Created
October 11, 2023 17:05
-
-
Save misirov/c4bd6cee72df7b1e81b7b4686b125525 to your computer and use it in GitHub Desktop.
EtherscanLabelScraping
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| user_agents = [ | |
| "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537", | |
| "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0", | |
| "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36", | |
| "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36", | |
| "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.1.1 Safari/603.2.4", | |
| "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36", | |
| "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36", | |
| "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0", | |
| "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36", | |
| "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; AS; rv:11.0) like Gecko" | |
| ] | |
| def get_label_name(address): | |
| url = f"https://etherscan.io/address/{address}" | |
| # Etherscan blocks python agents so need to change user agent | |
| headers = { | |
| 'User-Agent': random.choice(user_agents) | |
| } | |
| response = r.get(url, headers=headers) | |
| response.raise_for_status() | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| # Find all relevant HTML elements by using the inspector | |
| label_element = soup.find_all('span', {'class': 'hash-tag text-truncate'}) | |
| if label_element: | |
| return label_element[0].text.strip() | |
| else: | |
| return None | |
| test_address = "0x7d1afa7b718fb893db30a3abc0cfc608aacfebb0" | |
| label_name = get_label_name(test_address) | |
| if label_name: | |
| print(f"Label name for address {test_address}: {label_name}") | |
| else: | |
| print(f"No label name") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment