adding multiple urls

This commit is contained in:
2023-12-20 15:21:30 +01:00
parent 3359cc1ca9
commit 18c8fdee7d

View File

@@ -5,40 +5,28 @@ from bs4 import BeautifulSoup
os.environ["OPENAI_API_KEY"] = "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"
client = OpenAI()
from openai import OpenAI
client = OpenAI()
url = 'https://srpskainfo.com/tuzilastvo-ih-tek-jutros-obavijestilo-da-istrazuje-debeveca-disciplinski-tuzilac-vsts-trazi-suspenziju-predsjednika-suda-bih/'
urls = ['https://klix.ba/', 'https://srpskainfo.com/', 'https://bljesak.info/']
response = requests.get(url)
html = response.text
for url in urls:
response = requests.get(url)
html = response.text
soup = BeautifulSoup(html, 'html.parser')
tags = soup.find_all(['h2', 'p'])
soup = BeautifulSoup(html, 'html.parser')
onlyText = ' '.join(filter(None, [text.strip() for text in soup.stripped_strings]))
prompt_text = ''
for tag in tags:
text = tag.get_text(strip=True)
prompt_text = prompt_text + text
def takeDataFrom(url):
try:
response = requests.get(url)
response.raise_for_status()
data = response.text
print(f"Here:{data}")
return data
except Exception as e:
print(f"Error! :{e}")
return None
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "Data analytic"},
{"role": "user", "content": f"Extract for me title and full text from :{onlyText},make it clear for reading"}
]
)
print(completion.choices[0].message.content)
completion = client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "system", "content": "Data analytic, Journalist and News reporter"},
{"role": "user", "content": f"Extract for me evry title and full content for evry title from {prompt_text},without shortening,remove all thing that are not connected to news, make it clear for reading"}
]
)
generated_text = completion.choices[0].message.content
print(f"Text for {url}: \n {generated_text}\n")