Skip to content

feat: make Apify integration asynchronous #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
barjin wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat: make Apify integration asynchronous #10

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7242fca
feat: make Apify integration asynchronous
barjin Dec 1, 2025
5233a54
fix: load dataset items asynchronously
barjin Dec 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions engines/apify_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
import os
try:
from apify_client import ApifyClient # type: ignore
from apify_client import ApifyClientAsync # type: ignore
except Exception: # pragma: no cover - allow discovery without the dependency installed
ApifyClient = None # type: ignore[assignment]
ApifyClientAsync = None # type: ignore[assignment]
from .base import Scraper, ScrapeResult
from dotenv import load_dotenv
import logging
Expand All @@ -18,23 +18,23 @@ class ApifyAPIScraper(Scraper):
"""
def __init__(self):
self.api_token = os.getenv("APIFY_API_TOKEN")
if ApifyClient is None:
if ApifyClientAsync is None:
# Keep import-time lightweight so discovery works; fail when actually used
raise RuntimeError("apify-client is not installed. Please `pip install apify-client`. ")
if not self.api_token:
raise RuntimeError("APIFY_API_TOKEN environment variable not set.")
self.client = ApifyClient(self.api_token)
self.client = ApifyClientAsync(self.api_token)
self.actor_id = "apify/web-scraper"

def scrape(self, url: str, run_id: str) -> ScrapeResult:
async def scrape(self, url: str, run_id: str) -> ScrapeResult:
error = None
html = ""
content_size = 0
status_code = 500
status_code = 500
try:
# Start the actor and wait for it to finish
actor_client = self.client.actor(self.actor_id)
run_result = actor_client.call(
run_result = await actor_client.call(
run_input={
"startUrls": [{"url": url}],
"maxRequestsPerCrawl": 1,
Expand All @@ -59,7 +59,7 @@ def scrape(self, url: str, run_id: str) -> ScrapeResult:
else:
dataset_id = run_result["defaultDatasetId"]
dataset_client = self.client.dataset(dataset_id)
items = dataset_client.list_items().items
items = (await dataset_client.list_items()).items
if items and "html" in items[0]:
html = items[0]["html"] or ""
status_code = items[0].get("status_code")
Expand All @@ -68,7 +68,7 @@ def scrape(self, url: str, run_id: str) -> ScrapeResult:
error = "No HTML found in Apify dataset result."
except Exception as e:
error = str(e)

return ScrapeResult(
run_id=run_id,
scraper="apify_api",
Expand All @@ -79,4 +79,4 @@ def scrape(self, url: str, run_id: str) -> ScrapeResult:
format="html",
created_at=datetime.now().isoformat(),
content=html,
)
)