Skip to content

Instantly share code, notes, and snippets.

@wenweih
Last active January 11, 2019 05:58
Show Gist options
  • Save wenweih/1cac6afabba7bd0b67aa32dcfcd480b5 to your computer and use it in GitHub Desktop.
Save wenweih/1cac6afabba7bd0b67aa32dcfcd480b5 to your computer and use it in GitHub Desktop.
Query top accounts from Etherscan
#!/usr/bin/env python
import requests
from bs4 import BeautifulSoup
import csv
def dump(soup):
table = soup.find_all("div", class_="table-responsive")
for t in table:
for tr in t.find_all('tr'):
tds = tr.find_all('td')
rows = [0] * len(tds)
for i in range(len(tds)):
rows[i] = tds[i].get_text()
if i == 1:
isContract = tds[i].find("i")
if isContract is not None:
rows[i] = "contract account"
else:
rows[i] = 'normal account'
try:
writer.writerow({'Rank': rows[0],
'Type': rows[1],
'Address': rows[2],
'Belong': rows[3],
'Balance': rows[4],
'Percentage': rows[5],
'TxCount': rows[6]
})
print("Rank: " + rows[0] + " Address: ", rows[2])
except:
pass
with open('ethereum_top_accounts.csv', 'w') as f:
fieldnames = ['Rank', 'Type', 'Address', 'Belong', 'Balance', 'Percentage', 'TxCount']
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
for page in range (1, 101):
URL = "https://etherscan.io/accounts/" + str(page) + "?ps=100"
sess = requests.Session()
soup = BeautifulSoup(sess.get(URL).text, 'html.parser')
rows = dump(soup)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment