limits the number of links that a webpage can return.
parent
d78613e558
commit
23f19a8611
|
@ -34,7 +34,7 @@ def format_hyperlinks(hyperlinks):
|
|||
formatted_links = []
|
||||
for link_text, link_url in hyperlinks:
|
||||
formatted_links.append(f"{link_text} ({link_url})")
|
||||
return '\n'.join(formatted_links)
|
||||
return formatted_links
|
||||
|
||||
def scrape_links(url):
|
||||
response = requests.get(url)
|
||||
|
@ -49,14 +49,8 @@ def scrape_links(url):
|
|||
script.extract()
|
||||
|
||||
hyperlinks = extract_hyperlinks(soup)
|
||||
|
||||
text = soup.get_text()
|
||||
lines = (line.strip() for line in text.splitlines())
|
||||
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
|
||||
text = '\n'.join(chunk for chunk in chunks if chunk)
|
||||
text = format_hyperlinks(hyperlinks)
|
||||
|
||||
return text
|
||||
|
||||
return format_hyperlinks(hyperlinks)
|
||||
|
||||
def split_text(text, max_length=8192):
|
||||
paragraphs = text.split("\n")
|
||||
|
|
|
@ -80,6 +80,10 @@ def browse_website(url):
|
|||
summary = get_text_summary(url)
|
||||
links = get_hyperlinks(url)
|
||||
|
||||
# Limit links to 5
|
||||
if len(links) > 5:
|
||||
links = links[:5]
|
||||
|
||||
result = f"""Website Content Summary: {summary}\n\nLinks: {links}"""
|
||||
|
||||
return result
|
||||
|
@ -90,8 +94,8 @@ def get_text_summary(url):
|
|||
return """ "Result" : """ + summary
|
||||
|
||||
def get_hyperlinks(url):
|
||||
text = browse.scrape_links(url)
|
||||
return text
|
||||
link_list = browse.scrape_links(url)
|
||||
return link_list
|
||||
|
||||
def check_news(source):
|
||||
print("Checking news from BBC world instead of " + source)
|
||||
|
|
Loading…
Reference in New Issue