manuelver/Curso-lenguaje-python
manuelver/Curso-lenguaje-python
1
0
Fork 0
Code Issues Pull Requests Releases Activity

Update url with format and url_base

Browse Source
This commit is contained in:
Manuel Vergara 2023-04-12 22:47:39 +02:00
parent c681de5c61
commit c47a45839e
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
dia_11/03_web_scraping_03.py
View File

@ -9,8 +9,7 @@ import bs4
import requests import requests
# Variables # Variables
raiz = 'http://books.toscrape.com/catalogue/page-' url_base = 'http://books.toscrape.com/catalogue/page-{}.html'
extension = '.html'
fin_url = True fin_url = True
page = 0 page = 0
lista_titulos = [] lista_titulos = []
@ -21,7 +20,7 @@ while fin_url:
page += 1 page += 1
page = str(page) page = str(page)
enlace = raiz + page + extension enlace = url_base.format(page)
resultado = requests.get(enlace) resultado = requests.get(enlace)
sopa = bs4.BeautifulSoup(resultado.text, 'lxml') sopa = bs4.BeautifulSoup(resultado.text, 'lxml')
@ -31,9 +30,12 @@ while fin_url:
# Todos los títulos # Todos los títulos
titulos = sopa.select('.product_pod a') titulos = sopa.select('.product_pod a')
for title in titulos: for title in titulos:
if title.get('title') != None: if title.get('title') != None:
lista_titulos.append(title.get('title')) lista_titulos.append(title.get('title'))
else: else:
fin_url = False fin_url = False
print(lista_titulos)