def save_question(cols): mysql_conn = get_mysql_connection() # sql, vals = insert_sql('question_db_offline.wln100_question_20170919', cols, ignore=True) execute(mysql_conn, sql, values=vals)
def record_questions(rows): mysql_conn = get_mysql_connection() for row in rows: html_string = row[1] spider_url = row[2] info = json.loads(row[3]) # if is_archived(spider_url): # continue logging.info(spider_url) try: cols = parser.parse(html_string, spider_url, info) except Exception as err: logging.error('[parser.parse] {}, {}'.format(err, spider_url)) continue if not cols: continue # print(json.dumps(cols, indent=4, ensure_ascii=False)) sql, vals = insert_sql( 'question_db_offline.manfen5_zujuan_question_20161205', cols, ignore=True) execute(mysql_conn, sql, values=vals) mysql_conn.commit()
def record_questions(rows): mysql_conn = get_mysql_connection() for row in rows: js = json.loads(row[1]) spider_url = row[2] aft_subj_id = row[3] try: cols = parser.parse(spider_url, js, aft_subj_id) except Exception as err: logging.error('[parser.parse] {}, {}'.format(err, spider_url)) continue # print(json.dumps(cols, indent=4, ensure_ascii=False)) sql, vals = insert_sql('question_db_offline.17zuoye_question_20160719', cols, ignore=True) execute(mysql_conn, sql, values=vals)
def record_questions(rows): mysql_conn = get_mysql_connection() for row in rows: html_string = row[1] spider_url = row[2] try: cols = parser.parse(html_string, spider_url) except Exception as err: logging.error('[parser.parse] {}, {}'.format(err, spider_url)) continue if not cols: continue # print(json.dumps(cols, indent=4, ensure_ascii=False)) sql, vals = insert_sql('question_db_offline.gzywtk_question_20161109', cols, ignore=True) execute(mysql_conn, sql, values=vals)
def record_questions(rows): mysql_conn = get_mysql_connection() for row in rows: try: js = json.loads(row[1]) spider_url = row[2] cols = parser.parse(js, spider_url) except Exception as err: logging.error('[parser.parse] {}, {}'.format(err, spider_url)) continue if not cols: continue # print(json.dumps(cols, indent=4, ensure_ascii=False)) logging.info(spider_url) sql, vals = insert_sql('question_db_offline.vko_question_20161116', cols, ignore=True) execute(mysql_conn, sql, values=vals)