Multiple search engines in a html file with variable parameters

1

Good morning everyone.

Need to search for the name of the presidents of Brazil, in html files. I created a json with the names of the presidents to facilitate.

Follow the code:

# !/bin/env python
# coding: utf-8
__author__ = '@britodfbr'

import json
import re
import os
from bs4 import BeautifulSoup


value = '''{
    "presidentes": {
        "1" : {
            "nome": "Manuel Deodoro da Fonseca",
            "vice": "Floriano Vieira Peixoto",
            "imandato": "15 de novembro de 1889",
            "fmandato": "23 de novembro de 1891"
            },
        "2": {
            "nome":"Floriano Vieira Peixoto",
            "vice": null,
            "imandato": "23 de novembro de 1891",
            "fmandato": "15 de novembro de 1894"
            },
        "3": {
            "nome":"Prudente José de Morais e Barros",
            "vice": "Manuel Vitorino Pereira",
            "imandato": "15 de novembro de 1894",
            "fmandato": "15 de novembro de 1898"
        },
        "4": {
            "nome":"Manuel Ferraz de Campos Sales",
            "vice": "Francisco de Assis Rosa e Silva",
            "imandato": "15 de novembro de 1898",
            "fmandato": "15 de novembro de 1902"
        },
        "5": {
            "nome":"Francisco de Paula Rodrigues Alves",
            "vice": "Francisco Silviano de Almeida Brandão",
            "imandato": "15 de novembro de 1902",
            "fmandato": "15 de novembro de 1906"
        }
    }
}'''

def truncus13(file = '../data/teste02.html'):
    soup = BeautifulSoup(open(file).read(), 'html5lib')
    presidentes = json.loads(value)

    for item in presidentes['presidentes'].values():
        #print(item)
        regex = ''
        for i in [x.lower() for x in item['nome'].split() if len(x) > 2]:
            regex += f'("{i} ")?'
        regex = f"'{regex}'"
        print(regex)
        result = soup.find_all(string=re.compile(regex, re.I), limit=10)
        if result:
            return result
    return False

if __name__ == '__main__':
    for file in [os.path.abspath(f) for f in os.listdir() if f.endswith('.html')]:
        truncus13(file)

HTML examples

<!DOCTYPE html>
<html lang="pt-br">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>

Deodoro da Fonseca<br />
Floriano Peixoto

</body>
</html>

<!DOCTYPE html>
<html lang="pt-br">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
<p> Manuel Deodoro</p>
<p> Vieira Peixoto</p>
</body>
</html>

<!DOCTYPE html>
<html lang="pt-br">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
<p> Deodoro da Fonseca</p>
<p> Vieira Peixoto</p>
</body>
</html>

Expected Goal A class 'bs4.element.ResultSet' with the name of the chair that exists in the HTML document.

    
asked by anonymous 26.06.2018 / 16:42

0 answers