def main(): # Get ISO codes iso_codes_hash = scraper.get_iso_codes_hash() for k, v in iso_codes_hash.iteritems(): v['isoCode'] = k iso_codes_hash[k] = v iso_language_hashes = sorted(iso_codes_hash.values(), key = lambda h: h['isoCode']) h = None good_h = [] for h in iso_language_hashes: if h['isoCode'] in ['is']: good_h.append(h) # Create a pool and execute jobs #pool = multiprocessing.Pool(parallel_level) #pool.map(process_main, ['fr']) for lang in good_h: process_main(lang)
import scraper h = scraper.get_iso_codes_hash() things = [] for code, subh in h.iteritems(): name = subh['name'] if 'wiktionaryName' in subh: name = subh['wiktionaryName'] print "%s: %s" % (code, name)
invalidcharpattern = r"\"|\(|\)|\[|\]|\{|\}|\<|\>|!|&|\?|%|\+|:|;|«|»|=|\*|#|\n|\.|@|\$|\\|~|\_"
# Set up an arg parser
parser = argparse.ArgumentParser()
parser.add_argument("lang")
parser.add_argument("path")
# Parse the arguments
args = parser.parse_args()
# Connect to the DB
db = dbutils.DBConnect()
# Get langauge hash
language_info_hash = scraper.get_iso_codes_hash()[args.lang]
total_count = 0
################################################################################
# Main
#
################################################################################
def Main():
db.phrase_counts.remove({
'lang': args.lang,
})
xml_file = args.path #io.open(args.path, encoding='utf-8', errors='replace')