add examples

Author: VinciGit00

examples/gemini/xml_scraper_gemini.py

@@ -0,0 +1,57 @@
+"""
+Basic example of scraping pipeline using XMLScraperGraph from XML documents
+"""
+
+import os
+from dotenv import load_dotenv
+from scrapegraphai.graphs import XMLScraperGraph
+from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
+load_dotenv()
+
+# ************************************************
+# Read the XML file
+# ************************************************
+
+FILE_NAME = "inputs/books.xml"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+with open(file_path, 'r', encoding="utf-8") as file:
+    text = file.read()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+gemini_key = os.getenv("GOOGLE_APIKEY")
+
+graph_config = {
+    "llm": {
+        "api_key": gemini_key,
+        "model": "gemini-pro",
+    },
+}
+# ************************************************
+# Create the XMLScraperGraph instance and run it
+# ************************************************
+
+xml_scraper_graph = XMLScraperGraph(
+    prompt="List me all the authors, title and genres of the books",
+    source=text,  # Pass the content of the file, not the file object
+    config=graph_config
+)
+
+result = xml_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = xml_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+
+# Save to json or csv
+convert_to_csv(result, "result")
+convert_to_json(result, "result")
+

examples/oneapi/smart_scraper_oneapi.py

@@ -0,0 +1,38 @@
+""" 
+Basic example of scraping pipeline using SmartScraper
+"""
+from scrapegraphai.graphs import SmartScraperGraph
+from scrapegraphai.utils import prettify_exec_info
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+
+graph_config = {
+    "llm": {
+        "api_key": "***************************",
+        "model": "oneapi/qwen-turbo",
+        "base_url": "http://127.0.0.1:3000/v1",  # 设置 OneAPI URL
+    }
+}
+
+# ************************************************
+# Create the SmartScraperGraph instance and run it
+# ************************************************
+
+smart_scraper_graph = SmartScraperGraph(
+    prompt="List me all the titles",
+    # also accepts a string with the already downloaded HTML code
+    source="https://www.wired.com/",
+    config=graph_config
+)
+
+result = smart_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = smart_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))