Converting pdf table into html format

Question

I have a pdf which has this type of table and I need to convert the respective table into html file using python but I am not able to calculate rowspan and colspan attributes and the generated table looks different.

I tried this code but it not able to calculate rowspan and colspan properly. can Camelot able to do this?

import pdfplumber
from bs4 import BeautifulSoup

# Function to convert list of lists to HTML table
def list_to_html_table(data):
    html_table = "<table>\n"
    for row in data:
        html_table += "  <tr>\n"
        for cell in row:
            html_table += cell
        html_table += "  </tr>\n"
    html_table += "</table>"
    return html_table

# PDF file path
pdf_file = 'simple_rowspan_colspan.pdf'

# Extract tables from the PDF using pdfplumber
pdf = pdfplumber.open(pdf_file)
html_tables = []

for page in pdf.pages:
    page_tables = page.extract_tables()
    for table_data in page_tables:
        num_rows = len(table_data)
        num_cols = max(len(row) for row in table_data)
        cell_data = [[''] * num_cols for _ in range(num_rows)]

        for i, row in enumerate(table_data):
            for j, cell in enumerate(row):
                if cell:
                    rowspan, colspan = 1, 1

                    # Check for rowspan
                    for k in range(i + 1, num_rows):
                        if cell_data[k][j] == '':
                            rowspan += 1
                        else:
                            break

                    # Check for colspan
                    for k in range(j + 1, j + colspan):
                        if k < num_cols:
                            if cell_data[i][k] == '':
                                colspan += 1
                            else:
                                break

                    cell_text = f'<td rowspan="{rowspan}" colspan="{colspan}">{cell}</td>'
                    cell_data[i][j] = cell_text

        # Convert the data into an HTML table
        html_table = list_to_html_table(cell_data)
        html_tables.append(html_table)

# Combine all HTML tables into a single HTML document
output_html = "\n".join(html_tables)

# Parse the HTML to beautify it
soup = BeautifulSoup(output_html, 'html.parser')
pretty_html = soup.prettify()

# Print or save the prettified HTML output as needed
print(pretty_html)

# Save the HTML table to a file or print it as needed
with open('output_table.html', 'w', encoding='utf-8') as html_file:
    html_file.write(output_html)

Answer 1

• Camelot is be used to extract tables from PDF files, you can give a try on that too. In this code
• When you are checking colspan, it only checks for colspan in the next column (j + 1), but it should check for colspan in the range from j + 1 to j + colspan and also not to exceed no. of columns.

# Check for colspan
for k in range(j + 1, min(j + 1 + colspan, num_cols)):
    if cell_data[i][k] == '':
        colspan += 1
    else:
        break
# ...rest