def test_convert_to_dict_most_fields_works():
faker = Faker()
source = Article(url=faker.url())
source.authors = [faker.name(), faker.name()]
source.top_image = faker.image_url()
source.article_html = faker.text()
source.images = [faker.image_url(), faker.image_url()]
source.meta_data = [faker.city(), faker.state(), faker.country()]
result = extractor.to_dict(source, "article_html", "authors", "images",
"keywords", "meta_data", "source_url",
"summary", "top_image", "url", "tags",
"meta_favicon")
assert result
assert len(result) == 7
assert "article_html" in result
assert "authors" in result
assert "images" in result
assert "keywords" not in result
assert "meta_data" in result
assert "source_url" in result
assert "summary" not in result
assert "top_image" in result
assert "url" in result
assert "tags" not in result
assert "meta_favicon" not in result
def build_news_article_from_url(source_url, sNLP):
"""build new article object from source url, if build fail would return None
"""
try:
print('start to scrape from url: ', source_url)
# pre-process news by NewsPaper3k and Boilerpipe library
article = Article(source_url, keep_article_html=True)
article.build()
article.nlp()
e = Extractor(extractor='DefaultExtractor', html=article.html)
article.text = e.getText()
article.article_html = e.getHTML()
news_article = NewsArticle(article, sNLP)
print('success to scrape from url: ', source_url)
return news_article
except Exception as e:
print('fail to scrape from url: ', source_url)
print('reason:', e)
return None
#parse
#title and
try:
article = Article(url, language='de', keep_article_html=True)
article.download()
article.parse()
filename = feed[3] + ''.join(
random.choices(string.ascii_uppercase + string.digits,
k=8))
file = open("html/" + filename + ".html", "w")
article.article_html = "<meta property='baseurl' content='" + feed[
4] + "'>" + article.article_html
article.article_html = "<script src='https://ajax.googleapis.com/ajax/libs/jquery/3.2.1/jquery.min.js'></script>" + article.article_html
article.article_html = "<link href='https://fonts.googleapis.com/css?family=Slabo+27px' rel='stylesheet'>" + article.article_html
article.article_html = "<img src='" + article.top_image + "' width='100%' >" + article.article_html
article.article_html = "<h1 class='realTitle'>" + entrie.title + "</h1>" + article.article_html
article.article_html = article.article_html + "<link type='text/css' rel='stylesheet' href='../css/renderStyles.css'/>"
article.article_html = article.article_html + "<script src='../js/renderScript.js'></script>"
article.article_html = "<div class='pr0news pr0-text text-orange " + feed[
3] + "'>" + article.article_html + "</div>"
file.write(article.article_html)
file.close()
if article.title != entrie.title:
print(
str(len(article.title)) + " || " +
