如何抓取<script text/javascript>

Question

所以我想知道如何使用regex来抓取javascript标记，我相信这可能是最简单的方法。在

标签看起来像：

<script type="text/javascript">

var spConfig=newApex.Config({
  "attributes": {
    "199": {
      "id": "199",
      "code": "legend",
      "label": "Weapons",
      "options": [
        {
          "label": "10",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "10.5",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "11",
          "priceInGame": "0",          
          "id": [
            "66659"
          ]
        },
        {
          "label": "11.5",
          "priceInGame": "0",          
          "id": [            
          ]
        },
        {
          "label": "12",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "12.5",
          "priceInGame": "0",          
          "id": [           
          ]
        },
        {
          "label": "13",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "4",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "4.5",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "5",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "5.5",
          "priceInGame": "0",        
          "id": [

          ]
        },
        {
          "label": "6",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "6.5",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "7",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "7.5",
          "priceInGame": "0",         
          "id": [

          ]
        },
        {
          "label": "8",
          "priceInGame": "0",          
          "id": [
            "66672"
          ]
        },
        {
          "label": "8.5",
          "priceInGame": "0",          
          "id": [
            "66673"
          ]
        },
        {
          "label": "9",
          "priceInGame": "0",          
          "id": [

          ]
        },
        {
          "label": "9.5",
          "priceInGame": "0",        
          "id": [
            "66675"
          ]
        }
      ]
    }
  },
  "weaponID": "66733",
  "chooseText": "Apex Legends",
  "Config": {
    "includeCoins": false,
  }
});

</script>

我想把所有标签

我想做的是：

^{pr2}$

但它只返回一个空值[]

所以我在这里问我能做些什么来刮掉标签？在

Answer 1

您需要使用attr=value或attrs={'attr': 'value'}语法指定属性。在

https://www.crummy.com/software/BeautifulSoup/bs4/doc/#the-keyword-arguments

import json
import re
from ast import literal_eval

from bs4 import BeautifulSoup

if __name__ == '__main__':
    html = '''
<script type="text/javascript">

var spConfig=newApex.Config({
  "attributes": {
    "199": {
      "id": "199",
      "code": "legend",
      "label": "Weapons",
      "options": [
        { "label": "10", "priceInGame": "0", "id": [] },
        { "label": "10.5", "priceInGame": "0", "id": [] },
        { "label": "11", "priceInGame": "0", "id": [ "66659" ] },
        { "label": "7.5", "priceInGame": "0", "id": [] },
        { "label": "8", "priceInGame": "0", "id": ["66672"] }
      ]
    }
  },
  "weaponID": "66733",
  "chooseText": "Apex Legends",
  "taxConfig": {
    "includeCoins": False,
  }
});

</script>    
    '''

    soup = BeautifulSoup(html, 'html.parser')
    # this one works too
    # script = soup.find('script', attrs={'type':'text/javascript'})
    script = soup.find('script', type='text/javascript')
    js: str = script.text.replace('\n', '')
    raw_json = re.search('var spConfig=newApex.Config\(({.*})\);', js, flags=re.MULTILINE).group(1)
    # if `"includeCoins": False,` weren't in the JSON,
    # you could have used json.loads() but it fails here.
    # Yet, ast.literal_eval works fine.
    data = literal_eval(raw_json)
    labels = [opt['label'] for opt in data['attributes']['199']['options']]
    print(labels)

输出：

^{pr2}$

Answer 2

如果您只是在JSON对象中查找整个行字段，请使用以下命令

("label":) "([^"]+)",

如果要返回实际值，只需使用

^{pr2}$

把第二组拉回来