Download all USPTO patent grants 1976 - present

download_patent_grants.py

# Download patent grants 1976 - 2014

import os
import urllib
import urllib2
import lxml.html

if not os.path.exists('data'):
    os.mkdir('data')


URL = "http://www.google.com/googlebooks/uspto-patents-grants-text.html"
doc = lxml.html.parse(URL)
body = doc.find("body")
count = 0
for link in body.findall("a"):
    href = link.get("href")
    if href and href.endswith(".zip"):
        count += 1
        path, year, fname = href.rsplit("/", 2)
        if not os.path.exists("data/%s" % year):
            os.mkdir("data/%s" % year)
        fullname = "data/%s/%s" % (year, fname)
        print "%04d - Retrieving %s" % (count, fullname)
        urllib.urlretrieve(href, fullname)