "Source"):
tagType = child.text
if child.name == "a":
try:
if child['class'][0] == "external-link" :
item['source'] = child.text
except:
pass
tagType = ""
else:
if reachedBreak:
if(tagType != ""):
if not stringContents.isspace():
parentDetails[tagType] = stringContents
tagType = ""
else:
detailHolder.append(stringContents)
if inHeader:
if tagType != "":
parentDetails[tagType] = stringContents
tagType = ""
if reachedItem:
if tagType != "":
item[tagType] = stringContents
tagType = ""
else:
if not stringContents.isspace():
itemDetailHolder.append(stringContents)
#print(stringContents)
for key in parentDetails.keys():
item[key] = parentDetails[key]
item['text'] = detailHolder + itemDetailHolder
items.append(item)
return items
def get_single(link):
details = {}
itemDetails = {}
res2 = requests.get(link)
res2.raise_for_status()
soup2 = BeautifulSoup(res2.text, 'lxml')
detail = soup2.find(lambda tag: tag.name=='span' and tag.has_attr('id') and tag['id']=="ctl00_MainContent_DetailedOutput")
traits = detail.find_all("span", {"class" : lambda L: L and L.startswith('trai')})
traitHolder = []
for trait in traits:
traitHolder.append(trait.text)
details['traits'] = traitHolder
children = detail.contents
reachedBreak = False
detailHolder = []
tagType = ""
for child in children:
stringContents = str(child)
if stringContents.startswith("<"):
if child.name == "h1":
name = child.text
start = name.find("Item")
details['name'] = name[0:start].strip()
if child.name == "hr":
tagType = ""
reachedBreak = True
if child.name == "a":
try:
if child['class'][0] == "external-link" :
details['source'] = child.text
except:
pass
tagType = ""
if child.name == "b":
if(child.text != "Source"):
tagType = child.text
if child.name == "img":
details['actions'] = child['alt']
if child.name == "i":
if(reachedBreak):
detailHolder.append(child.text)
#else:
#if not stringContents.isspace() :
#detailHolder.append(child.text)
else:
if reachedBreak:
if tagType != "":
if not stringContents.isspace():
details[tagType] = stringContents
else:
if not stringContents.isspace() :
detailHolder.append(stringContents)
else:
if tagType != "":
if not stringContents.isspace():
details[tagType] = stringContents
#print(child)
details['text'] = detailHolder
return details
def get_from_csv(fileName):
items = []
listOfPages = codecs.open(fileName, encoding='utf-8')
t = 0
for line in listOfPages:
t += 1
runeMD = line.split(",")
print("Getting structure for :", runeMD[0],"This url:", runeMD[2].strip('\n'),"|is it multi:",runeMD[1])
if runeMD[1] == "True":
multiHolder = get_multi(runeMD[2].strip('\n'))
for shield in multiHolder:
shield['category'] = "structure"
items.append(shield)
else:
items.append(get_single(runeMD[2].strip('\n')))
return items
def get_all():
structHolder['structures'] = get_from_csv("structures.csv")
return structHolder
#print(get_all())
json_data = json.dumps(get_all(), indent=4)
#print(json_data)
filename = "structures-pf2.json"
f = open(filename, "w")
f.write(json_data)
f.close