Ejemplo extraer datos web

Aquí vamos a introducir, con un ejemplo, como obtener datos de una web

# Importamos los paquetes
from requests_html import HTML 

with open(r"F:\curso_python_uruguay\lectures\lecture5_scrapping\simple.html") as file_html:
    source = file_html.read()
    html = HTML(html = source)

type(html)

#print(html.html)
print(html.text)

match = html.find("title") #css selector
print(match)

type(match)

print(match[0])

print(match[0].text)

dir(match[0])

# Si solo queremos buscar el primero
match = html.find("title", first = True)
print(match)

# find utiliza css selectors: ver https://www.w3schools.com/cssref/css_selectors.php

# que pasa si queremos ver el 
# Si solo queremos buscar el primero
match = html.find("#site_title", first = True)
print(match.text)

# article headlines
# Si solo queremos buscar el primero
match = html.find("div.article", first = True)
print(match.text)

# quiero cada parte por separado
print(match.html)

head = match.find("h2", first = True)
print(head.text)

resumen = match.find("p", first = True)
print(resumen.text)

# que pasa sino pongo first
match = html.find("div.article")
print(match)

for artic in match:
    head = artic.find("h2", first = True)
    print(head.text)
    resumen = artic.find("p", first = True)
    print(resumen.text)
    print("\n")

Beautiful Soup

from bs4 import BeautifulSoup
import requests

with open(r"F:\curso_python_uruguay\lectures\lecture5_scrapping\simple.html") as file_html:
    soup = BeautifulSoup(file_html, 'lxml')
    

print(soup)

print(soup.prettify())

match = soup.title
print(match)
print(match.text)

# Coge la primera ocurrencia
match = soup.div
print(match)

# Coge la primera ocurrencia
match = soup.find("div")
print(match)

match = soup.find("div", class_ = "article")
print(match)

# Obtener el titulo del artículo
match = soup.find(id = "site_title")
print(match)

#obtener el titulo del articul
article = soup.find("div", class_ = "article")
titulo = article.h2.a.text
print(titulo)

resumen = article.p.text
print(resumen)

# Si queremos el titulo de todos los articulos

article = soup.find_all("div", class_ = "article")

article

# es una lista
for art in soup.find_all("div", class_ = "article"):
    titulo = art.h2.a.text
    print(titulo)