wehub-resource-sync
48 lines
1.3 KiB
Python
48 lines
1.3 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": {
|
|
"api_key": "API_KEY",
|
|
"model": "openai/gpt-3.5-turbo",
|
|
},
|
|
"loader_kwargs": {
|
|
"proxy": {
|
|
"server": "http:/**********",
|
|
"username": "********",
|
|
"password": "***",
|
|
},
|
|
},
|
|
"verbose": True,
|
|
"headless": False,
|
|
}
|
|
|
|
# ************************************************
|
|
# Create the SmartScraperGraph instance and run it
|
|
# ************************************************
|
|
|
|
smart_scraper_graph = SmartScraperGraph(
|
|
prompt="List me all the projects with their description",
|
|
# also accepts a string with the already downloaded HTML code
|
|
source="https://perinim.github.io/projects/",
|
|
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))
|