How to extract PCSO lottery winning combinations using Python

python -m pip install selenium beautifulsoup4 pandas

# Selenium for simulating clicks in a browser
from selenium import webdriver
from selenium.webdriver.support.ui import Select
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as ec

# BeautifulSoup for scraping
from bs4 import BeautifulSoup

# pandas for processing the data
import pandas as pd

# datetime for getting today's date and formatting
from datetime import datetime
from datetime import date
from datetime import datetime, timedelta

# Set the path to where the webdriver executuble is
# For me it's the following:
path = ("path/to/your/<browser>driver.exe")

# Designate the url to be scraped to a variable
url = "https://www.pcso.gov.ph/SearchLottoResult.aspx"

# Initialize the webdriver, here we use Edge
driver = webdriver.Edge(executable_path=path) 

# Grab the web page
driver.get(url)                              

# Designate a variable for waiting for the page to load
wait = WebDriverWait(driver, 5)

# wait for the div class "pre-con" to be invisible to ensure clicks work
wait.until(ec.invisibility_of_element_located((By.CLASS_NAME, "pre-con")))

# Get today's date with the datetime import
today = date.today()

# Store the current year, month, and day to variables
td_year = today.strftime("%Y")
td_month = today.strftime("%B")
td_day = today.strftime("%d").lstrip("0").replace(" 0", " ")

startyr = int(td_year) - 10
startyr = str(startyr)
print("Today is " + td_month + " " + td_day + ", " + td_year + ".\n")

# Select Start Date as January 1, 2012
start_month = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlStartMonth"))
start_month.select_by_value("January")

start_day = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlStartDate"))
start_day.select_by_value("1")

start_year = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlStartYear"))
start_year.select_by_value(startyr)

# Select End Date as Today
end_month = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlEndMonth"))
end_month.select_by_value(td_month)

end_day = Select(driver.find_element_by_id("cphContainer_cpContent_ddlEndDay"))
end_day.select_by_value(td_day)

end_year = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlEndYear"))
end_year.select_by_value(td_year)

# Lotto Game
game = Select(driver.find_element_by_id(
    "cphContainer_cpContent_ddlSelectGame"))

# If you inspect the page, the value of the option for "All Games" is 0
game.select_by_value('0')

# Submit the parameters by clicking the search button
search_button = driver.find_element_by_id("cphContainer_cpContent_btnSearch")
search_button.click()

# Feed the page's source code into Beautiful Soup
doc = BeautifulSoup(driver.page_source, "html.parser")

# Find the table of the results by id (
rows = doc.find('table', id='cphContainer_cpContent_GridView1').find_all(
    'tr', attrs={'class': "alt"})

# Initialize a list to hold our data
entries = []

# Now loop through the rows and put the data into the list to make a table
for row in rows:
    cells = row.select("td")
    entry = {
        "Game": cells[0].text,
        "Combination": cells[1].text,
        "Date": cells[2].text,
        "Prize": cells[3].text,
        "Winners": cells[4].text,
    }
    entries.append(entry)

# Turn the list into a DataFrame
df = pd.DataFrame(entries)

# Remove duplicate rows
df.drop_duplicates(inplace=True, keep=False)

# Remove rows that have no combination associated
df = df[df["Combination"] != "-                "]

# Convert the dates to datetime type
df["Date"] = df["Date"].astype('datetime64[ns]')

# Remove the commas in the prize amounts
df["Prize"] = df["Prize"].replace(',','', regex=True)
    
# Convert data types of Prize and Winners to float and integers
df["Prize"] = df["Prize"].astype(float)     # float because there are still centavos
df["Winners"] = df["Winners"].astype(int)

df

# Sort the DataFrame by game
df.sort_values(by=["Game"], inplace=True)

# Get a list of the games
games = df["Game"].unique().tolist()

# Now we can create DataFrames for each game
lotto_658 = df.loc[df["Game"]=="Ultra Lotto 6/58"].copy()
lotto_655 = df.loc[df["Game"]=="Grand Lotto 6/55"].copy()

# Sidenote: Super Lotto 6/49 and Mega Lotto 6/45 have different values from
# what was on the dropdown menu
lotto_649 = df.loc[df["Game"]=="Superlotto 6/49"].copy()
lotto_645 = df.loc[df["Game"]=="Megalotto 6/45"].copy()

# Anyways, continuing...
lotto_642 = df.loc[df["Game"]=="Lotto 6/42"].copy()
lotto_6d = df.loc[df["Game"]=="6Digit"].copy()
lotto_4d = df.loc[df["Game"]=="4Digit"].copy()

lotto_3da = df.loc[df["Game"]=="Suertres Lotto 11AM"].copy()
lotto_3db = df.loc[df["Game"]=="Suertres Lotto 4PM"].copy()
lotto_3dc = df.loc[df["Game"]=="Suertres Lotto 9PM"].copy()

lotto_2da = df.loc[df["Game"]=="EZ2 Lotto 11AM"].copy()
lotto_2db = df.loc[df["Game"]=="EZ2 Lotto 4PM"].copy()
lotto_2dc = df.loc[df["Game"]=="EZ2 Lotto 9PM"].copy()

lotto_2da.tail()

# Add 11 hours to the datetime for Suertres Lotto 11AM game to match because of time zones
lotto_3da["Date"] = lotto_3da["Date"] + timedelta(hours=11)

# Add 16 hours to the datetime for Suertres Lotto 4PM game to match
lotto_3db["Date"] = lotto_3db["Date"] + timedelta(hours=16)

# Add 21 hours to the datetime for Suertres Lotto 9PM game to match
lotto_3dc["Date"] = lotto_3dc["Date"] + timedelta(hours=21)

# Rename all the game entries as just Suertres Lotto
lotto_3da["Game"] = "Suertres Lotto"
lotto_3db["Game"] = "Suertres Lotto"
lotto_3dc["Game"] = "Suertres Lotto"

# Combine the three Suertres Lotto DataFrames into one
lotto_3d = lotto_3da
lotto_3d = lotto_3d.append(lotto_3db)
lotto_3d = lotto_3d.append(lotto_3dc)

# Do the same for EZ2 Lotto
lotto_2da["Date"] = lotto_2da["Date"] + timedelta(hours=11)
lotto_2db["Date"] = lotto_2db["Date"] + timedelta(hours=16)
lotto_2dc["Date"] = lotto_2dc["Date"] + timedelta(hours=21)

# Rename all the game entries as just EZ2 Lotto
lotto_2da["Game"] = "EZ2 Lotto"
lotto_2db["Game"] = "EZ2 Lotto"
lotto_2dc["Game"] = "EZ2 Lotto"

# Combine the three EZ2 Lotto DataFrames into one
lotto_2d = lotto_2da
lotto_2d = lotto_2d.append(lotto_2db)
lotto_2d = lotto_2d.append(lotto_2dc)

lotto_2da

lotto_2d

# Create Excel writer object
writer = pd.ExcelWriter("lotto.xlsx")

# Write DataFrames to excel worksheets
df.to_excel(writer, "All Data")
lotto_658.to_excel(writer, "Ultra Lotto 6-58")
lotto_655.to_excel(writer, "Grand Lotto 6-55")
lotto_649.to_excel(writer, "Super Lotto 6-49")
lotto_645.to_excel(writer, "Mega Lotto 6-45")
lotto_642.to_excel(writer, "Lotto 6-42")

lotto_6d.to_excel(writer, "6 Digit")
lotto_4d.to_excel(writer, "4 Digit")
lotto_3d.to_excel(writer, "Suertres Lotto")
lotto_2d.to_excel(writer, "EZ2 Lotto")

# Save the Excel workbook
writer.save()