def update_scoreboard(
): # day is the number of days completed, hour is the latest tipoff to be included on the incomplete day
f1 = None
with browser.Browser(headless=True) as b:
b.visit(
"https://www.sports-reference.com/cbb/postseason/2022-ncaa.html")
scoreboard_html = b.html_snapshot()
f1 = open(scoreboard_html)
all_text = f1.read()
winners = {}
for longwinner in re.findall("<div class=\"winner\".*?</a>.*?</a>",
all_text, re.DOTALL):
winner = re.findall(">.*?</a>", longwinner)[-2][1:-4]
longdate = re.findall("<a href=\".*?>", longwinner)[-1]
date = re.search("\d{4}-\d\d-\d\d-\d\d", longdate)[0]
game_month = int(date[-8])
game_day = int(date[-5:-3]) + (31 if game_month == 4 else 0)
game_hour = date[-2:]
try:
winners[str(game_day) + game_hour] += "," + winner
except KeyError:
winners[str(game_day) + game_hour] = winner
f1.close()
with open("corefolder/scoreboard2022.txt", 'w') as f2:
day = -1
last_date = 0
for winner in sorted(winners):
hour = winner[-2:]
date = int(winner[:2])
if date > last_date:
last_date = date
day += 1
f2.write("d" + str(day) + "h" + hour + ":" + winners[winner] +
',' + str(date) + '\n')
def update_kp():
f1 = None
f2 = None
with browser.Browser(headless=True) as b:
b.visit("https://kenpom.com")
kp_html = b.html_snapshot()
f1 = open(kp_html)
for line in f1.readlines():
if "update\">Data" in line:
longdate = re.search("Data.*?</a>", line)[0]
date = re.search("\d{4}-\d\d-\d\d", longdate)[0]
game_month = int(date[-4])
game_day = int(date[-2:]) + (31 if game_month == 4 else 0)
f2 = open("corefolder/kp" + str(game_day) + ".txt", 'w')
f2.write("team,rating,tempo\n")
if "a href=\"team.php" in line:
teamname = re.search("a href=\"team.php.*?</a>",
line)[0].split('>')[1][:-3]
kp = re.search(r"[+-]\d\d?\.\d\d", line)[0]
kptempo = re.findall(r"\d\d?\.\d", line)[3]
f2.write(teamname + ',' + kp + ',' + kptempo + '\n')
f1.close()
f2.close()
loadsData = json.loads(temp.read())
if CheckDataItems():
if len(loadsData):
fdata = data.copy()
temp = open('Verified.json', 'r')
VerifiedData = json.loads(temp.read())
temp.close()
temp = open(nameData, 'r')
items = json.loads(temp.read())
for item in fdata:
index = VerifiedData.index(item['pricepos_code'])
print(index)
if index != -1:
data.remove(item['pricepos_code'])
browser = browser.Browser('chrome', incognito=True)
for item in data:
items.append()
temp = open(nameData, 'w')
jsdata = json.dumps(items)
temp.write(jsdata)
VerifiedData.append(item['pricepos_code'])
jsdata = json.dumps(VerifiedData)
temp = open('Verified.json', 'w')
temp.write(jsdata)
temp.close()
time.sleep(2)
def getBfromP(groupID: str, path="html_sources/", year="2019", entry_limit=40):
print("Connecting...", end=' ')
with browser.Browser(headless=True) as b:
if path == "html_sources/":
path += groupID + '/'
print("Connecting...", end=' ')
myurl = "http://fantasy.espn.com/tournament-challenge-bracket/" + str(
year) + "/en/group?groupID=" + groupID + "&_301_=2022"
b.visit(myurl)
group_html = b.html_snapshot()
with open(group_html) as f:
group_text = f.read()
try:
re.search(r"<header class=\"group-header\">.*?</header>",
group_text)[0][29:-9] + '/'
except TypeError:
raise ValueError(
"This pool is not publicly accessible, therefore the program cannot run"
)
mylinks = []
links = b.links.find_by_partial_href("entry?entryID=")
for i, j in enumerate(links):
mylinks.append(j.value)
if len(mylinks) > entry_limit:
raise ValueError(
"This program is intended for small groups. It is too expensive to visit "
+ len(mylinks) + " URLs.")
linkcount = 0
for i in mylinks:
linkcount += 1
if linkcount % 10 == 1:
print("\nProgress: " + str(linkcount) + '/' +
str(len(mylinks)),
end=' ')
else:
print(str(linkcount) + '/' + str(len(mylinks)), end=' ')
try:
b.links.find_by_text(i).click()
if "game" in b.url:
ID = re.search(r"entryID=\d*", b.url)[0]
urlBase = "http://fantasy.espn.com/tournament-challenge-bracket/" + str(
year) + "/en/entry?"
b.visit(urlBase + ID)
notFound = False
except splinter.exceptions.ElementDoesNotExist:
print('\n' + i, "could not be found")
notFound = True
screenshot_path = b.html_snapshot()
with open(screenshot_path) as f1:
entryName = b.title.split(' -')[0]
if notFound is True:
entryName = i
entryName = entryName.replace('/', '_')
try:
with open(path + entryName, 'w') as f2:
if notFound is False:
all_text = f1.read()
f2.write(all_text)
else:
f2.write(i + " could not be found")
except (FileNotFoundError, NotADirectoryError):
try:
os.mkdir(path)
except (FileNotFoundError, NotADirectoryError):
os.mkdir(path.split('/')[0])
os.mkdir(path)
with open(path + entryName, 'w') as f2:
if notFound is False:
all_text = f1.read()
f2.write(all_text)
else:
f2.write(i + " could not be found")
b.visit(myurl)
print('\n', end='')
# -*- coding: utf-8 -*-
"""
@CREATETIME: 05/07/2018 14:04
@AUTHOR: Chans
@VERSION:
"""
from selenium import webdriver
from splinter import browser
import sys
print(sys.path)
# chromedriver = '/Users/Apple/datadata/chrome/chromedriver'
# driver = webdriver.Chrome(chromedriver)
b = browser.Browser('chrome')
b.visit('https://www.baidu.com')