GramsHelixExplorer/sort_wallets.py at master · galmeida-dev/GramsHelixExplorer · GitHub

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
import csv
import os
from datetime import datetime
from bs4 import BeautifulSoup
import urllib.request
import urllib
import re
import threading
import traceback

class Transaction(object):
	"""docstring for Transaction"""
	def __init__(self, date, address, amount, trans):
		super(Transaction, self).__init__()
		self.date = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
		self.address = address
		self.amount = amount
		self.trans = trans

	def __eq__(self, other):
		return self.date == other.date and self.address == other.address and self.amount == other.amount and self.trans == other.trans

	def __hash__(self):
		return hash(('date', self.date,	'address', self.address, 'amount', self.amount, 'trans', self.trans))

def get_address(date, wallet, amount, txid):

	base = 'https://www.walletexplorer.com/txid/'
	url = base + txid

	j = 0
	while True:
		try:
			soup = BeautifulSoup(urllib.request.urlopen(url).read(), 'html.parser')
			break
		except Exception:
			j = j + 1
			if j > 50:
				print('Skipping '+url)
				return
			continue
		break

	try:
		tx_table = soup.find_all('table', class_='tx')[0]
	except Exception as e:
		print(url)

	top = tx_table.find_all('tr')
	address = ""
	for tr in top[1].find_all('table', class_='empty')[1].find_all('tr'):
		link = tr.find_all('td')
		text_amount = link[2].text

		if '(' in text_amount:
			continue

		amn = float(re.findall('\d+\.?\d*',text_amount)[0])

		if float(amount) == amn:
			address = link[0].text
			#print(address)
			break


	trans.append(Transaction(date, address, amount, txid))

	pass

path = os.getcwd()
trans = []
threads = []
with open(path+'\..\..\inputs.csv', 'r') as inputfile:
	file_contents = inputfile.read().splitlines(True)
	content = file_contents[1:]
	lines = len(content)
	j = 0

	inputfile.seek(0)
	reader = csv.DictReader(inputfile)
	for line in reader:
		if line['received_amount']:
			while threading.active_count() > 50:
				continue

			t = threading.Thread(target=get_address, args=(line['date'], line['received_from'], line['received_amount'], line['transaction'], ))
	#for line in content:
	#	line_content = line.split(',')
	#	if line_content[2]:
	#		while threading.active_count() > 50:
	#			continue
#
#			t = threading.Thread(target=get_address, args=(line_content[0], line_content[1], line_content[2], line_content[6], ))

			threads.append(t)
			t.start()
			j = j + 1
			print(j/lines)

	j = 0
	for t in threads:
		j = j + 1
		print('Waiting for: '+str(j)+'/'+str(len(threads)))
		t.join()

with open('sorted_input.csv', 'w') as sortedinputfile:
	sortedinputfile.write('date,received_amount,address,txid\n')
	for t in sorted(list(set(trans)), key=lambda s: s.date, reverse=True):
		sortedinputfile.write(str(t.date)+','+str(t.amount)+','+t.address+','+t.trans+'\n')

print('Sorting outputs')
trans = []
with open('outputs.csv', 'r') as outputfile:
	reader = csv.DictReader(outputfile)
	for line in reader:
		trans.append(Transaction(line['date'], line['address'], line['amount'], line['txid']))

	#file_contents = outputfile.read().splitlines(True)
	#content = file_contents[1:]
	#trans = []
	#for line in content:
	#	line_content = line.split(',')
	#	if line_content[2]:
	#		trans.append(Transaction(line_content[0], line_content[1], line_content[2], line_content[3]))


with open('sorted_output.csv', 'w') as sortedoutputfile:
	sortedoutputfile.write('date,sent_amount,address,txid\n')
	for t in sorted(list(set(trans)), key=lambda s: s.date, reverse=True):
		sortedoutputfile.write(str(t.date)+','+str(t.amount)+','+t.address+','+t.trans+'\n')