capint
4/8/2017 - 5:20 PM

Python >> Web crawling

Python >> Web crawling

source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text, 'html.parser')
for link in soup.findAll('a', {'class','title_list_top_news'}):
  print(link.get('href'))