Python は、newspaper3k を使用して記事のタイトル、画像、キーワード、テキストなどを抽出します
1. レンダリング
最初の写真は次のとおりです。
2. インストールとエラーの解決
Python 3.7.4
pip インストール新聞3k==0.2.8
3. ソースコード
import newspaper
from newspaper import Config
sina_paper = newspaper.build('http://www.sina.com.cn/', language='zh')
for category in sina_paper.category_urls():
print(category)
# http://health.sina.com.cn
# http://eladies.sina.com.cn
# http://english.sina.com
user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_2) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.4 Safari/605.1.15'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36'
config = Config()
config.browser_user_agent = user_agent
article = sina_paper.articles[0]
article.config = config
print(len(article.url), article.url)
if (article.url.find("http") > 4): article.url = 'http' + article.url.split("http")[2]
print(len(article.url), article.url)
article.url = article.url.replace(' ', '')
print(len(article.url), article.url)
article.download()
article.parse()
print('text: ', article.text)
print('title: ', article.title)
print('publish_date: ', article.publish_date)
print('tags: ', article.tags)
print('top_image: ', article.top_image)
print('top_img: ', article.top_img)
print('url: ', article.url)
print('meta_keywords: ', article.meta_keywords)
print('meta_img: ', article.meta_img)
print('keywords: ', article.keywords)
print('images:', len(article.images), article.images)
print('imgs', len(article.imgs), article.imgs)
# url = "https://www.newsweek.com/new-mexico-compound-charges-dropped-children-1096830".strip()
#
# content = []
# for i in [article.url]:
# article = Article(str(i), config=config)
# try:
# article.download()
# article.parse()
# article.download()
# print(article.html)
# article.parse()
# text = article.text
# print(i, text)
# content.append(text)
# except Exception as e:
# print(e)
# content.append('error')
# continue
# print(content)