Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -167,14 +167,19 @@ def google_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_
|
|
167 |
print(f"Total results fetched: {len(all_results)}")
|
168 |
return all_results
|
169 |
|
170 |
-
def google_news_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_verify=None):
|
171 |
print(f"Searching Google News for term: {term}")
|
172 |
|
173 |
-
#
|
174 |
-
|
|
|
175 |
|
176 |
-
#
|
177 |
-
|
|
|
|
|
|
|
|
|
178 |
|
179 |
escaped_term = urllib.parse.quote_plus(search_term)
|
180 |
start = 0
|
@@ -513,16 +518,20 @@ def save_text_to_pdf(text, output_path):
|
|
513 |
print("PDF saved successfully.")
|
514 |
|
515 |
# Integrated function to perform web scraping, formatting, and text generation
|
516 |
-
def scrape_and_display(query, num_results, instructions, web_search=True, use_news=False, temperature=0.7, repetition_penalty=1.0, top_p=0.9):
|
517 |
print(f"Scraping and displaying results for query: {query} with num_results: {num_results}")
|
518 |
if web_search:
|
|
|
|
|
|
|
|
|
519 |
if use_news:
|
520 |
-
|
|
|
|
|
521 |
else:
|
522 |
-
|
523 |
-
|
524 |
-
days_in_year = 365 if current_year % 4 != 0 else 366 # Account for leap years
|
525 |
-
search_results = google_search(query, num_results=num_results, instructions=instructions, days_back=days_in_year)
|
526 |
|
527 |
# Summarize each result
|
528 |
summarized_results = []
|
|
|
167 |
print(f"Total results fetched: {len(all_results)}")
|
168 |
return all_results
|
169 |
|
170 |
+
def google_news_search(term, num_results=5, lang="en", timeout=5, safe="active", ssl_verify=None, days_back=30):
|
171 |
print(f"Searching Google News for term: {term}")
|
172 |
|
173 |
+
# Calculate the date range
|
174 |
+
end_date = datetime.now()
|
175 |
+
start_date = end_date - timedelta(days=days_back)
|
176 |
|
177 |
+
# Format dates as strings
|
178 |
+
start_date_str = start_date.strftime("%Y-%m-%d")
|
179 |
+
end_date_str = end_date.strftime("%Y-%m-%d")
|
180 |
+
|
181 |
+
# Add the date range to the search term
|
182 |
+
search_term = f"{term} after:{start_date_str} before:{end_date_str}"
|
183 |
|
184 |
escaped_term = urllib.parse.quote_plus(search_term)
|
185 |
start = 0
|
|
|
518 |
print("PDF saved successfully.")
|
519 |
|
520 |
# Integrated function to perform web scraping, formatting, and text generation
|
521 |
+
def scrape_and_display(query, num_results, instructions, web_search=True, use_news=False, days_back=None, temperature=0.7, repetition_penalty=1.0, top_p=0.9):
|
522 |
print(f"Scraping and displaying results for query: {query} with num_results: {num_results}")
|
523 |
if web_search:
|
524 |
+
if days_back is None:
|
525 |
+
current_year = datetime.now().year
|
526 |
+
days_back = 365 if current_year % 4 != 0 else 366 # Account for leap years
|
527 |
+
|
528 |
if use_news:
|
529 |
+
# For news, we might want to use a shorter time frame by default
|
530 |
+
news_days_back = min(days_back, 30) # Use at most 30 days for news
|
531 |
+
search_results = google_news_search(query, num_results, days_back=news_days_back)
|
532 |
else:
|
533 |
+
search_results = google_search(query, num_results=num_results, instructions=instructions, days_back=days_back)
|
534 |
+
|
|
|
|
|
535 |
|
536 |
# Summarize each result
|
537 |
summarized_results = []
|