def main():
db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)
source = data.load_source("musicbrainz")
scraper = data.load_latest_scraper_for_source(source)
print(scraper)
mbids = get_mbids()
total = len(mbids)
starttime = time.time()
done = 0
for mblist in util.chunks(mbids, 100):
lookup(mblist, scraper)
done += 100
durdelta, remdelta = util.stats(done, total, starttime)
log.info("Done %s/%s in %s; %s remaining", done, total, str(durdelta), str(remdelta))
def main():
db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)
source = data.load_source("musicbrainz")
scraper = data.load_latest_scraper_for_source(source)
print(scraper)
mbids = get_mbids()
total = len(mbids)
starttime = time.time()
done = 0
for mblist in util.chunks(mbids, 100):
lookup(mblist, scraper)
done += 100
durdelta, remdelta = util.stats(done, total, starttime)
log.info("Done %s/%s in %s; %s remaining", done, total, str(durdelta),
str(remdelta))
def process_file(module, filename, numworkers, save=False):
data = []
with open(filename) as csvfile:
for query in csv.DictReader(csvfile):
data.append(query)
total = len(data)
starttime = time.time()
done = 0
CHUNK_SIZE = 1
for items in util.chunks(data, CHUNK_SIZE):
process_items(items, module, save, numworkers)
done += CHUNK_SIZE
durdelta, remdelta = util.stats(done, total, starttime)
time.sleep(random.uniform(.5, 1.5))
log.info("Done %s/%s in %s; %s remaining", done, total, str(durdelta),
str(remdelta))
def main():
db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)
source = data.load_source("musicbrainz")
scraper = data.load_latest_scraper_for_source(source)
recordings = get_recordings()
total = len(recordings)
done = 0
starttime = time.time()
log.info("starting..., %s recordings to process", total)
for reclist in util.chunks(recordings, 10000):
log.info("have %s recordings", len(reclist))
with db.engine.connect() as connection:
saveddata = get_data(connection, scraper["id"], reclist)
log.info(" - got %s rows matching them", len(saveddata))
process(connection, saveddata)
done += len(reclist)
durdelta, remdelta = util.stats(done, total, starttime)
log.info("Done %s/%s in %s; %s remaining", done, total, str(durdelta), str(remdelta))
def main():
db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)
source = data.load_source("musicbrainz")
scraper = data.load_latest_scraper_for_source(source)
recordings = get_recordings()
total = len(recordings)
done = 0
starttime = time.time()
log.info("starting..., %s recordings to process", total)
for reclist in util.chunks(recordings, 10000):
log.info("have %s recordings", len(reclist))
with db.engine.connect() as connection:
saveddata = get_data(connection, scraper["id"], reclist)
log.info(" - got %s rows matching them", len(saveddata))
process(connection, saveddata)
done += len(reclist)
durdelta, remdelta = util.stats(done, total, starttime)
log.info("Done %s/%s in %s; %s remaining", done, total, str(durdelta),
str(remdelta))