Spaces:
Sleeping
Sleeping
File size: 4,009 Bytes
15b55f0 2a0c42f 15b55f0 2a0c42f 15b55f0 2a0c42f 15b55f0 |
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 |
from langchain.tools import tool
import requests
from bs4 import BeautifulSoup
from typing import Optional
import re
import sys
from constants import TAVILY_KEY
import os
from tavily import TavilyClient
# Initialize Tavily client (set your API key as an environment variable)
tavily = TavilyClient(TAVILY_KEY)
@tool
def get_npb_player_info(player_name: str) -> str:
"""
Finds a Nippon Professional Baseball (NPB) player's jersey number and team name using Tavily search.
Parameters:
- player_name (str): Full name of the player (e.g., "Taisho Tamai")
Returns:
- str: The player's jersey number and team name, or an error message if not found.
"""
try:
# Search using Tavily for the NPB English profile page
query = f"site:npb.jp/bis/eng/players {player_name}"
search_results = tavily.search(query=query, include_answer=False)
# Find first relevant link to the NPB player profile
player_url = next(
(result["url"] for result in search_results["results"]
if re.match(r"https://npb\.jp/bis/eng/players/\d+\.html", result["url"])),
None
)
if not player_url:
return f"No player page found for '{player_name}'."
# Fetch the player page and extract number and team
headers = {"User-Agent": "Mozilla/5.0"}
response = requests.get(player_url, headers=headers)
soup = BeautifulSoup(response.text, "html.parser")
number = soup.find("li", {"id": "pc_v_no"})
team = soup.find("li", {"id": "pc_v_team"})
if number and team:
return f"{player_name} - #{number.text.strip()} - Team: {team.text.strip()}"
else:
return f"Player page found, but info not parsed properly: {player_url}"
except Exception as e:
return f"Error fetching info for '{player_name}': {e}"
#if __name__ == "__main__":
# print(get_npb_player_info("Taisho Tamai"))
@tool
def get_team_players_by_season(team_name: str, year: int) -> list[str]:
"""
Given a team name and year, returns the list of player names for that NPB season.
Parameters:
- team_name (str): Team name (e.g., "Yomiuri Giants")
- year (int): Season year (e.g., 2023)
Returns:
- List of player names (strings) in the format last name, first name
"""
try:
query = f"site:npb.jp/bis/eng/{year}/stats {team_name}"
search_results = tavily.search(query=query, include_answer=False)
# Find the correct stats page URL for that year
stats_url = next(
(result["url"] for result in search_results["results"]
if re.match(rf"https://npb\.jp/bis/eng/{year}/stats/.+\.html", result["url"])),
None
)
if not stats_url:
print(f"No stats page found for {team_name} in {year}.")
return []
print(stats_url)
headers = {"User-Agent": "Mozilla/5.0"}
response = requests.get(stats_url, headers=headers)
safe_text = response.text.encode(sys.stdout.encoding, errors='replace').decode(sys.stdout.encoding)
response = requests.get(stats_url, headers=headers)
soup = BeautifulSoup(response.text, "html.parser")
# Find all <td class="stplayer"> elements
player_tds = soup.find_all("td", class_="stplayer")
player_names = []
for td in player_tds:
player_name = td.get_text(strip=True)
player_names.append(player_name)
# Remove duplicates preserving order
player_names = list(dict.fromkeys(player_names))
return player_names
except Exception as e:
print(f"Error fetching players for {team_name} {year}: {e}")
return []
if __name__ == "__main__":
team = "Hokkaido Nippon-Ham Fighters"
season_year = 2023
players = get_team_players_by_season(team, season_year)
print(f"Players for {team} in {season_year} season:\n", players)
|