def category_read_main(): finish = True rows = db_zoom.db_get_g(db_sql.sql_zoom_cate_read_get, ()) i_t = len(rows) i = 0 for row in rows: i = i + 1 print '%d of %d'%(i, i_t) finish = False cate_name = row[0] cate_path = row[1] cate_param = row[2] category_read(cate_name, cate_path, cate_param) #break return finish
def app_read_main(): finish = True rows = db_zoom.db_get_g(db_sql.sql_zoom_app_get, ()) i_t = len(rows) i = 0 for row in rows: i = i + 1 print '%d of %d'%(i, i_t), finish = False app_name = row[0] app_path = row[1] app_id = row[2] app_read_status = row[3] url = app_path.replace('.html', '_download.html').strip() #url = app_path.replace('.html', '_download.html?nav=halloween').strip() print '** zoom app %s **'%(url) status, body = zoom_http_get(url) if status == 404: print '== 404' db_zoom.db_execute_g(db_sql.sql_zoom_app_update, ('', app_path, )) continue if status != 200: print 'exception' continue soup = BeautifulSoup(body) if soup.body.text.strip().find('Access not allowed. If you think this is an error, please contact us at [email protected]') > 0: raise Exception('Access not allowed. If you think this is an error, please contact us at [email protected]') ### from here app_id = None divs_fa = soup.find_all(name='span', attrs={'class':'package'}) for divs_f in divs_fa: app_id = divs_f.text.replace('Package ', '').strip() print app_id db_zoom.db_execute_g(db_sql.sql_app_insert, (app_id, )) db_zoom.db_execute_g(db_sql.sql_zoom_app_update, (app_id, app_path)) util.sleep_i(10) return finish