Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -13,12 +13,12 @@ openai_api_key = os.getenv("OPENAI_API_KEY")
|
|
13 |
def scrape_content(url):
|
14 |
response = requests.get(url)
|
15 |
soup = BeautifulSoup(response.content, 'html.parser')
|
16 |
-
|
17 |
# Example of extracting title and body content - modify based on actual structure of the websites
|
18 |
title = soup.find('title').get_text()
|
19 |
paragraphs = soup.find_all('p')
|
20 |
content = '\n'.join([para.get_text() for para in paragraphs])
|
21 |
-
|
22 |
return title, content
|
23 |
|
24 |
# Function to create newsletter using OpenAI
|
@@ -38,22 +38,22 @@ def create_newsletter(contents):
|
|
38 |
],
|
39 |
max_tokens=1500
|
40 |
)
|
41 |
-
|
42 |
newsletter = response.choices[0].message['content'].strip()
|
43 |
return newsletter
|
44 |
|
45 |
# Function to process URLs and generate the newsletter
|
46 |
def process_urls(url1, url2, url3, url4, url5):
|
47 |
urls = [url for url in [url1, url2, url3, url4, url5] if url]
|
48 |
-
|
49 |
if not urls:
|
50 |
return "No URLs provided."
|
51 |
-
|
52 |
contents = []
|
53 |
for url in urls:
|
54 |
title, content = scrape_content(url)
|
55 |
contents.append((title, content, url))
|
56 |
-
|
57 |
newsletter = create_newsletter(contents)
|
58 |
return newsletter
|
59 |
|
|
|
13 |
def scrape_content(url):
|
14 |
response = requests.get(url)
|
15 |
soup = BeautifulSoup(response.content, 'html.parser')
|
16 |
+
|
17 |
# Example of extracting title and body content - modify based on actual structure of the websites
|
18 |
title = soup.find('title').get_text()
|
19 |
paragraphs = soup.find_all('p')
|
20 |
content = '\n'.join([para.get_text() for para in paragraphs])
|
21 |
+
|
22 |
return title, content
|
23 |
|
24 |
# Function to create newsletter using OpenAI
|
|
|
38 |
],
|
39 |
max_tokens=1500
|
40 |
)
|
41 |
+
|
42 |
newsletter = response.choices[0].message['content'].strip()
|
43 |
return newsletter
|
44 |
|
45 |
# Function to process URLs and generate the newsletter
|
46 |
def process_urls(url1, url2, url3, url4, url5):
|
47 |
urls = [url for url in [url1, url2, url3, url4, url5] if url]
|
48 |
+
|
49 |
if not urls:
|
50 |
return "No URLs provided."
|
51 |
+
|
52 |
contents = []
|
53 |
for url in urls:
|
54 |
title, content = scrape_content(url)
|
55 |
contents.append((title, content, url))
|
56 |
+
|
57 |
newsletter = create_newsletter(contents)
|
58 |
return newsletter
|
59 |
|