python3 使用newspaper库提取新闻内容(readability，jparser)

pip3 install newspaper3k
or 
pip3 install --ignore-installed --upgrade newspaper3k

import time
from newspaper import Article

url = 'https://www.chinaventure.com.cn/news/78-20190819-347269.html'
url='https://36kr.com/p/5237348'
# 创建文章对象
news = Article(url, language='zh')
# 下载网页
news.download()
## 网页解析
news.parse()
print("title=",news.title)# 获取文章标题
print("author=", news.authors)   # 获取文章作者
print("publish_date=", news.publish_date)   # 获取文章日期
# 自然语言处理
news.nlp()
print('keywords=',news.keywords)#从文本中提取关键字
print("summary=",news.summary)# 获取文章摘要
# time.sleep(30)
print("text=",news.text,"\n")# 获取文章正文

print("movies=",news.movies)   # 获取文章视频链接
print("top_iamge=",news.top_image)   # 获取文章顶部图片地址
print("images=",news.images)#从html中提取所有图像
print("imgs=",news.imgs)
print("html=",news.html)#获取html

import newspaper

url='http://www.coscocs.com/'
'''注：文章缓存：默认情况下，newspaper缓存所有以前提取的文章，并删除它已经提取的任何文章。
此功能用于防止重复的文章和提高提取速度。可以使用memoize_articles参数选择退出此功能。'''
news = newspaper.build(url, language='zh', memoize_articles=False)
article = news.articles[0]
article.download()
article.parse()
print('text=',article.text)
print('brand=',news.brand)  #提取源品牌
print('description=',news.description) # 提取描述
print("一共获取%s篇文章" % news.size())  # 文章的数目

# 所有文章的url
for article in news.articles:
    print(article.url)

#提取源类别
for category in news.category_urls():
    print(category)

#提取源提要
for feed_url in news.feed_urls():
    print(feed_url)

import requests
from newspaper import fulltext

html = requests.get('https://www.washingtonpost.com/business/economy/2019/01/17/19662748-1a84-11e9-9ebf-c5fed1b7a081_story.html?utm_term=.26198c91916f').text
text = fulltext(html)
print(text)

import newspaper

print(newspaper.languages())#获取支持的语言
print(newspaper.hot())#hot()使用公共api返回谷歌上的热门词汇列表
print(newspaper.popular_urls())#popular_urls()返回一个流行新闻源url列表

import newspaper
from newspaper import news_pool

# 创建并行任务
slate_paper = newspaper.build('http://slate.com')
tc_paper = newspaper.build('http://techcrunch.com')
espn_paper = newspaper.build('http://espn.com')

papers = [slate_paper, tc_paper, espn_paper]
news_pool.set(papers, threads_per_source=2) # (3*2) = 6 共6个线程

news_pool.join()

print(slate_paper.articles[10].html)

pip install requests
pip install readability-lxml

import requests
from readability import Document
response = requests.get('https://news.163.com/18/1123/13/E1A4T8F40001899O.html')
doc = Document(response.text)
print doc.title()
print doc.content()