feat: add api integration

Author: VinciGit00

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>=0.0.3"
 ]
 
 license = "MIT"

requirements-dev.lock

@@ -353,7 +353,7 @@ pyasn1==0.6.0
     # via rsa
 pyasn1-modules==0.4.0
     # via google-auth
-pydantic==2.8.2
+pydantic==2.10.1
     # via burr
     # via fastapi
     # via fastapi-pagination
@@ -368,7 +368,8 @@ pydantic==2.8.2
     # via openai
     # via pydantic-settings
     # via qdrant-client
-pydantic-core==2.20.1
+    # via scrapegraph-py
+pydantic-core==2.27.1
     # via pydantic
 pydantic-settings==2.5.2
     # via langchain-community
@@ -396,6 +397,7 @@ python-dateutil==2.9.0.post0
     # via pandas
 python-dotenv==1.0.1
     # via pydantic-settings
+    # via scrapegraph-py
     # via scrapegraphai
 pytz==2024.1
     # via pandas
@@ -424,6 +426,7 @@ requests==2.32.3
     # via langchain-community
     # via langsmith
     # via mistral-common
+    # via scrapegraph-py
     # via sphinx
     # via streamlit
     # via tiktoken
@@ -439,6 +442,8 @@ s3transfer==0.10.2
     # via boto3
 safetensors==0.4.5
     # via transformers
+scrapegraph-py==0.0.3
+    # via scrapegraphai
 semchunk==2.2.0
     # via scrapegraphai
 sentencepiece==0.2.0

requirements.lock

@@ -257,7 +257,7 @@ pyasn1==0.6.0
     # via rsa
 pyasn1-modules==0.4.0
     # via google-auth
-pydantic==2.8.2
+pydantic==2.10.1
     # via google-generativeai
     # via langchain
     # via langchain-aws
@@ -269,7 +269,8 @@ pydantic==2.8.2
     # via openai
     # via pydantic-settings
     # via qdrant-client
-pydantic-core==2.20.1
+    # via scrapegraph-py
+pydantic-core==2.27.1
     # via pydantic
 pydantic-settings==2.5.2
     # via langchain-community
@@ -286,6 +287,7 @@ python-dateutil==2.9.0.post0
     # via pandas
 python-dotenv==1.0.1
     # via pydantic-settings
+    # via scrapegraph-py
     # via scrapegraphai
 pytz==2024.1
     # via pandas
@@ -313,6 +315,7 @@ requests==2.32.3
     # via langchain-community
     # via langsmith
     # via mistral-common
+    # via scrapegraph-py
     # via tiktoken
     # via transformers
 rpds-py==0.20.0
@@ -324,6 +327,8 @@ s3transfer==0.10.2
     # via boto3
 safetensors==0.4.5
     # via transformers
+scrapegraph-py==0.0.3
+    # via scrapegraphai
 semchunk==2.2.0
     # via scrapegraphai
 sentencepiece==0.2.0

scrapegraphai/graphs/smart_scraper_graph.py

@@ -13,6 +13,7 @@
     ConditionalNode
 )
 from ..prompts import REGEN_ADDITIONAL_INFO
+from scrapegraph_py import ScrapeGraphClient, smart_scraper
 
 class SmartScraperGraph(AbstractGraph):
     """
@@ -59,6 +60,11 @@ def _create_graph(self) -> BaseGraph:
         Returns:
             BaseGraph: A graph instance representing the web scraping workflow.
         """
+        if self.llm_model == "scrapegraphai/smart-scraper":
+            client = ScrapeGraphClient(self.config.get("api_key"))
+
+            result = smart_scraper(client, self.source, self.prompt)
+            return result
 
         fetch_node = FetchNode(
             input="url| local_dir",