Skip to main content

​
Downloading BORME Files

bormeparser provides convenient functions to download BORME files directly from the official BOE (Boletín Oficial del Estado) website.

​
Quick Start

import bormeparser
import datetime

# Download a single PDF file
date = datetime.date(2015, 6, 1)
bormeparser.download_pdf(
    date=date,
    filename='BORME-A-2015-101-29.pdf',
    seccion=bormeparser.SECCION.A,
    provincia=bormeparser.PROVINCIA.MALAGA
)

​
Downloading a Single PDF

Use download_pdf() to download a single BORME PDF file for a specific date, section, and province:

​
Function Signature

download_pdf(date, filename, seccion, provincia, parse=False)

​
Parameters

  • date: datetime.date object or tuple (year, month, day)
  • filename: Path where the file will be saved
  • seccion: SECCION.A or SECCION.B
  • provincia: A PROVINCIA constant (e.g., PROVINCIA.MADRID)
  • parse: If True, automatically parse the file after downloading (default: False)

​
Examples

1

Download with datetime.date

import bormeparser
import datetime

date = datetime.date(2015, 6, 1)
bormeparser.download_pdf(
    date=date,
    filename='downloads/BORME-A-2015-101-29.pdf',
    seccion=bormeparser.SECCION.A,
    provincia=bormeparser.PROVINCIA.MALAGA
)
2

Download with tuple date

import bormeparser

# Use tuple: (year, month, day)
bormeparser.download_pdf(
    date=(2015, 6, 1),
    filename='BORME-A-2015-101-28.pdf',
    seccion='A',
    provincia=bormeparser.PROVINCIA.MADRID
)
3

Download and parse automatically

import bormeparser

# Set parse=True to automatically parse after download
borme = bormeparser.download_pdf(
    date=(2015, 6, 1),
    filename='BORME-A-2015-101-29.pdf',
    seccion=bormeparser.SECCION.A,
    provincia=bormeparser.PROVINCIA.MALAGA,
    parse=True  # Returns Borme object instead of boolean
)

if borme:
    print(f'Downloaded and parsed {len(borme.get_anuncios())} announcements')

​
Downloading Multiple PDFs

Use download_pdfs() to download multiple BORME files at once:

​
Function Signature

download_pdfs(date, path, provincia=None, seccion=None, secure=True)

​
Parameters

  • date: datetime.date object or tuple
  • path: Directory where files will be saved
  • provincia: Download files for a specific province (optional)
  • seccion: Download files for a specific section (optional)
  • secure: Use HTTPS (default: True)

​
Examples

1

Download all files for a section

import bormeparser
import datetime

date = datetime.date(2015, 6, 1)
success, files = bormeparser.download_pdfs(
    date=date,
    path='downloads/',
    seccion=bormeparser.SECCION.A
)

print(f'Downloaded {len(files)} files')
for file in files:
    print(f'  - {file}')
2

Download files for a specific province

import bormeparser

# Download all sections for Barcelona
success, files = bormeparser.download_pdfs(
    date=(2015, 6, 1),
    path='downloads/',
    provincia=bormeparser.PROVINCIA.BARCELONA
)

​
Downloading XML Files

Download the XML summary file that contains metadata and URLs for all BORME files of a given date: 
import bormeparser
import datetime

date = datetime.date(2015, 6, 1)
bormeparser.download_xml(
    date=date,
    filename='BORME-S-20150601.xml'
)

​
Working with BormeXML

The XML file contains URLs for all BORME PDFs. You can use the BormeXML class to work with it: 
from bormeparser.borme import BormeXML
import datetime

# Load from file
bxml = BormeXML.from_file('BORME-S-20150601.xml')

# Or fetch directly from date
bxml = BormeXML.from_date(datetime.date(2015, 6, 1))

# Get available provinces for Section A
provincias = bxml.get_provincias(seccion='A')
print(provincias)

# Get URLs for all PDFs in Section A
urls = bxml.get_url_pdfs(seccion='A')
for provincia, url in urls.items():
    print(f'{provincia}: {url}')

# Download all files for Section A
success, files = bxml.download_borme(path='downloads/', seccion='A')

​
Getting Download URLs

You can retrieve download URLs without actually downloading the files:

​
Get URL for a single PDF

import bormeparser
import datetime

date = datetime.date(2015, 6, 1)
url = bormeparser.get_url_pdf(
    date=date,
    seccion=bormeparser.SECCION.A,
    provincia=bormeparser.PROVINCIA.MADRID
)

print(url)
# https://boe.es/borme/dias/2015/06/01/pdfs/BORME-A-2015-101-28.pdf
get_url_pdf() requires an internet connection to fetch the BORME number (nbo) from the XML file.

​
Get URLs for multiple PDFs

import bormeparser
import datetime

# Get all URLs for Section A on a specific date
urls = bormeparser.get_url_pdfs(
    date=datetime.date(2015, 6, 1),
    seccion=bormeparser.SECCION.A
)

# Returns a dictionary: {provincia: url}
for provincia, url in urls.items():
    print(f'{provincia}: {url}')

​
Get XML URL

import bormeparser
import datetime

url = bormeparser.get_url_xml(date=datetime.date(2015, 6, 1))
print(url)
# https://www.boe.es/diario_borme/xml.php?id=BORME-S-20150601

​
URL Patterns

bormeparser uses these URL patterns to download files: 
# PDF files (Sections A & B)
# https://boe.es/borme/dias/{year}/{month:02d}/{day:02d}/pdfs/BORME-{seccion}-{year}-{nbo}-{provincia}.pdf

# XML summary file
# https://www.boe.es/diario_borme/xml.php?id=BORME-S-{year}{month:02d}{day:02d}

# Section C XML files
# https://www.boe.es/diario_borme/xml.php?id=BORME-C-{year}-{anuncio}

# Section C PDF files
# https://boe.es/borme/dias/{year}/{month:02d}/{day:02d}/pdfs/BORME-C-{year}-{anuncio}.pdf

​
Province Constants

Use the PROVINCIA class to specify provinces: 
from bormeparser import PROVINCIA

# Major provinces
PROVINCIA.MADRID        # Madrid
PROVINCIA.BARCELONA     # Barcelona
PROVINCIA.VALENCIA      # Valencia
PROVINCIA.SEVILLA       # Sevilla
PROVINCIA.MALAGA        # Málaga
PROVINCIA.BILBAO        # Vizcaya

# All provinces available
PROVINCIA.ALAVA         # Álava
PROVINCIA.ALBACETE      # Albacete
PROVINCIA.ALICANTE      # Alicante
PROVINCIA.ALMERIA       # Almería
# ... and 48 more provinces

​
Advanced Example

Download multiple files with error handling: 
import bormeparser
from bormeparser.exceptions import BormeDoesntExistException
from bormeparser.borme import BormeXML
import datetime
import os

def download_borme_range(start_date, end_date, output_dir, seccion):
    """Download BORME files for a date range"""
    current_date = start_date
    total_downloaded = 0
    
    while current_date <= end_date:
        try:
            # Create output directory
            date_path = os.path.join(output_dir, current_date.isoformat())
            os.makedirs(date_path, exist_ok=True)
            
            # Download using BormeXML
            bxml = BormeXML.from_date(current_date)
            success, files = bxml.download_borme(
                path=date_path,
                seccion=seccion
            )
            
            print(f'{current_date}: Downloaded {len(files)} files')
            total_downloaded += len(files)
            
            # Move to next BORME date
            current_date = bxml.next_borme
            if not current_date:
                break
                
        except BormeDoesntExistException:
            print(f'{current_date}: No BORME published')
            current_date += datetime.timedelta(days=1)
        except Exception as e:
            print(f'{current_date}: Error - {e}')
            current_date += datetime.timedelta(days=1)
    
    print(f'Total files downloaded: {total_downloaded}')

# Usage
start = datetime.date(2015, 6, 1)
end = datetime.date(2015, 6, 30)
download_borme_range(start, end, 'downloads/', bormeparser.SECCION.A)

​
Next Steps

After downloading files, you can:

Build docs developers (and LLMs) love

Get started for freeTalk to us