def merge(): fid = open(DevExtractor.raw_cache_name, 'r') dev_tuple = Extractor.read_line(fid) dev_info_dict = dict() while dev_tuple is not None: for ip in dev_tuple: dev = dev_tuple[ip][DevExtractor.dev_id_index] if ip in dev_info_dict.keys(): dev_info = dev_info_dict[ip] dev_num_info = dev_info[DevExtractor.dev_num_info_index] if dev in dev_num_info.keys(): dev_num_info[dev] += 1 else: dev_num_info[dev] = 1 else: dev_info = list() dev_num_info = dict() dev_info.append(dev_num_info) dev_num_info[dev] = 1 dev_info_dict[ip] = dev_info # next line dev_tuple = Extractor.read_line(fid) fid = open(DevExtractor.cache_name, 'w') fid.writelines(json.dumps(dev_info_dict))
def merge(): fid = open(TagExtractor.raw_cache_name, 'r') tag_tuple = Extractor.read_line(fid) tag_info_dict = dict() while tag_tuple is not None: for ip in tag_tuple: tag = tag_tuple[ip][TagExtractor.tag_index] if ip in tag_info_dict.keys(): tag_info = tag_info_dict[ip] tag_num_info = tag_info[TagExtractor.tag_num_info_index] if tag in tag_num_info.keys(): tag_num_info[tag] += 1 else: tag_num_info[tag] = 1 else: tag_info = list() tag_num_info = dict() tag_info.append(tag_num_info) tag_num_info[tag] = 1 tag_info_dict[ip] = tag_info tag_tuple = Extractor.read_line(fid) fid = open(TagExtractor.cache_name, 'w') fid.writelines(json.dumps(tag_info_dict))
def merge(): fid = open(CookieExtractor.raw_cache_name, 'r') cookie_tuple = Extractor.read_line(fid) cookie_info_dict = dict() while cookie_tuple is not None: # 统计该 IP 的所有点击的 cookie 以及其数量 for ip in cookie_tuple: cookie = cookie_tuple[ip][CookieExtractor.cookie_index] if ip in cookie_info_dict.keys(): cookie_info = cookie_info_dict[ip] cookie_num = cookie_info[CookieExtractor.cookie_num_index] if cookie in cookie_num.kyes(): cookie_num[cookie] += 1 else: cookie_num[cookie] = 1 else: cookie_info = list() cookie_num = dict() cookie_info.append(cookie_num) cookie_num[cookie] = 1 cookie_info_dict[ip] = cookie_info # next line cookie_tuple = Extractor.read_line(fid) fid = open(CookieExtractor.cache_name, 'w') fid.writelines(json.dumps(cookie_info_dict))
def merge(): fid = open(PlacementExtractor.raw_cache_name, 'r') placement_tuple = Extractor.read_line(fid) placement_info_dict = dict() while placement_tuple is not None: for ip in placement_tuple: if placement_info_dict.has_key(ip): placement_info = placement_info_dict[ip] placement_num = placement_info[ PlacementExtractor.placement_num_index] if placement_num.has_key(ip): placement_num[ip] += 1 else: placement_num = 1 else: placement_info = list() placement_num = dict() placement_info.append(placement_num) placement_num[tuple[ip]] = 1 placement_info_dict[ip] = placement_info fid = open(PlacementExtractor.cache_name, 'w') fid.writelines(json.dumps(placement_info_dict))
def merge(): fid = open(UAExtractor.raw_cache_name, 'r') tuple = Extractor.read_line(fid) ua_info_dict = dict() while tuple != None: for ip in tuple: if ua_info_dict.has_key(ip): ua_info = ua_info_dict[ip] ua_num = ua_info[UAExtractor.ua_num_index] if ua_num.has_key(ip): ua_num[ip] += 1 else: ua_num = 1 else: ua_info = list() ua_num = dict() ua_info.append(ua_num) ua_num[tuple[ip]] = 1 ua_info_dict[ip] = ua_info fid = open(UAExtractor.cache_name, 'w') fid.writelines(json.dumps(ua_info_dict))