def get_most_read(key):
"""
Gets the most read news from a given page
:param key: the key of the source page (e.g: g1)
:return: a list with the most read news from the page and the name of news source
"""
ns = get_ns(key)
response, content = getpage(ns.url) # Download the page
soup = parsepage(content) # Then we parse it
strategy = strategies[key] # Then we execute the selected Strategy based on the source
return strategy(soup), ns.name
def get_most_read(key):
"""
Gets the most read news from a given page
:param key: the key of the source page (e.g: g1)
:return: a list with the most read news from the page and the name of news source
"""
ns = get_ns(key)
response, content = getpage(ns.url) # Download the page
soup = parsepage(content) # Then we parse it
strategy = strategies[key] # Then we execute the selected Strategy based on the source
return strategy(soup), ns.name
def g1(soup):
"""
Gets the most read news from the g1 page
:param soup: the BeautifulSoup object
:return: a list with the most read news from the G1 Page
"""
news = []
scripts = soup.find_all('script')
for script in scripts:
script_content = script.text
# O conteúdo do G1 agora é gerado por script. Primeiro achamos o script correto, pois são vários
if script_content.find('#G1-POST-TOP') != -1:
i = 0
# Recuperamos as URLs mais acessadas
while True:
# Primeiro achamos um top-post (url) com essa chave de busca
key_index = script_content.find('#G1-POST-TOP', i)
if key_index == -1:
break
# Agora achamos o começo da url
start_index = script_content.rfind('"', 0, key_index) + 1
# Agora achamos o final da url
end_index = script_content.find('"', key_index)
# E agora pegamos a URL (substring)
url = script_content[start_index:end_index]
# Com a URL, entramos na página e descobrimos o título dela
response, content = getpage(url)
soup2 = parsepage(content)
title = soup2.find('h1', class_='content-head__title').string
news.append(dict(title=title, link=url))
# Preparamos o próximo índice de busca
i = key_index + 10
return news