代码段

Posted 2021-09-10 大裤衩

啥都有

web_page_info = requests.get(url_base,headers=headers, timeout=(3,7))

names = kw_df.keyword.tolist()
document = kw_df.keywords.tolist()
use_str = [项⽬进展,Gas,eBay,Amazon,Web 3.0,项⽬进展,期权,流动性挖矿,矿工,算力,节点,私钥,观点,Gas 费,技术,委内瑞拉,美联储,东加勒比中央银行,巴哈马
公链,项⽬进展,游戏,公链,钱包,跨链,基础设施,市场,推特,黑客攻击,溢价,观点,政策法规,监管,扩容,债券, USDT, 技术, 空投, 股票, ...]
document[0]
# \'以太坊, DeFi, DEX, Gas, NFT, Loot, 项⽬进展\'
document[0].split(\',\')
# [\'以太坊\', \' DeFi\', \' DEX\', \' Gas\', \' NFT\', \' Loot\', \' 项⽬进展\']
[item.strip(\' \') for item in document[0].split(\',\')]
# [\'以太坊\', \'DeFi\', \'DEX\', \'Gas\', \'NFT\', \'Loot\', \'项⽬进展\']
kw_dele = kw_df[~kw_df.keyword.isin(use_str)]
s=kw_dele[\'keyword\'].str.findall(u"([\\u4e00-\\u9fa5])")
# 识别出一个中文
s=kw_dele[\'keyword\'].str.findall(u"([\\u4e00-\\u9fa5]*)")
# 识别出一堆中文
item_sum.drop_duplicates(subset=None,keep=\'first\',inplace=True)