The download module provides functions to download BORME (Spanish Official Gazette of the Commercial Registry) files in PDF and XML formats.
download_pdf()
Download a single BORME PDF file for a specific date, section, and province.
download_pdf(date, filename, seccion, provincia, parse=False)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Path where the PDF file will be saved
Section: 'A', 'B', 'C' or SECCION.A, SECCION.B, SECCION.C
Province object (e.g., PROVINCIA.MADRID, PROVINCIA.BARCELONA)
Whether to parse the PDF file after downloading
bool - True if downloaded and parsed (when parse=True), False otherwise
from bormeparser import download_pdf
from bormeparser.provincia import PROVINCIA
from bormeparser.seccion import SECCION
import datetime
# Download BORME for Madrid, Section A
date = datetime.date(2024, 1, 15)
download_pdf(
date=date,
filename="borme-madrid.pdf",
seccion=SECCION.A,
provincia=PROVINCIA.MADRID
)
# Using tuple for date
download_pdf(
date=(2024, 1, 15),
filename="borme-barcelona.pdf",
seccion='A',
provincia=PROVINCIA.BARCELONA,
parse=True
)
download_pdfs()
Download multiple BORME PDF files for a specific date and province or section.
download_pdfs(date, path, provincia=None, seccion=None, secure=True)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Directory path where PDF files will be saved
Province to download BORMEs for (mutually exclusive with seccion)
Section to download BORMEs for: 'A' or 'B' only (mutually exclusive with provincia)
Use HTTPS instead of HTTP
tuple[bool, list[str]] - (True, list_of_downloaded_files)
You must specify either provincia or seccion, but not both.
import datetime
from bormeparser import download_pdfs
from bormeparser.provincia import PROVINCIA
from bormeparser.seccion import SECCION
# Download all Section A BORMEs for a specific date
date = datetime.date(2024, 1, 15)
success, files = download_pdfs(
date=date,
path="./borme_files",
seccion=SECCION.A
)
print(f"Downloaded {len(files)} files")
# Download all BORMEs for a specific province
success, files = download_pdfs(
date=(2024, 1, 15),
path="./madrid_borme",
provincia=PROVINCIA.MADRID
)
download_xml()
Download the XML summary file containing URLs of all BORMEs for a specific date.
download_xml(date, filename, secure=True)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Path where the XML file will be saved
Use HTTPS instead of HTTP
bool - True if downloaded, False if file already exists
import datetime
from bormeparser import download_xml
# Download XML summary for a specific date
date = datetime.date(2024, 1, 15)
download_xml(
date=date,
filename="borme-summary.xml"
)
get_url_pdf()
Get the URL for downloading a specific BORME PDF file.
get_url_pdf(date, seccion, provincia, secure=True)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Section: 'A', 'B', or 'C'
Use HTTPS instead of HTTP
str - URL to download the PDF
This function requires an internet connection as it fetches the XML to determine the bulletin number (nbo).
from bormeparser import get_url_pdf
from bormeparser.provincia import PROVINCIA
from bormeparser.seccion import SECCION
import datetime
date = datetime.date(2024, 1, 15)
url = get_url_pdf(
date=date,
seccion=SECCION.A,
provincia=PROVINCIA.MADRID
)
print(url)
# https://boe.es/borme/dias/2024/01/15/pdfs/BORME-A-2024-10-28.pdf
get_url_pdfs()
Get URLs for downloading multiple BORME PDF files.
get_url_pdfs(date, seccion=None, provincia=None, secure=True)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Section: 'A' or 'B' only (mutually exclusive with provincia)
Province object (mutually exclusive with seccion)
Use HTTPS instead of HTTP
dict - Dictionary mapping province names (or sections) to URLs
from bormeparser import get_url_pdfs
from bormeparser.seccion import SECCION
import datetime
# Get all URLs for Section A
date = datetime.date(2024, 1, 15)
urls = get_url_pdfs(date=date, seccion=SECCION.A)
for provincia, url in urls.items():
print(f"{provincia}: {url}")
# Output:
# A CORUÑA: https://boe.es/borme/dias/2024/01/15/pdfs/BORME-A-2024-10-15.pdf
# ALBACETE: https://boe.es/borme/dias/2024/01/15/pdfs/BORME-A-2024-10-02.pdf
# ...
get_url_xml()
Get the URL for the XML summary file for a specific date.
get_url_xml(date, secure=True)
date
tuple | datetime.date
required
Date as either a tuple (year, month, day) or a datetime.date object
Use HTTPS instead of HTTP
str - URL to download the XML summary
from bormeparser import get_url_xml
import datetime
date = datetime.date(2024, 1, 15)
url = get_url_xml(date=date)
print(url)
# https://www.boe.es/diario_borme/xml.php?id=BORME-S-20240115
URL Patterns
The module uses the following URL patterns:
# PDF URLs for sections A and B
BORME_AB_PDF_URL = "{protocol}://boe.es/borme/dias/{year}/{month:02d}/{day:02d}/pdfs/BORME-{seccion}-{year}-{nbo}-{provincia}.pdf"
# XML summary URL
BORME_XML_URL = "{protocol}://www.boe.es/diario_borme/xml.php?id=BORME-S-{year}{month:02d}{day:02d}"
# Section C URLs
BORME_C_PDF_URL = "{protocol}://boe.es/borme/dias/{year}/{month:02d}/{day:02d}/pdfs/BORME-C-{year}-{anuncio}.pdf"
BORME_C_XML_URL = "{protocol}://boe.es/diario_borme/xml.php?id=BORME-C-{year}-{anuncio}"
BORME_C_HTM_URL = "{protocol}://boe.es/diario_borme/txt.php?id=BORME-C-{year}-{anuncio}"
