Last active
October 5, 2021 12:43
-
-
Save dnkls/5c40b5d7bbf05d35ce650d8236f10f83 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
articles = [] | |
for feed in feeds: | |
response = requests.get(feed, headers=headers) | |
webpage = response.content | |
soup = BeautifulSoup(webpage, features="xml") | |
# every article link will be found in an item tag | |
items = soup.find_all("item", text = re.findall(keywords)) | |
for kewords in items.find_all(words) | |
word = items.find_all(text: keywords ) | |
# extract the link | |
for item in word: | |
link = item.find("link").text | |
articles.append(link) | |
news_dict = {} | |
for url in articles: # Вот тут из списка articles сверху мы достаем линки/url и они спускаются вниз для дальнейшей | |
# обработки и добавления в словарь со значениями title,url, description итд не суть... | |
# каким образом в этом месте сделать цикл так чтобы он доставал линки по одному в течении опред | |
# времени в стуки пару раз. 🤷🏻♂️ | |
info = Article(url) | |
info.download() | |
info.parse() | |
info.nlp() | |
article_url = info.url | |
article_title = info.title | |
keywords = info.keywords | |
text = info.text | |
article_sum = summarize(text, ratio=0.2) | |
article_id = info.link_hash | |
tikers = ['tsla','ko','apple','abbv','pltr'] | |
for word in tikers: | |
if word in keywords or text: | |
news_dict[article_id] = { | |
"article_title": article_title, | |
"article_url": article_url, | |
"article_summary": article_sum, | |
"article_keyword" : keywords | |
} | |
else: | |
continue |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment