def test_generate_headline_draw():
matches = []
new_match = match.Match(date.today(), "PREM", "1", "MAN U", 'H')
new_match.set_result_data('D', (1, 1))
matches.append(new_match)
selected_match = match.choose_random_match(matches)
assert onthisday.generate_headline(selected_match).find("drew") != -1
def parse_and_save_dataset(fname_in, fname_out):
# load in the dataset and save it out again in a more normalised form
# open the file, read a line in at a time
file_in = open(fname_in, "r")
matches = []
loaded_match = None
for line in file_in:
match_details = line.split(',')
match_date = datetime.strptime(match_details[0], "%Y-%m-%d")
found_myteam = False
opponent = ""
place = 'N'
my_team_score = -1
opponent_score = -1
result = ''
if match_details[5] == config.MY_TEAM: # MY_TEAM is the home team
found_myteam = True
opponent = match_details[6]
my_team_score = int(match_details[7])
opponent_score = int(match_details[8])
place = ('H' if match_details[4] == "TRUE" else 'N')
elif match_details[6] == config.MY_TEAM: # MY_TEAM is the away team
found_myteam = True
opponent = match_details[5]
my_team_score = int(match_details[8])
opponent_score = int(match_details[7])
place = ('A' if match_details[4] == "TRUE" else 'N')
if found_myteam:
result = ('W' if my_team_score > opponent_score else ('L' if my_team_score < opponent_score else 'D'))
loaded_match = match.Match(match_date, match_details[2], '', opponent, place)
loaded_match.set_result_data(result, tuple(match_details[7], match_details[8]))
matches.append(loaded_match)
file_in.close()
match.save_matches_to_file(fname_out, matches)
def test_cupfinal_winners():
new_match = match.Match(date(2019, 1, 1), "FA Cup", "Final", "MAN U", 'H')
new_match.set_result_data('W', (5, 1))
assert onthisday.generate_headline(new_match).find("are champions!") != -1
def test_format_competition_round_headline_noround():
new_match = match.Match(date(2019, 1, 1), "PREM", "", "MAN U", 'H')
new_match.set_result_data('L', (5, 1))
assert onthisday.format_competition_round_headline(new_match).find(
"round") == -1
def test_format_intro_headline_roundnotnil():
new_match = match.Match(date(2019, 1, 1), "PREM", "2", "MAN U", 'H')
new_match.set_result_data('L', (5, 1))
assert onthisday.format_intro_headline(new_match).find("round") != -1
def test_format_intro_headline_date():
new_match = match.Match(date(2019, 1, 1), "PREM", "1", "MAN U", 'H')
new_match.set_result_data('L', (5, 1))
assert onthisday.format_intro_headline(new_match).find(
"01 Jan, 2019") != -1
def test_generate_headline_aet():
new_match = match.Match(date(2019, 1, 1), "PREM", "", "MAN U", 'H')
new_match.set_result_data('W', (4, 3), "AET", "")
assert onthisday.generate_headline(new_match).find("after extra time") > -1
def test_generate_headline_pst():
new_match = match.Match(date(2019, 1, 1), "PREM", "", "MAN U", 'H')
new_match.set_result_data('W', (4, 3), "PST", "")
assert onthisday.generate_headline(new_match).find("penalties") > -1
def scrape_worldfootball(team, year):
url = WF_URL + "/teams/{}/{}/3/"
page = requests.get(url.format(team, year))
soup = BeautifulSoup(page.text, 'html.parser')
div_list_box = soup.find_all("div", {"class": "box"})
competition = ""
score = (1, 1)
matches = []
new_match = None
match_report = ""
normal_time = "NT"
for div in div_list_box:
div_class_data = div.find("div", {"class": "data"})
if div_class_data:
table_list = div_class_data.find_all(
"table", {
"class": "standard_tabelle",
"cellpadding": "3",
"cellspacing": "1"
})
if table_list:
for table in table_list:
table_competition = table.find_all("td", {
"colspan": "8",
"class": "hell"
})
if table_competition:
# if we have found a competition heading then know we have the result data
# need to loop over all of the rows inside this table
# if the row is a header then capture this as the competition
# then loop through all of the rows to see if they contain a result
table_rows = table.find_all("tr")
for row in table_rows:
if row.find_all("td", {
"colspan": "8",
"class": "hell"
}):
print("competition found"
) # of form name 1984/1985
competition = row.find("td").find("a").find(
"b").contents[0].strip()
print(
row.find("td").find("a").find(
"b").contents[0].strip())
else:
if row.find("td"):
cols = row.find_all("td")
print(competition)
competition_round = cols[0].find(
"a").contents[0].strip()
print(competition_round)
date = datetime.strptime(
cols[1].find("a").contents[0].strip(),
"%d/%m/%Y")
print(date)
location = cols[3].contents[0]
print(location)
opponent = cols[5].find(
"a").contents[0].strip()
print(opponent)
# some of the matches have a results page linked from the score
if cols[6].find("a"):
score, normal_time = parse_score(
cols[6].find(
"a").contents[0].strip())
match_report = WF_URL + cols[6].find(
"a").get("href")
else:
score, normal_time = parse_score(
cols[6].contents[0].strip())
match_report = ""
new_match = match.Match(
date, competition, competition_round,
opponent, location)
new_match.set_result_data(
match.calc_result_myteam_first(score),
score, normal_time, match_report)
matches.append(new_match)
# TD[6] is score with everton first, shows 2:1 (0:1,1:1) aet
# final score is before the brackets, in the brackets may
# show half time and at end of normal tim
# aet used to indicate after extra time
# so up until the first space (or end of string as
# HT score isn't always shown), is the end score
# to get scorers, need to follow a link to go onto
# match report page, not always present
print(len(matches))
return matches
