kw_tools/choozmo/googlenews.py

from newspaper import Article
from GoogleNews import GoogleNews


def news(title_and_link):
    for i in title_and_link:
        try:
            article = Article(i['link'])
            article.download()
            article.parse()
            text = article.text
            title = i['title']
            try:
                print(title)
                with open(f'/Users/zooeytsai/ig_tags/googlenews/{title}.txt','x') as f:
                    f.write(text)
            except FileExistsError:
                print('已有同樣新聞文章','title')
                pass
        except:
            print('403')
            pass
    return text


def google_news(keyword,page):
    g = GoogleNews()
    g.setlang('cn')
    g.setencode('utf-8')
    g.search(keyword)
    g.clear()
    news_link = []
    for i in range(page):
        g.get_page(page)
        result = g.result()
        for j in result:
            d ={'title':j['title'],'link':j['link']}
            news_link.append(d)
    g.clear()
    print(len(news_link))
    print(news_link)
    return news_link


k = ['寵物蛋糕','寵物住宿','寵物餐廳','寵物用品','寵物美容','寵物友善']
for i in k:
    result = google_news(i,5)
    news(result)