def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
BASE = 'https://buyandsell.gc.ca'
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
# No new data is being published, so just get the four
# years that exist.
urls = []
for i in range(13, 17):
url = '%s/cds/public/ocds/tpsgc-pwgsc_ocds_EF-FY-%s-%s.json' \
% (BASE, i, i + 1)
urls.append(url)
else:
folder += '/sample'
urls = ['%s/cds/public/ocds/tpsgc-pwgsc_ocds_EF-FY-15-16.json' % BASE]
for url in urls:
print("Fetching releases for %s" % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'http://datos.gob.mx/busca/api/3/action/'
url += 'package_search?q=organization:inai&rows=500'
folder = os.path.dirname(os.path.realpath(__file__))
release_packages = getReleasePackages(url)
if options.all:
folder += '/all'
else:
folder += '/sample'
for url in release_packages:
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
if not options.all:
data = data[:10]
if type(data) == list:
for d in data:
common.writeReleases(d['releases'], folder, d, url)
else:
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
BASE = 'http://moldova-ocds.yipl.com.np'
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
url = '%s/multiple-file-api/releases.json' % BASE
year_urls = fetchYears(url)
for url in year_urls:
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
else:
folder += '/all'
url = '%s/ocds-api/year/2017' % BASE
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
parser.add_option('-p',
'--page',
type="int",
default=1,
help='Fetch records from the given page')
parser.add_option('-R',
'--resume',
action='store_true',
default=False,
help='Continue from the last page (in page.n)')
parser.add_option('-b',
'--bigquery',
action='store_true',
default=False,
help='Fetch records in bigquery format')
(options, args) = parser.parse_args()
if options.resume:
with open("page.n", 'r') as n:
page = int(n.read())
else:
page = options.page
url = 'https://api.colombiacompra.gov.co/releases/?page=' + str(page)
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
packages = 1
next_url = url
while next_url:
print('fetching %s' % next_url)
data = common.getUrlAndRetry(next_url, folder)
if data is None:
current_page = int(next_url.split('page=')[1])
next_url = next_url.replace('page=' + str(current_page),
'page=' + str(current_page + 1))
continue
if options.bigquery:
common.writeReleases(data['releases'], folder, data, next_url)
else:
common.writeFile('%s.json' % str(packages), folder, data,
next_url)
next_url = data['links']['next']
with open("page.n", 'w') as n:
n.write(str(packages))
packages = packages + 1
else:
folder += '/sample'
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def fetchReleases(data, folder, url):
print('Fetching %s' % url)
for r in data['releases']:
# These releases are lacking IDs - set the ID to the OCID
# (which is unique).
r['id'] = r['ocid']
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'https://tenders.nsw.gov.au'
url += '/?event=public.api.%s.search&ResultsPerPage=1000'
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
release_types = ['planning', 'tender', 'contract']
for r in release_types:
next_url = url % r
while next_url:
print('fetching', next_url)
data = common.getUrlAndRetry(next_url, folder)
common.writeReleases(data['releases'], folder, data, next_url)
if 'next' in data['links']:
next_url = data['links']['next']
else:
next_url = None
else:
folder += '/sample'
next_url = url % 'planning'
print('fetching', next_url)
data = common.getUrlAndRetry(next_url, folder)
common.writeReleases(data['releases'], folder, data, next_url)
def fetchRecord(record_id, folder, get_releases, page=0):
'''
Given a record ID, construct the package URL and save locally.
'''
url = 'https://www.contrataciones.gov.py:443/'
url += 'datos/api/v2/doc/ocds/record-package/%s' % record_id
print("Fetching record %s ID: %s > %s" % (page, record_id, url))
data = common.getUrlAndRetry(url, folder)
if data:
try:
common.writeReleases(
[data['records'][0]['compiledRelease']], folder, data, url, 'records')
if get_releases and 'packages' in data:
releases = data['packages']
for url in releases:
# Rewrite the release URL - they are published
# in an incorrect format.
release_url = url\
.replace('/datos/id/', '/datos/api/v2/doc/ocds/')\
.replace('.json', '')
print('fetching %s' % release_url)
release_data = common.getUrlAndRetry(release_url, folder)
if release_data and 'releases' in release_data:
common.writeReleases(
release_data['releases'], folder,
release_data, release_url)
except KeyError:
err = 'No compiledReleases, skipping this one: %s \n' % url
print(err)
with open('%s/errors.txt' % folder, 'a') as errors:
errors.write(err)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'https://ville.montreal.qc.ca/vuesurlescontrats/api/releases.json'
folder = os.path.dirname(os.path.realpath(__file__))
more_releases = True
if options.all:
folder += '/all'
offset = 0
while more_releases:
next_url = url + '?limit=10000&offset=%s' % offset
print('fetching %s' % next_url)
data = common.getUrlAndRetry(next_url, folder)
more_releases = len(
common.writeReleases(data['releases'], folder, data, next_url))
offset += 10000
else:
folder += '/sample'
url += '?limit=10'
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
parser.add_option('-R',
'--resume',
action='store_true',
default=False,
help='Continue from the last page (in page.n)')
parser.add_option('-p',
'--page',
action='store',
type="int",
default=1,
help='Start from page n of the results')
(options, args) = parser.parse_args()
if options.resume:
with open("page.n", 'r') as n:
page = int(n.read())
else:
page = options.page
tags = ['planning', 'tender', 'award', 'contract']
for tag in tags:
folder = os.path.dirname(os.path.realpath(__file__))
base = 'http://gpp.ppda.go.ug'
url = '%s/api/v1/releases?tag=%s&page=%s' % (base, tag, 1)
if options.all:
folder += '/all/' + tag
r = requests.get(url)
data = r.json()
num_pages = data['pagination']['last_page']
print('%s pages to retrieve' % num_pages)
for i in range(page, num_pages + 1):
url = '%s/api/v1/releases?tag=%s&page=%s' % \
(base, tag, i)
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
if data is None:
continue
for r in data['releases']:
common.writeReleases([r], folder, data, url)
with open("page.n", 'w') as n:
n.write(str(i))
with open("page.n", 'w') as n:
n.write("1")
else:
folder += '/sample/' + tag
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
for r in data['releases'][:10]:
common.writeReleases([r], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
parser.add_option('-R',
'--resume',
action='store_true',
default=False,
help='Continue from the last page (in page.n)')
parser.add_option('-p',
'--page',
action='store',
type="int",
default=1,
help='Start from page n of the results')
(options, args) = parser.parse_args()
if options.resume:
with open("page.n", 'r') as n:
page = n.read()
else:
page = options.page
folder = os.path.dirname(os.path.realpath(__file__))
BASE = 'https://www.contractsfinder.service.gov.uk'
url = '%s/Published/Notices/OCDS/Search?order=asc&page=%s' % (BASE, 1)
if options.all:
folder += '/all'
r = requests.get(url)
data = r.json()
num_pages = data['maxPage']
print('%s pages to retrieve' % num_pages)
for i in range(page, num_pages + 1):
url = '%s/Published/Notices/OCDS/Search?order=asc&page=%s' % \
(BASE, i)
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
for r in data['results']:
common.writeReleases(r['releases'], folder, r, url)
with open("page.n", 'w') as n:
n.write(str(i))
with open("page.n", 'w') as n:
n.write("1")
else:
folder += '/sample'
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
for r in data['results'][:10]:
common.writeReleases(r['releases'], folder, r, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
parser.add_option('-b',
'--bigquery',
action='store_true',
default=False,
help='Save the data in big query format')
parser.add_option('-r',
'--releases',
action='store_true',
default=False,
help='Fetch individual releases')
(options, args) = parser.parse_args()
url = 'https://contratacionesabiertas.jalisco.gob.mx/OCApi/2017/contracts'
r = requests.get(url)
data = r.json()
package_urls = [d['URIContract'] for d in data]
folder = os.path.dirname(os.path.realpath(__file__))
count = 1
if options.all:
folder += '/all'
else:
folder += '/sample'
package_urls = package_urls[:10]
for url in package_urls:
print('fetching', url)
data = common.getUrlAndRetry(url, folder)
if options.bigquery:
common.writeReleases([data['records'][0]['compiledRelease']],
folder, data, url, 'records')
else:
common.writeFile('%s.json' % str(data['uri'].split('/')[-1]),
folder, data, url, 'records')
if options.releases:
for release_url in data['packages']:
if count > 10 and not options.all:
break
print('fetching', release_url)
release = common.getUrlAndRetry(release_url, folder)
count = count + 1
if options.bigquery:
common.writeReleases(release['releases'], folder, release,
release_url)
else:
common.writeFile(
'%s.json' % str(release_url.split('/')[-1]), folder,
release, release_url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a', '--all', action='store_true', default=False,
help='Fetch all records, rather than a small extract')
parser.add_option(
'-R', '--resume', action='store_true', default=False,
help='Continue from last page (in page.n) for when download broken')
parser.add_option('-p', '--page', action='store', type="int", default=1,
help='Start from page n of the results')
(options, args) = parser.parse_args()
if options.resume:
with open("page.n", 'r') as n:
page = n.read()
else:
page = options.page
BASE = 'http://ocds.prozorro.openprocurement.io'
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
urls = []
r = requests.get(BASE)
d = pq(r.content)
links = d('.container ol li a')
latest_url = "%s/%s" % (BASE, links[-2].attrib['href'])
if 'with_extensions' in latest_url:
r = requests.get(latest_url)
d = pq(r.content)
links = d('.container ol li a')
for l in links:
release_url = "%s/%s" % (latest_url, l.attrib['href'])
urls.append(release_url)
else:
print('Latest URL does not contain extensions - check page')
else:
folder += '/sample'
urls = [
'%s/merged_with_extensions_2017-06-23/release-0000001.json' % BASE
]
print('%s release packages to fetch' % len(urls))
for url in urls:
package_num = int(url.split('-')[-1].replace('.json', ''))
if package_num < page:
continue
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(
data['releases'], folder, data, url)
with open("page.n", 'w') as n:
n.write(str(package_num))
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'http://nigeriaoc.org/downloadSelected'
r = requests.get(url)
data = r.json()
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
else:
folder += '/sample'
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'http://www.contratosabiertos.cdmx.gob.mx/api/contratos/todos'
r = requests.get(url)
data = r.json()
package_urls = [d['uri'] for d in data]
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
else:
folder += '/sample'
package_urls = package_urls[:4]
for url in package_urls:
print('fetching', url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'https://api.colombiacompra.gov.co/releases/'
folder = os.path.dirname(os.path.realpath(__file__))
if options.all:
folder += '/all'
next_url = url
while next_url:
print('fetching %s' % next_url)
data = common.getUrlAndRetry(next_url, folder)
common.writeReleases(data['releases'], folder, data, next_url)
next_url = data['links']['next']
else:
folder += '/sample'
print('fetching %s' % url)
data = common.getUrlAndRetry(url, folder)
common.writeReleases(data['releases'], folder, data, url)
def main():
usage = 'Usage: %prog [ --all --cont ]'
parser = optparse.OptionParser(usage=usage)
parser.add_option('-a',
'--all',
action='store_true',
default=False,
help='Fetch all records, rather than a small extract')
(options, args) = parser.parse_args()
url = 'http://datos.gob.mx/busca/api/3/action/'
url += 'package_search?q=organization:contrataciones-abiertas&rows=500'
folder = os.path.dirname(os.path.realpath(__file__))
release_packages = getReleasePackages(url)
if options.all:
folder += '/all'
else:
folder += '/sample'
for url in release_packages:
print('fetching %s' % url)
urllib.request.urlretrieve(url, "file.zip")
with zipfile.ZipFile("file.zip", "r") as zip_ref:
zip_ref.extractall(os.getcwd())
zip_ref.close()
with open(os.getcwd() +
'/contratacionesabiertas_bulk.json') as data_file:
data = json.load(data_file, encoding='latin1')
if not options.all:
data = data[:10]
if type(data) == list:
for d in data:
common.writeReleases([d['records'][0]['compiledRelease']],
folder, d, url, 'records')
else:
common.writeReleases(data['releases'], folder, data, url)
data_file.close()
break
