Python newspaper.Article类代码示例

def get_details():
    url = request.args.get('url', '')
    if not url:
      abort(400)

    if is_image(url):
      result = {
        "url": url,
        "top_image": url,
        "text": "",
      }
      return jsonify(result)

    article = Article(url)
    article.download()

    try:
      article.parse()
    except (IOError, UnicodeDecodeError):
      return '', 422

    try:
      top_image = article.top_image.rsplit('?',1)[0]
    except AttributeError:
      top_image = ''

    result = {
      "url": url,
      "top_image": top_image,
      "text": article.text,
    }

    return jsonify(result)

 def test_spanish_fulltext_extract(self):
     url = "http://ultimahora.es/mallorca/noticia/noticias/local/fiscalia-anticorrupcion-estudia-recurre-imputacion-infanta.html"
     article = Article(url=url, language="es")
     article.download()
     article.parse()
     with codecs.open(os.path.join(TEXT_FN, "spanish_text_1.txt"), "r", "utf8") as f:
         assert article.text == f.read()

def get_text(url):
    article = Article(url)
    download=article.download()
    parser= article.parse()
    authors=article.authors
    publish_date=article.publish_date # TODO: Slice publish date
    body_text=article.text
    body_text=body_text.replace('"','\"')
    body_text=body_text.replace('"','')
    #nlp=article.nlp()
    keywords=article.keywords
    summary=article.summary
    title=article.title
    tags=article.tags

    #print body_text

    title=strip_non_ascii(title)
    summary=strip_non_ascii(summary)
    body_text=strip_non_ascii(body_text)
    keywords=' '.join(keywords)
    keywords=strip_non_ascii(keywords)

    #print (title, summary, authors, publish_date, body_text, keywords)

    return (title, summary, authors, publish_date, body_text, keywords, tags)

def main():
    try:
        headlines = requests.get(headline_url)
        
        headlines = json.loads(headlines.text)
        for headline in headlines['Headlines']:
            print("Processing Article %s" % headline['Url'])
            article = Article(headline['Url'])
            article.download()
            article.parse()
            
            
            response = requests.post(calais_url, files={'file': article.text}, headers=headers, timeout=80)
            rdf = json.loads(response.text)
            
            for x in rdf:
                if '_type' in rdf[x] and 'name' in rdf[x]:
                    print("Output for %s %s" % (rdf[x]['_type'], rdf[x]['name']))
                    for instance in rdf[x]['instances']:
                        text = instance['prefix'] + instance['suffix']
                        blob = TextBlob(text)
                        for sentence in blob.sentences:
                            print(sentence)
                            print(sentence.sentiment.polarity)
            print('--------------------')
            
            #print(rdf)
    except Exception as e:
        print ('Error in connect ' , e)

 def test_chinese_fulltext_extract(self):
     url = "http://www.bbc.co.uk/zhongwen/simp/chinese_news/2012/12/121210_hongkong_politics.shtml"
     article = Article(url=url, language="zh")
     article.download()
     article.parse()
     with codecs.open(os.path.join(TEXT_FN, "chinese_text_1.txt"), "r", "utf8") as f:
         assert article.text == f.read()

 def test_chinese_fulltext_extract(self):
     url = 'http://www.bbc.co.uk/zhongwen/simp/chinese_news/2012/12/121210_hongkong_politics.shtml'
     article = Article(url=url, language='zh')
     article.build()
     # assert isinstance(article.stopwords_class, StopWordsChinese)
     with codecs.open(os.path.join(TEXT_FN, 'chinese_text_1.txt'), 'r', 'utf8') as f:
         assert article.text == f.read()

def main(argv):
    if len(argv) > 1:
        htmlist = argv[1]
    else:
        htmlist = 'htmlist'

    # Our permanent config for html cleaning
    config = Config()
    config.language = 'id'
    config.MIN_SENT_COUNT = 20
    config.memoize = False
    config.fetch_images = False
    config.verbose= True

    cleaner = Article(url='', config=config)

    with open(htmlist, 'r') as f:
        htmfile = f.read().split('\n')

    raw = []

    for htm in htmfile:
        print (htm)
        if not htm.endswith("rss.html"):
            with open(htm, 'r') as f:
                h = f.read()

            cleaner.set_html(h)
            cleaner.parse()
            sentences = nlp.split_sentences(cleaner.text)
            #raw.append(sentences])
        
            with open('htm-out', 'a') as f:
                [f.write(r + '\n') for r in sentences]

    def extract(self, item):
        """Creates an instance of Article without a Download and returns an ArticleCandidate with the results of
        parsing the HTML-Code.

        :param item: A NewscrawlerItem to parse.
        :return: ArticleCandidate containing the recovered article data.
        """
        article_candidate = ArticleCandidate()
        article_candidate.extractor = self._name()

        article = Article('')
        article.set_html(item['spider_response'].body)
        article.parse()
        article_candidate.title = article.title
        article_candidate.description = article.meta_description
        article_candidate.text = article.text
        article_candidate.topimage = article.top_image
        article_candidate.author = article.authors
        if article.publish_date is not None:
            try:
                article_candidate.publish_date = article.publish_date.strftime('%Y-%m-%d %H:%M:%S')
            except ValueError as exception:
                self.log.debug('%s: Newspaper failed to extract the date in the supported format,'
                              'Publishing date set to None' % item['url'])
        article_candidate.language = article.meta_lang

        return article_candidate

def get_article(url):
    a = Article(url)
    a.download()
    a.parse()

    article = dict()

    article['title'] = a.title
    article['publish_date'] = a.published_date
    article['authors'] = a.authors
    article['lead_image'] = a.top_image
    article['movies'] = a.movies
    article['text'] = a.text
    article['keywords'] = get_keywords(a.text)


    # This is more likely to fail.
    # try:
    #     article.nlp()
    #     article['summary'] = 'This summary is generated: \n ' + a.summary
    # except Exception:
    #     print Exception
    #     article['summary'] = a.summary

    return article

def insert_url(url):
    conn = sqlite3.connect('publico_news_sqllite3.db')
    cursor = conn.cursor()

    # get the article in plain text
    article = Article(url)
    article.download()
    article.parse()
    date = article.publish_date
    title = article.title
    text = article.text

    item = dict()
    item['datetime'] = date
    item['title'] = title
    item['text'] = text
    item['category'] = sys.argv[1].split('/')[6]
    item['link'] = sys.argv[1]
    item['origLink'] = sys.argv[1]

    print(item['category'])
    print(item['datetime'])

    if not duplicate(item, item['category'], cursor):
        status = insert_db(item, item['category'], cursor)
        if status == 1:
            print(sys.argv[1], "inserted")
        else:
            print("Error", status)
    else:
        print(url, "already in BD")

    conn.commit()
    conn.close()

def makeDocs():
    utc = pytz.utc
    es = Elasticsearch(BONSAI_URL, verify_certs= True)
    es.indices.delete(index='news', ignore=[400, 404])
    es.indices.create(index='news', ignore=400)

    print "Created"
    cnn_paper = newspaper.build(u'http://cnn.com', memoize_articles=False)
    a = defaultdict(int)
    cnn_articles = cnn_paper.articles
    print cnn_paper.size()
    for i in range(10):
        article = cnn_articles[i]
        url = article.url
        art = Article(url)
        art.download()
        art.parse()
        print art.publish_date
        print art.text
        print "Article" + str(i)
        print art.publish_date is not None
        print art.text is not None
        if (art.publish_date is not None) and (art.text is not None):
            try:
                doc = {
                'domain': 'CNN',
                'date': utc.localize(art.publish_date), 
                'text': art.text
                }
                res = es.index(index="news", doc_type='article', id=i, body=doc)
                print "Doc" + str(i)
            except:
                print "Doc not accepted"

 def test2(self):
     articles =[
      'http://www.radionz.co.nz/news/national/281869/seven-arrests-over-police-manhunt',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11491573',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11580358',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11580350',
      'http://www.stuff.co.nz/national/crime/75978990/whanganui-woman-accused-of-leaving-child-in-car-overnight.html',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11574608',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11577923',
      'http://www.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11591401',
      'http://m.nzherald.co.nz/wanganui-chronicle/news/article.cfm?c_id=1503426&objectid=11566180'
      ]
     
     articles = [
      'http://www.express.co.uk/news/uk/657926/New-Zealand-John-Key-slams-David-Cameron-Britain-forgetting-history-European-Union-EU',
      'http://www.bbc.co.uk/news/uk-wales-35954982',
      'http://www.telegraph.co.uk/news/2016/04/04/david-cameron-will-be-an-excellent-former-prime-minister/',
      'http://www.pressandjournal.co.uk/fp/news/aberdeenshire/880519/david-camerons-father-named-panamanian-company-aberdeenshire-home/',
      'http://www.theguardian.com/politics/2016/apr/01/senior-tories-brexit-vote-leave-attacks-david-cameron-letter-nhs-staff',
      'http://www.dailymail.co.uk/news/article-3519908/Nuclear-drones-threat-British-cities-Cameron-Obama-hold-war-game-session-respond-attack-kill-thousands-people.html',
      'http://www.telegraph.co.uk/news/2016/03/31/if-david-cameron-cant-stop-the-tory-fighting-hell-clear-jeremy-c/',
      'http://www.manchestereveningnews.co.uk/news/greater-manchester-news/gmp-boost-number-armed-officers-11125178',
      'http://www.theguardian.com/commentisfree/2016/apr/03/cameron-headphones-what-is-cool-what-is-not']
     
     with open("./Output2.txt", "w") as text_file:
         for url in articles:
             print(url)
             a = Article(url)
             a.download()
             a.parse()
             text_file.write(a.text.encode('utf-8'))
             text_file.write('\n')

    def runTest(self):
        # The "correct" fulltext needs to be manually checked
        # we have 50 so far
        FULLTEXT_PREPARED = 50
        domain_counters = {}

        with open(URLS_FILE, 'r') as f:
            urls = [d.strip() for d in f.readlines() if d.strip()]

        for url in urls[:FULLTEXT_PREPARED]:
            domain = get_base_domain(url)
            if domain in domain_counters:
                domain_counters[domain] += 1
            else:
                domain_counters[domain] = 1

            res_filename = domain + str(domain_counters[domain])
            html = mock_resource_with(res_filename, 'html')
            try:
                a = Article(url)
                a.download(html)
                a.parse()
            except Exception:
                print('<< URL: %s parse ERROR >>' % url)
                traceback.print_exc()
                continue

            correct_text = mock_resource_with(res_filename, 'txt')
            condensed_url = url[:30] + ' ...'
            print('%s -- fulltext status: %s' %
                  (condensed_url, a.text == correct_text))

def get_image():
  url = request.args.get('url', '')
  if not url:
    abort(400)

  if is_image(url):
    return redirect(url)

  article = Article(url)
  article.download()

  try:
    article.parse()
  except (IOError, UnicodeDecodeError):
    return '', 422

  try:
    top_image = article.top_image.rsplit('?',1)[0]
  except AttributeError:
    top_image = ''

  if not top_image == '':
    return redirect(top_image)
  else:
    return '', 422

def f(url):
	url_urls = url.text
	try:
		response = urllib2.urlopen(url_urls)
		status = response.code

		#print "detected webpage code:", status

		if(status == 404):
			pass
		else:
			a_zh = Article(url_urls, language = 'zh')
			a_zh.download()
			a_zh.parse()
			# content_urls = a_zh.text

			# if(content_urls == ''):
			# 	a_en = Article(url_urls, language = 'en')
			# 	a_en.download()
			# 	a_en.parse()
			# 	content_urls = content_urls + a_en.text

			# if(content_urls != ''):
			# 	pass
			# 	# compare_article(url_urls, content_urls)			
	except:
		pass