steam-group-crawler/group_info.py
2023-06-04 17:21:24 +01:00

71 lines
2.1 KiB
Python

import requests
from bs4 import BeautifulSoup
from ratelimit import limits, sleep_and_retry
# Set up rate limiter, one request per second
CALLS = 1
RATE_LIMIT = 1
@sleep_and_retry
@limits(calls=CALLS, period=RATE_LIMIT)
def get_group_details(group_url_name):
# Regular group page URL
group_url = f"https://steamcommunity.com/groups/{group_url_name}"
try:
group_page_response = requests.get(group_url)
group_page_response.raise_for_status()
except requests.HTTPError as http_err:
print(f"HTTP error occurred: {http_err}")
return
except Exception as err:
print(f"Other error occurred: {err}")
return
group_page_soup = BeautifulSoup(group_page_response.text, "lxml")
# Group Tag
tag_span = group_page_soup.find("span", {"class": "grouppage_header_abbrev"})
tag = tag_span.text.strip() if tag_span else "No tag"
# Group details XML page URL
group_details_url = (
f"https://steamcommunity.com/groups/{group_url_name}/memberslistxml/?xml=1"
)
try:
group_details_response = requests.get(group_details_url)
group_details_response.raise_for_status()
except requests.HTTPError as http_err:
print(f"HTTP error occurred: {http_err}")
return
except Exception as err:
print(f"Other error occurred: {err}")
return
try:
group_details_soup = BeautifulSoup(group_details_response.content, "lxml-xml")
# Group Name
group_name = group_details_soup.find("groupName").text
# Group ID64
group_id64 = group_details_soup.find("groupID64").text
# Member List
members = [member.text for member in group_details_soup.find_all("steamID64")]
return {
"group_id64": group_id64,
"group_name": group_name,
"group_url": group_url,
"tag": tag,
"members": members,
}
except Exception as err:
print(f"Error occurred during parsing of group details XML page: {err}")
if __name__ == "__main__":
# Replace 'ilovebloop' with the desired group URL name
print(get_group_details("CheeseFraud"))