加载 csv 并将每个值传递给 url 参数？

Question

我正在尝试从 nba.com 汇总 NBA 球员数据。我在 csv 中有一个玩家 ID 列表。我想加载每个玩家 id 并将其传递到参数列表中。然后使用 requests.get 中的参数列表。当我直接输入玩家 ID 作为参数时，request.get 起作用。并且通过该函数循环的 csv 测试似乎有效。但是，我无法成功地将 playerids 传递到参数列表中。我试过查看类似的 nba python 代码，但看不出哪里出错了。

'''

import pandas as pd
import requests
import csv

best_db=pd.DataFrame()


def table_Scrape():
    
    global best_db 
    
    with open("SHORT_ID_plyr.csv", "r") as f_urls: 
        f_urls_list = csv.reader(f_urls, delimiter=',') 
        next(f_urls_list)    
        
        ##step5. open 1st url from .csv
        for lines in f_urls_list:        
            u = lines[0]
            print(u) #<loop test
            # import requests
            player_id = u
            
            url = """
            http://stats.nba.com/stats/playergamelogs?DateFrom=&DateTo=&GameSegment=&LastNGames=0&LeagueID=00&Location=&MeasureType=Base&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Totals&Period=0&PlayerID=203932&PlusMinus=N&Rank=N&Season=2021-22&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&VsConference=&VsDivision=
            """
                #url = """
                #https://stats.nba.com/stats/leaguedashplayerstats?College=&Conference=&Country=&DateFrom=&DateTo=&Division=&DraftPick=&DraftYear=&GameScope=&GameSegment=&Height=&LastNGames=0&LeagueID=00&Location=&MeasureType=Base&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Totals&Period=0&PlayerExperience=&PlayerPosition=&PlusMinus=N&Rank=N&Season=2021-22&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&StarterBench=&TeamID=0&TwoWay=0&VsConference=&VsDivision=&Weight=
                #"""
            header_dict = {
                'User-Agent': 'Mozilla/5.0',
                'x-nba-stats-origin': 'stats',
                'x-nba-stats-token': 'true',
                'Referer': 'https://stats.nba.com',
                'Connection': 'keep-alive',
                'Pragma': 'no-cache',
                'Cache-Control': 'no-cache',
                'Host': 'stats.nba.com'
            }

            params = {
                'LastNGames': '0',
                'LeagueID': '00',
                'MeasureType': 'Base',
                'Month': '0',
                'OpponentTeamID': '0',
                'PORound': '0',
                'PaceAdjust': 'N',
                'PerMode': 'Totals',
                'Period': '0',
                'PlayerID': u,
                'PlusMinus': 'N',
                'Rank': 'N',
                'Season': '2021-22',
                'SeasonType': 'Regular+Season'
                }

            res = requests.get(url, headers=header_dict, params=params)
            json_set = res.json()
            headers = json_set['resultSets'][0]['headers']
            data_set = json_set['resultSets'][0]['rowSet']
            df = pd.DataFrame(columns=headers)
            df.head #test the dataframe NOTE: does not appear to be working either
            
table_Scrape() #call the function

Answer 1

您正在将有效负载传递到已经具有带有硬编码播放器 ID 的有效负载的 url。将 palyer_id 变量放入 url

import pandas as pd
import requests


best_db=pd.DataFrame()


def table_Scrape():
    
    df = pd.read_csv('SHORT_ID_plyr.csv')
    player_id_list = list(df['PLAYER_ID'])
        
    for player_id in player_id_list:
        print(player_id)
        url = f"""http://stats.nba.com/stats/playergamelogs?DateFrom=&DateTo=&GameSegment=&LastNGames=0&LeagueID=00&Location=&MeasureType=Base&Month=0&OpponentTeamID=0&Outcome=&PORound=0&PaceAdjust=N&PerMode=Totals&Period=0&PlayerID={player_id}&PlusMinus=N&Rank=N&Season=2021-22&SeasonSegment=&SeasonType=Regular+Season&ShotClockRange=&VsConference=&VsDivision="""

        header_dict = {
            'User-Agent': 'Mozilla/5.0',
            'x-nba-stats-origin': 'stats',
            'x-nba-stats-token': 'true',
            'Referer': 'https://stats.nba.com',
            'Connection': 'keep-alive',
            'Pragma': 'no-cache',
            'Cache-Control': 'no-cache',
            'Host': 'stats.nba.com'
        }

        res = requests.get(url, headers=header_dict)
        print(res.text)
        json_set = res.json()
        headers = json_set['resultSets'][0]['headers']
        data_set = json_set['resultSets'][0]['rowSet']
        df = pd.DataFrame(data_set,columns=headers)
        print(df.head()) #test the dataframe NOTE: does not appear to be working either
            
table_Scrape() #call the function