How to export specific div from webpage to dataframe?-CodePudding

I want to export a specific div from the webpage. In this case, I want to export div with id "producer-votes-wrapper"; this part of the page has all the numbers(data) I want to get.

Using previous examples and questions, I tried to do it by myself, but could not get the desired result. The current code looks like the following:

import urllib.request

url= 'https://bloks.io/account/eoseouldotio#votes'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36 Edg/106.0.1370.52',
    'Accept': 'text/html,application/xhtml xml,application/xml;q=0.9,*/*;q=0.8'
    
}

request=urllib.request.Request(url,None,headers) #The assembled request
response = urllib.request.urlopen(request)
data = response.read() # The data u need
data

I tried to get all the data mentioned on the webpage and then parse and leave the most important one. But using this code I am just getting useless text and info.

CodePudding user response：

You can use js2py/requests to get the list, for example:

import js2py
import requests


api_url = "https://eos.hyperion.eosrio.io/v2/state/get_voters?producer=eoseouldotio&limit=100"
data = requests.get(api_url).json()

js_func = """\
    function $(num) {

      var CHAIN = 'eos';
      var CORE_PRECISION = 4;

      function calculateVoteWeight() {
        let e = 'wax' === CHAIN ? 13 : 52,
        t = 946684800000,
        n = Date.now() / 1000 - t / 1000,
        a = Math.floor(n / 604800) / e;
        return Math.pow(2, a)
      }

      function weightedVoteToNumber(e, t) {
        return   e / t / Math.pow(10, CORE_PRECISION)
      }

      return weightedVoteToNumber(num, calculateVoteWeight());
    }
"""

get_votes = js2py.eval_js(js_func)

for i, v in enumerate(data["voters"], 1):
    print("{:>3} {:<15} {}".format(i, v["account"], get_votes(v["weight"])))

Prints:

  1 genpoolproxy    12223404.962632878
  2 proxy4nation    9988023.902857617
  3 brockpierce1    7567714.822700241
  4 votetobestbp    5000016.0222
  5 infstonespxy    4893994.756118013
  6 3g33s3yvm14o    4000186.264188379
  7 ujmbnmhhgege    3454463.383436105
  8 votefordefi3    3000006.4445
  9 boxproxyacc2    2991160.2925
 10 vjyfeimpfipm    2960178.44507899
 11 bestbpproxy3    2769515.4555716044
 12 eosblueocean    2017680.053802568
 13 votefordefi2    2000004.4447
 14 goodbpproxy2    2000001.279242206
 15 votebpproxy2    2000000.2716760403
 16 bestbpproxy2    2000000.1161000005
 17 foreosproxy2    2000000.0773
 18 22kon3zii2xj    1973517.3920720608
 19 eosproxy2222    1846278.1276148804
 20 eosuniverse4    1729434.0745837307
 21 max1research    1727233.497893132
 22 dfsbpsproxy1    1346609.485410652
 23 newdexproxy1    1190464.2408884696
 24 newdexproxy4    1146121.3897043345
 25 newposproxy4    1077755.6027183502
 26 iloveeosbp12    1000004.1188
 27 iloveeosbp11    1000002.0762
 28 tothemoonbp2    1000000.9467
 29 foreosvote12    1000000.6146
 30 tothemoonbp1    1000000.2276999998
 31 goodbpproxy1    1000000.1421999998
 32 kvotebpproxy    1000000.1080999998
 33 foreosvote11    1000000.0982
 34 foreosproxy1    1000000.0768
 35 votebpproxy1    1000000.0764
 36 zgjenxyhyr2f    986758.6966280856
 37 fzrv13xeykgc    986758.6963320582
 38 wynxe2mjlun3    986758.6959373545
 39 rbqdtrfzkjin    986679.7549457861
 40 binanceprxy4    963293.8089988151
 41 binanceprxy5    963245.2874580923
 42 5hedxzqf2up3    948077.5151924414
 43 43vxynfoilbp    948077.5150976336
 44 vwdkolamq5xh    948077.5150028258
 45 newdexproxy5    833220.2371066288
 46 newposproxy2    744271.3075562501
 47 newposproxy3    654466.93982948
 48 newdexproxy3    609038.8722571591
 49 newposproxyp    546820.5754945058
 50 newposproxy1    528395.2334034096
 51 2lnyrx1ojudz    493379.74351089983
 52 newposproxy5    461594.99237992516
 53 newdexproxy2    372770.3207974433
 54 newposproxyc    205402.62646861575
 55 newposproxyk    165242.03631287487
 56 newposproxyl    147335.32452166546
 57 newposproxyo    147117.71954609765
 58 whaleexproxy    124536.93289501838
 59 haydinruhage    120025.38310000002
 60 newposproxyd    119111.79127485356
 61 newposproxyq    113303.98983725329
 62 newposproxya    89222.96972714498
 63 bloksioproxy    75091.47129018814
 64 newposproxyb    65037.34360974116
 65 newposproxyf    62185.83976808534
 66 newposproxyi    47540.47210508377
 67 newposproxyj    44846.98636416771
 68 maxmaxmaxmac    42472.890608290276
 69 edenproxyrew    42039.79163716058
 70 proxy2nation    37521.97772731668
 71 newposproxye    24979.75775478982
 72 whaleexvotee    24651.26629999998
 73 whaleexvote2    18216.5297
 74 edenproxydon    16143.093300650424
 75 shankooooooo    10230.596108077649
 76 fvztvnwifaaa    9242.21950142053
 77 newposproxyn    5833.500486037437
 78 newposproxym    5376.35260346395
 79 whaleexvotei    3239.2693
 80 4cdfa3451ba3    2908.8954212365957
 81 start11.io      1603.294770884103
 82 rexproxy.tp     1582.6070414383278
 83 freeandpeace    1155.2506065612258
 84 charityalfap    1001.7386707908703
 85 bywire.com      853.1515670570791
 86 whaleexvotej    707.0379
 87 buziliauskas    490.1615893241484
 88 voteproxy134    358.65694154656836
 89 holdyourfire    355.73633343799105
 90 guytsobyg4ge    300
 91 gu2tcnjvguge    279.737124995751
 92 gm2teojvhege    275.5550399573742
 93 darks1de2111    260.70447331984116
 94 tvuskwallete    203.2589396612221
 95 xy1gullq42cp    201.3439671772095
 96 fvztvnwifaab    199.76702136820313
 97 songchunlong    194.0824157723007
 98 nxcpnfylm.gm    187.10474602129185
 99 tlorusso1.gm    184.74382433954523
100 boidcomproxy    182.69725348851