scrape_async with proxy and js support

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "vl-apify-shared"
-version = "0.1.1"
+version = "0.1.2"
 description = "Shared utility package for use with Apify actors"
 authors = [{ name = "Ryan Byrne", email = "ryanjbyrne30@gmail.com" }]
 requires-python = ">=3.12"

src/vl_apify_shared/zenrows.py

@@ -1,7 +1,8 @@
 import json
 import time
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from typing import Optional
+
 from vl_apify_shared.logger import Logger
 from zenrows import ZenRowsClient
 
@@ -12,6 +13,28 @@ class ZenRowsConfig:
     api_key: str
 
 
+def _build_params(
+    *,
+    js_render: bool = False,
+    wait: Optional[int] = None,
+    wait_for: Optional[str] = None,
+    premium_proxy: bool = False,
+    js_instructions: Optional[list] = None,
+) -> dict:
+    params: dict = {}
+    if js_render:
+        params["js_render"] = "true"
+    if premium_proxy:
+        params["premium_proxy"] = "true"
+    if wait is not None:
+        params["wait"] = str(wait)
+    if wait_for is not None:
+        params["wait_for"] = wait_for
+    if js_instructions is not None:
+        params["js_instructions"] = json.dumps(js_instructions)
+    return params
+
+
 class ZenRowsScraper:
     def __init__(self, config: ZenRowsConfig):
         self.client = ZenRowsClient(config.api_key)
@@ -37,17 +60,13 @@ class ZenRowsScraper:
             js_instructions: list of ZenRows instruction dicts (evaluate, wait_for, click, etc.)
         """
         self.logger.debug(f"ZenRows scraping url: {url}...")
-        params: dict = {}
-        if js_render:
-            params["js_render"] = "true"
-        if premium_proxy:
-            params["premium_proxy"] = "true"
-        if wait is not None:
-            params["wait"] = str(wait)
-        if wait_for is not None:
-            params["wait_for"] = wait_for
-        if js_instructions is not None:
-            params["js_instructions"] = json.dumps(js_instructions)
+        params = _build_params(
+            js_render=js_render,
+            wait=wait,
+            wait_for=wait_for,
+            premium_proxy=premium_proxy,
+            js_instructions=js_instructions,
+        )
         start = time.monotonic()
         response = self.client.get(url, params=params)
         elapsed_time = round((time.monotonic() - start) * 1000)
@@ -56,17 +75,33 @@ class ZenRowsScraper:
         )
         return response
 
-    async def scrape_async(self, url: str, premium_proxy: bool = False):
-        """Fetch a URL asynchronously through ZenRows as a plain proxy (no JS rendering).
+    async def scrape_async(
+        self,
+        url: str,
+        js_render: bool = False,
+        wait: Optional[int] = None,
+        wait_for: Optional[str] = None,
+        premium_proxy: bool = False,
+        js_instructions: Optional[list] = None,
+    ):
+        """Fetch a URL asynchronously through ZenRows.
 
         Args
             url: URL to fetch
+            js_render: whether to wait for JavaScript to execute
+            wait: milliseconds to wait after page load
+            wait_for: css selector to wait for
             premium_proxy: use residential proxy (ZenRows premium_proxy=true)
+            js_instructions: list of ZenRows instruction dicts (evaluate, wait_for, click, etc.)
         """
         self.logger.debug(f"ZenRows fetching url: {url}...")
-        params: dict = {}
-        if premium_proxy:
-            params["premium_proxy"] = "true"
+        params = _build_params(
+            js_render=js_render,
+            wait=wait,
+            wait_for=wait_for,
+            premium_proxy=premium_proxy,
+            js_instructions=js_instructions,
+        )
         start = time.monotonic()
         response = await self.client.get_async(url, params=params)
         elapsed_time = round((time.monotonic() - start) * 1000)