my-fix-branch
Shane 7 months ago
parent 6376129827
commit c1dd68d832
  1. 28
      foodie_utils.py

@ -1032,11 +1032,11 @@ def get_flickr_image(search_query, relevance_keywords):
flickr_request_count += 1
logging.info(f"Flickr request count: {flickr_request_count}/3600")
# Enforce a minimum delay of 1 second between Flickr requests
# Enforce a minimum delay of 5 seconds between Flickr requests
current_time = time.time()
time_since_last_request = current_time - last_flickr_request_time
if time_since_last_request < 1:
time.sleep(1 - time_since_last_request)
if time_since_last_request < 5:
time.sleep(5 - time_since_last_request)
last_flickr_request_time = time.time()
@ -1085,8 +1085,19 @@ def get_flickr_image(search_query, relevance_keywords):
temp_file = None
try:
img_response = requests.get(img_url, headers=headers, timeout=10)
img_response.raise_for_status()
for attempt in range(3):
img_response = requests.get(img_url, headers=headers, timeout=10)
if img_response.status_code == 429:
wait_time = 5 * (2 ** attempt)
logging.warning(f"Rate limit hit for {img_url}. Retrying after {wait_time}s (attempt {attempt+1}/3).")
time.sleep(wait_time)
continue
img_response.raise_for_status()
break
else:
logging.warning(f"Rate limit hit for {img_url} after retries. Falling back to Pixabay.")
return None
with tempfile.NamedTemporaryFile(delete=False, suffix='.jpg') as temp_file:
temp_file.write(img_response.content)
temp_path = temp_file.name
@ -1126,7 +1137,7 @@ def get_flickr_image(search_query, relevance_keywords):
except requests.exceptions.HTTPError as e:
if e.response.status_code == 429:
logging.warning(f"Rate limit hit for {img_url}. Falling back to Pixabay.")
logging.warning(f"Rate limit hit for {img_url} after retries. Falling back to Pixabay.")
return None
else:
logging.warning(f"Download failed for {img_url}: {e}")
@ -1148,15 +1159,14 @@ def get_flickr_image(search_query, relevance_keywords):
soup = BeautifulSoup(response.text, 'html.parser')
photo_ids = set()
# Look for Flickr URLs in the search results
for link in soup.find_all('a', href=True):
href = link['href']
# Match Flickr photo URLs like https://www.flickr.com/photos/username/1234567890
match = re.search(r'flickr\.com/photos/[^/]+/(\d+)', href)
if match:
photo_id = match.group(1)
photo_ids.add(photo_id)
photo_ids = list(photo_ids)[:5] # Limit to 5 IDs
logging.info(f"Found {len(photo_ids)} Flickr photo IDs via DDG: {photo_ids}")
return photo_ids
except Exception as e:
@ -1173,7 +1183,7 @@ def get_flickr_image(search_query, relevance_keywords):
"```json\n"
"{\n"
" \"Wingstop\": \"specific\",\n"
" \"dining\": \"generic\"\n"
" " \"dining\": \"generic\"\n"
"}\n```"
)
try:

Loading…
Cancel
Save