python 从字符串中提取数据

素颜马尾好姑娘i 2022-05-28 09:15 258阅读 0赞

1.  使用正则表达式，用法如下：
    
    <table style="width:778.889px; border-spacing:0px; font-family:Monaco,Menlo,Consolas,'Courier New',monospace; margin:.3em 0px; background:rgb(245,245,245) none; border:1px solid rgb(204,204,204); float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; font-size:13px; padding:0px"> 
     <tbody style="background:none; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px"> 
      <tr style="border-top:0px; background:none; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px"> 
       <td style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; border-top-width:0px; border-bottom-width:0px; border-left-width:0px; border-right-color:rgb(225,225,232); font-size:13px; color:rgb(175,175,175); line-height:1.1em; padding:9.5px 0px 9.5px 9.5px; margin:0px; background:rgb(247,247,249) none; float:none; vertical-align:baseline; min-height:auto"> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          1 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          2 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          3 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          4 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          5 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          6 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          7 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          8 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          9 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          10 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          11 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          12 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          13 
        </div> </td> 
       <td style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; border-width:0px; font-size:13px; line-height:1.1em; padding:0px; margin:0px; background:none; float:none; vertical-align:baseline; min-height:auto"> 
        <div style="margin:0px auto; background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; padding:0px"> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;总结</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;^&nbsp;匹配字符串的开始。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;$&nbsp;匹配字符串的结尾。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;\b&nbsp;匹配一个单词的边界。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;\d&nbsp;匹配任意数字。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;\D&nbsp;匹配任意非数字字符。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;x?&nbsp;匹配一个可选的&nbsp;x&nbsp;字符&nbsp;(换言之，它匹配&nbsp;1&nbsp;次或者&nbsp;0&nbsp;次&nbsp;x&nbsp;字符)。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;x*&nbsp;匹配0次或者多次&nbsp;x&nbsp;字符。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;x+&nbsp;匹配1次或者多次&nbsp;x&nbsp;字符。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;x{n,m}&nbsp;匹配&nbsp;x&nbsp;字符，至少&nbsp;n&nbsp;次，至多&nbsp;m&nbsp;次。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;(a|b|c)&nbsp;要么匹配&nbsp;a，要么匹配&nbsp;b，要么匹配&nbsp;c。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;(x)&nbsp;一般情况下表示一个记忆组&nbsp;(remembered&nbsp;group)。你可以利用&nbsp;re.search&nbsp;函数返回对象的&nbsp;groups()&nbsp;函数获取它的值。</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">##&nbsp;正则表达式中的点号通常意味着&nbsp;“匹配任意单字符”</code> 
         </div> 
        </div> </td> 
      </tr> 
     </tbody> 
    </table>
2.  解题思路：
    
    2.1 既然是提取数字，那么数字的形式一般是：整数，小数，整数加小数；
    
    2.2 所以一般是形如：----.-----；
    
    2.3 根据上述正则表达式的含义，可写出如下的表达式："\\d+\\.?\\d\*"；
    
    2.4 \\d+匹配1次或者多次数字，注意这里不要写成\*，因为即便是小数，小数点之前也得有一个数字；\\.?这个是匹配小数点的，可能有，也可能没有；\\d\*这个是匹配小数点之后的数字的，所以是0个或者多个；
3.  代码如下：
    
    <table style="width:778.889px; border-spacing:0px; font-family:Monaco,Menlo,Consolas,'Courier New',monospace; margin:.3em 0px; background:rgb(245,245,245) none; border:1px solid rgb(204,204,204); float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; font-size:13px; padding:0px"> 
     <tbody style="background:none; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px"> 
      <tr style="border-top:0px; background:none; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px"> 
       <td style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; border-top-width:0px; border-bottom-width:0px; border-left-width:0px; border-right-color:rgb(225,225,232); font-size:13px; color:rgb(175,175,175); line-height:1.1em; padding:9.5px 0px 9.5px 9.5px; margin:0px; background:rgb(247,247,249) none; float:none; vertical-align:baseline; min-height:auto"> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          1 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          2 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          3 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          4 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          5 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          6 
        </div> 
        <div style="background:none; border:0px; float:none; line-height:1.1em; text-align:right; vertical-align:baseline; min-height:auto; margin:0px; padding:0px .5em 0px 1em; white-space:pre">
          7 
        </div> </td> 
       <td style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; border-width:0px; font-size:13px; line-height:1.1em; padding:0px; margin:0px; background:none; float:none; vertical-align:baseline; min-height:auto"> 
        <div style="margin:0px auto; background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; padding:0px"> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">#&nbsp;-*-&nbsp;coding:&nbsp;cp936&nbsp;-*-</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(255,120,0); background:none; border:0px; float:none; vertical-align:baseline; font-weight:700; min-height:auto; margin:0px; padding:0px">import</code>&nbsp; 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">re</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em">
           &nbsp; 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">string</code> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(255,120,0); background:none; border:0px; float:none; vertical-align:baseline; font-weight:700; min-height:auto; margin:0px; padding:0px">=</code> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,0,255); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">"A1.45，b5，6.45，8.82"</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(255,120,0); background:none; border:0px; float:none; vertical-align:baseline; font-weight:700; min-height:auto; margin:0px; padding:0px">print</code>&nbsp; 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">re.findall(r</code> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,0,255); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">"\d+\.?\d*"</code> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">,string)</code> 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em">
           &nbsp; 
         </div> 
         <div style="background:none; border:0px; float:none; line-height:1.1em; vertical-align:baseline; min-height:auto; margin:0px; padding:0px 1em"> 
          <code style="font-family:Monaco,Menlo,Consolas,'Courier New',monospace; font-size:14px; line-height:1.1em; color:rgb(0,130,0); background:none; border:0px; float:none; vertical-align:baseline; min-height:auto; margin:0px; padding:0px">#&nbsp;['1.45',&nbsp;'5',&nbsp;'6.45',&nbsp;'8.82']</code> 
         </div> 
        </div> </td> 
      </tr> 
     </tbody> 
    </table>