Created
May 18, 2022 01:31
-
-
Save zduymz/c45007064b1b56093716d7b0399f91c7 to your computer and use it in GitHub Desktop.
crawling eldenring dataset from gamerguides.com
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
import requests | |
from bs4 import BeautifulSoup | |
paths = ["armors", "ashes-of-war", "bosses", "enemies", "items", "locations", "magic-spells", "npcs", "shields", "skills", "spirit-ashes", "weapons"] | |
def download(path): | |
output = f'/tmp/{path}.csv' | |
data = [] | |
headers = [] | |
text = requests.get(f'https://www.gamerguides.com/elden-ring/database/{path}').text | |
soup = BeautifulSoup(text, 'html.parser') | |
# header | |
for th in soup.find_all('table')[1].find('thead').find('tr').find_all('th'): | |
headers.append(th.text) | |
# data | |
for tr in soup.find_all('table')[1].find('tbody').find_all('tr'): | |
line = {} | |
for td in tr.find_all('td'): | |
index = td.get('data-title') | |
if index.lower() == 'icon': | |
value = td.find('img').get('src') | |
else: | |
value = td.text | |
line[index] = value | |
data.append(line) | |
header_tpl = ','.join([f'{{{x}}}' for x in headers]) + '\n' | |
with open(output, 'w') as f: | |
f.write(','.join(headers) + '\n') | |
for line in data: | |
f.write(header_tpl.format(**line)) | |
print("Done") | |
for path in paths: | |
print(f'Downloading {path}') | |
download(path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment