Import HTML files

from deephaven import pandas as dhpd
from deephaven import merge

import os

os.system("pip install lxml")

import pandas as pd
import lxml

deephaven_theme_colors = merge(
    [
        dhpd.to_table(df)
        for df in pd.read_html(
            "https://deephaven.io/core/docs/how-to-guides/data-import-export/html-import/"
        )
    ]
)

import os

os.system("pip install beautifulsoup4 requests lxml")
from deephaven.column import string_col, int_col
from deephaven import new_table
from bs4 import BeautifulSoup
import requests

url = "https://deephaven.io/core/docs/how-to-guides/data-import-export/html-import/"
headers = {"User-Agent": "Mozilla/5.0"}  # helps avoid being blocked

r = requests.get(url, headers=headers)

soup = BeautifulSoup(r.content, "lxml")

# Try to find the table
table = soup.find("table")  # you can add class_="..." if needed

# Extract headers
headers = [th.text.strip() for th in table.find("thead").find_all("th")]

# Extract rows
rows = []
for tr in table.find("tbody").find_all("tr"):
    row = [td.text.strip() for td in tr.find_all("td")]
    if row:
        rows.append(row)

deephaven_theme_colors = new_table(
    [
        string_col("Color", [row[0] for row in rows]),
        string_col("Shades", [row[1] for row in rows]),
        string_col("Shades_1", [row[2] for row in rows]),
        string_col("Shades_2", [row[3] for row in rows]),
        string_col("Shades_3", [row[4] for row in rows]),
        string_col("Shades_4", [row[5] for row in rows]),
        string_col("Shades_5", [row[6] for row in rows]),
        string_col("Shades_6", [row[7] for row in rows]),
        string_col("Shades_7", [row[8] for row in rows]),
        string_col("Shades_8", [row[9] for row in rows]),
        string_col("Shades_9", [row[10] for row in rows]),
        string_col("Shades_10", [row[11] for row in rows]),
    ]
)

from deephaven import pandas as dhpd
import pandas as pd
import os

os.system("pip install beautifulsoup4 requests")
os.system("pip install requests")
os.system("pip install lxml")
from bs4 import BeautifulSoup
import requests

url = "https://deephaven.io/core/docs/how-to-guides/data-import-export/html-import/"
headers = {"User-Agent": "Mozilla/5.0"}  # helps avoid being blocked

r = requests.get(url, headers=headers)

soup = BeautifulSoup(r.content, "lxml")

# Try to find the table
table = soup.find("table")  # you can add class_="..." if needed

# Get basic headers from thead (usually just 'Color' and 'Shades')
basic_headers = [th.text.strip() for th in table.find("thead").find_all("th")]

# Extract rows
rows = []
for tr in table.find("tbody").find_all("tr"):
    row = [td.text.strip() for td in tr.find_all("td")]
    if row:
        rows.append(row)

# Create expanded headers to match the actual number of columns
# First column keeps its name (usually 'Color')
headers = [basic_headers[0]]
# For remaining columns, use second header name with index suffix if needed
for i in range(1, len(rows[0])):
    if i == 1:
        headers.append(basic_headers[1])  # Usually 'Shades'
    else:
        headers.append(f"{basic_headers[1]}_{i-1}")  # 'Shades_1', 'Shades_2', etc.

df = pd.DataFrame(rows, columns=headers)

# infer_objects is set to `True` be default
# in this case, all columns are inferred as Strings
deephaven_theme_colors = dhpd.to_table(df)

table_typed = deephaven_theme_colors.update(
    [
        "Color = String.valueOf(Color)",
        "Shades = String.valueOf(Shades)",
        "Shades_1 = String.valueOf(Shades_1)",
        "Shades_2 = String.valueOf(Shades_2)",
        "Shades_3 = String.valueOf(Shades_3)",
        "Shades_4 = String.valueOf(Shades_4)",
        "Shades_5 = String.valueOf(Shades_5)",
        "Shades_6 = String.valueOf(Shades_6)",
        "Shades_7 = String.valueOf(Shades_7)",
        "Shades_8 = String.valueOf(Shades_8)",
        "Shades_9 = String.valueOf(Shades_9)",
        "Shades_10 = String.valueOf(Shades_10)",
    ]
)

from deephaven import pandas as dhpd
import pandas as pd
import os

os.system("pip install beautifulsoup4 requests")
os.system("pip install requests")
os.system("pip install lxml")
from bs4 import BeautifulSoup
import requests

url = "https://deephaven.io/core/docs/how-to-guides/data-import-export/html-import/"
headers = {"User-Agent": "Mozilla/5.0"}  # helps avoid being blocked

r = requests.get(url, headers=headers)

soup = BeautifulSoup(r.content, "lxml")

# Try to find the table
table = soup.find("table")

# Get basic headers
basic_headers = [th.text.strip() for th in table.find("thead").find_all("th")]

# Extract rows
rows = []
for tr in table.find("tbody").find_all("tr"):
    row = [td.text.strip() for td in tr.find_all("td")]
    if row:
        rows.append(row)

# Create expanded headers to match the actual number of columns
# First column keeps its name (usually 'Color')
headers = [basic_headers[0]]
# For remaining columns, use second header name with index suffix if needed
for i in range(1, len(rows[0])):
    if i == 1:
        headers.append(basic_headers[1])  # Usually 'Shades'
    else:
        headers.append(f"{basic_headers[1]}_{i-1}")  # 'Shades_1', 'Shades_2', etc.

# create the dataframe and specify types for each column
df = pd.DataFrame(rows, columns=headers).astype(
    {
        "Color": "string",
        "Shades": "string",
        "Shades_1": "string",
        "Shades_2": "string",
        "Shades_3": "string",
        "Shades_4": "string",
        "Shades_5": "string",
        "Shades_6": "string",
        "Shades_7": "string",
        "Shades_8": "string",
        "Shades_9": "string",
        "Shades_10": "string",
    }
)

# convert to table - Deephaven correctly interprets "string" as a String
deephaven_theme_colors = dhpd.to_table(df)