def parse_page(url):
x = Ureq(url)
page = x.read()
x.close()
page_parsed = Bsoup(page, 'html.parser')
return (page_parsed)
def get_json(url):
req = Request(url, headers=hdr)
page = Ureq(req)
try:
js = page.read().decode()
js = json.loads(js)
except:
js = None
return js
def hockey_bet():
# Pull in url for schedule
# TODO: Check date, and if it is not during the season, exit function
url = 'https://www.hockey-reference.com/leagues/NHL_2020_games.html'
# Run through BeautifulSoup steps
uClient = Ureq(url)
raw_content = uClient.read()
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
game = html.findAll(class_ = 'left')
game = [team.get_text() for team in game]
drop_list = ['Date','Visitor','Home','Notes','']
# Clean data
game = [game for game in game if game not in drop_list]
bin_len = 3
start = 0
end = start + bin_len
week_list = []
while end < (len(game) + 1):
week = game[start:end]
start = end
end = start + bin_len
week_list.append(week)
df = pd.DataFrame(week_list)
df.columns = ['Date','Visitor','Home']
# Clean team names into readable format
row_count = 0
visitor = df['Visitor'].str.split(" ", expand = True)
home = df['Home'].str.split(" ", expand = True)
while row_count < len(df):
if visitor[2][row_count] == None:
df['Visitor'][row_count] = visitor[1][row_count]
elif visitor[2][row_count] != None:
df['Visitor'][row_count] = visitor[2][row_count]
if home[2][row_count] == None:
df['Home'][row_count] = home[1][row_count]
elif home[2][row_count] != None:
df['Home'][row_count] = home[2][row_count]
row_count += 1
# Only select todays games
todays_date = datetime.now().strftime('%Y-%m-%d')
todays_games = df[df['Date'] == todays_date]
todays_games = todays_games.reset_index()
todays_games = todays_games[['Visitor','Home']]
return todays_games
from urllib.request import urlopen as Ureq
from bs4 import BeautifulSoup as soup
my_url = "https://www.newegg.com/Video-Cards-Video-Devices/Category/ID-38"
#opening url and grabbing page
uClint = Ureq(my_url)
page_html = uClint.read()
uClint.close()
#html parser
page_soup = soup(page_html, "html.parser")
#print(page_soup.h1) # prints H1
#print(page_soup.p)# prints paragraphs
#print(page_soup.body.div)
#grab each product
containers = page_soup.findAll("div", {"class": "item-container"})
print(len(containers))
# to open a file
file_name = "product.csv"
f = open(file_name, "w")
headers = "Brand", "prouct name", "Shipping\n"
f.write("Brand, product name, shippig\n")
#below 3 lines of code is for container 1 that is 0th
#container = containers[0]
#print(container.a)
#print(container.div.div.a.img["title"]) # will return the title
def basketball_bet():
# Get the current month and day in order to get the games playing today
current_month_text = datetime.now().strftime('%B').lower()
current_day = datetime.now().strftime('%d')
# Pull the url based on the current month
try:
url = 'https://www.basketball-reference.com/leagues/NBA_2020_games-' + current_month_text + '.html'
except:
print('There are currently no basketball games being played today')
return
uClient = Ureq(url)
raw_content = uClient.read()
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
schedule_text = html.findAll(class_="left")
# Get the text from the html
schedule = [game.get_text() for game in schedule_text]
# Fill dataframe with game date, visiting team name, and home team name
bin_len = 3
start = 0
end = start + bin_len
week_list = []
while end < (len(schedule) + 1):
week = schedule[start:end]
start = end + 1
end = start + bin_len
week_list.append(week)
df_1 = pd.DataFrame(week_list)
df_1.columns = ['Date', 'Visitor', 'Home']
# Clean all of the comlumns
row_count = 0
new = df_1['Date'].str.split(" ", n=3, expand=True)
while row_count < len(df_1):
df_1['Date'][row_count] = new[2][row_count][:-1]
row_count += 1
game_time = html.findAll(class_='right')
game_time = [team.get_text() for team in game_time]
bin_len = 4
start = 0
end = start + bin_len
week_list = []
while end < (len(game_time) + 1):
week = game_time[start:end]
start = end
end = start + bin_len
week_list.append(week)
df = pd.DataFrame(week_list)
df.columns = ['Game_Time (EST)', 'Stat1', 'Stat2', 'Stat3']
df = df['Game_Time (EST)']
# Concat the dataframes to get desired data
todays_games = pd.concat([df_1, df], axis=1, join='inner')
todays_games = todays_games[todays_games['Date'] == current_day]
# If there are no games being played, exit function
if len(todays_games) == 0:
print('There are currently no basketball games being played today.')
return
# Clean team names into more readable forms
todays_games = todays_games.reset_index()
todays_games = todays_games[['Visitor', 'Home', 'Game_Time (EST)']]
todays_games['Home'] = todays_games['Home'].apply(lambda x: teams_dict[x])
todays_games['Visitor'] = todays_games['Visitor'].apply(
lambda x: teams_dict[x])
# Return games being played today
return todays_games
from urllib.request import urlopen as Ureq
from bs4 import BeautifulSoup as soup
from newsapi import NewsApiClient
# pre-processor
my_url = 'http://topforeignstocks.com/stock-lists/the-complete-list-of-biotech-stocks-trading-on-nasdaq/' # List of biotech companies
uClient = Ureq(my_url) #downloads webpage
page_html = uClient.read()
page_soup = soup(page_html, "html.parser")
# print(page_soup.tbody.td)
bio_tech_companies = page_soup.findAll("td", {"class": "column-2"})
for i in range(1):
query = str(bio_tech_companies[i].text.strip())
print(query)
newsapi = NewsApiClient(api_key='42eab217e53348febe920e907f524b0f')
top_headlines = newsapi.get_top_headlines(q=str('biotech'), language='en')
print(top_headlines)
uClient.close()
page_numbers = 1
headers = "Album | Artist | Score | Author | Genre | Review Date \n"
#open csv file
with open('albums_complete_second_half.csv', 'wb') as csvfile:
csvfile.write((headers).encode('utf8'))
items = []
#Iterate through every page on https://pitchfork.com/reviews/albums/
while(True):
url = (base_url_main_page+"?page="+str(page_numbers))
#iterate through until no page is found. Ignore other HTTP response errors
try:
response = Ureq(url)
except urllib.error.HTTPError as e:
error_message = e.read()
if e.getcode() == 404:
sys.exit("No page found")
else:
print(error_message)
else:
page_html = response.read()
page_soup = soup(page_html, "html.parser")
url_names = page_soup.findAll("div",class_= "review")
count = 0
#enter urls of album reviews
for item in url_names:
def basketball_win(date):
current_month = date[0:2]
current_day = date[3:5]
string = current_month
current_month_text = datetime.strptime(string, "%m")
current_month_text = datetime.strftime(current_month_text, "%B").lower()
# Pull the url based on the current month
try:
url = 'https://www.basketball-reference.com/leagues/NBA_2020_games-' + current_month_text + '.html'
except:
print('There are currently no basketball games being played today')
return
uClient = Ureq(url)
raw_content = uClient.read()
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
schedule_text = html.findAll(class_="left")
# Get the text from the html
schedule = [game.get_text() for game in schedule_text]
# Fill dataframe with game date, visiting team name, and home team name
bin_len = 3
start = 0
end = start + bin_len
week_list = []
while end < (len(schedule) + 1):
week = schedule[start:end]
start = end + 1
end = start + bin_len
week_list.append(week)
df_1 = pd.DataFrame(week_list)
df_1.columns = ['Date', 'Visitor', 'Home']
# Clean all of the comlumns
row_count = 0
new = df_1['Date'].str.split(" ", n=3, expand=True)
while row_count < len(df_1):
df_1['Date'][row_count] = new[2][row_count][:-1]
row_count += 1
game_time = html.findAll(class_='right')
game_time = [team.get_text() for team in game_time]
bin_len = 4
start = 0
end = start + bin_len
week_list = []
while end < (len(game_time) + 1):
week = game_time[start:end]
start = end
end = start + bin_len
week_list.append(week)
df = pd.DataFrame(week_list)
df.columns = ['Game_Time', 'Visitor_Points', 'Home_Points', 'Stat3']
df.drop(columns=['Stat3'], inplace=True)
total_df = pd.concat([df_1, df], axis=1, join='inner')
win_list = []
row_count = 0
for row in total_df['Date']:
if (total_df['Visitor_Points'][row_count]) > (
total_df['Home_Points'][row_count]):
win_list.append(total_df['Visitor'][row_count])
elif (total_df['Home_Points'][row_count]) > (
total_df['Visitor_Points'][row_count]):
win_list.append(total_df['Home'][row_count])
elif (total_df['Home_Points'][row_count]) != '' and (
total_df['Visitor_Points'][row_count]) != '' and (
total_df['Home_Points'][row_count]) == (
total_df['Visitor_Points'][row_count]):
win_list.append('Tie')
else:
win_list.append('Incomplete')
row_count += 1
total_df['Winner'] = win_list
todays_games = total_df[total_df['Date'] == current_day]
if len(todays_games) == 0:
print('There are currently no basketball games being played today.')
todays_games['Home'] = todays_games['Home'].apply(lambda x: teams_dict[x])
todays_games['Visitor'] = todays_games['Visitor'].apply(
lambda x: teams_dict[x])
todays_games['Winner'] = todays_games['Winner'].apply(
lambda x: teams_dict[x])
return todays_games
import bs4
from urllib.request import urlopen as Ureq
from bs4 import BeautifulSoup as soup
#target web page
my_url = "https://www.shelflife.co.za/Online-store/sneakers"
#opening connection and grabbing page
uClient = Ureq(my_url)
page_html = uClient.read()
uClient.close()
#html parsing
page_soup = soup(page_html, "html.parser")
#grabs each product
containers = page_soup.find_all("div", {"class": "col-xs-6 col-sm-3"})
title = page_soup.find_all("div", {"class": "title"})
price = page_soup.findAll("div", {"class" : "price"})
#finds sale product
sale_products = page_soup.findAll('div', {"class" : "special_label sale"} )
#open a new csv file to write data scraped from website
filename = "shelf_life_sneaks_sale.csv"
f = open(filename, "w")
headers = "product_name,price\n"
f.write(headers)
#writing the data to the csv file
for i in range (0, len(containers)):
def scrape():
####################################################################################
concat = Sentry.get()
#my_url = "file:///C:/Users/Adam-22-26/Desktop/graphics%20card%20-%20Newegg.com.html"
my_url = 'https://www.newegg.com/global/ph-en/p/pl?d={}'.format(concat)
my_url = my_url.replace(' ', '+')
####################################################################################
uClient = Ureq(my_url)
page_html = uClient.read()
uClient.close()
#html_parsing
page_soup = Soup(page_html, "html.parser")
#grabe each
containers = page_soup.findAll("div", {"class": "item-container"})
#manufacturer = page_soup.findAll("label",{"class": "form-checkbox"})
#print(manufacturer )
#print(len(containers))
#print(containers[5:])
#container = containers[5]
#---------------------------------------- save the csv files
fileName = "{}.csv".format(
concat) ###############################################
f = open(fileName, "w")
headers = "BRAND , PRICES , SAVES , TITLES , LINK \n" #
f.write(headers)
for container in containers[4:]:
#---------------------------------------------------------
brand_container = container.findAll("a", {"class": "item-brand"})
brand = brand_container[0].img["title"] #brand name
#-------------------------------------------------------------------
may_know = container.findAll("a", {"class": "item-title"})
#print(may_know)
####################################################################
title = container.a.img["title"] #Name of selling
#print(container)
#######################################################3
hyper = brand_container[0]["href"]
#hyper = container.findAll("div",{"class": "item-info"})
#hyper = hypers.a
#print(hyper)
#--------------------------------------------------------------
price_container = container.findAll("li",
{"class": "price-current"})
price_container2 = price_container[0].strong
price = re.findall(r'.\d.\d\d\d', str(price_container2))
prices = ''.join(price)
#------------------------------------------------------------------------
save_container = container.findAll("span",
{"class": "price-save-percent"})
save = re.findall(r'\d\d.', str(save_container))
saves = ''.join(save)
if saves == '':
saves = "None"
else:
saves = saves
if prices == "":
prices = "Not Available"
else:
prices = prices
brandlistbox.insert(END, " : " + brand)
pricelistbox.insert(END, "₱ " + prices)
savelistbox.insert(END, saves)
Listbox4.insert(END, " : " + title)
hyperlink.insert(END, ' ' + hyper)
#-------------------------------------------------------------------------
f.write(
brand.replace(',', '') + ", " + prices.replace(
',', '.').replace('0', '1').replace('>', ' ') + ',' +
saves.replace('', '').replace('None', '0%') + ', ' +
title.replace(',', '') + ', ' + hyper + "\n")
f.close()
new_win = Button(window,
width=10,
text="New_Win",
command=mainwindow,
height=1,
font="Jokerman",
relief=RAISED,
activebackground="LightBlue1",
background='sky blue')
new_win.place(x=105, y=90)
messagebox.showinfo("Happens", "DONE! \n press ok to proceed")
def notifyprice(price,type,updown):
sub = 'attention! {} price {} to {}'.format(type,updown,price)
attention_body = 'please attention {} price!!! current price is {} to {}'.format(type,updown,price)
# wechat_msg(attention_body)
mail_msg(sub,attention_body)
if __name__ == '__main__':
# itchat.auto_login()
while True:
queryurl = ''
#Set datasource here
req = Ureq(queryurl)
china_gold =
china_silver =
#your way of obtaining price data
print('gold price is: {}'.format(china_gold))
print('silver price is: {}'.format(china_silver))
if china_silver>=silver_high or china_silver<=silver_low:
if china_silver >= silver_high:
notifyprice(china_silver,'silver','up')
silver_high += silver_range
print('silver notify range raised to {}'.format(silver_high))
if china_silver <= silver_low:
notifyprice(china_silver,'silver','down')
silver_low -= silver_range
print('silver notify range down to {}'.format(silver_low))
def football_bet():
# Ensure that the football season is currently going on
year_date = datetime.now().strftime('%Y-%m-%d')
if year_date > 'February 2 2020' and year_date < 'September 10 2020':
print(
"The next football season hasn't begun yet. Please come back on September 10."
)
return
elif year_date < 'February 2 2020':
url = 'https://www.pro-football-reference.com/years/2019/games.htm'
else:
url = 'https://www.pro-football-reference.com/years/2020/games.htm'
# Run through BeautifulSoup steps to pull wanted data
uClient = Ureq(url)
raw_content = uClient.read()
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
teams_win_loss = html.findAll(class_='left')
game = html.findAll(class_='right')
game = [team.get_text() for team in game]
teams_win_loss = [team.get_text() for team in teams_win_loss]
removal = ['Day']
teams_win_loss = [item for item in teams_win_loss if item not in removal]
# Set todays date that will be used to select todays games
date = datetime.now().strftime('%B %d')
# Clean stats
bin_len = 8
start = 0
end = start + bin_len
week_list = []
while end < (len(game) + 1):
week = game[start:end]
start = end + 1
end = start + bin_len
week_list.append(week)
df_1 = pd.DataFrame(week_list)
df_1.columns = [
'Game_Week', 'Time (EST)', 'Stat1', 'Stat2', 'Stat3', 'Stat4', 'Stat5',
'Stat6'
]
bin_len = 4
start = 0
end = start + bin_len
week_list = []
while end < (len(teams_win_loss) + 1):
week = teams_win_loss[start:end]
start = end
end = start + bin_len
week_list.append(week)
df_2 = pd.DataFrame(week_list)
df_2.columns = ['Day_Of_Week', 'Date', 'Home', 'Visitor']
# Concat data frames
football = pd.concat(
[df_1[['Game_Week', 'Time (EST)']], df_2[['Date', 'Home', 'Visitor']]],
axis=1,
join='inner')
# Select only games being played today
todays_games = football[football['Date'] == date]
# Return dataframe
return todays_games
import bs4
from urllib.request import urlopen as Ureq
from bs4 import BeautifulSoup as soup
my_url = []
for x in range(10):
my_url.append("https://de.aliexpress.com/category/2118/printers/" +
str(x) + "html?site=deu&tag=")
for y in range(10):
uClient = Ureq(my_url[y])
page_html = uClient.read()
uClient.close()
page_soup = soup(page_html, "html.parser")
#grabs each product
#containers = page_soup.findAll("li",{"class":"list-item"})
#filename = "printers.csv"
#f = open(filename, "w")
#headers ="brand,product_name, shipping, price_real\n"
# f.write(headers)
ullist = page_soup.findAll("div", {"class": "col-main"})
error_p = page_soup.findAll(
"p", {"class": "ui-notice ui-notice-normal ui-notice-prompt"})
error = []
error.append(error_p)
if error == [[]]:
def hockey_win(date):
url = 'https://www.hockey-reference.com/leagues/NHL_2020_games.html'
# Run through BeautifulSoup steps
uClient = Ureq(url)
raw_content = uClient.read()
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
game = html.findAll(class_ = 'left')
results = html.findAll(class_ = 'right')
game = [team.get_text() for team in game]
results = [team.get_text() for team in results]
results_drop = ['LOG']
results = [results for results in results if results not in results_drop]
drop_list = ['Date','Visitor','Home','Notes','']
# Clean data
game = [game for game in game if game not in drop_list]
bin_len = 3
start = 0
end = start + bin_len
week_list = []
while end < (len(game) + 1):
week = game[start:end]
start = end
end = start + bin_len
week_list.append(week)
df = pd.DataFrame(week_list)
df.columns = ['Date','Visitor','Home']
# Clean team names into readable format
bin_len = 4
start = 0
end = start + bin_len
week_list = []
while end < (len(results) + 1):
week = results[start:end]
start = end
end = start + bin_len
week_list.append(week)
df_1 = pd.DataFrame(week_list)
row_count = 0
visitor = df['Visitor'].str.split(" ", expand = True)
home = df['Home'].str.split(" ", expand = True)
while row_count < len(df):
if visitor[2][row_count] == None:
df['Visitor'][row_count] = visitor[1][row_count]
elif visitor[2][row_count] != None:
df['Visitor'][row_count] = visitor[2][row_count]
if home[2][row_count] == None:
df['Home'][row_count] = home[1][row_count]
elif home[2][row_count] != None:
df['Home'][row_count] = home[2][row_count]
row_count += 1
# Only select todays games
df_1.columns = ['Visitor_Goals','Home_Goals','Attendance','Time']
total_df = pd.concat([df,df_1],axis=1,join='inner')
win_count = 0
win_list = []
while win_count < len(total_df):
if (total_df['Visitor_Goals'][win_count]) > (total_df['Home_Goals'][win_count]):
win_list.append(total_df['Visitor'][win_count])
elif (total_df['Home_Goals'][win_count]) > (total_df['Visitor_Goals'][win_count]):
win_list.append(total_df['Home'][win_count])
elif (total_df['Home_Goals'][win_count]) != '' and (total_df['Visitor_Goals'][win_count]) != '' and (total_df['Home_Goals'][win_count]) == (total_df['Visitor_Goals'][win_count]):
win_list.append('Tie')
else:
win_list.append('Incomplete')
win_count += 1
total_df['Winner'] = win_list
todays_games = total_df[total_df['Date'] == date]
todays_games = todays_games.reset_index()
return todays_games
def baseball_bet():
# Set the current date in a readable form and the form used for the html
todays_date = datetime.now().strftime('%m-%d-%Y')
date_html = datetime.now().strftime('%Y%m%d')
# Set Opening Day date
openeing_day = "03-26-2020"
# Parse OD date
OD = datetime.strptime(openeing_day, "%m-%d-%Y")
# Set current date
present = datetime.now()
# If it is before OD, return from function
if present.date() < OP.date():
print('Opening Day is not until March 26. Please come back then.')
return
# Set url for todays date if season has already started
url = 'https://www.espn.com/mlb/schedule/_/date/' + date_html
# Make sure that there are acutally games being played
# If there are not, the url will not work
try:
uClient = Ureq(url)
raw_content = uClient.read()
except:
print('There are no games being played on this day.')
return
# Run through BeautifulSoup steps to pull out desired data
page_soup = soup(raw_content, "html.parser")
html = list(page_soup.children)[3]
game = html.findAll(class_='external')
game_date_list = []
# Fix dates given into readable datetime format
for x in range(1, len(game)):
game_date = game[x]['href'].split('/')[5].split('-')[-3:-1]
game_date.append('2020')
sent_str = ""
for i in game_date:
sent_str += str(i) + "-"
sent_str = sent_str[:-1]
date = datetime.strptime(sent_str, '%m-%d-%Y')
date = date.strftime('%m-%d-%Y')
game_date_list.append(date)
# Get the names of the teams that are playing on that day
game = html.findAll(class_='team-name')
game = [team.get_text() for team in game]
game_list = []
for item in game:
# The abbrvs are only the last three characters in the str
item = item[-3:]
game_list.append(item)
# Split home and away teams from the list of cleaned teams
bin_len = 2
start = 0
end = start + bin_len
week_list = []
while end < (len(game_list) + 1):
week = game_list[start:end]
start = end
end = start + bin_len
week_list.append(week)
df = pd.DataFrame(week_list)
df.columns = ['Visitor', 'Home']
df['Date'] = game_date_list
todays_games = df[df['Date'] == todays_date]
# Apply the lambda function that will clean the team names into more colloquial names
todays_games['Home'] = todays_games['Home'].apply(lambda x: teams_dict[x])
todays_games['Visitor'] = todays_games['Visitor'].apply(
lambda x: teams_dict[x])
# return data frame of games that are being played today
return todays_games