mirror of
https://github.com/VinciGit00/Scrapegraph-ai.git
synced 2026-07-01 21:00:48 +08:00
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
"""
|
|
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": {
|
|
"model": "ollama/mistral",
|
|
"temperature": 0,
|
|
"format": "json", # Ollama needs the format to be specified explicitly
|
|
# "base_url": "http://localhost:11434", # set ollama URL arbitrarily
|
|
},
|
|
"embeddings": {
|
|
"model": "ollama/nomic-embed-text",
|
|
"temperature": 0,
|
|
# "base_url": "http://localhost:11434", # set ollama URL arbitrarily
|
|
},
|
|
"loader_kwargs": {
|
|
"slow_mo": 10000
|
|
},
|
|
"verbose": True,
|
|
"headless": False
|
|
}
|
|
|
|
# ************************************************
|
|
# 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)) |