__main__.py 文件源码

def restart_harvest(args):
    harvest = get_harvest(args)
    data_dir = os.path.join(os.getcwd(), 'data', harvest)
    meta = get_metadata(data_dir)
    if meta:
        try:
            with open(os.path.join(data_dir, 'results.csv'), 'rb') as csv_file:
                reader = csv.reader(csv_file, delimiter=',', encoding='utf-8')
                rows = list(reader)
            if len(rows) > 1:
                start = len(rows) - 2
                # Remove the last row in the CSV just in case there was a problem
                rows = rows[:-1]
                with open(os.path.join(data_dir, 'results.csv'), 'wb') as csv_file:
                    writer = csv.writer(csv_file, delimiter=',', encoding='utf-8')
                    for row in rows:
                        writer.writerow(row)
            else:
                start = 0
        except IOError:
            # Nothing's been harvested
            start = 0
        start_harvest(data_dir=data_dir, key=meta['key'], query=meta['query'], pdf=meta['pdf'], text=meta['text'], start=start, max=meta['max'])