不知道为什么大家那么偏爱json格式,清晰?跨平台?或许这都是它的优点吧,之前我都是将我的数据放到txt中,今后就用json吧。初步写了一个写入json的模板,就这么用吧。
def get_qq_0528(): import math,re,json cnt = 0 SEG = 5 REGEX = re.compile(r\'(\d{4})(-|/)(\d{2})(-|/)(\d{2})\') for file in FILE_LIST: with open(os.path.join(PATH, file), \'r\', encoding=\'utf8\') as fr: with open(os.path.join(\'./data/qq_data/\', \'qq_data_0528.json\'), \'w\', encoding=\'utf8\') as json_file: accept_content = [] content = fr.readlines()[8:] for each in content: if each.replace(\'\n\', \'\') != \'\': new_str = REGEX.sub(\'######\', each) clean_each = new_str.strip() if \'######\' in clean_each : accept_content.append(\'#######\n\') continue elif clean_each.strip() == \'\': continue else: # DATA = {"id": "", "content": ""} # DATA["id"] = cnt # DATA[\'content\'] = clean_each # accept_content.append(DATA) # print(DATA) cnt += 1 accept_content.append(clean_each) json.dump(accept_content, json_file, ensure_ascii=False) print(\'总共有:{}\'.format(cnt))