[英]Add data from web-scraping in Python
我有这个 python 脚本,用于从 understat.com 获取 xG 值(特别感谢 @chitown88)。
我想在比赛中至少收到一个红旗的球队名称中添加一个星号 (*)。 例如,在https://understat.com/match/9458 中,哈德斯菲尔德收到了一张红牌,因此在输出中,如果名称旁边有一个 *,即哈德斯菲尔德 *。
有任何想法吗?
这是我的python脚本:
import requests
import json
import re
from pandas.io.json import json_normalize
import pandas as pd
response = requests.get('https://understat.com/match/9458')
shotsData = re.search("shotsData\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(shotsData.groups()[0], 'utf-8').decode('unicode_escape')
shotsObj = json.loads(decoded_string)
match_info = re.search("match_info\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(match_info.groups()[0], 'utf-8').decode('unicode_escape')
matchObj = json.loads(decoded_string)
rostersData = re.search("rostersData\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(rostersData.groups()[0], 'utf-8').decode('unicode_escape')
rostersObj = json.loads(decoded_string)
# Shots Data into a DataFrame
away_shots_df = json_normalize(shotsObj['a'])
home_shots_df = json_normalize(shotsObj['h'])
shots_df = away_shots_df.append(home_shots_df)
# Rosters Data into a DataFrame
away_rosters_df = pd.DataFrame()
for key, v in rostersObj['a'].items():
temp_df = pd.DataFrame.from_dict([v])
away_rosters_df = away_rosters_df.append(temp_df)
home_rosters_df = pd.DataFrame()
for key, v in rostersObj['h'].items():
temp_df = pd.DataFrame.from_dict([v])
home_rosters_df = home_rosters_df.append(temp_df)
rosters_df = away_rosters_df.append(home_rosters_df)
teams_dict = {'a':matchObj['team_a'], 'h':matchObj['team_h']}
match_title = matchObj['team_h'] + ' vs. ' + matchObj['team_a']
#print (shots_df)
# Cumulative chart of xG from the shotsData
import numpy as np
# Convert 'minute' astype int and sort the dataframe by 'minute'
shots_df['minute'] = shots_df['minute'].astype(int)
shots_df['xG'] = shots_df['xG'].astype(float)
timing_chart_df = shots_df[['h_a', 'minute', 'xG']].sort_values('minute')
timing_chart_df['h_a'] = timing_chart_df['h_a'].map(teams_dict)
# Get max value of the 'minute' column to interpolate minute interval between that range
max_value = timing_chart_df['minute'].max()
# Aggregate xG within the same minute
timing_chart_df = timing_chart_df.groupby(['h_a','minute'], as_index=False)['xG'].sum()
# Interpolate for each team/group
min_idx = np.arange(timing_chart_df['minute'].max() + 1)
m_idx = pd.MultiIndex.from_product([timing_chart_df['h_a'].unique(), min_idx], names=['h_a', 'minute'])
# Calculate the running sum
timing_chart_df = timing_chart_df.set_index(['h_a', 'minute']).reindex(m_idx, fill_value=0).reset_index()
timing_chart_df['running_sum_xG'] = timing_chart_df.groupby('h_a')['xG'].cumsum()
timing_chart_T_df = timing_chart_df.pivot(index='h_a', columns='minute', values='running_sum_xG')
timing_chart_T_df = timing_chart_T_df.reset_index().rename(columns={timing_chart_T_df.index.name:match_title})
print (timing_chart_T_df.to_string())
很高兴再次见到你。
您可以简单地检查数据框中红牌的总和:
if away_rosters_df['red_card'].astype(int).sum() > 0:
a_red_card = '*'
else:
a_red_card = ''
if home_rosters_df['red_card'].astype(int).sum() > 0:
h_red_card = '*'
else:
h_red_card = ''
然后将其连接到您想要的文本上:即:
teams_dict = {'a':matchObj['team_a']+a_red_card, 'h':matchObj['team_h']+h_red_card}
完整代码:
import requests
import json
import re
from pandas.io.json import json_normalize
import pandas as pd
response = requests.get('https://understat.com/match/9458')
shotsData = re.search("shotsData\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(shotsData.groups()[0], 'utf-8').decode('unicode_escape')
shotsObj = json.loads(decoded_string)
match_info = re.search("match_info\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(match_info.groups()[0], 'utf-8').decode('unicode_escape')
matchObj = json.loads(decoded_string)
rostersData = re.search("rostersData\s+=\s+JSON.parse\('([^']+)", response.text)
decoded_string = bytes(rostersData.groups()[0], 'utf-8').decode('unicode_escape')
rostersObj = json.loads(decoded_string)
# Shots Data into a DataFrame
away_shots_df = json_normalize(shotsObj['a'])
home_shots_df = json_normalize(shotsObj['h'])
shots_df = away_shots_df.append(home_shots_df)
# Rosters Data into a DataFrame
away_rosters_df = pd.DataFrame()
for key, v in rostersObj['a'].items():
temp_df = pd.DataFrame.from_dict([v])
away_rosters_df = away_rosters_df.append(temp_df)
home_rosters_df = pd.DataFrame()
for key, v in rostersObj['h'].items():
temp_df = pd.DataFrame.from_dict([v])
home_rosters_df = home_rosters_df.append(temp_df)
rosters_df = away_rosters_df.append(home_rosters_df)
if away_rosters_df['red_card'].astype(int).sum() > 0:
a_red_card = '*'
else:
a_red_card = ''
if home_rosters_df['red_card'].astype(int).sum() > 0:
h_red_card = '*'
else:
h_red_card = ''
teams_dict = {'a':matchObj['team_a']+a_red_card, 'h':matchObj['team_h']+h_red_card}
match_title = matchObj['team_h'] + ' vs. ' + matchObj['team_a']
#########################################################################
# Timing Chart is an aggregation (running sum) of xG from the shotsData
#########################################################################
import numpy as np
# Convert 'minute' astype int and sort the dataframe by 'minute'
shots_df['minute'] = shots_df['minute'].astype(int)
shots_df['xG'] = shots_df['xG'].astype(float)
timing_chart_df = shots_df[['h_a', 'minute', 'xG']].sort_values('minute')
timing_chart_df['h_a'] = timing_chart_df['h_a'].map(teams_dict)
# Get max value of the 'minute' column to interpolate minute interval between that range
max_value = timing_chart_df['minute'].max()
# Aggregate xG within the same minute
timing_chart_df = timing_chart_df.groupby(['h_a','minute'], as_index=False)['xG'].sum()
# Interpolate for each team/group
min_idx = np.arange(timing_chart_df['minute'].max() + 1)
m_idx = pd.MultiIndex.from_product([timing_chart_df['h_a'].unique(), min_idx], names=['h_a', 'minute'])
# Calculate the running sum
timing_chart_df = timing_chart_df.set_index(['h_a', 'minute']).reindex(m_idx, fill_value=0).reset_index()
timing_chart_df['running_sum_xG'] = timing_chart_df.groupby('h_a')['xG'].cumsum()
timing_chart_T_df = timing_chart_df.pivot(index='h_a', columns='minute', values='running_sum_xG')
timing_chart_T_df = timing_chart_T_df.reset_index().rename(columns={timing_chart_T_df.index.name:match_title})
from datetime import datetime
home_team = matchObj['team_h']+h_red_card
away_team = matchObj['team_a']+a_red_card
league = matchObj['league']
season = matchObj['season']
date = matchObj['date']
datetime_object = datetime.strptime(date, '%Y-%m-%d %H:%M:%S')
date = datetime_object.strftime('%A, %B %d, %Y')
results_df = pd.DataFrame([[league, season, date, home_team, away_team]], columns = ['League','Season','Date','Home team','Away team'])
home_xg_sum = timing_chart_df[timing_chart_df['h_a'] == home_team].pivot(index='h_a', columns='minute', values='running_sum_xG')
away_xg_sum = timing_chart_df[timing_chart_df['h_a'] == away_team].pivot(index='h_a', columns='minute', values='running_sum_xG')
data = [league, season, date, home_team, away_team] + home_xg_sum.values.tolist()[0] + away_xg_sum.values.tolist()[0]
cols = ['League','Season','Date','Home team','Away team'] + list(home_xg_sum.columns) + list(away_xg_sum.columns)
results_df = pd.DataFrame([data], columns = cols)
输出:
print(results_df.to_string())
League Season Date Home team Away team 0 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 0 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
0 EPL 2018 Saturday, February 23, 2019 Newcastle United Huddersfield* 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.087855 0.087855 0.087855 0.087855 0.474551 0.474551 0.474551 0.474551 0.52089 0.52089 0.52089 0.588242 0.588242 0.588242 0.588242 0.588242 0.588242 0.588242 0.650563 0.650563 0.650563 0.713521 0.765269 0.765269 0.765269 0.765269 0.765269 0.765269 0.765269 0.765269 0.765269 0.780235 0.862191 0.862191 0.862191 0.972581 1.00803 1.00803 2.01324 2.01324 2.103931 2.103931 2.103931 2.103931 2.248354 2.248354 2.248354 2.278213 2.278213 2.278213 2.278213 2.278213 2.278213 2.397133 2.397133 2.397133 2.397133 2.397133 2.397133 2.484387 2.484387 2.624275 2.624275 2.755339 2.868987 2.868987 2.868987 2.868987 3.011753 3.011753 3.011753 3.011753 3.011753 3.011753 3.011753 3.011753 3.026651 3.026651 3.026651 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.110397 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.120421 0.133949
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.