javascript - 如何计算 JavaScript 中 url 列表中的单词出现次数？

Question

我在 WordPress 的 JSON 对象中有 url 列表。我想计算 url 第二部分的出现次数。

下面的代码当前获取前缀 https://www.example.co 之后的其余 url。接下来我要做的是计算 url 第二部分的出现次数，即 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);
});

您知道如何使用当前的 forEach 循环实现这一目标吗？

非常感谢任何帮助。谢谢

Answer 1

使用正则表达式匹配 .co/ 之后的非 /:

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]
);

如果您想跟踪所有使用的完整 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);