Web Scraping en Colombia: Consulta personas por cédula de identificación
En este scraping utilizamos python y django las librerias que se necesitan son
requests
************************HTML**********************
<!DOCTYPE html>
<html>
<head>
<meta name="viewport" content="width=device-width" />
<title>Index</title>
{% load static %}
<link rel="stylesheet" type="text/css" href="{% static 'styles/general.css' %}" />
<style>
.cntpreview{
background: #000;
padding: 10px;
width: 50%;
min-height: 300px;
color: #fff
}
</style>
</head>
<body>
<div id="divLoading" class="wrap_loading hide">
<div class="lds-ring">
<div></div>
<div></div>
<div></div>
<div></div>
</div>
<div class="loading_text">Procesando ...</div>
</div>
<div class="titulo">Scrapping Consulta Persona por Identificación Colombia (Barranquilla)</div>
<div class="fila">
<input type="text" id="txtIdentificador" value="8532141"/>
<button id="btnProcesar" class="boton">Procesar</button>
</div>
<div style="display: flex;justify-content: center;">
<pre id="txtPre" class="cntpreview"></pre>
</div>
<div>
{% csrf_token %}
</div>
<script src="{% static 'scripts/Demo34.js' %}" ></script>
</body>
</html>
************************JAVASCRIPT**********************
let foto=null;
window.onload=function(){
let btnProcesar=document.getElementById("btnProcesar");
btnProcesar.onclick=function(){
let txtIdentificador=document.getElementById("txtIdentificador").value;
let fd=new FormData();
fd.append("data",txtIdentificador)
servidor({url:"procesar",data:fd,responsetype:"json"}).then((data)=>{
document.getElementById("txtPre").innerHTML=JSON.stringify(data,null,2);
});
}
}
function servidor({ metodo = "post", url = null, data = null, responsetype = "text" } = {}) {
return new Promise((resolve, reject) => {
let divLoading=document.getElementById("divLoading");
if(divLoading){
divLoading.classList.remove("hide");
}
let xhr = new XMLHttpRequest();
xhr.open(metodo, url);
var csrftoken=document.getElementsByName("csrfmiddlewaretoken")[0].value;
xhr.setRequestHeader("X-CSRFToken", csrftoken);
xhr.responseType = responsetype;
xhr.onreadystatechange = function () {
if (xhr.readyState == 4 && xhr.status == 200) {
divLoading.classList.add("hide");
resolve(xhr.response);
}
}
xhr.onerror = function (e) {
reject(e)
}
xhr.send(data);
});
}
************************PYTHON**********************
from django.shortcuts import render
from django.http.response import HttpResponse,JsonResponse
from django.conf import settings
import requests
import json
def index(request):
return render(request,"Demo34.html")
def procesar(request):
identificacion=request.POST.get("data")
rptaJson={}
print("buscar dni "+identificacion)
try:
header={"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36",
"origin":"https://portal.barranquilla.gov.co:8181",
"host":"portal.barranquilla.gov.co:9393",
"referer":"https://portal.barranquilla.gov.co:8181/",
"content-type":"application/json"}
payload={"username":"transito","password":"Transito2025*"}
sesion=requests.session()
req=sesion.post("https://portal.barranquilla.gov.co:9393/api/auth/signin",headers=header,data=json.dumps(payload),verify=False)
if req.status_code==200:
obj=req.json()
header["authorization"]="Bearer "+obj["token"]
req=sesion.get("https://portal.barranquilla.gov.co:9393/baq/transito/consultas/persona/"+identificacion,headers=header,verify=False)
if req.status_code==200:
rptaJson=req.json()
except Exception as e:
print("Error "+ str(e))
return JsonResponse(rptaJson,safe=False)
Comentarios
Publicar un comentario