def main():
parser = argparse.ArgumentParser(
description='Scrape data for single bill, saving data to disk.',
parents=[base_arg_parser],
)
parser.add_argument('module', type=str, help='scraper module (eg. nc)')
parser.add_argument('chamber', type=str, help='chamber for bill to scrape')
parser.add_argument('session', type=str, help='session for bill to scrape')
parser.add_argument('bill_id', type=str, help='bill_id to scrape')
parser.add_argument('--strict',
action='store_true',
dest='strict',
default=False,
help="fail immediately when"
"encountering validation warning")
parser.add_argument('-n',
'--no_cache',
action='store_true',
dest='no_cache',
help="don't use web page cache")
parser.add_argument('--fastmode',
help="scrape in fast mode",
action="store_true",
default=False)
parser.add_argument('-r',
'--rpm',
action='store',
type=int,
dest='rpm',
default=60),
parser.add_argument('--import',
dest='do_import',
help="import bill after scrape",
action="store_true",
default=False)
args = parser.parse_args()
settings.update(args)
# set up search path
sys.path.insert(
0, os.path.join(os.path.dirname(__file__), '../../openstates'))
# get metadata
metadata = __import__(args.module, fromlist=['metadata']).metadata
abbr = metadata['abbreviation']
# configure logger
configure_logging(args.verbose, abbr)
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, abbr)
_run_scraper(args, metadata)
if args.do_import:
import_bills(abbr, settings.BILLY_DATA_DIR)
def main():
parser = argparse.ArgumentParser(
description='Import scraped data into database.',
parents=[base_arg_parser],
)
parser.add_argument('abbreviation', type=str,
help=('the short name of the data to import'))
parser.add_argument('-r', '--rpm', type=int, default=60,
help=('maximum number of documents to download '
'per minute'))
parser.add_argument('--bills', action='store_true',
help='scrape bill data')
parser.add_argument('--legislators', action='store_true',
help='scrape legislator data')
parser.add_argument('--committees', action='store_true',
help='scrape (separate) committee data')
parser.add_argument('--events', action='store_true',
help='scrape event data')
parser.add_argument('--alldata', action='store_true', dest='alldata',
default=False, help="import all available data")
args = parser.parse_args()
if not (args.bills or args.legislators or args.committees or
args.events or args.alldata):
raise Exception("Must specify at least one type: --bills, "
"--legislators, --committees, --events, "
"--alldata")
settings.update(args)
data_dir = settings.BILLY_DATA_DIR
# configure logger
configure_logging(args.verbose, args.abbreviation)
# always import metadata
import_metadata(args.abbreviation, data_dir)
if args.legislators or args.alldata:
import_legislators(args.abbreviation, data_dir)
if args.bills or args.alldata:
import_bills(args.abbreviation, data_dir)
if args.committees or args.alldata:
import_committees(args.abbreviation, data_dir)
# events currently excluded from --alldata
if args.events:
import_events(args.abbreviation, data_dir)
def main():
parser = argparse.ArgumentParser(
description='Scrape data for state, saving data to disk.',
parents=[base_arg_parser],
)
parser.add_argument('state', type=str,
help='state scraper module (eg. nc)')
parser.add_argument('chamber', type=str,
help='chamber for bill to scrape')
parser.add_argument('session', type=str,
help='session for bill to scrape')
parser.add_argument('bill_id', type=str,
help='bill_id to scrape')
parser.add_argument('--strict', action='store_true', dest='strict',
default=False, help="fail immediately when"
"encountering validation warning")
parser.add_argument('-n', '--no_cache', action='store_true',
dest='no_cache', help="don't use web page cache")
parser.add_argument('--fastmode', help="scrape in fast mode",
action="store_true", default=False)
parser.add_argument('-r', '--rpm', action='store', type=int, dest='rpm',
default=60),
parser.add_argument('--import', dest='do_import',
help="import bill after scrape",
action="store_true", default=False)
args = parser.parse_args()
settings.update(args)
# set up search path
sys.path.insert(0, os.path.join(os.path.dirname(__file__),
'../../openstates'))
# get metadata
metadata = __import__(args.state, fromlist=['metadata']).metadata
state = metadata['abbreviation']
# configure logger
configure_logging(args.verbose, state)
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, args.state)
_run_scraper(args.state, state, args, metadata)
if args.do_import:
import_bills(args.state, settings.BILLY_DATA_DIR)
def main():
import argparse
configure_logging(1)
parser = argparse.ArgumentParser(
description=('Dump API information to a zipped directory of JSON files'
', optionally uploading to S3 when done.'),
parents=[base_arg_parser],
)
parser.add_argument(
'abbrs',
metavar='ABBR',
type=str,
nargs='+',
help=('the two-letter abbreviation for the data to export'))
parser.add_argument('--file',
'-f',
help='filename to output to (defaults to <abbr>.zip)')
parser.add_argument('--schema_dir',
help='directory to use for API schemas (optional)',
default=None)
parser.add_argument('--nodump',
action='store_true',
default=False,
help="don't run the dump, only upload")
parser.add_argument('--novalidate',
action='store_true',
default=False,
help="don't run validation")
parser.add_argument('--upload',
'-u',
action='store_true',
default=False,
help='upload the created archive to S3')
args = parser.parse_args()
settings.update(args)
for abbr in args.abbrs:
if not args.file:
args.file = abbr + '.zip'
if not args.nodump:
dump_json(abbr, args.file, not args.novalidate, args.schema_dir)
if args.upload:
upload(abbr, args.file)
def main():
try:
parser = argparse.ArgumentParser(
description="Scrape data for single bill, saving data to disk.", parents=[base_arg_parser]
)
parser.add_argument("module", type=str, help="scraper module (eg. nc)")
parser.add_argument("chamber", type=str, help="chamber for bill to scrape")
parser.add_argument("session", type=str, help="session for bill to scrape")
parser.add_argument("bill_id", type=str, help="bill_id to scrape")
parser.add_argument(
"--strict",
action="store_true",
dest="strict",
default=False,
help="fail immediately when" "encountering validation warning",
)
parser.add_argument("-n", "--no_cache", action="store_true", dest="no_cache", help="don't use web page cache")
parser.add_argument("--fastmode", help="scrape in fast mode", action="store_true", default=False)
parser.add_argument("-r", "--rpm", action="store", type=int, dest="rpm", default=60),
parser.add_argument(
"--import", dest="do_import", help="import bill after scrape", action="store_true", default=False
)
args = parser.parse_args()
settings.update(args)
# set up search path
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../../openstates"))
# get metadata
metadata = __import__(args.module, fromlist=["metadata"]).metadata
abbr = metadata["abbreviation"]
# configure logger
configure_logging(args.verbose, abbr)
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, abbr)
_run_scraper(args, metadata)
if args.do_import:
import_bills(abbr, settings.BILLY_DATA_DIR)
except ScrapeError as e:
print "Error:", e
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
description='Convert state bills to SFM-ready text',
parents=[base_arg_parser],
)
parser.add_argument('state', type=str, help='state')
parser.add_argument('--sfm_server', type=str, help='URL of SFM instance',
default='http://localhost:8080/')
args = parser.parse_args()
settings.update(args)
configure_logging(args.verbose, args.state)
process_state_files(args.state, args.sfm_server)
def main():
try:
parser = argparse.ArgumentParser(
description='Scrape data for single bill, saving data to disk.',
parents=[base_arg_parser],
)
parser.add_argument('module', type=str, help='scraper module (eg. nc)')
parser.add_argument('chamber', type=str,
help='chamber for bill to scrape')
parser.add_argument('session', type=str,
help='session for bill to scrape')
parser.add_argument('bill_id', type=str, help='bill_id to scrape')
parser.add_argument('--strict', action='store_true', dest='strict',
default=False, help="fail immediately when"
"encountering validation warning")
parser.add_argument('-n', '--no_cache', action='store_true',
dest='no_cache', help="don't use web page cache")
parser.add_argument('--fastmode', help="scrape in fast mode",
action="store_true", default=False)
parser.add_argument('-r', '--rpm', action='store', type=int,
dest='rpm', default=60),
parser.add_argument('--import', dest='do_import',
help="import bill after scrape",
action="store_true", default=False)
args = parser.parse_args()
settings.update(args)
# get metadata
metadata = __import__(args.module, fromlist=['metadata']).metadata
abbr = metadata['abbreviation']
# configure logger
configure_logging(args.verbose, abbr)
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, abbr)
_run_scraper(args, metadata)
if args.do_import:
import_bills(abbr, settings.BILLY_DATA_DIR)
except ScrapeError as e:
print 'Error:', e
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
description='Convert state bills to SFM-ready text',
parents=[base_arg_parser],
)
parser.add_argument('state', type=str, help='state')
parser.add_argument('--sfm_server',
type=str,
help='URL of SFM instance',
default='http://localhost:8080/')
args = parser.parse_args()
settings.update(args)
configure_logging(args.verbose, args.state)
process_state_files(args.state, args.sfm_server)
def main():
parser = argparse.ArgumentParser(description='generic billy util',
parents=[base_arg_parser])
subparsers = parser.add_subparsers(dest='subcommand')
# import command plugins
for mod in COMMAND_MODULES:
import_command_module(mod)
# instantiate all subcommands
subcommands = {}
for SubcommandCls in BaseCommand.subcommands:
subcommands[SubcommandCls.name] = SubcommandCls(subparsers)
# parse arguments, update settings, then run the appropriate function
args = parser.parse_args()
settings.update(args)
configure_logging(args.subcommand)
subcommands[args.subcommand].handle(args)
def main():
parser = argparse.ArgumentParser(description='generic billy util',
parents=[base_arg_parser])
subparsers = parser.add_subparsers(dest='subcommand')
# import command plugins
for mod in COMMAND_MODULES:
import_command_module(mod)
# instantiate all subcommands
subcommands = {}
for SubcommandCls in BaseCommand.subcommands:
subcommands[SubcommandCls.name] = SubcommandCls(subparsers)
# parse arguments, update settings, then run the appropriate function
args = parser.parse_args()
settings.update(args)
configure_logging(args.subcommand)
subcommands[args.subcommand].handle(args)
def main():
import argparse
configure_logging(1)
parser = argparse.ArgumentParser(
description=('Dump API information to a zipped directory of JSON files'
', optionally uploading to S3 when done.'),
parents=[base_arg_parser],
)
parser.add_argument('abbrs', metavar='ABBR', type=str, nargs='+',
help=('the two-letter abbreviation for the data to export'))
parser.add_argument('--file', '-f',
help='filename to output to (defaults to <abbr>.zip)')
parser.add_argument('--schema_dir',
help='directory to use for API schemas (optional)',
default=None)
parser.add_argument('--nodump', action='store_true', default=False,
help="don't run the dump, only upload")
parser.add_argument('--novalidate', action='store_true', default=False,
help="don't run validation")
parser.add_argument('--upload', '-u', action='store_true', default=False,
help='upload the created archive to S3')
args = parser.parse_args()
settings.update(args)
for abbr in args.abbrs:
if not args.file:
args.file = abbr + '.zip'
if not args.nodump:
dump_json(abbr, args.file, not args.novalidate, args.schema_dir)
if args.upload:
upload(abbr, args.file)
def main():
parser = argparse.ArgumentParser(
description='Scrape data for state, saving data to disk.',
parents=[base_arg_parser],
)
parser.add_argument('state', type=str,
help='state scraper module (eg. nc)')
parser.add_argument('-s', '--session', action='append', dest='sessions',
help='session(s) to scrape')
parser.add_argument('-t', '--term', action='append', dest='terms',
help='term(s) to scrape')
parser.add_argument('--upper', action='store_true', dest='upper',
default=False, help='scrape upper chamber')
parser.add_argument('--lower', action='store_true', dest='lower',
default=False, help='scrape lower chamber')
parser.add_argument('--bills', action='store_true', dest='bills',
default=False, help="scrape bill data")
parser.add_argument('--legislators', action='store_true',
dest='legislators', default=False,
help="scrape legislator data")
parser.add_argument('--committees', action='store_true', dest='committees',
default=False, help="scrape committee data")
parser.add_argument('--votes', action='store_true', dest='votes',
default=False, help="scrape vote data")
parser.add_argument('--events', action='store_true', dest='events',
default=False, help='scrape event data')
parser.add_argument('--alldata', action='store_true', dest='alldata',
default=False,
help="scrape all available types of data")
parser.add_argument('--strict', action='store_true', dest='strict',
default=False, help="fail immediately when"
"encountering validation warning")
parser.add_argument('-n', '--no_cache', action='store_true',
dest='no_cache', help="don't use web page cache")
parser.add_argument('--fastmode', help="scrape in fast mode",
action="store_true", default=False)
parser.add_argument('-r', '--rpm', action='store', type=int, dest='rpm',
default=60),
parser.add_argument('--timeout', action='store', type=int, dest='timeout',
default=10)
args = parser.parse_args()
settings.update(args)
# set up search path
sys.path.insert(0, os.path.join(os.path.dirname(__file__),
'../../openstates'))
# get metadata
metadata = __import__(args.state, fromlist=['metadata']).metadata
state = metadata['abbreviation']
configure_logging(args.verbose, args.state)
# make output dir
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, args.state)
try:
os.makedirs(args.output_dir)
except OSError as e:
if e.errno != 17:
raise e
# write metadata
try:
schema_path = os.path.join(os.path.split(__file__)[0],
'../schemas/metadata.json')
schema = json.load(open(schema_path))
validator = DatetimeValidator()
validator.validate(metadata, schema)
except ValueError as e:
logging.getLogger('billy').warning('metadata validation error: '
+ str(e))
with open(os.path.join(args.output_dir, 'state_metadata.json'), 'w') as f:
json.dump(metadata, f, cls=JSONDateEncoder)
# determine time period to run for
if args.terms:
for term in metadata['terms']:
if term in args.terms:
args.sessions.extend(term['sessions'])
args.sessions = set(args.sessions or [])
# determine chambers
args.chambers = []
if args.upper:
args.chambers.append('upper')
if args.lower:
args.chambers.append('lower')
if not args.chambers:
args.chambers = ['upper', 'lower']
if not (args.bills or args.legislators or args.votes or
args.committees or args.events or args.alldata):
raise ScrapeError("Must specify at least one of --bills, "
"--legislators, --committees, --votes, --events, "
"--alldata")
if args.alldata:
args.bills = True
args.legislators = True
args.votes = True
args.committees = True
if args.bills:
_run_scraper(args.state, state, 'bills', args, metadata)
if args.legislators:
_run_scraper(args.state, state, 'legislators', args, metadata)
if args.committees:
_run_scraper(args.state, state, 'committees', args, metadata)
if args.votes:
_run_scraper(args.state, state, 'votes', args, metadata)
if args.events:
_run_scraper(args.state, state, 'events', args, metadata)
help="import all available data")
args = parser.parse_args()
if not (args.bills or args.legislators or args.committees or args.events
or args.alldata):
raise Exception("Must specify at least one type: --bills, "
"--legislators, --committees, --events, "
"--alldata")
settings.update(args)
data_dir = settings.BILLY_DATA_DIR
# configure logger
configure_logging(args.verbose, args.abbreviation)
# always import metadata
import_metadata(args.abbreviation, data_dir)
if args.legislators or args.alldata:
import_legislators(args.abbreviation, data_dir)
if args.bills or args.alldata:
import_bills(args.abbreviation, data_dir)
if args.committees or args.alldata:
import_committees(args.abbreviation, data_dir)
# events currently excluded from --alldata
if args.events:
import_events(args.abbreviation, data_dir)
k.key = s3_path
logging.info('beginning upload to %s' % s3_url)
k.set_contents_from_filename(filename)
k.set_acl('public-read')
meta['latest_dump_url'] = s3_url
meta['latest_dump_date'] = datetime.datetime.utcnow()
db.metadata.save(meta, safe=True)
logging.info('upload complete')
if __name__ == '__main__':
import argparse
configure_logging(1)
parser = argparse.ArgumentParser(
description=('Dump API information to a zipped directory of JSON files'
', optionally uploading to S3 when done.'),
parents=[base_arg_parser],
)
parser.add_argument(
'abbrs',
metavar='ABBR',
type=str,
nargs='+',
help=('the two-letter abbreviation for the data to export'))
parser.add_argument('--file',
'-f',
help='filename to output to (defaults to <abbr>.zip)')
def main(old_scrape_compat=False):
try:
parser = argparse.ArgumentParser(
description='update billy data',
parents=[base_arg_parser],
)
what = parser.add_argument_group(
'what to scrape', 'flags that help select what data to scrape')
scrape = parser.add_argument_group('scraper config',
'settings for the scraper')
parser.add_argument('module', type=str, help='scraper module (eg. nc)')
what.add_argument('-s',
'--session',
action='append',
dest='sessions',
default=[],
help='session(s) to scrape')
what.add_argument('-t',
'--term',
action='append',
dest='terms',
help='term(s) to scrape',
default=[])
for arg in ('upper', 'lower'):
what.add_argument('--' + arg,
action='append_const',
dest='chambers',
const=arg)
for arg in ('bills', 'legislators', 'committees', 'votes', 'events'):
what.add_argument('--' + arg,
action='append_const',
dest='types',
const=arg)
for arg in ('scrape', 'import', 'report'):
parser.add_argument('--' + arg,
dest='actions',
action="append_const",
const=arg,
help='only run %s step' % arg)
# special modes for debugging
scrape.add_argument('--nonstrict',
action='store_false',
dest='strict',
default=True,
help="don't fail immediately when"
" encountering validation warning")
scrape.add_argument('--fastmode',
help="scrape in fast mode",
action="store_true",
default=False)
# scrapelib overrides
scrape.add_argument('-r',
'--rpm',
action='store',
type=int,
dest='SCRAPELIB_RPM')
scrape.add_argument('--timeout',
action='store',
type=int,
dest='SCRAPELIB_TIMEOUT')
scrape.add_argument('--retries',
type=int,
dest='SCRAPELIB_RETRY_ATTEMPTS')
scrape.add_argument('--retry_wait',
type=int,
dest='SCRAPELIB_RETRY_WAIT_SECONDS')
args = parser.parse_args()
# inject scraper paths so scraper module can be found
for newpath in settings.SCRAPER_PATHS:
sys.path.insert(0, newpath)
# get metadata
module = __import__(args.module)
metadata = module.metadata
module_settings = getattr(module, 'settings', {})
abbrev = metadata['abbreviation']
# load state settings, then command line settings
settings.update(module_settings)
settings.update(args)
configure_logging(args.module)
# configure oyster
if settings.ENABLE_OYSTER:
from oyster.conf import settings as oyster_settings
oyster_settings.DOCUMENT_CLASSES[
args.module + ':billtext'] = module.document_class
# make output dir
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, abbrev)
_clear_scraped_data(args.output_dir)
# if terms aren't set, use latest
if not args.terms:
if args.sessions:
for session in args.sessions:
args.terms.append(
term_for_session(metadata['abbreviation'], session,
metadata))
args.terms = list(set(args.terms or []))
else:
latest_term = metadata['terms'][-1]['name']
args.terms = [latest_term]
# only set sessions from terms if sessions weren't set
elif not args.sessions:
for term in metadata['terms']:
if term['name'] in args.terms:
args.sessions.extend(term['sessions'])
# dedup sessions
args.sessions = list(set(args.sessions or []))
if not args.sessions:
args.sessions = [metadata['terms'][-1]['sessions'][-1]]
# determine chambers
if not args.chambers:
args.chambers = ['upper', 'lower']
if not args.actions:
if old_scrape_compat:
args.actions = ['scrape']
else:
args.actions = ['scrape', 'import', 'report']
if not args.types:
args.types = [
'bills', 'legislators', 'votes', 'committees', 'alldata'
]
if 'events' in metadata['feature_flags']:
args.types.append('events')
plan = """billy-update abbr=%s
actions=%s
types=%s
sessions=%s
terms=%s""" % (args.module, ','.join(args.actions), ','.join(
args.types), ','.join(args.sessions), ','.join(args.terms))
logging.getLogger('billy').info(plan)
scrape_data = {}
if 'scrape' in args.actions:
# validate then write metadata
if hasattr(module, 'session_list'):
session_list = module.session_list()
else:
session_list = []
check_sessions(metadata, session_list)
try:
schema_path = os.path.join(
os.path.split(__file__)[0], '../schemas/metadata.json')
schema = json.load(open(schema_path))
validator = DatetimeValidator()
validator.validate(metadata, schema)
except ValueError as e:
logging.getLogger('billy').warning(
'metadata validation error: ' + str(e))
with open(os.path.join(args.output_dir, 'metadata.json'),
'w') as f:
json.dump(metadata, f, cls=JSONDateEncoder)
run_record = []
exec_record = {
"run_record": run_record,
"args": sys.argv,
"state": abbrev
}
lex = None
exc_traceback = None
# start to run scrapers
exec_start = dt.datetime.utcnow()
# scraper order matters
order = ('legislators', 'committees', 'votes', 'bills', 'events')
try:
for stype in order:
if stype in args.types:
run_record += _run_scraper(stype, args, metadata)
except Exception as e:
_traceback = _, _, exc_traceback = sys.exc_info()
run_record += [{"exception": e, "type": stype}]
lex = e
exec_end = dt.datetime.utcnow()
exec_record['started'] = exec_start
exec_record['ended'] = exec_end
scrape_data['scraped'] = exec_record
scrape_data['state'] = abbrev
for record in run_record:
if "exception" in record:
ex = record['exception']
fb = traceback.format_exception(*_traceback)
trace = ""
for t in fb:
trace += t
record['exception'] = {
"type": ex.__class__.__name__,
"message": ex.message,
'traceback': trace
}
scrape_data['failure'] = True
if lex:
if 'import' in args.actions:
try:
db.billy_runs.save(scrape_data, safe=True)
except Exception:
raise lex, None, exc_traceback
# XXX: This should *NEVER* happen, but it has
# in the past, so we're going to catch any errors
# writing # to pymongo, and raise the original
# exception rather then let it look like Mongo's fault.
# Thanks for catching this, Thom.
#
# We lose the stack trace, but the Exception is the
# same in every other way.
# -- paultag
raise
# imports
if 'import' in args.actions:
import_report = _do_imports(abbrev, args)
scrape_data['imported'] = import_report
# We're tying the run-logging into the import stage - since import
# already writes to the DB, we might as well throw this in too.
db.billy_runs.save(scrape_data, safe=True)
# reports
if 'report' in args.actions:
_do_reports(abbrev, args)
except ScrapeError as e:
print 'Error:', e
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
description='Import scraped data into database.',
parents=[base_arg_parser],
)
parser.add_argument('abbreviation',
type=str,
help=('the short name of the data to import'))
parser.add_argument('-r',
'--rpm',
type=int,
default=60,
help=('maximum number of documents to download '
'per minute'))
parser.add_argument('--bills',
action='store_true',
help='scrape bill data')
parser.add_argument('--legislators',
action='store_true',
help='scrape legislator data')
parser.add_argument('--committees',
action='store_true',
help='scrape (separate) committee data')
parser.add_argument('--events',
action='store_true',
help='scrape event data')
parser.add_argument('--alldata',
action='store_true',
dest='alldata',
default=False,
help="import all available data")
args = parser.parse_args()
if not (args.bills or args.legislators or args.committees or args.events
or args.alldata):
raise Exception("Must specify at least one type: --bills, "
"--legislators, --committees, --events, "
"--alldata")
settings.update(args)
data_dir = settings.BILLY_DATA_DIR
# configure logger
configure_logging(args.verbose, args.abbreviation)
# always import metadata
import_metadata(args.abbreviation, data_dir)
if args.legislators or args.alldata:
import_legislators(args.abbreviation, data_dir)
if args.bills or args.alldata:
import_bills(args.abbreviation, data_dir)
if args.committees or args.alldata:
import_committees(args.abbreviation, data_dir)
# events currently excluded from --alldata
if args.events:
import_events(args.abbreviation, data_dir)
def main(old_scrape_compat=False):
try:
parser = argparse.ArgumentParser(
description='update billy data',
parents=[base_arg_parser],
)
what = parser.add_argument_group('what to scrape',
'flags that help select what data to scrape')
scrape = parser.add_argument_group('scraper config',
'settings for the scraper')
parser.add_argument('module', type=str, help='scraper module (eg. nc)')
what.add_argument('-s', '--session', action='append',
dest='sessions', default=[],
help='session(s) to scrape')
what.add_argument('-t', '--term', action='append', dest='terms',
help='term(s) to scrape', default=[])
for arg in ('upper', 'lower'):
what.add_argument('--' + arg, action='append_const',
dest='chambers', const=arg)
for arg in ('bills', 'legislators', 'committees', 'votes', 'events'):
what.add_argument('--' + arg, action='append_const', dest='types',
const=arg)
for arg in ('scrape', 'import', 'report'):
parser.add_argument('--' + arg, dest='actions',
action="append_const", const=arg,
help='only run %s step' % arg)
# special modes for debugging
scrape.add_argument('--nonstrict', action='store_false', dest='strict',
default=True, help="don't fail immediately when"
" encountering validation warning")
scrape.add_argument('--fastmode', help="scrape in fast mode",
action="store_true", default=False)
# scrapelib overrides
scrape.add_argument('-r', '--rpm', action='store', type=int,
dest='SCRAPELIB_RPM')
scrape.add_argument('--timeout', action='store', type=int,
dest='SCRAPELIB_TIMEOUT')
scrape.add_argument('--retries', type=int,
dest='SCRAPELIB_RETRY_ATTEMPTS')
scrape.add_argument('--retry_wait', type=int,
dest='SCRAPELIB_RETRY_WAIT_SECONDS')
args = parser.parse_args()
# inject scraper paths so scraper module can be found
for newpath in settings.SCRAPER_PATHS:
sys.path.insert(0, newpath)
# get metadata
module = __import__(args.module)
metadata = module.metadata
module_settings = getattr(module, 'settings', {})
abbrev = metadata['abbreviation']
# load state settings, then command line settings
settings.update(module_settings)
settings.update(args)
configure_logging(args.module)
# configure oyster
if settings.ENABLE_OYSTER:
from oyster.conf import settings as oyster_settings
oyster_settings.DOCUMENT_CLASSES[args.module + ':billtext'] = module.document_class
# make output dir
args.output_dir = os.path.join(settings.BILLY_DATA_DIR, abbrev)
_clear_scraped_data(args.output_dir)
# if terms aren't set, use latest
if not args.terms:
if args.sessions:
for session in args.sessions:
args.terms.append(
term_for_session(metadata['abbreviation'], session,
metadata))
args.terms = list(set(args.terms or []))
else:
latest_term = metadata['terms'][-1]['name']
args.terms = [latest_term]
# only set sessions from terms if sessions weren't set
elif not args.sessions:
for term in metadata['terms']:
if term['name'] in args.terms:
args.sessions.extend(term['sessions'])
# dedup sessions
args.sessions = list(set(args.sessions or []))
if not args.sessions:
args.sessions = [metadata['terms'][-1]['sessions'][-1]]
# determine chambers
if not args.chambers:
args.chambers = ['upper', 'lower']
if not args.actions:
if old_scrape_compat:
args.actions = ['scrape']
else:
args.actions = ['scrape', 'import', 'report']
if not args.types:
args.types = ['bills', 'legislators', 'votes', 'committees',
'alldata']
if 'events' in metadata['feature_flags']:
args.types.append('events')
plan = """billy-update abbr=%s
actions=%s
types=%s
sessions=%s
terms=%s""" % (args.module, ','.join(args.actions), ','.join(args.types),
','.join(args.sessions), ','.join(args.terms))
logging.getLogger('billy').info(plan)
scrape_data = {}
if 'scrape' in args.actions:
# validate then write metadata
if hasattr(module, 'session_list'):
session_list = module.session_list()
else:
session_list = []
check_sessions(metadata, session_list)
try:
schema_path = os.path.join(os.path.split(__file__)[0],
'../schemas/metadata.json')
schema = json.load(open(schema_path))
validator = DatetimeValidator()
validator.validate(metadata, schema)
except ValueError as e:
logging.getLogger('billy').warning(
'metadata validation error: ' + str(e))
with open(os.path.join(args.output_dir, 'metadata.json'),
'w') as f:
json.dump(metadata, f, cls=JSONDateEncoder)
run_record = []
exec_record = {
"run_record": run_record,
"args": sys.argv,
"state": abbrev
}
lex = None
exc_traceback = None
# start to run scrapers
exec_start = dt.datetime.utcnow()
# scraper order matters
order = ('legislators', 'committees', 'votes', 'bills', 'events')
try:
for stype in order:
if stype in args.types:
run_record += _run_scraper(stype, args, metadata)
except Exception as e:
_traceback = _, _, exc_traceback = sys.exc_info()
run_record += [{"exception": e, "type": stype }]
lex = e
exec_end = dt.datetime.utcnow()
exec_record['started'] = exec_start
exec_record['ended'] = exec_end
scrape_data['scraped'] = exec_record
scrape_data['state'] = abbrev
for record in run_record:
if "exception" in record:
ex = record['exception']
fb = traceback.format_exception(*_traceback)
trace = ""
for t in fb:
trace += t
record['exception'] = {
"type": ex.__class__.__name__,
"message": ex.message,
'traceback': trace
}
scrape_data['failure'] = True
if lex:
if 'import' in args.actions:
try:
db.billy_runs.save(scrape_data, safe=True)
except Exception:
raise lex, None, exc_traceback
# XXX: This should *NEVER* happen, but it has
# in the past, so we're going to catch any errors
# writing # to pymongo, and raise the original
# exception rather then let it look like Mongo's fault.
# Thanks for catching this, Thom.
#
# We lose the stack trace, but the Exception is the
# same in every other way.
# -- paultag
raise
# imports
if 'import' in args.actions:
import_report = _do_imports(abbrev, args)
scrape_data['imported'] = import_report
# We're tying the run-logging into the import stage - since import
# already writes to the DB, we might as well throw this in too.
db.billy_runs.save(scrape_data, safe=True)
# reports
if 'report' in args.actions:
_do_reports(abbrev, args)
except ScrapeError as e:
print 'Error:', e
sys.exit(1)
default=False, help="import all available data")
args = parser.parse_args()
if not (args.bills or args.legislators or args.committees or
args.events or args.alldata):
raise Exception("Must specify at least one type: --bills, "
"--legislators, --committees, --events, "
"--alldata")
settings.update(args)
data_dir = settings.BILLY_DATA_DIR
# configure logger
configure_logging(args.verbose, args.abbreviation)
# always import metadata
import_metadata(args.abbreviation, data_dir)
if args.legislators or args.alldata:
import_legislators(args.abbreviation, data_dir)
if args.bills or args.alldata:
import_bills(args.abbreviation, data_dir)
if args.committees or args.alldata:
import_committees(args.abbreviation, data_dir)
# events currently excluded from --alldata
if args.events:
import_events(args.abbreviation, data_dir)
#!/usr/bin/env python
from __future__ import print_function
from billy.utils import configure_logging, term_for_session
# we need this before the command line args are read in
configure_logging("startup")
import logging
_log = logging.getLogger('billy')
import importlib
#import bson.binary
#from bson.binary import ALL_UUID_SUBTYPES
#from bson.binary import OLD_UUID_SUBTYPE
import os
import sys
import json
import glob
import logging
import inspect
import argparse
import traceback
#import importlib
import unicodecsv
import os.path
import datetime as dt
import pdb
# code snippet, to be included in 'sitecustomize.py'
from billy.scrape.validator import DatetimeValidator
#from pymongo.errors import OperationFailure
import pymongo
params['literal.state'] = doc.metadata['bill']['state']
params['literal.chamber'] = doc.metadata['bill']['chamber']
params['literal.bill_title'] = (
doc.metadata['bill']['title'].encode('ascii', 'replace'))
params['literal.document_name'] = doc.metadata['name']
params['literal.url'] = doc.metadata['url']
params['literal.id'] = version['document_id']
params['commit'] = 'false'
url = "%supdate/extract?%s" % (solr_url, urllib.urlencode(params))
req = urllib2.Request(url, {'file': doc})
urllib2.urlopen(req)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
parents=[base_arg_parser],
description="Download and store copies of bill versions.")
parser.add_argument('-u',
'--url',
type=str,
dest='url',
default='http://localhost:8983/solr/',
help='the solr instance URL')
args = parser.parse_args()
configure_logging(args.verbose, args.state)
import_versions(args.state, args.url)
params = {}
params['literal.bill_id'] = doc.metadata['bill']['bill_id']
params['literal.state'] = doc.metadata['bill']['state']
params['literal.chamber'] = doc.metadata['bill']['chamber']
params['literal.bill_title'] = (
doc.metadata['bill']['title'].encode('ascii', 'replace'))
params['literal.document_name'] = doc.metadata['name']
params['literal.url'] = doc.metadata['url']
params['literal.id'] = version['document_id']
params['commit'] = 'false'
url = "%supdate/extract?%s" % (solr_url, urllib.urlencode(params))
req = urllib2.Request(url, {'file': doc})
urllib2.urlopen(req)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
parents=[base_arg_parser],
description="Download and store copies of bill versions.")
parser.add_argument('-u', '--url', type=str, dest='url',
default='http://localhost:8983/solr/',
help='the solr instance URL')
args = parser.parse_args()
configure_logging(args.verbose, args.state)
import_versions(args.state, args.url)
k.key = s3_path
logging.info('beginning upload to %s' % s3_url)
k.set_contents_from_filename(filename)
k.set_acl('public-read')
meta['latest_dump_url'] = s3_url
meta['latest_dump_date'] = datetime.datetime.utcnow()
db.metadata.save(meta, safe=True)
logging.info('upload complete')
if __name__ == '__main__':
import argparse
configure_logging(1)
parser = argparse.ArgumentParser(
description=('Dump API information to a zipped directory of JSON files'
', optionally uploading to S3 when done.'),
parents=[base_arg_parser],
)
parser.add_argument('abbrs', metavar='ABBR', type=str, nargs='+',
help=('the two-letter abbreviation for the data to export'))
parser.add_argument('--file', '-f',
help='filename to output to (defaults to <abbr>.zip)')
parser.add_argument('--schema_dir',
help='directory to use for API schemas (optional)',
default=None)
parser.add_argument('--nodump', action='store_true', default=False,
help="don't run the dump, only upload")
import argparse
import logging
from billy.conf import settings, base_arg_parser
from billy.utils import configure_logging
from billy.commands import BaseCommand
logger = logging.getLogger('billy')
configure_logging()
COMMAND_MODULES = (
# lots of these commands can go away as billy matures
'billy.commands.serve', # useful for development
'billy.commands.textextract', # useful for development
'billy.commands.load_legislators', # allow editing legislators in admin
'billy.commands.download_photos',
'billy.commands.dump',
'billy.commands.update_external_ids',
'billy.commands.update_leg_ids',
'billy.commands.validate_api',
)
if settings.ENABLE_OYSTER:
COMMAND_MODULES += ('billy.commands.oysterize',)
def import_command_module(mod):
try:
__import__(mod)
except ImportError, e:
logger.warning(
import argparse
import logging
from billy.conf import settings, base_arg_parser
from billy.utils import configure_logging
from billy.commands import BaseCommand
logger = logging.getLogger('billy')
configure_logging()
COMMAND_MODULES = (
# lots of these commands can go away as billy matures
'billy.commands.serve', # useful for development
'billy.commands.textextract', # useful for development
'billy.commands.load_legislators', # allow editing legislators in admin
'billy.commands.download_photos',
'billy.commands.dump',
'billy.commands.update_external_ids',
'billy.commands.update_leg_ids',
'billy.commands.validate_api',
)
if settings.ENABLE_OYSTER:
COMMAND_MODULES += ('billy.commands.oysterize', )
def import_command_module(mod):
try:
__import__(mod)
except ImportError, e:
logger.warning('error "{0}" prevented loading of {1} module'.format(
