I'm an intermediate coder, and I made a project where a user can input an NBA player and data of that player shows up from a JSON file. Now, I'm trying to add a picture of the player but it almost seems impossible. I have never been able to add a picture to a python project.
from requests import get
from pprint import PrettyPrinter
from IPython.display import Image
from IPython.core.display import HTML
from difflib import get_close_matches
BASE_URL = "https://data.nba.net"
ALL_JSON = "/prod/v1/today.json"
printer = PrettyPrinter()
data = get(BASE_URL + ALL_JSON).json()
def get_links():
data = get(BASE_URL + ALL_JSON).json()
links = data['links']
return links
def get_teams():
teams = get_links()['teams']
all_teams = get(BASE_URL + teams).json()['league']['standard']
return all_teams
def ask_player():
players = get_links()['leagueRosterPlayers']
all_players = get(BASE_URL + players).json()['league']['standard']
all_teams = get_teams()
topic = input('Type the player you wish to know more about:')
firstName = topic.split()[0]
lastName = topic.split()[1]
playerselected = list(filter(lambda x: x['firstName'] == firstName and x['lastName'] == lastName, all_players ))
if not playerselected:
# Get a list of all player names for suggestions
player_names = [f"{p['firstName']} {p['lastName']}" for p in all_players]
# Find the closest match to the entered player name
suggestions = get_close_matches(topic, player_names)
if suggestions:
if len(suggestions) > 1:
print(f"Player {topic} was not found. Did you mean:")
for i, suggestion in enumerate(suggestions):
print(f"{i + 1}. {suggestion}")
choice = int(input("Enter the number of your choice:"))
playerselected = list(filter(lambda x: f"{x['firstName']} {x['lastName']}" == suggestions[choice - 1], all_players))
else:
playerselected = list(filter(lambda x: f"{x['firstName']} {x['lastName']}" == suggestions[0], all_players))
else:
print(f"Player {topic} was not found.")
return
if not playerselected:
return
for standard in playerselected:
name = standard['firstName']
name2 = standard['lastName']
team_id = standard['teamId']
team = next(t['fullName'] for t in all_teams if t['teamId'] == team_id)
jersey = standard['jersey']
college = standard['collegeName']
dob = standard['dateOfBirthUTC']
years = standard['yearsPro']
printer.pprint(f"{name} {name2}, jersey number {jersey}, is playing for {team}, went to {college} college, was born in {dob}, and has been in the nba for {years} full year(s).")
ask_player()
My code is above. I tried using IPython displays, but that didnt work. Please help me!
I'm just a few hours into learning Python so please go easy with me! I'm just wanting to scrape scores and scorers off a website, I've been able to do that, however, I'm only getting one scorer (if there is one!), when there are multiple goal scorers I am only getting the first. I think I'm trying to look for multiple scorers under '# Home Scorers'.
My code:
from bs4 import BeautifulSoup
import requests
import pandas as pd
url = "https://www.skysports.com/football-results"
match_results = {}
match_details = {}
match_no = 0
response = requests.get(url)
data = response.text
soup = BeautifulSoup(data,'html.parser')
matches = soup.find_all('div',{'class':'fixres__item'})
for match in matches:
try:
match_url_get = match.find('a',{'class':'matches__item matches__link'}).get('href')
match_url = match_url_get if match_url_get else "unknown"
event_id = match_url[-6:]
match_response = requests.get(match_url)
match_data = match_response.text
match_soup = BeautifulSoup(match_data,'html.parser')
# Match Details
match_date = match_soup.find('time',{'class':'sdc-site-match-header__detail-time'}).text
match_location = match_soup.find('span',{'class':'sdc-site-match-header__detail-venue'}).text
match_info = match_soup.find('p',{'class':'sdc-site-match-header__detail-fixture'}).text
# Home Scores & Team
home_details = match_soup.find_all('span',{'class':'sdc-site-match-header__team-name sdc-site-match-header__team-name--home'})
for home_detail in home_details:
home_team = home_detail.find('span',{'class':'sdc-site-match-header__team-name-block-target'}).text
home_score_get = match_soup.find('span',{'class':'sdc-site-match-header__team-score-block','data-update':'score-home'})
home_score = home_score_get.text if home_score_get else "none"
# Home Scorers
home_scorer_details = match_soup.find_all('ul',{'class':'sdc-site-match-header__team-synopsis','data-update':'synopsis-home'})
for home_scorer_detail in home_scorer_details:
goal_scorer_get = home_scorer_detail.find('li',{'class':'sdc-site-match-header__team-synopsis-line'})
goal_scorer = goal_scorer_get.text if goal_scorer_get else "none"
goal_score_minute_get = home_scorer_detail.find('span',{'class':'sdc-site-match-header__event-time'})
goal_score_minute = goal_score_minute_get.text if goal_score_minute_get else "none"
# Away Scores & Team
away_details = match_soup.find_all('span',{'class':'sdc-site-match-header__team-name sdc-site-match-header__team-name--away'})
for away_detail in away_details:
away_team = away_detail.find('span',{'class':'sdc-site-match-header__team-name-block-target'}).text
away_score_get = match_soup.find('span',{'class':'sdc-site-match-header__team-score-block','data-update':'score-away'})
away_score = away_score_get.text if away_score_get else "none"
# Home Scorers
away_scorer_details = match_soup.find_all('ul',{'class':'sdc-site-match-header__team-synopsis','data-update':'synopsis-away'})
for away_scorer_detail in away_scorer_details:
away_goal_scorer_get = away_scorer_detail.find('li',{'class':'sdc-site-match-header__team-synopsis-line'})
away_goal_scorer = away_goal_scorer_get.text if away_goal_scorer_get else "none"
away_goal_score_minute_get = away_scorer_detail.find('span',{'class':'sdc-site-match-header__event-time'})
away_goal_score_minute = away_goal_score_minute_get.text if away_goal_score_minute_get else "none"
print("Match: ",event_id , "Match Date:", match_date, "Match Location:", match_location, "Match Info:", match_info, "\nResult: ", home_team, home_score, away_team, away_score)
print("Home Scorer:", goal_scorer, "Minute:",goal_score_minute, "\nAway Scorer:", away_goal_scorer, "Minute:",away_goal_score_minute)
print(match_date)
except:
pass
match_no+=1
match_results[match_no] = [event_id, home_team, home_score, away_team, away_score, match_url, match_date, match_location, match_info]
match_details[match_no] = [event_id, goal_scorer, goal_score_minute, away_goal_scorer, away_goal_score_minute]
Period = "2021-22"
print("Total Matches: ", match_no)
match_results = pd.DataFrame.from_dict(match_results, orient='index', columns = ['Event_ID:', 'Home Team:','Home Score:','Away Team:','Away Score:','Link:','Match Date:','Match Location:','Match Info:'])
match_results.to_csv("Python/FL/Premier League Results (SkySports.com) " + Period + ".csv")
match_details = pd.DataFrame.from_dict(match_details, orient='index', columns = ['Event_ID:', 'Home Goal:','Home Goal Minute:','Away Goal:','Away Goal Minute:'])
match_details.to_csv("Python/FL/Premier League Details (SkySports.com) " + Period + ".csv")
So the bit that's not working correctly is:
# Home Scorers
home_scorer_details = match_soup.find_all('ul',{'class':'sdc-site-match-header__team-synopsis','data-update':'synopsis-home'})
for home_scorer_detail in home_scorer_details:
goal_scorer_get = home_scorer_detail.find('li',{'class':'sdc-site-match-header__team-synopsis-line'})
goal_scorer = goal_scorer_get.text if goal_scorer_get else "none"
goal_score_minute_get = home_scorer_detail.find('span',{'class':'sdc-site-match-header__event-time'})
goal_score_minute = goal_score_minute_get.text if goal_score_minute_get else "none"
Any ideas how I can return multiple rows for that bit?!
Thanks in advance :)
home_scorer_details only has 1 item, the unordered list itself.
To get all the scorers you need to get the items in that list.
The following code, which is pretty rough, will create a list of dictionaries where each dictionary has the name of the scorer and the minute(s) they scored.
You could use similar code to get all the away scorers.
Like I said, this code is rough and needs refined but it should give you a start.
# Home Scorers
home_scorer_details = match_soup.find_all('ul',{'class':'sdc-site-match-header__team-synopsis','data-update':'synopsis-home'})
home_scorers = []
for home_scorer_detail in home_scorer_details[0].find_all('li'):
goal_scorer = home_scorer_detail.text
goal_score_minute_get = home_scorer_detail.find('span',{'class':'sdc-site-match-header__event-time'})
goal_score_minute = goal_score_minute_get.text if goal_score_minute_get else "none"
home_scorers.append({'scorer': goal_scorer, 'minute': goal_score_minute})
print(home_scorers)
I'm attempting to extract review data from a popular review aggregator. I'm running into an issue with the data being returned. Essentially the for loop "for review in reviews" is just extracting the first item in the list regardless of the position in the iteration. For example, a page with 20 reviews, I'll just get the information of the first review repeated 20 times.
I apologize for the html tags... it didn't make it easy...
def parse_gym_reviews_page(self, response):
reviews = response.xpath('//li [#class="lemon--li__373c0__1r9wz margin-b3__373c0__q1DuY padding-b3__373c0__342DA border--bottom__373c0__3qNtD border-color--default__373c0__3-ifU"]')
gym = response.xpath('//h1[#class="lemon--h1__373c0__2ZHSL heading--h1__373c0__dvYgw undefined heading--inline__373c0__10ozy"]/text()').extract_first()
about = response.xpath('//div [#class="lemon--div__373c0__1mboc margin-b1__373c0__1khoT border-color--default__373c0__3-ifU"]/p/span//text()').extract_first()
region = response.xpath('//p [#class="lemon--p__373c0__3Qnnj text__373c0__2Kxyz text-color--normal__373c0__3xep9 text-align--left__373c0__2XGa-"]/text()').extract_first()
avg_rating = float(response.xpath('//span [#class="lemon--span__373c0__3997G display--inline__373c0__3JqBP border-color--default__373c0__3-ifU"]/div/#aria-label').extract_first().split()[0])
for review in reviews:
user_name = review.xpath('//div [#class="lemon--div__373c0__1mboc border-color--default__373c0__3-ifU"]//a [#class="lemon--a__373c0__IEZFH link__373c0__1G70M link-color--inherit__373c0__3dzpk link-size--inherit__373c0__1VFlE"]/text()').extract_first()
user_id = review.xpath('//div [#class="lemon--div__373c0__1mboc border-color--default__373c0__3-ifU"]//a [#class="lemon--a__373c0__IEZFH link__373c0__1G70M link-color--inherit__373c0__3dzpk link-size--inherit__373c0__1VFlE"]/#href').extract_first().partition("=")[2]
rating = int(review.xpath('//div [#class="lemon--div__373c0__1mboc arrange-unit__373c0__o3tjT arrange-unit-grid-column--8__373c0__2dUx_ border-color--default__373c0__3-ifU"]//div/#aria-label').extract_first().split()[0])
text = review.xpath('//div [#class ="lemon--div__373c0__1mboc arrange-unit__373c0__o3tjT arrange-unit-grid-column--8__373c0__2dUx_ border-color--default__373c0__3-ifU"]//p [#class= "lemon--p__373c0__3Qnnj text__373c0__2Kxyz comment__373c0__3EKjH text-color--normal__373c0__3xep9 text-align--left__373c0__2XGa-"]/span [#class="lemon--span__373c0__3997G raw__373c0__3rKqk"]/text()').extract_first()
reviewer_date = review.xpath('//span [#class="lemon--span__373c0__3997G text__373c0__2Kxyz text-color--mid__373c0__jCeOG text-align--left__373c0__2XGa-"]/text()').extract_first()
item = YelpItem()
item["gym"] = gym
item["about"] = about
item["region"] = region
item["num_review"] = num_review
item["avg_rating"] = avg_rating
item["user_name"] = user_name
item["user_id"] = user_id
item["rating"] = rating
item["text"] = text
item["reviewer_date"] = reviewer_date
yield item
I am trying to return an array of constructed objects that are build on top of objects that I retrieve from some url plus another fields that I get from another url.
I have an array that consists of two arrays that each has about 8000 objects...
I have tried to make each object construction as a thread however it still takes a lot of time...
Any solution? Here is my code:
def get_all_players_full_data(ea_players_json):
all = []
ea_players_json = list(ea_players_json.values())
for i in range(len(ea_players_json)):
for player_obj in ea_players_json[i]:
all.append(player_obj)
for player_obj in range(len(all)):
all_data = []
with concurrent.futures.ThreadPoolExecutor(len(all)) as executor:
for player_data in all:
future = executor.submit(build_full_player_data_obj, player_data)
print(future.result())
all_data.append(future.result())
def build_full_player_data_obj(ea_player_data):
if ea_player_data.get("c") is not None:
player_full_name = ea_player_data.get("c")
else:
player_full_name = ea_player_data.get("f") + " " + ea_player_data.get("l")
player_id = ea_player_data.get("id")
# go to futhead to find all cards of that player
futhead_url_player_data = f'{FUTHEAD_PLAYER}{player_full_name}'
details_of_specific_player = json.loads(requests.get(futhead_url_player_data).content)
cards_from_the_same_id = []
for player_in_json_futhead in details_of_specific_player:
if player_in_json_futhead["player_id"] == player_id:
rating = player_in_json_futhead["rating"]
specific_card_id = player_in_json_futhead["def_id"]
revision = player_in_json_futhead["revision_type"]
name = player_in_json_futhead["full_name"]
nation = player_in_json_futhead["nation_name"]
position = player_in_json_futhead["position"]
club = player_in_json_futhead["club_name"]
cards_from_the_same_id.append(Player(specific_card_id, name, rating, revision, nation,
position, club))
return cards_from_the_same_id
I am trying to parse data from a website by inserting the data into a list, but the list comes back empty.
url =("http://www.releasechimps.org/resources/publication/whos-there-md- anderson")
http = urllib3.PoolManager()
r = http.request('Get',url)
soup = BeautifulSoup(r.data,"html.parser")
#print(r.data)
loop = re.findall(r'<td>(.*?)</td>',str(r.data))
#print(str(loop))
newLoop = str(loop)
#print(newLoop)
for x in range(1229):
if "\\n\\t\\t\\t\\t" in loop[x]:
loop[x] = loop[x].replace("\\n\\t\\t\\t\\t","")
list0_v2.append(str(loop[x]))
print(loop[x])
print(str(list0_v2))
Edit: Didn't really have anything else going on, so I made your data format into a nice list of dictionaries. There's a weird <td height="26"> on monkey 111, so I had to change the regex slightly.
Hope this helps you, I did it cause I care about the monkeys man.
import html
import re
import urllib.request
list0_v2 = []
final_list = []
url = "http://www.releasechimps.org/resources/publication/whos-there-md-anderson"
data = urllib.request.urlopen(url).read()
loop = re.findall(r'<td.*?>(.*?)</td>', str(data))
for item in loop:
if "\\n\\t\\t\\t\\t" or "em>" in item:
item = item.replace("\\n\\t\\t\\t\\t", "").replace("<em>", "")\
.replace("</em>", "")
if " " == item:
continue
list0_v2.append(item)
n = 1
while len(list0_v2) != 0:
form = {"n":0, "name":"", "id":"", "gender":"", "birthdate":"", "notes":""}
try:
if list0_v2[5][-1] == '.':
numb, name, ids, gender, birthdate, notes = list0_v2[0:6]
form["notes"] = notes
del(list0_v2[0:6])
else:
raise Exception('foo')
except:
numb, name, ids, gender, birthdate = list0_v2[0:5]
del(list0_v2[0:5])
form["n"] = int(numb)
form["name"] = html.unescape(name)
form["id"] = ids
form["gender"] = gender
form["birthdate"] = birthdate
final_list.append(form)
n += 1
for li in final_list:
print("{:3} {:10} {:10} {:3} {:10} {}".format(li["n"], li["name"], li["id"],\
li["gender"], li["birthdate"], li["notes"]))