Ejemplo n.º 1
0
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))
Ejemplo n.º 2
0
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))
Ejemplo n.º 3
0
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))
Ejemplo n.º 4
0
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))
Ejemplo n.º 5
0
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))
Ejemplo n.º 6
0
def main():
    db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)

    log.info("Release groups")
    releasegroups = get_rgs()
    fieldnames = ["mbid", "release_title", "artist", "year"]
    with open("release-group-meta.csv", "w") as fp:
        w = csv.DictWriter(fp, fieldnames=fieldnames)
        w.writeheader()
        for rg in releasegroups:
            w.writerow(rg)

    log.info("Recordings")
    recordings = get_recordings()
    fieldnames = ["mbid", "recording", "artist"]
    count = (len(recordings) // 8) + 1
    for i, reclist in enumerate(util.chunks(recordings, count), 1):
        with open("recording-meta-{}.csv".format(i), "w") as fp:
            w = csv.DictWriter(fp, fieldnames=fieldnames)
            w.writeheader()
            for rec in reclist:
                w.writerow(rec)
Ejemplo n.º 7
0
def main():
    db.init_db_engine(config.SQLALCHEMY_DATABASE_URI)

    log.info("Release groups")
    releasegroups = get_rgs()
    fieldnames = ["mbid", "release_title", "artist", "year"]
    with open("release-group-meta.csv", "w") as fp:
        w = csv.DictWriter(fp, fieldnames=fieldnames)
        w.writeheader()
        for rg in releasegroups:
            w.writerow(rg)

    log.info("Recordings")
    recordings = get_recordings()
    fieldnames = ["mbid", "recording", "artist"]
    count = (len(recordings)//8) + 1
    for i, reclist in enumerate(util.chunks(recordings, count), 1):
        with open("recording-meta-{}.csv".format(i), "w") as fp:
            w = csv.DictWriter(fp, fieldnames=fieldnames)
            w.writeheader()
            for rec in reclist:
                w.writerow(rec)