├── README.md ├── requirements.txt ├── LICENSE ├── .gitignore └── app.py /README.md: -------------------------------------------------------------------------------- 1 | # crawler-demo 2 | Firecrawl based web crawler 3 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | streamlit==1.28.1 2 | requests==2.31.0 3 | python-dotenv==1.0.0 4 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2025 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[codz] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py.cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # UV 98 | # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | #uv.lock 102 | 103 | # poetry 104 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 105 | # This is especially recommended for binary packages to ensure reproducibility, and is more 106 | # commonly ignored for libraries. 107 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 108 | #poetry.lock 109 | #poetry.toml 110 | 111 | # pdm 112 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 113 | # pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python. 114 | # https://pdm-project.org/en/latest/usage/project/#working-with-version-control 115 | #pdm.lock 116 | #pdm.toml 117 | .pdm-python 118 | .pdm-build/ 119 | 120 | # pixi 121 | # Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control. 122 | #pixi.lock 123 | # Pixi creates a virtual environment in the .pixi directory, just like venv module creates one 124 | # in the .venv directory. It is recommended not to include this directory in version control. 125 | .pixi 126 | 127 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 128 | __pypackages__/ 129 | 130 | # Celery stuff 131 | celerybeat-schedule 132 | celerybeat.pid 133 | 134 | # SageMath parsed files 135 | *.sage.py 136 | 137 | # Environments 138 | .env 139 | .envrc 140 | .venv 141 | env/ 142 | venv/ 143 | ENV/ 144 | env.bak/ 145 | venv.bak/ 146 | 147 | # Spyder project settings 148 | .spyderproject 149 | .spyproject 150 | 151 | # Rope project settings 152 | .ropeproject 153 | 154 | # mkdocs documentation 155 | /site 156 | 157 | # mypy 158 | .mypy_cache/ 159 | .dmypy.json 160 | dmypy.json 161 | 162 | # Pyre type checker 163 | .pyre/ 164 | 165 | # pytype static type analyzer 166 | .pytype/ 167 | 168 | # Cython debug symbols 169 | cython_debug/ 170 | 171 | # PyCharm 172 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 173 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 174 | # and can be added to the global gitignore or merged into this file. For a more nuclear 175 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 176 | #.idea/ 177 | 178 | # Abstra 179 | # Abstra is an AI-powered process automation framework. 180 | # Ignore directories containing user credentials, local state, and settings. 181 | # Learn more at https://abstra.io/docs 182 | .abstra/ 183 | 184 | # Visual Studio Code 185 | # Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 186 | # that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore 187 | # and can be added to the global gitignore or merged into this file. However, if you prefer, 188 | # you could uncomment the following to ignore the entire vscode folder 189 | # .vscode/ 190 | 191 | # Ruff stuff: 192 | .ruff_cache/ 193 | 194 | # PyPI configuration file 195 | .pypirc 196 | 197 | # Cursor 198 | # Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to 199 | # exclude from AI features like autocomplete and code analysis. Recommended for sensitive data 200 | # refer to https://docs.cursor.com/context/ignore-files 201 | .cursorignore 202 | .cursorindexingignore 203 | 204 | # Marimo 205 | marimo/_static/ 206 | marimo/_lsp/ 207 | __marimo__/ 208 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import requests 3 | import os 4 | from dotenv import load_dotenv 5 | import time 6 | 7 | # Load environment variables 8 | load_dotenv() 9 | 10 | st.title("🕷️ Web Crawler with Firecrawl") 11 | st.write("Enter a URL to crawl and extract content using Firecrawl API") 12 | 13 | # Input for URL 14 | url_to_crawl = st.text_input("Enter URL to crawl:", placeholder="https://example.com") 15 | 16 | # Crawl options 17 | col1, col2 = st.columns(2) 18 | with col1: 19 | limit = st.number_input("Limit pages", min_value=1, max_value=50, value=10) 20 | crawl_entire_domain = st.checkbox("Crawl entire domain", value=False) 21 | 22 | with col2: 23 | include_sitemap = st.checkbox("Include sitemap", value=True) 24 | only_main_content = st.checkbox("Only main content", value=False) 25 | 26 | # Crawl button 27 | if st.button("🚀 Start Crawling", type="primary"): 28 | if not url_to_crawl: 29 | st.error("Please enter a URL to crawl") 30 | else: 31 | # Get API key from environment 32 | api_key = os.getenv("FIRECRAWL_API_KEY") 33 | if not api_key: 34 | st.error("FIRECRAWL_API_KEY not found in environment variables") 35 | st.stop() 36 | 37 | # Prepare the payload 38 | payload = { 39 | "url": url_to_crawl, 40 | "sitemap": "include" if include_sitemap else "exclude", 41 | "crawlEntireDomain": crawl_entire_domain, 42 | "limit": limit, 43 | "scrapeOptions": { 44 | "onlyMainContent": only_main_content, 45 | "maxAge": 172800000, 46 | "parsers": ["pdf"], 47 | "formats": ["markdown"] 48 | } 49 | } 50 | 51 | headers = { 52 | "Authorization": f"Bearer {api_key}", 53 | "Content-Type": "application/json" 54 | } 55 | 56 | # Show loading spinner 57 | with st.spinner("🔄 Starting crawl job... This may take a few minutes."): 58 | try: 59 | # Make the initial API request to start crawling 60 | response = requests.post( 61 | "https://api.firecrawl.dev/v2/crawl", 62 | json=payload, 63 | headers=headers, 64 | timeout=60 65 | ) 66 | 67 | if response.status_code == 200: 68 | result = response.json() 69 | 70 | if "id" in result: 71 | crawl_id = result["id"] 72 | st.info(f"🆔 Crawl job started with ID: {crawl_id}") 73 | 74 | # Poll for results 75 | with st.spinner("🔄 Waiting for crawl to complete... This may take several minutes."): 76 | max_attempts = 60 # Maximum 10 minutes (60 * 10 seconds) 77 | attempt = 0 78 | 79 | while attempt < max_attempts: 80 | # Check crawl status 81 | status_response = requests.get( 82 | f"https://api.firecrawl.dev/v2/crawl/{crawl_id}", 83 | headers=headers, 84 | timeout=30 85 | ) 86 | 87 | if status_response.status_code == 200: 88 | status_result = status_response.json() 89 | 90 | # Check if crawl is completed 91 | if status_result.get("status") == "completed": 92 | st.success("✅ Crawling completed successfully!") 93 | 94 | # Display the results 95 | st.subheader("📄 Crawl Results") 96 | 97 | # Show raw JSON response in expandable section 98 | with st.expander("View Raw Response"): 99 | st.json(status_result) 100 | 101 | # Display formatted results if data is available 102 | if "data" in status_result and status_result["data"]: 103 | st.subheader("📋 Extracted Content") 104 | for i, page in enumerate(status_result["data"], 1): 105 | with st.expander(f"Page {i}: {page.get('url', 'Unknown URL')}"): 106 | if "markdown" in page: 107 | st.markdown(page["markdown"]) 108 | elif "content" in page: 109 | st.text(page["content"]) 110 | else: 111 | st.json(page) 112 | else: 113 | st.warning("No content data found in the response.") 114 | break 115 | 116 | elif status_result.get("status") == "failed": 117 | st.error("❌ Crawl job failed!") 118 | st.error(f"Error: {status_result.get('error', 'Unknown error')}") 119 | break 120 | 121 | else: 122 | # Still in progress, show status 123 | current_status = status_result.get("status", "unknown") 124 | st.info(f"⏳ Status: {current_status}") 125 | time.sleep(10) # Wait 10 seconds before next check 126 | attempt += 1 127 | 128 | else: 129 | st.error(f"❌ Error checking status: {status_response.status_code}") 130 | break 131 | 132 | if attempt >= max_attempts: 133 | st.warning("⏰ Crawl is taking longer than expected. You can check the status manually using the crawl ID above.") 134 | 135 | else: 136 | st.error("❌ No crawl ID returned from the API") 137 | st.json(result) 138 | 139 | else: 140 | st.error(f"❌ Error: {response.status_code}") 141 | st.error(f"Response: {response.text}") 142 | 143 | except requests.exceptions.Timeout: 144 | st.error("⏰ Request timed out. The crawling process is taking longer than expected.") 145 | except requests.exceptions.RequestException as e: 146 | st.error(f"❌ Request failed: {str(e)}") 147 | except Exception as e: 148 | st.error(f"❌ An unexpected error occurred: {str(e)}") 149 | 150 | # Sidebar with information 151 | with st.sidebar: 152 | st.header("ℹ️ About") 153 | st.write("This app uses Firecrawl API to crawl websites and extract content.") 154 | 155 | st.header("⚙️ Settings") 156 | st.write("Configure your crawling options in the main panel.") 157 | 158 | st.header("📚 Features") 159 | st.write("• Extract content in Markdown format") 160 | st.write("• Crawl single pages or entire domains") 161 | st.write("• Include/exclude sitemaps") 162 | st.write("• Filter main content only") 163 | st.write("• PDF parsing support") 164 | --------------------------------------------------------------------------------