lfx-firecrawl 0.1.0__py3-none-any.whl

lfx_firecrawl/__init__.py

@@ -0,0 +1,14 @@
+"""lfx-firecrawl: Firecrawl bundle.
+
+Distribution unit ``lfx-firecrawl``.  At runtime Langflow's loader
+discovers ``extension.json`` shipped alongside this ``__init__.py`` and
+registers the bundle's components under the namespaced IDs
+``ext:firecrawl:<Class>@official``.
+"""
+
+from lfx_firecrawl.components.firecrawl.firecrawl_crawl_api import FirecrawlCrawlApi
+from lfx_firecrawl.components.firecrawl.firecrawl_map_api import FirecrawlMapApi
+from lfx_firecrawl.components.firecrawl.firecrawl_scrape_api import FirecrawlScrapeApi
+from lfx_firecrawl.components.firecrawl.firecrawl_search_api import FirecrawlSearchApi
+
+__all__ = ["FirecrawlCrawlApi", "FirecrawlMapApi", "FirecrawlScrapeApi", "FirecrawlSearchApi"]

lfx_firecrawl/components/firecrawl/__init__.py

@@ -0,0 +1,13 @@
+"""Component re-exports for the ``firecrawl`` bundle.
+
+Saved-flow migration entries that target ``lfx.components.firecrawl.<Class>``
+resolve through this package, so the moved Component class(es) must be
+importable from here by name.
+"""
+
+from .firecrawl_crawl_api import FirecrawlCrawlApi
+from .firecrawl_map_api import FirecrawlMapApi
+from .firecrawl_scrape_api import FirecrawlScrapeApi
+from .firecrawl_search_api import FirecrawlSearchApi
+
+__all__ = ["FirecrawlCrawlApi", "FirecrawlMapApi", "FirecrawlScrapeApi", "FirecrawlSearchApi"]

lfx_firecrawl/components/firecrawl/firecrawl_crawl_api.py

@@ -0,0 +1,109 @@
+import re
+
+from lfx.custom.custom_component.component import Component
+from lfx.io import DataInput, IntInput, MultilineInput, Output, SecretStrInput, StrInput
+from lfx.schema.data import Data
+
+_CAMEL_TO_SNAKE_RE = re.compile(r"(?<!^)(?=[A-Z])")
+
+
+def _to_snake_case_kwargs(params: dict) -> dict:
+    """Convert camelCase option keys to snake_case keyword arguments.
+
+    The firecrawl-py v1 convention uses camelCase, while the v2 SDK expects
+    snake_case keyword arguments. Keys that are already snake_case are passed
+    through unchanged.
+    """
+    return {_CAMEL_TO_SNAKE_RE.sub("_", key).lower(): value for key, value in params.items()}
+
+
+class FirecrawlCrawlApi(Component):
+    display_name: str = "Firecrawl Crawl API"
+    description: str = "Crawls a URL and returns the results."
+    name = "FirecrawlCrawlApi"
+
+    documentation: str = "https://docs.firecrawl.dev/v1/api-reference/endpoint/crawl-post"
+
+    inputs = [
+        SecretStrInput(
+            name="api_key",
+            display_name="Firecrawl API Key",
+            required=True,
+            password=True,
+            info="The API key to use Firecrawl API.",
+        ),
+        MultilineInput(
+            name="url",
+            display_name="URL",
+            required=True,
+            info="The URL to scrape.",
+            tool_mode=True,
+        ),
+        IntInput(
+            name="timeout",
+            display_name="Timeout",
+            info="Timeout in milliseconds for the request.",
+        ),
+        StrInput(
+            name="idempotency_key",
+            display_name="Idempotency Key",
+            info="Optional idempotency key to ensure unique requests.",
+        ),
+        DataInput(
+            name="crawlerOptions",
+            display_name="Crawler Options",
+            info="The crawler options to send with the request.",
+        ),
+        DataInput(
+            name="scrapeOptions",
+            display_name="Scrape Options",
+            info="The page options to send with the request.",
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="JSON", name="data", method="crawl"),
+    ]
+    idempotency_key: str | None = None
+
+    def crawl(self) -> Data:
+        try:
+            from firecrawl import Firecrawl
+            from firecrawl.v2.types import ScrapeOptions
+        except ImportError as e:
+            msg = "Could not import firecrawl integration package. Please install it with `pip install firecrawl-py`."
+            raise ImportError(msg) from e
+
+        params = dict(self.crawlerOptions.__dict__.get("data", {})) if self.crawlerOptions else {}
+        scrape_options_dict = dict(self.scrapeOptions.__dict__.get("data", {})) if self.scrapeOptions else {}
+
+        # Set default values for crawl parameters.
+        # Note: firecrawl-py v2 renamed several options. "maxDepth" -> "max_discovery_depth"
+        # and "allowBackwardLinks" -> "crawl_entire_domain".
+        params.setdefault("maxDepth", 2)
+        params.setdefault("limit", 10000)
+        params.setdefault("allowExternalLinks", False)
+        params.setdefault("allowBackwardLinks", False)
+        params.setdefault("ignoreQueryParameters", False)
+
+        # Ensure onlyMainContent is explicitly set if not provided.
+        scrape_options_dict.setdefault("onlyMainContent", True)
+
+        # Translate legacy v1 camelCase option names to the firecrawl-py v2 keyword args.
+        kwargs = _to_snake_case_kwargs(params)
+        if "max_depth" in kwargs:
+            kwargs["max_discovery_depth"] = kwargs.pop("max_depth")
+        if "allow_backward_links" in kwargs:
+            kwargs["crawl_entire_domain"] = kwargs.pop("allow_backward_links")
+        # v2 removed "ignore_sitemap"; it is now the "sitemap" mode enum.
+        if kwargs.pop("ignore_sitemap", False):
+            kwargs["sitemap"] = "skip"
+
+        # Build the typed ScrapeOptions object expected by v2 from the (snake_cased) dict.
+        scrape_kwargs = _to_snake_case_kwargs(scrape_options_dict)
+        kwargs["scrape_options"] = ScrapeOptions(**scrape_kwargs)
+
+        app = Firecrawl(api_key=self.api_key)
+        # v2 polls to completion and returns a typed CrawlJob object.
+        crawl_job = app.crawl(self.url, **kwargs)
+        return Data(data={"results": crawl_job.model_dump()})

lfx_firecrawl/components/firecrawl/firecrawl_map_api.py

@@ -0,0 +1,94 @@
+from lfx.custom.custom_component.component import Component
+from lfx.io import (
+    BoolInput,
+    MultilineInput,
+    Output,
+    SecretStrInput,
+)
+from lfx.schema.data import Data
+
+
+class FirecrawlMapApi(Component):
+    display_name: str = "Firecrawl Map API"
+    description: str = "Maps a URL and returns the results."
+    name = "FirecrawlMapApi"
+
+    documentation: str = "https://docs.firecrawl.dev/api-reference/endpoint/map"
+
+    inputs = [
+        SecretStrInput(
+            name="api_key",
+            display_name="Firecrawl API Key",
+            required=True,
+            password=True,
+            info="The API key to use Firecrawl API.",
+        ),
+        MultilineInput(
+            name="urls",
+            display_name="URLs",
+            required=True,
+            info="List of URLs to create maps from (separated by commas or new lines).",
+            tool_mode=True,
+        ),
+        BoolInput(
+            name="ignore_sitemap",
+            display_name="Ignore Sitemap",
+            info="When true, the sitemap.xml file will be ignored during crawling.",
+        ),
+        BoolInput(
+            name="sitemap_only",
+            display_name="Sitemap Only",
+            info="When true, only links found in the sitemap will be returned.",
+        ),
+        BoolInput(
+            name="include_subdomains",
+            display_name="Include Subdomains",
+            info="When true, subdomains of the provided URL will also be scanned.",
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="JSON", name="data", method="map"),
+    ]
+
+    def map(self) -> Data:
+        try:
+            from firecrawl import Firecrawl
+        except ImportError as e:
+            msg = "Could not import firecrawl integration package. Please install it with `pip install firecrawl-py`."
+            raise ImportError(msg) from e
+
+        # Validate URLs
+        if not self.urls:
+            msg = "URLs are required"
+            raise ValueError(msg)
+
+        # Split and validate URLs (handle both commas and newlines)
+        urls = [url.strip() for url in self.urls.replace("\n", ",").split(",") if url.strip()]
+        if not urls:
+            msg = "No valid URLs provided"
+            raise ValueError(msg)
+
+        # firecrawl-py v2 replaced the separate "ignoreSitemap"/"sitemapOnly" flags with a
+        # single "sitemap" mode: "only" (sitemap only), "skip" (ignore sitemap), or the
+        # default mixed behavior.
+        kwargs: dict = {"include_subdomains": self.include_subdomains}
+        if self.sitemap_only:
+            kwargs["sitemap"] = "only"
+        elif self.ignore_sitemap:
+            kwargs["sitemap"] = "skip"
+
+        app = Firecrawl(api_key=self.api_key)
+
+        # Map all provided URLs and combine results.
+        combined_links = []
+        for url in urls:
+            result = app.map(url, **kwargs)
+            # v2 returns a typed MapData object whose .links is a list of typed
+            # SearchResult objects; serialize each to a dict for downstream consumers.
+            links = getattr(result, "links", None) or []
+            combined_links.extend(link.model_dump() if hasattr(link, "model_dump") else link for link in links)
+
+        map_result = {"success": True, "links": combined_links}
+
+        return Data(data=map_result)

lfx_firecrawl/components/firecrawl/firecrawl_scrape_api.py

@@ -0,0 +1,97 @@
+import re
+
+from lfx.custom.custom_component.component import Component
+from lfx.io import (
+    DataInput,
+    IntInput,
+    MultilineInput,
+    Output,
+    SecretStrInput,
+)
+from lfx.schema.data import Data
+
+_CAMEL_TO_SNAKE_RE = re.compile(r"(?<!^)(?=[A-Z])")
+
+
+def _to_snake_case_kwargs(params: dict) -> dict:
+    """Convert camelCase option keys to snake_case keyword arguments.
+
+    The firecrawl-py v1 convention uses camelCase, while the v2 SDK expects
+    snake_case keyword arguments. Keys that are already snake_case are passed
+    through unchanged.
+    """
+    return {_CAMEL_TO_SNAKE_RE.sub("_", key).lower(): value for key, value in params.items()}
+
+
+class FirecrawlScrapeApi(Component):
+    display_name: str = "Firecrawl Scrape API"
+    description: str = "Scrapes a URL and returns the results."
+    name = "FirecrawlScrapeApi"
+
+    documentation: str = "https://docs.firecrawl.dev/api-reference/endpoint/scrape"
+
+    inputs = [
+        SecretStrInput(
+            name="api_key",
+            display_name="Firecrawl API Key",
+            required=True,
+            password=True,
+            info="The API key to use Firecrawl API.",
+        ),
+        MultilineInput(
+            name="url",
+            display_name="URL",
+            required=True,
+            info="The URL to scrape.",
+            tool_mode=True,
+        ),
+        IntInput(
+            name="timeout",
+            display_name="Timeout",
+            info="Timeout in milliseconds for the request.",
+        ),
+        DataInput(
+            name="scrapeOptions",
+            display_name="Scrape Options",
+            info="The page options to send with the request.",
+        ),
+        DataInput(
+            name="extractorOptions",
+            display_name="Extractor Options",
+            info="The extractor options to send with the request.",
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="JSON", name="data", method="scrape"),
+    ]
+
+    def scrape(self) -> Data:
+        try:
+            from firecrawl import Firecrawl
+        except ImportError as e:
+            msg = "Could not import firecrawl integration package. Please install it with `pip install firecrawl-py`."
+            raise ImportError(msg) from e
+
+        params = dict(self.scrapeOptions.__dict__.get("data", {})) if self.scrapeOptions else {}
+
+        # Set default values for parameters
+        params.setdefault("formats", ["markdown"])  # Default output format
+        params.setdefault("onlyMainContent", True)  # Default to only main content
+        if self.timeout:
+            params.setdefault("timeout", self.timeout)
+
+        kwargs = _to_snake_case_kwargs(params)
+
+        # In firecrawl-py v2, structured extraction is requested via a "json" format entry
+        # on the scrape call rather than a separate extractor option.
+        extractor_options_dict = self.extractorOptions.__dict__.get("data", {}) if self.extractorOptions else {}
+        if extractor_options_dict:
+            formats = list(kwargs.get("formats", []))
+            formats.append({"type": "json", **_to_snake_case_kwargs(extractor_options_dict)})
+            kwargs["formats"] = formats
+
+        app = Firecrawl(api_key=self.api_key)
+        document = app.scrape(self.url, **kwargs)
+        # v2 returns a typed Document object; serialize to a dict for downstream consumers.
+        return Data(data=document.model_dump())

lfx_firecrawl/components/firecrawl/firecrawl_search_api.py

@@ -0,0 +1,76 @@
+from lfx.custom.custom_component.component import Component
+from lfx.io import (
+    IntInput,
+    MultilineInput,
+    Output,
+    SecretStrInput,
+    StrInput,
+)
+from lfx.schema.data import Data
+
+
+class FirecrawlSearchApi(Component):
+    display_name: str = "Firecrawl Search API"
+    description: str = "Searches the web and returns the results."
+    name = "FirecrawlSearchApi"
+
+    documentation: str = "https://docs.firecrawl.dev/api-reference/endpoint/search"
+
+    inputs = [
+        SecretStrInput(
+            name="api_key",
+            display_name="Firecrawl API Key",
+            required=True,
+            password=True,
+            info="The API key to use Firecrawl API.",
+        ),
+        MultilineInput(
+            name="query",
+            display_name="Query",
+            required=True,
+            info="The search query to run.",
+            tool_mode=True,
+        ),
+        IntInput(
+            name="limit",
+            display_name="Limit",
+            info="Maximum number of results to return.",
+            value=5,
+        ),
+        StrInput(
+            name="location",
+            display_name="Location",
+            info="Location to bias the search results (e.g. a country or region).",
+            advanced=True,
+        ),
+    ]
+
+    outputs = [
+        Output(display_name="JSON", name="data", method="search"),
+    ]
+
+    def search(self) -> Data:
+        try:
+            from firecrawl import Firecrawl
+        except ImportError as e:
+            msg = "Could not import firecrawl integration package. Please install it with `pip install firecrawl-py`."
+            raise ImportError(msg) from e
+
+        if not self.query:
+            msg = "Query is required"
+            raise ValueError(msg)
+
+        kwargs: dict = {}
+        if self.limit:
+            kwargs["limit"] = self.limit
+        if self.location:
+            kwargs["location"] = self.location
+
+        app = Firecrawl(api_key=self.api_key)
+        result = app.search(self.query, **kwargs)
+
+        # v2 returns a typed SearchData object (results grouped by source);
+        # serialize to a dict for downstream consumers.
+        search_result = result.model_dump() if hasattr(result, "model_dump") else result
+
+        return Data(data=search_result)

lfx_firecrawl/extension.json

@@ -0,0 +1,16 @@
+{
+  "$schema": "https://schemas.langflow.org/extension/v1.json",
+  "id": "lfx-firecrawl",
+  "version": "0.1.0",
+  "name": "Firecrawl",
+  "description": "Firecrawl components (Scrape, Crawl, Map, and Search APIs) as a standalone Langflow Extension Bundle.",
+  "lfx": {
+    "compat": ["1"]
+  },
+  "bundles": [
+    {
+      "name": "firecrawl",
+      "path": "components/firecrawl"
+    }
+  ]
+}

lfx_firecrawl-0.1.0.dist-info/METADATA

@@ -0,0 +1,44 @@
+Metadata-Version: 2.4
+Name: lfx-firecrawl
+Version: 0.1.0
+Summary: Firecrawl components (Scrape, Crawl, Map, and Search APIs) as a standalone Langflow Extension Bundle.
+Project-URL: Homepage, https://github.com/langflow-ai/langflow
+Project-URL: Documentation, https://docs.langflow.org/extensions
+Project-URL: Repository, https://github.com/langflow-ai/langflow
+Author-email: Langflow <contact@langflow.org>
+License: MIT
+Keywords: bundle,extension,firecrawl,langflow,lfx
+Requires-Python: <3.15,>=3.10
+Requires-Dist: firecrawl-py<5.0.0,>=4.0.0
+Requires-Dist: lfx<2.0.0,>=1.11.0.dev0
+Description-Content-Type: text/markdown
+
+# lfx-firecrawl
+
+Firecrawl components (Scrape, Crawl, Map, and Search APIs) as a standalone
+Langflow Extension Bundle, built against the firecrawl-py v2 SDK.
+
+## Install
+
+```bash
+pip install lfx-firecrawl
+```
+
+The bundle is registered automatically via the `langflow.extensions`
+entry-point.  After install, restart your Langflow server; the bundle's
+components will appear in the palette under the `firecrawl` group.
+
+## Develop
+
+```bash
+cd src/bundles/firecrawl
+pip install -e .
+lfx extension validate src/lfx_firecrawl
+```
+
+## Migration
+
+Saved flows referencing the legacy class name(s) or the old import paths
+under `lfx.components.firecrawl.*` are rewritten to the new namespaced
+IDs by the migration table in
+`src/lfx/src/lfx/extension/migration/migration_table.json`.

lfx_firecrawl-0.1.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+lfx_firecrawl/__init__.py,sha256=LSgReguH1y01WCNbQ-moqIknCDnT1ShNoV2WQrAHZNM,712
+lfx_firecrawl/extension.json,sha256=SrOl7qR09aEmJ-MiXC_QjhDjpIhzKQ3v9033f9fsKGs,390
+lfx_firecrawl/components/firecrawl/__init__.py,sha256=r22GFArvunu6fi1Ed-AUxmITGEMLy9UU7OXU6L-AGAo,539
+lfx_firecrawl/components/firecrawl/firecrawl_crawl_api.py,sha256=EwGDi68PU7ePuJhAgXhXZJQ4xAn2e5ph95-2uTDHDA0,4266
+lfx_firecrawl/components/firecrawl/firecrawl_map_api.py,sha256=VqI_MTVJLbYaS_t2mS8ELOKfcBpxfYXYNzXqmM7iqQE,3304
+lfx_firecrawl/components/firecrawl/firecrawl_scrape_api.py,sha256=ICSPl8JIXs4vKpaLE2AMlVvnpjiLuds9ciCPJlQB09M,3395
+lfx_firecrawl/components/firecrawl/firecrawl_search_api.py,sha256=9syAHHJnAi21gE81zgwxewHc49Ik2mui4GTpEZ2Qwkk,2269
+lfx_firecrawl-0.1.0.dist-info/METADATA,sha256=70UFD_Rl7xKltzfwWtLd8Sg09GUIrqFqnp9TpsXVPgQ,1397
+lfx_firecrawl-0.1.0.dist-info/WHEEL,sha256=mffPy8wBnZQn2VnJUU5jE99KsxaSfiyMHV9Yt0aLVxs,87
+lfx_firecrawl-0.1.0.dist-info/entry_points.txt,sha256=AVgggm-Bt6-8xHeIx_gzT305TJ1kcgMe7PX-TXkKZj0,52
+lfx_firecrawl-0.1.0.dist-info/RECORD,,

lfx_firecrawl-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.30.1
+Root-Is-Purelib: true
+Tag: py3-none-any

lfx_firecrawl-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[langflow.extensions]
+lfx-firecrawl = lfx_firecrawl