Question

我在WordPress中的JSON对象中有网址列表。我想计算网址第二部分的出现。

下面的代码当前获取前缀https://www.example.co之后的其余URL。接下来，我要计算的是第二个网址cat1, cat3, cat2, xmlrpc.php

var urlList = [
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc/dd/ee",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat3/aa/bb/cc/",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/xmlrpc.php",
    "Last crawled": "Jun 19, 2019"
  }
]

const paths = urlList.map(value => value.URL.replace('https://www.example.co', ''));

//console.log(paths);

paths.forEach(function(item) {
    var urlSecondPart = item.split("/")[1];
    console.log(urlSecondPart);
});

您知道如何在当前的forEach循环中实现这一目标吗？

任何帮助将不胜感激。谢谢

Answer 1

使用正则表达式匹配/之后的非.co/：

var urlList = [
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc/dd/ee",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat3/aa/bb/cc/",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/xmlrpc.php",
    "Last crawled": "Jun 19, 2019"
  }
]

const paths = urlList.map(
  ({ URL }) => URL.match(/\.co\/([^\/]+)/)[1]
);
console.log(paths);

const counts = paths.reduce((a, str) => {
  a[str] = (a[str] || 0) + 1;
  return a;
}, {});
console.log(counts);

在较新的引擎上，您可以使用lookbehind而不是提取捕获组：

const paths = urlList.map(
  ({ URL }) => URL.match(/(?<=\.co\/)[^\/]+/)[0]
);

如果要跟踪使用的所有完整URL，不仅要减少计数，还要减少这些完整URL的数组：

var urlList = [
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb/cc/dd/ee",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat3/aa/bb/cc/",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat2/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/cat1/aa/bb",
    "Last crawled": "Jun 23, 2019"
  },
  {
    "URL": "https://www.example.co/xmlrpc.php",
    "Last crawled": "Jun 19, 2019"
  }
]

const getSecond = url => url.match(/\.co\/([^\/]+)/)[1];

const counts = urlList.reduce((a, { URL }) => {
  const second = getSecond(URL);
  if (!a[second]) {
    a[second] = { count: 0, fullUrls: [] };
  }
  a[second].count++;
  a[second].fullUrls.push(URL);
  return a;
}, {});
console.log(counts);

如何从JavaScript中的网址列表中统计单词出现的次数？

1 个答案: