Firecrawl /interact: multi-step navigation against a Hugging Face model page

dashboard.py

"""A multi-step navigation flow against a Hugging Face model page.

The shape: one scrape opens the live session on the model card. Two further
interact calls reuse that session to navigate to the Files tab and the Community
tab and pull data each tab renders. The browser is the same browser across all
three calls — page state and history carry over.

Target: Qwen/Qwen2.5-7B-Instruct (popular, public, no gate).
"""

import os

from dotenv import load_dotenv
from firecrawl import Firecrawl

load_dotenv()
app = Firecrawl(api_key=os.getenv("FIRECRAWL_API_KEY"))

result = app.scrape(
    "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct",
    formats=["markdown"],
)
scrape_id = result.metadata.scrape_id
print(f"scrape_id={scrape_id}\n")


# 1. Click into the Files tab and list the top files with their sizes.
files = app.interact(
    scrape_id,
    prompt=(
        "Click the 'Files' tab in the model navigation. Once the file list "
        "renders, return the names and sizes of the top 5 files at the repo "
        "root as a JSON list."
    ),
)
print("Files tab:")
print(files.output)


# 2. Reuse the same session: navigate to the Community tab.
community = app.interact(
    scrape_id,
    prompt=(
        "Click the 'Community' tab. Once the discussion list renders, return "
        "the titles and reply counts of the top 3 discussion threads as a JSON list."
    ),
)
print("\nCommunity tab:")
print(community.output)


app.stop_interaction(scrape_id)