Merge branch 'api-integration' into pre/beta

examples/scrapegraph-api/smart_scraper_api.py

@@ -0,0 +1,44 @@
+""" 
+Basic example of scraping pipeline using SmartScraper
+"""
+import os
+import json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import SmartScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+
+load_dotenv()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+
+graph_config = {
+    "llm": {
+        "model": "scrapegraphai/smart-scraper",
+        "api_key": os.getenv("SCRAPEGRAPH_API_KEY")
+    },
+    "verbose": True,
+    "headless": False,
+}
+
+# ************************************************
+# Create the SmartScraperGraph instance and run it
+# ************************************************
+
+smart_scraper_graph = SmartScraperGraph(
+    prompt="Extract me all the articles",
+    source="https://www.wired.com",
+    config=graph_config
+)
+
+result = smart_scraper_graph.run()
+print(json.dumps(result, indent=4))
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = smart_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))

pyproject.toml

@@ -43,7 +43,8 @@ dependencies = [
     "transformers>=4.44.2",
     "googlesearch-python>=1.2.5",
     "simpleeval>=1.0.0",
-    "async_timeout>=4.0.3"
+    "async_timeout>=4.0.3",
+    "scrapegraph-py>=0.0.4"
 ]
 
 license = "MIT"