web_scraper_stage4

def save_article():
    url = "https://www.nature.com/nature/articles"
    r = requests.get(url)
    if r.status_code == 200:
        soup = BeautifulSoup(r.content, 'html.parser')
        title_news = []
        puncs = string.punctuation
        for x in soup.find_all('article'):
            article_type = x.find('span', attrs={'data-test': 'article.type'}).text
            # print(article_type)
            if article_type == '\nNews\n':
                title = x.find('a', {'data-track-action': "view article"}).text
                name = title.strip(' ').translate(str.maketrans(" ", "_", puncs)) + '.text'
                print(name)
                title_news.append(name)
                article_url = f"https://www.nature.com{x.a.get('href')}"
                r2 = requests.get(article_url)
                soup2 = BeautifulSoup(r2.content, 'html.parser')
                text = soup2.find('div', {'class': 'c-article-body'}).text.strip()
                # print(text)
                # with open(name, 'w') as file:
                    # file.write(text)
                file = open(name, 'w')
                file.write(text.strip())
                print('file written')
                file.close()


save_article()