Last active
August 29, 2015 14:11
-
-
Save AndreyAkinshin/25dea1f4eb932414d916 to your computer and use it in GitHub Desktop.
Template for fips bulletin downloading
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Main link: http://www1.fips.ru/wps/wcm/connect/content_ru/ru/ofic_pub/ofic_bul/ofic_bul_prevm | |
# pdf->txt converter: pdfminer, https://pypi.python.org/pypi/pdfminer/ | |
import urllib, os | |
def get_link(year, month, number): | |
link = "http://www1.fips.ru/Archive/EVM/" + \ | |
str(year) + "/" + str(year) + "." + str(month).zfill(2) + ".20" + \ | |
"/DOC/RUNW/000/00" + str(year)[0:1] + "/" + str(year)[1:4].zfill(3) + "/" + \ | |
str(number)[0:3].zfill(3) + "/" + str(number)[3:6].zfill(3) + "/document.pdf" | |
return link | |
def download(link, number): | |
url = urllib.URLopener() | |
url.retrieve(link, str(number) + ".pdf") | |
os.system("pdf2txt.py " + str(number) + ".pdf > " + str(number) + ".txt") | |
print "DONE: " + str(number) | |
def download_bulletin(year, month, fromNumber, toNumber): | |
for number in xrange(fromNumber, toNumber + 1): | |
download(get_link(year, month, number), number) | |
# Download bulletin example: December 2014 | |
download_bulletin(2014, 12, 661608, 662651) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment