Spaces:
Running
Running
Update main.py
Browse files
main.py
CHANGED
@@ -598,7 +598,8 @@ async def _run_apify_actor_for_web_content(url: str, api_token: str, actor_id: s
|
|
598 |
# --- END ADDED PROXY CONFIG ---
|
599 |
}
|
600 |
logger.debug(f"{log_prefix} Using input format for Default YT Actor ({APIFY_ACTOR_ID}) with Residential Proxy")
|
601 |
-
|
|
|
602 |
# Input specific to the Structured YT Actor β wrap your single URL in a list
|
603 |
run_input = {
|
604 |
"urls": [url], # β wrap your URL in a list
|
@@ -608,10 +609,10 @@ async def _run_apify_actor_for_web_content(url: str, api_token: str, actor_id: s
|
|
608 |
},
|
609 |
"maxRetries": 5,
|
610 |
}
|
|
|
611 |
logger.debug(f"{log_prefix} Using list input format for Structured YT Actor ({actor_id}) with Residential Proxy")
|
612 |
-
|
613 |
-
|
614 |
-
logger.debug(f"{log_prefix} Using input format for Structured YT Actor ({APIFY_STRUCTURED_YT_ACTOR_ID}) with Residential Proxy")
|
615 |
elif actor_id == APIFY_TEXT_SCRAPER_ACTOR_ID:
|
616 |
# Input specific to Text Scraper Free (2gbQiRSpJIIag2FdR) - Likely expects LIST
|
617 |
run_input = {
|
@@ -637,7 +638,7 @@ async def _run_apify_actor_for_web_content(url: str, api_token: str, actor_id: s
|
|
637 |
# Fallback default input if actor ID doesn't match known ones
|
638 |
run_input = {"urls": [url]} # <<< Default to LIST
|
639 |
logger.warning(f"{log_prefix} Unknown Actor ID '{actor_id}'. Using default input format: {run_input}")
|
640 |
-
|
641 |
|
642 |
headers = {"Content-Type": "application/json"}
|
643 |
try:
|
@@ -746,6 +747,8 @@ async def _run_apify_actor_for_web_content(url: str, api_token: str, actor_id: s
|
|
746 |
except httpx.RequestError as e: logger.error(f"{log_prefix} Request error during API interaction for {url}: {e}"); return None
|
747 |
except Exception as e: logger.error(f"{log_prefix} Unexpected error during {actor_name} call for {url}: {e}", exc_info=True); return None
|
748 |
|
|
|
|
|
749 |
|
750 |
async def get_website_content_via_apify_crawler(url: str, api_token: str) -> Optional[str]:
|
751 |
"""Fallback 4: Fetches website content using Apify Website Content Crawler."""
|
|
|
598 |
# --- END ADDED PROXY CONFIG ---
|
599 |
}
|
600 |
logger.debug(f"{log_prefix} Using input format for Default YT Actor ({APIFY_ACTOR_ID}) with Residential Proxy")
|
601 |
+
# --- CORRECTED BLOCK START (Ensure this 'elif' has same indentation as the 'if' above) ---
|
602 |
+
elif actor_id == APIFY_STRUCTURED_YT_ACTOR_ID:
|
603 |
# Input specific to the Structured YT Actor β wrap your single URL in a list
|
604 |
run_input = {
|
605 |
"urls": [url], # β wrap your URL in a list
|
|
|
609 |
},
|
610 |
"maxRetries": 5,
|
611 |
}
|
612 |
+
# Log using the actor_id variable passed into the function
|
613 |
logger.debug(f"{log_prefix} Using list input format for Structured YT Actor ({actor_id}) with Residential Proxy")
|
614 |
+
# --- END ADDED PROXY CONFIG ---
|
615 |
+
# (Extra brace and redundant logger call removed from here)
|
|
|
616 |
elif actor_id == APIFY_TEXT_SCRAPER_ACTOR_ID:
|
617 |
# Input specific to Text Scraper Free (2gbQiRSpJIIag2FdR) - Likely expects LIST
|
618 |
run_input = {
|
|
|
638 |
# Fallback default input if actor ID doesn't match known ones
|
639 |
run_input = {"urls": [url]} # <<< Default to LIST
|
640 |
logger.warning(f"{log_prefix} Unknown Actor ID '{actor_id}'. Using default input format: {run_input}")
|
641 |
+
# --- END OF if/elif/else block for run_input ---
|
642 |
|
643 |
headers = {"Content-Type": "application/json"}
|
644 |
try:
|
|
|
747 |
except httpx.RequestError as e: logger.error(f"{log_prefix} Request error during API interaction for {url}: {e}"); return None
|
748 |
except Exception as e: logger.error(f"{log_prefix} Unexpected error during {actor_name} call for {url}: {e}", exc_info=True); return None
|
749 |
|
750 |
+
# ... (Rest of your main.py code below this function) ...
|
751 |
+
|
752 |
|
753 |
async def get_website_content_via_apify_crawler(url: str, api_token: str) -> Optional[str]:
|
754 |
"""Fallback 4: Fetches website content using Apify Website Content Crawler."""
|