Beautiful soup to get data (web mining)

blog.py

#!/usr/bin/python
import peewee
from peewee  import *
from bs4 import BeautifulSoup
import sys
import os

db = MySQLDatabase("redacao_inteligente", user="root", passwd="emakersjr")

class Blog(peewee.Model):
    title = peewee.CharField()
    text = peewee.TextField()
    author = peewee.CharField()
    author_url = peewee.CharField()

    class Meta:
        database = db

files = os.listdir(sys.argv[1])

for file in files:
    print(file)
    try:
        fileobj = open(sys.argv[1] + file, 'r')
    except IndexError:
        fileobj = sys.stdin

    with fileobj:
        data = fileobj.read()
    soup = BeautifulSoup(data, 'html.parser')

    if soup.find('div',class_='container_conteudo_publicacao').a is None:
        author = ""
        author_url = ""
    else:
        author = soup.find('div',class_='container_conteudo_publicacao').a.getText()
        author_url = soup.find('div',class_='container_conteudo_publicacao').a['href']

    if soup.find('div',class_='container_conteudo_publicacao').h1 is None:
        title = file
    else:
        title = soup.find('div',class_='container_conteudo_publicacao').h1.getText()

    if soup.find('div', class_='container_conteudo_publicacao').article is None:
        text = soup.find('div',class_='container_conteudo_publicacao').getText()
    else:
        text = soup.find('div',class_='container_conteudo_publicacao').article.getText()

    Blog.create_table()
    blog = Blog(title=title, author=author, author_url=author_url, text=text)

    blog.save()

blog.sh

#!/bin/bash

for entry in "$1"/*.html
do
  python3 blog.py $entry
  echo "$entry"
done

db.py

#!/usr/bin/python
import peewee
from peewee import *

db = MySQLDatabase("redacao_inteligente", user="root",         # your username
                     passwd="emakersjr")  # your password

class Blog(peewee.Model):
	title = peewee.CharField()
	text = peewee.TextField()
	author = peewee.CharField()
	author_url = peewee.CharField()

	class Meta:
		database = db

Blog.create_table()
blog = Blog(title="Introducao", author="eu", author_url="uiutubiuponcotom", text="LALLALALAL ALLALALALLALLALA")
blog.save()
# you must create a Cursor object. It will let
#  you execute all the queries you need
#cur = db.cursor()

# Use all the SQL you like
#cur.execute("SELECT * FROM blog")

# print all the first cell of all the rows
#for row in cur.fetchall():
#    print (row[1])

db.close()

temas.py

#!/usr/bin/python
import peewee
from peewee  import *
from bs4 import BeautifulSoup
import sys
import os

db = MySQLDatabase("redacao_inteligente", user="root", passwd="emakersjr")

class Tema(peewee.Model):
    title = peewee.CharField()
    text = peewee.TextField()
    author = peewee.CharField()
    author_url = peewee.CharField()

    class Meta:
        database = db

files = os.listdir(sys.argv[1])

for file in files:
    print(file)
    try:
        fileobj = open(sys.argv[1] + file, 'r')
    except IndexError:
        fileobj = sys.stdin

    with fileobj:
        data = fileobj.read()
    soup = BeautifulSoup(data, 'html.parser')

    author = ""
    author_url = ""

    if soup.find('h1',class_='barra_paginas_internas') is None:
        title = file
    else:
        title = soup.find('h1',class_='barra_paginas_internas').getText()

    if soup.find('div', class_='container_conteudo_publicacao').article is None:
        text = soup.find('div',class_='container_conteudo_publicacao').getText()
    else:
        text = soup.find('div',class_='container_conteudo_publicacao').article.getText()

    Tema.create_table()
    tema = Tema(title=title, author=author, author_url=author_url, text=text)

    tema.save()