从大括号和方括号中包含的复杂html中提取子字符串在python中使用正则表达式正则表达式

-1

（我已更新此帖子以反映更准确的问题图片，其中包括提供更多信息，我最初将其忽略）从大括号和方括号中包含的复杂html中提取子字符串在python中使用正则表达式正则表达式

所有我试图得到所需的字符串导致AttributeError：'NoneType'对象没有属性'组'。

这里是我的代码：

image = re.search("photo: /\[[^\]]+\]/", text)   
image = image.group(1)

我还在努力学习regex，但是这一个已经被我扔对于太长的循环。

我想抓取包含照片链接的JSON部分。这是该"uploadTime"排除"id"先于一切：

这里是有问题的一块JSON的：

photo: [{ 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418383-59832.jpg", 
    "uploadTime": { 
     "sec": 1498418386, 
     "usec": 192000 
    }, 
    "extension": "jpg", 
    "md5": "6fac68fbcbdb31d17af7be277ab673be", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_0D993ADA-8AFC-4A79-8F9B-18E6F6C30B94.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418389-472609.jpg", 
    "uploadTime": { 
     "sec": 1498418392, 
     "usec": 118000 
    }, 
    "extension": "jpg", 
    "md5": "6470e562d650099a1cafe9281f951c21", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_335B7BC0-F6DE-4E19-8489-3AA7B3920144.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418397-06491.jpg", 
    "uploadTime": { 
     "sec": 1498418400, 
     "usec": 161000 
    }, 
    "extension": "jpg", 
    "md5": "5f2df3edfed164c062e739c0c3258970", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_9C57A971-9748-4DBD-919D-8D532C8D7C1A.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418403-391642.jpg", 
    "uploadTime": { 
     "sec": 1498418406, 
     "usec": 936000 
    }, 
    "extension": "jpg", 
    "md5": "098dfa4d40e33c6897f62edc471670dd", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_A55BD209-3BFB-447E-AE59-40CF656664A8.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418409-263588.jpg", 
    "uploadTime": { 
     "sec": 1498418412, 
     "usec": 789000 
    }, 
    "extension": "jpg", 
    "md5": "50b69c1db486f4bb6af723f7395a360b", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_8BCDC2F0-8CBA-442C-98F5-0389455C8014.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418415-54882.jpg", 
    "uploadTime": { 
     "sec": 1498418418, 
     "usec": 462000 
    }, 
    "extension": "jpg", 
    "md5": "34296cda28b212a6c5590f233a2dca09", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_726D1636-E3A9-4515-9B95-55161FAAF730.jpg" 
}, { 
    "id": "http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418421-389128.jpg", 
    "uploadTime": { 
     "sec": 1498418424, 
     "usec": 518000 
    }, 
    "extension": "jpg", 
    "md5": "265087f19c17a99561a817f02a097b21", 
    "height": 600, 
    "width": 800, 
    "description": "", 
    "originalFilePath": "", 
    "originalFileName": "photo_09B01A71-46F2-4D8F-9153-CE0F0017495A.jpg" 
}]

这JSON片是一个较大字符串的一部分：

<script type="text/javascript"> 
     var listingData = {}; 
     var userData = {}; 

     window.detailPage = window.detailPage || {}; 
        window.detailPage.listingData = { 
       id: 44782446, 
       status: "Active", 
       createTime: 1498418380, 
       displayTime: 1500694902, 
       expireTime: 1503286902, 
       title: "Yamaha RX-V461", 
       description: "Great Audio\/Video 5.1 surround receiver. Great condition ", 
       city: "South Jordan", 
       state: "UT", 
       zip: 84095, 
       contactName: "Robert", 
       contactHomePhone: "801-635-6040", 
       contactCellPhone: "801-635-6040", 
       contactEmail: "hasEmail", 
       lat: 40.5693, 
       lon: -111.9672, 
       latLon: "40.5693,-111.9672", 
       price: 50, 
       category: "Electronics", 
       subCategory: "Home Audio Receivers", 
       marketType: "Sale", 
       sellerType: "Private", 
       photo: [{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418383-59832.jpg","uploadTime":{"sec":1498418386,"usec":192000},"extension":"jpg","md5":"6fac68fbcbdb31d17af7be277ab673be","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_0D993ADA-8AFC-4A79-8F9B-18E6F6C30B94.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418389-472609.jpg","uploadTime":{"sec":1498418392,"usec":118000},"extension":"jpg","md5":"6470e562d650099a1cafe9281f951c21","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_335B7BC0-F6DE-4E19-8489-3AA7B3920144.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418397-06491.jpg","uploadTime":{"sec":1498418400,"usec":161000},"extension":"jpg","md5":"5f2df3edfed164c062e739c0c3258970","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_9C57A971-9748-4DBD-919D-8D532C8D7C1A.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418403-391642.jpg","uploadTime":{"sec":1498418406,"usec":936000},"extension":"jpg","md5":"098dfa4d40e33c6897f62edc471670dd","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_A55BD209-3BFB-447E-AE59-40CF656664A8.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418409-263588.jpg","uploadTime":{"sec":1498418412,"usec":789000},"extension":"jpg","md5":"50b69c1db486f4bb6af723f7395a360b","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_8BCDC2F0-8CBA-442C-98F5-0389455C8014.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418415-54882.jpg","uploadTime":{"sec":1498418418,"usec":462000},"extension":"jpg","md5":"34296cda28b212a6c5590f233a2dca09","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_726D1636-E3A9-4515-9B95-55161FAAF730.jpg"},{"id":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418421-389128.jpg","uploadTime":{"sec":1498418424,"usec":518000},"extension":"jpg","md5":"265087f19c17a99561a817f02a097b21","height":600,"width":800,"description":"","originalFilePath":"","originalFileName":"photo_09B01A71-46F2-4D8F-9153-CE0F0017495A.jpg"}], 
       standardFeaturedDates: [], 
       favorited: 1, 
       pageViews: 68    }; 

      window.detailPage.sellerData = { 
       sellerId: 1159545, 
       sellerAccountAge: "Nov 2010", 
       moreListingsFromSeller: [{"id":44782211,"displayTime":1500694907,"price":100,"title":"Moto Gear 3 Helmets and Alpine Star Tech 6 Boots S","photo":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498417151-456217.jpg"},{"id":44782400,"displayTime":1500694904,"price":30,"title":"Belts Pouch, Canteen Holsters For 2 Canteens","photo":"http:\/\/img.ksl.com\/mx\/mplace-classifieds.ksl.com\/1159545-1498418072-282620.jpg"}]    }; 

      window.detailPage.userData = { 
       testUser: Boolean(0) 
      }; 
          </script>

我如何提取我想要的那件？

感谢您看我的问题！

来源

2017-07-22 Thania

哇。这不是HTML。这是json。你应该使用JSON解析器。 –

此外，您还没有指定您想要哪种语言的解决方案。 –

可能是发布[此问题]的用户@AlexR的假帐户（https://stackoverflow.com/questions/45257932/how-to-extract-一小时之前，从复杂的javascript-text-html-container-nested-in-betw）。 –

也许你不会再问了吗？如果这个工作，你知道你打算标记它接受，呃？

如果您愿意，可以将这个丑陋的东西视为json'parsables'列表。我把它放在一个我可以读入脚本的文件中。在阅读它时，我敲掉了最初的几个字符，最后的']'只留下可解析的项目，减去它们的初始位。

然后我做了分割，不要忘记分割的第一块不会被使用。将每个片段送入json解析器产生了一个字典，从中可以选择所需的项目。

>>> import json 
>>> import re 
>>> complete = open('temp.json').read()[6:-1] 
>>> pieces = re.split(r',?\s*\{\s*"id"', complete) 
>>> for piece in pieces[1:]: 
...  items = json.loads('{"id"'+piece) 
...  items['id'] 
... 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418383-59832.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418389-472609.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418397-06491.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418403-391642.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418409-263588.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418415-54882.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418421-389128.jpg'

编辑：改变了问题。非常相似，除了这是一个更多的工作来剔除包含所需信息的行。这是额外的match操作的目的。还要注意前一行已经改变。

>>> import json 
>>> import re 
>>> complete = open('temp.json').read() 
>>> m = re.match(r'.*?photo:\s+\[([^]]+)]', complete, re.DOTALL) 
>>> pieces = re.split(r',?\s*\{\s*"id"', m.groups(0)[0]) 
>>> for piece in pieces[1:]: 
...  items = json.loads('{"id"'+piece) 
...  items['id'] 
...  
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418383-59832.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418389-472609.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418397-06491.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418403-391642.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418409-263588.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418415-54882.jpg' 
'http://img.ksl.com/mx/mplace-classifieds.ksl.com/1159545-1498418421-389128.jpg'

来源

2017-07-22 21:29:58

我不欣赏态度，但我非常感谢您的时间和解决方案，谢谢比尔。但是，我还没有能够在我的机器上重现结果，因为我没有给你足够的上下文进入我的代码！（Doh！）我提供的这段代码是“javascript/text”较大部分的代码;我无法隔离我给你们的JSON解析器。 – Thania

我更新了这个问题，以反映我正在努力与什么。 – Thania

没有违法意图。我真的不在乎你是否伪造你的身份。无法抗拒戏弄。 –

从大括号和方括号中包含的复杂html中提取子字符串在python中使用正则表达式正则表达式

回答

相关问题