def populate_notices():
notices = extract_notices()
for notice in notices:
title = notice[0]
link = notice[1]
notice = Noticia(titulo=title, enlace=link)
print(notice)
notice.save()
def noticiasPoliticaELMUNDO():
codigoHtml = extraerCodigo("https://www.elmundo.es/t/po/politica.html")
listaLinks = []
listaLinksImagenes = []
for i in codigoHtml.find_all('a', class_='ue-c-cover-content__link'):
if i.get('href').startswith("https://www.elmundo.es/espana") or i.get(
'href').startswith("https://www.elmundo.es/cataluna"):
listaLinks.append(i.get('href'))
titulares = []
fechas = []
autores = []
for i in listaLinks:
codigoHtml = extraerCodigo(i)
a = codigoHtml.find("meta", property="og:image")
if a:
listaLinksImagenes.append(a['content'])
else:
b = codigoHtml.find("meta", attrs={'name': 'og:image'})
listaLinksImagenes.append(b['content'])
for i in codigoHtml.find('title'):
titulares.append(i.split("|")[0])
x = codigoHtml.find("meta", property="article:modified_time")
fechas.append(x['content'][0:10])
aut = codigoHtml.find('div', class_="ue-c-article__byline-name")
autores.append(aut.text)
print("Cargando Politica elMundo...")
for i, x in enumerate(titulares):
if not (Noticia.objects.filter(titulo=titulares[i])):
Noticia(titulo=titulares[i],
fecha=fechas[i],
imagen=listaLinksImagenes[i],
autor=autores[i],
categoria="Politica",
link=listaLinks[i]).save()
def noticiasDiarioPolitica():
links = []
linksImag = []
codHtml = extraerCodigo("https://www.eldiario.es/temas/politica/")
for i in codHtml.find_all('li', class_='lst-item cf '):
for j in i.find_all('h2', class_="bkn headline typ-x4"):
for p in j.find_all('a', class_='lnk'):
if not ("autores" in p["href"]):
links.append(str("https://www.eldiario.es" + p["href"]))
break
for j in i.find_all('div', class_='mg fl'):
if (len(i.find_all('img')) >= 1):
for p in i.find_all('img'):
linksImag.append(str("https://www.eldiario.es" + p["src"]))
else:
linksImag.append(
str("http://www.sanisidrolonas.com.ar/wp-content/uploads/2011/05/sin-imagen12.jpg"
))
fechas = []
autores = []
titulares = []
for item in links:
codHtml = extraerCodigo(str(item))
#Titulo
for i in codHtml.find_all('h1', class_="pg-headline"):
titulares.append(str(i.get_text().strip()))
#fecha
for i in codHtml.find_all('span', class_="date"):
fechas.append(str(i.get_text().strip()))
break
#autor
for i in codHtml.find_all('small', class_="byline"):
if (i.find_all('a', class_='lnk')):
for p in i.find_all('a', class_='lnk'):
autores.append(str(i.get_text().strip()))
else:
autores.append("Sin autor")
nuevasFechas = []
for item in fechas:
s = item.replace("-", "").replace(" ", "")
w = s.split("/")
nuevasFechas.append(w[2] + "-" + w[1] + "-" + w[0])
for i in range(len(titulares)):
if not (Noticia.objects.filter(titulo=titulares[i])):
Noticia(titulo=titulares[i],
fecha=fechas[i],
autor=autores[i],
link=links[i],
categoria="Politica",
imagen=linksImag[i]).save()
def noticiasPublicoCultura():
codigoHtml = extraerCodigo("https://www.publico.es/culturas")
listaLinks = []
listaLinksImagenes = []
#HREF
for i in codigoHtml.find_all('div', class_='listing-item'):
for p in i.find_all('a', class_='page-link'):
listaLinks.append(str("https://www.publico.es" + p["href"]))
break
if (not (len(list(str(i.find_all('img')))) == 2)):
for p in i.find_all('img'):
listaLinksImagenes.append(
str("https://www.publico.es" + p["src"]))
break
else:
listaLinksImagenes.append(
str("http://www.sanisidrolonas.com.ar/wp-content/uploads/2011/05/sin-imagen12.jpg"
))
#titulares
titulares = []
fechas = []
autores = []
for item in listaLinks:
codigoHtml = extraerCodigo(str(item))
#titulares
for i in codigoHtml.find_all('div', class_="article-header-title"):
for ii in i.find_all('h1'):
titulares.append(str(ii.text.strip()))
#fechas
for i in codigoHtml.find('span', class_="published"):
fechaa = str(i.strip()).split(" ")
fechaa1 = fechaa[0].replace("/", "-")
d = fechaa1.split("-")
fechas.append(d[2] + "-" + d[1] + "-" + d[0])
#autor
for i in codigoHtml.find_all('div', class_="article-info"):
for ii in i.find('p'):
autores.append(str(i.text.strip()))
#im
for i in range(len(titulares)):
if not (Noticia.objects.filter(titulo=titulares[i])):
Noticia(titulo=titulares[i],
fecha=fechas[i],
autor=autores[i],
link=listaLinks[i],
categoria="Cultura",
imagen=listaLinksImagenes[i]).save()